diff --git a/README.md b/README.md index 6cc2b24..12e4566 100644 --- a/README.md +++ b/README.md @@ -49,6 +49,10 @@ This repository contains tabular-format and xlsx spreadsheet metadata templates | [ERC000051](./templates/ERC000051) | PDX Checklist | Minimum information required for reporting samples associated with patient-derived xenograft (PDX) models or patient samples | | [ERC000052](./templates/ERC000052) | HoloFood Checklist | Minimum information required for reporting HoloFood samples. HoloFood is a 'hologenomic' approach that will improve the efficiency of food production systems by understanding the biomolecular and physiological processes affected by incorporating feed additives and novel sustainable feeds in farmed animals (https://www.holofood.eu/). | | [ERC000053](./templates/ERC000053) | Tree of Life Checklist | Minimum information required for reporting samples associated with the Tree of Life Programme (https://www.sanger.ac.uk/programme/tree-of-life/). | +| [ERC000055](./templates/ERC000055) | GSC MIxS agriculture | Genomic Standards Consortium package extension for reporting of measurements and observations obtained from the environment where the sample was obtained. By choosing the environmental package, a selection of fields can be made from a relevant subsets of the GSC terms. | +| [ERC000056](./templates/ERC000056) | GSC MIxS Food and Production | Genomic Standards Consortium package extension for reporting of measurements and observations obtained from the environment where the sample was obtained. By choosing the environmental package, a selection of fields can be made from a relevant subsets of the GSC terms. This package is a combination of the four food extensions (MIxS-food-animal and animal feed, MIxS-food-farm environment, MIxS-food-food production facility, MIxS-food-human foods). | +| [ERC000057](./templates/ERC000057) | GSC MIxS Symbiont | Genomic Standards Consortium package extension for reporting of measurements and observations obtained from the environment where the sample was obtained. By choosing the environmental package, a selection of fields can be made from a relevant subsets of the GSC terms. | +| [ERC000058](./templates/ERC000058) | GSC MIxS Hydrocarbon | Genomic Standards Consortium package extension for reporting of measurements and observations obtained from the environment where the sample was obtained. By choosing the environmental package, a selection of fields can be made from a relevant subsets of the GSC terms. | ## Tabular metadata templates (*.tsv) diff --git a/checklist_overview.json b/checklist_overview.json index 3b4ebbd..f2136a8 100644 --- a/checklist_overview.json +++ b/checklist_overview.json @@ -318,5 +318,37 @@ "dataType": "CHECKLIST", "status": 4, "statusDescription": "public" + }, + { + "accession": "ERC000055", + "description": "Genomic Standards Consortium package extension for reporting of measurements and observations obtained from the environment where the sample was obtained. By choosing the environmental package, a selection of fields can be made from a relevant subsets of the GSC terms.", + "name": "GSC MIxS agriculture", + "dataType": "CHECKLIST", + "status": 4, + "statusDescription": "public" + }, + { + "accession": "ERC000056", + "description": "Genomic Standards Consortium package extension for reporting of measurements and observations obtained from the environment where the sample was obtained. By choosing the environmental package, a selection of fields can be made from a relevant subsets of the GSC terms. This package is a combination of the four food extensions (MIxS-food-animal and animal feed, MIxS-food-farm environment, MIxS-food-food production facility, MIxS-food-human foods).", + "name": "GSC MIxS Food and Production", + "dataType": "CHECKLIST", + "status": 4, + "statusDescription": "public" + }, + { + "accession": "ERC000057", + "description": "Genomic Standards Consortium package extension for reporting of measurements and observations obtained from the environment where the sample was obtained. By choosing the environmental package, a selection of fields can be made from a relevant subsets of the GSC terms.", + "name": "GSC MIxS Symbiont", + "dataType": "CHECKLIST", + "status": 4, + "statusDescription": "public" + }, + { + "accession": "ERC000058", + "description": "Genomic Standards Consortium package extension for reporting of measurements and observations obtained from the environment where the sample was obtained. By choosing the environmental package, a selection of fields can be made from a relevant subsets of the GSC terms.", + "name": "GSC MIxS Hydrocarbon", + "dataType": "CHECKLIST", + "status": 4, + "statusDescription": "public" } ] \ No newline at end of file diff --git a/templates/ERC000011/metadata_template_ERC000011.xlsx b/templates/ERC000011/metadata_template_ERC000011.xlsx index 35c0ed9..258537a 100644 Binary files a/templates/ERC000011/metadata_template_ERC000011.xlsx and b/templates/ERC000011/metadata_template_ERC000011.xlsx differ diff --git a/templates/ERC000012/metadata_template_ERC000012.xlsx b/templates/ERC000012/metadata_template_ERC000012.xlsx index b33aa6b..ec8a3b4 100644 Binary files a/templates/ERC000012/metadata_template_ERC000012.xlsx and b/templates/ERC000012/metadata_template_ERC000012.xlsx differ diff --git a/templates/ERC000013/metadata_template_ERC000013.xlsx b/templates/ERC000013/metadata_template_ERC000013.xlsx index 231932e..6ee5a99 100644 Binary files a/templates/ERC000013/metadata_template_ERC000013.xlsx and b/templates/ERC000013/metadata_template_ERC000013.xlsx differ diff --git a/templates/ERC000014/metadata_template_ERC000014.xlsx b/templates/ERC000014/metadata_template_ERC000014.xlsx index 0e87da5..8c42a0b 100644 Binary files a/templates/ERC000014/metadata_template_ERC000014.xlsx and b/templates/ERC000014/metadata_template_ERC000014.xlsx differ diff --git a/templates/ERC000015/metadata_template_ERC000015.xlsx b/templates/ERC000015/metadata_template_ERC000015.xlsx index 9d446d9..f008bfe 100644 Binary files a/templates/ERC000015/metadata_template_ERC000015.xlsx and b/templates/ERC000015/metadata_template_ERC000015.xlsx differ diff --git a/templates/ERC000016/metadata_template_ERC000016.xlsx b/templates/ERC000016/metadata_template_ERC000016.xlsx index 923d638..6eb592b 100644 Binary files a/templates/ERC000016/metadata_template_ERC000016.xlsx and b/templates/ERC000016/metadata_template_ERC000016.xlsx differ diff --git a/templates/ERC000017/metadata_template_ERC000017.xlsx b/templates/ERC000017/metadata_template_ERC000017.xlsx index a5a8cef..4a39a43 100644 Binary files a/templates/ERC000017/metadata_template_ERC000017.xlsx and b/templates/ERC000017/metadata_template_ERC000017.xlsx differ diff --git a/templates/ERC000018/metadata_template_ERC000018.xlsx b/templates/ERC000018/metadata_template_ERC000018.xlsx index 64781b9..5757d61 100644 Binary files a/templates/ERC000018/metadata_template_ERC000018.xlsx and b/templates/ERC000018/metadata_template_ERC000018.xlsx differ diff --git a/templates/ERC000019/metadata_template_ERC000019.xlsx b/templates/ERC000019/metadata_template_ERC000019.xlsx index 1669283..a45c603 100644 Binary files a/templates/ERC000019/metadata_template_ERC000019.xlsx and b/templates/ERC000019/metadata_template_ERC000019.xlsx differ diff --git a/templates/ERC000020/metadata_template_ERC000020.xlsx b/templates/ERC000020/metadata_template_ERC000020.xlsx index a2eab18..3e6fbee 100644 Binary files a/templates/ERC000020/metadata_template_ERC000020.xlsx and b/templates/ERC000020/metadata_template_ERC000020.xlsx differ diff --git a/templates/ERC000021/metadata_template_ERC000021.xlsx b/templates/ERC000021/metadata_template_ERC000021.xlsx index ee556c0..c64b642 100644 Binary files a/templates/ERC000021/metadata_template_ERC000021.xlsx and b/templates/ERC000021/metadata_template_ERC000021.xlsx differ diff --git a/templates/ERC000022/metadata_template_ERC000022.xlsx b/templates/ERC000022/metadata_template_ERC000022.xlsx index f28e998..f639421 100644 Binary files a/templates/ERC000022/metadata_template_ERC000022.xlsx and b/templates/ERC000022/metadata_template_ERC000022.xlsx differ diff --git a/templates/ERC000023/metadata_template_ERC000023.xlsx b/templates/ERC000023/metadata_template_ERC000023.xlsx index 511649d..59dad13 100644 Binary files a/templates/ERC000023/metadata_template_ERC000023.xlsx and b/templates/ERC000023/metadata_template_ERC000023.xlsx differ diff --git a/templates/ERC000024/metadata_template_ERC000024.xlsx b/templates/ERC000024/metadata_template_ERC000024.xlsx index 51218f7..c97698f 100644 Binary files a/templates/ERC000024/metadata_template_ERC000024.xlsx and b/templates/ERC000024/metadata_template_ERC000024.xlsx differ diff --git a/templates/ERC000025/metadata_template_ERC000025.xlsx b/templates/ERC000025/metadata_template_ERC000025.xlsx index 1b16f99..3280b89 100644 Binary files a/templates/ERC000025/metadata_template_ERC000025.xlsx and b/templates/ERC000025/metadata_template_ERC000025.xlsx differ diff --git a/templates/ERC000027/metadata_template_ERC000027.xlsx b/templates/ERC000027/metadata_template_ERC000027.xlsx index f35c66b..9881e27 100644 Binary files a/templates/ERC000027/metadata_template_ERC000027.xlsx and b/templates/ERC000027/metadata_template_ERC000027.xlsx differ diff --git a/templates/ERC000028/metadata_template_ERC000028.xlsx b/templates/ERC000028/metadata_template_ERC000028.xlsx index bef3e3d..671d38e 100644 Binary files a/templates/ERC000028/metadata_template_ERC000028.xlsx and b/templates/ERC000028/metadata_template_ERC000028.xlsx differ diff --git a/templates/ERC000029/metadata_template_ERC000029.xlsx b/templates/ERC000029/metadata_template_ERC000029.xlsx index 1bc1bdb..528478e 100644 Binary files a/templates/ERC000029/metadata_template_ERC000029.xlsx and b/templates/ERC000029/metadata_template_ERC000029.xlsx differ diff --git a/templates/ERC000030/metadata_template_ERC000030.xlsx b/templates/ERC000030/metadata_template_ERC000030.xlsx index 7d887ec..a986d18 100644 Binary files a/templates/ERC000030/metadata_template_ERC000030.xlsx and b/templates/ERC000030/metadata_template_ERC000030.xlsx differ diff --git a/templates/ERC000031/metadata_template_ERC000031.xlsx b/templates/ERC000031/metadata_template_ERC000031.xlsx index 4562547..e945268 100644 Binary files a/templates/ERC000031/metadata_template_ERC000031.xlsx and b/templates/ERC000031/metadata_template_ERC000031.xlsx differ diff --git a/templates/ERC000032/metadata_template_ERC000032.xlsx b/templates/ERC000032/metadata_template_ERC000032.xlsx index e5a72b1..464d2b8 100644 Binary files a/templates/ERC000032/metadata_template_ERC000032.xlsx and b/templates/ERC000032/metadata_template_ERC000032.xlsx differ diff --git a/templates/ERC000033/metadata_template_ERC000033.xlsx b/templates/ERC000033/metadata_template_ERC000033.xlsx index c7cdbe0..5103bfc 100644 Binary files a/templates/ERC000033/metadata_template_ERC000033.xlsx and b/templates/ERC000033/metadata_template_ERC000033.xlsx differ diff --git a/templates/ERC000034/metadata_template_ERC000034.xlsx b/templates/ERC000034/metadata_template_ERC000034.xlsx index 79b61da..f45e6a1 100644 Binary files a/templates/ERC000034/metadata_template_ERC000034.xlsx and b/templates/ERC000034/metadata_template_ERC000034.xlsx differ diff --git a/templates/ERC000035/metadata_template_ERC000035.xlsx b/templates/ERC000035/metadata_template_ERC000035.xlsx index 2d19417..326d534 100644 Binary files a/templates/ERC000035/metadata_template_ERC000035.xlsx and b/templates/ERC000035/metadata_template_ERC000035.xlsx differ diff --git a/templates/ERC000036/metadata_template_ERC000036.xlsx b/templates/ERC000036/metadata_template_ERC000036.xlsx index 7955493..32fb121 100644 Binary files a/templates/ERC000036/metadata_template_ERC000036.xlsx and b/templates/ERC000036/metadata_template_ERC000036.xlsx differ diff --git a/templates/ERC000037/metadata_template_ERC000037.xlsx b/templates/ERC000037/metadata_template_ERC000037.xlsx index 1bece52..f1e3891 100644 Binary files a/templates/ERC000037/metadata_template_ERC000037.xlsx and b/templates/ERC000037/metadata_template_ERC000037.xlsx differ diff --git a/templates/ERC000038/metadata_template_ERC000038.xlsx b/templates/ERC000038/metadata_template_ERC000038.xlsx index c982e50..4e85ddd 100644 Binary files a/templates/ERC000038/metadata_template_ERC000038.xlsx and b/templates/ERC000038/metadata_template_ERC000038.xlsx differ diff --git a/templates/ERC000039/metadata_template_ERC000039.xlsx b/templates/ERC000039/metadata_template_ERC000039.xlsx index 9dab425..395a875 100644 Binary files a/templates/ERC000039/metadata_template_ERC000039.xlsx and b/templates/ERC000039/metadata_template_ERC000039.xlsx differ diff --git a/templates/ERC000040/metadata_template_ERC000040.xlsx b/templates/ERC000040/metadata_template_ERC000040.xlsx index b8bc628..717155e 100644 Binary files a/templates/ERC000040/metadata_template_ERC000040.xlsx and b/templates/ERC000040/metadata_template_ERC000040.xlsx differ diff --git a/templates/ERC000041/metadata_template_ERC000041.xlsx b/templates/ERC000041/metadata_template_ERC000041.xlsx index 6945ebe..48f333d 100644 Binary files a/templates/ERC000041/metadata_template_ERC000041.xlsx and b/templates/ERC000041/metadata_template_ERC000041.xlsx differ diff --git a/templates/ERC000043/metadata_template_ERC000043.xlsx b/templates/ERC000043/metadata_template_ERC000043.xlsx index 95dc1ac..1bb0d86 100644 Binary files a/templates/ERC000043/metadata_template_ERC000043.xlsx and b/templates/ERC000043/metadata_template_ERC000043.xlsx differ diff --git a/templates/ERC000044/metadata_template_ERC000044.xlsx b/templates/ERC000044/metadata_template_ERC000044.xlsx index 35131a1..9d8aad9 100644 Binary files a/templates/ERC000044/metadata_template_ERC000044.xlsx and b/templates/ERC000044/metadata_template_ERC000044.xlsx differ diff --git a/templates/ERC000045/metadata_template_ERC000045.xlsx b/templates/ERC000045/metadata_template_ERC000045.xlsx index 314f646..41eba32 100644 Binary files a/templates/ERC000045/metadata_template_ERC000045.xlsx and b/templates/ERC000045/metadata_template_ERC000045.xlsx differ diff --git a/templates/ERC000047/metadata_template_ERC000047.xlsx b/templates/ERC000047/metadata_template_ERC000047.xlsx index 4efba09..8960b59 100644 Binary files a/templates/ERC000047/metadata_template_ERC000047.xlsx and b/templates/ERC000047/metadata_template_ERC000047.xlsx differ diff --git a/templates/ERC000048/metadata_template_ERC000048.xlsx b/templates/ERC000048/metadata_template_ERC000048.xlsx index 3c17c4d..b88427f 100644 Binary files a/templates/ERC000048/metadata_template_ERC000048.xlsx and b/templates/ERC000048/metadata_template_ERC000048.xlsx differ diff --git a/templates/ERC000049/metadata_template_ERC000049.xlsx b/templates/ERC000049/metadata_template_ERC000049.xlsx index 71abf39..0aa837a 100644 Binary files a/templates/ERC000049/metadata_template_ERC000049.xlsx and b/templates/ERC000049/metadata_template_ERC000049.xlsx differ diff --git a/templates/ERC000050/metadata_template_ERC000050.xlsx b/templates/ERC000050/metadata_template_ERC000050.xlsx index 3748810..f65fbd6 100644 Binary files a/templates/ERC000050/metadata_template_ERC000050.xlsx and b/templates/ERC000050/metadata_template_ERC000050.xlsx differ diff --git a/templates/ERC000051/metadata_template_ERC000051.xlsx b/templates/ERC000051/metadata_template_ERC000051.xlsx index 10c8b7f..4b59b4a 100644 Binary files a/templates/ERC000051/metadata_template_ERC000051.xlsx and b/templates/ERC000051/metadata_template_ERC000051.xlsx differ diff --git a/templates/ERC000052/metadata_template_ERC000052.xlsx b/templates/ERC000052/metadata_template_ERC000052.xlsx index 8e992fd..cd64ed7 100644 Binary files a/templates/ERC000052/metadata_template_ERC000052.xlsx and b/templates/ERC000052/metadata_template_ERC000052.xlsx differ diff --git a/templates/ERC000053/metadata_template_ERC000053.xlsx b/templates/ERC000053/metadata_template_ERC000053.xlsx index 0b76858..aa863f0 100644 Binary files a/templates/ERC000053/metadata_template_ERC000053.xlsx and b/templates/ERC000053/metadata_template_ERC000053.xlsx differ diff --git a/templates/ERC000055/ERC000055.json b/templates/ERC000055/ERC000055.json new file mode 100644 index 0000000..1f7f893 --- /dev/null +++ b/templates/ERC000055/ERC000055.json @@ -0,0 +1,2482 @@ +{ + "study": { + "description": "A Study is a container for a sequencing investigation that may comprise multiple experiments. The Study has an overall goal, but is otherwise minimally defined in the SRA. A Study is composed of a descriptor, zero or more experiments, and zero or more analyses. The submitter may decorate the Study with web links and properties.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for a study. This is used to link experiments to the study.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "title", + "cardinality": "mandatory", + "description": "Title of the study as would be used in a publication.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "study_type", + "cardinality": "mandatory", + "description": "The STUDY_TYPE presents a controlled vocabulary for expressing the overall purpose of the study.", + "units": "", + "regex": "", + "cv": [ + "Whole Genome Sequencing", + "Metagenomics", + "Transcriptome Analysis", + "Resequencing", + "Epigenetics", + "Synthetic Genomics", + "Forensic or Paleo-genomics", + "Gene Regulation Study", + "Cancer Genomics", + "Population Genomics", + "RNASeq", + "Exome Sequencing", + "Pooled Clone Sequencing", + "Transcriptome Sequencing", + "Other" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "new_study_type", + "cardinality": "optional", + "description": "Optional if 'study_type' is not 'other'. To propose a new term, select Other and enter a new study type.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "study_abstract", + "cardinality": "optional", + "description": "Briefly describes the goals, purpose, and scope of the Study. This need not be listed if it can be inherited from a referenced publication.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_AREA_FIELD" + } + ] + }, + "experiment": { + "description": "An experiment object serves as a metadata record encapsulating essential details about a sequencing experiment, including the experimental design, sequencing type, and relevant parameters. This information enhances the interpretation and contextual understanding of nucleotide sequences submitted to the archive.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for each experiment. This is used to link runs to experiments.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "title", + "cardinality": "optional", + "description": "Short text that can be used to call out experiment records in searches or in displays. This element is technically optional but should be used for all new records.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "study_alias", + "cardinality": "mandatory", + "description": "Identifies the parent study. (From study metadata)", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "sample_alias", + "cardinality": "mandatory", + "description": "(From sample metadata)", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "design_description", + "cardinality": "optional", + "description": "Goal and setup of the individual library including library was constructed.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_AREA_FIELD" + }, + { + "name": "library_name", + "cardinality": "optional", + "description": "The submitter's name for this library.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "library_strategy", + "cardinality": "mandatory", + "description": "Sequencing technique intended for this library.", + "units": "", + "regex": "", + "cv": [ + "WGS", + "WGA", + "WXS", + "RNA-Seq", + "ssRNA-seq", + "snRNA-seq", + "miRNA-Seq", + "ncRNA-Seq", + "FL-cDNA", + "EST", + "Hi-C", + "ATAC-seq", + "WCS", + "RAD-Seq", + "CLONE", + "POOLCLONE", + "AMPLICON", + "CLONEEND", + "FINISHING", + "ChIP-Seq", + "MNase-Seq", + "DNase-Hypersensitivity", + "Bisulfite-Seq", + "CTS", + "MRE-Seq", + "MeDIP-Seq", + "MBD-Seq", + "Tn-Seq", + "VALIDATION", + "FAIRE-seq", + "SELEX", + "RIP-Seq", + "ChIA-PET", + "Synthetic-Long-Read", + "Targeted-Capture", + "Tethered Chromatin Conformation Capture", + "NOMe-Seq", + "ChM-Seq", + "GBS", + "Ribo-Seq", + "OTHER" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "library_source", + "cardinality": "mandatory", + "description": "The LIBRARY_SOURCE specifies the type of source material that is being sequenced.", + "units": "", + "regex": "", + "cv": [ + "GENOMIC", + "GENOMIC SINGLE CELL", + "TRANSCRIPTOMIC", + "TRANSCRIPTOMIC SINGLE CELL", + "METAGENOMIC", + "METATRANSCRIPTOMIC", + "SYNTHETIC", + "VIRAL RNA", + "OTHER" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "library_selection", + "cardinality": "mandatory", + "description": "Method used to enrich the target in the sequence library preparation", + "units": "", + "regex": "", + "cv": [ + "RANDOM", + "PCR", + "RANDOM PCR", + "RT-PCR", + "HMPR", + "MF", + "repeat fractionation", + "size fractionation", + "MSLL", + "cDNA", + "cDNA_randomPriming", + "cDNA_oligo_dT", + "PolyA", + "Oligo-dT", + "Inverse rRNA", + "Inverse rRNA selection", + "ChIP", + "ChIP-Seq", + "MNase", + "DNase", + "Hybrid Selection", + "Reduced Representation", + "Restriction Digest", + "5-methylcytidine antibody", + "MBD2 protein methyl-CpG binding domain", + "CAGE", + "RACE", + "MDA", + "padlock probes capture method", + "other", + "unspecified" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "library_layout", + "cardinality": "mandatory", + "description": "LIBRARY_LAYOUT specifies whether to expect single, paired, or other configuration of reads. In the case of paired reads, information about the relative distance and orientation is specified.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "insert_size", + "cardinality": "optional", + "description": "Insert size for paired reads", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "library_construction_protocol", + "cardinality": "optional", + "description": "Free form text describing the protocol by which the sequencing library was constructed.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "platform", + "cardinality": "mandatory", + "description": "The PLATFORM record selects which sequencing platform and platform-specific runtime parameters. This will be determined by the Center. optional if 'instrument_model' is provided.", + "units": "", + "regex": "", + "cv": [ + "LS454", + "ILLUMINA", + "HELICOS", + "ABI_SOLID", + "COMPLETE_GENOMICS", + "BGISEQ", + "OXFORD_NANOPORE", + "PACBIO_SMRT", + "ION_TORRENT", + "CAPILLARY", + "DNBSEQ", + "ELEMENT", + "ULTIMA", + "VELA_DIAGNOSTICS", + "GENAPSYS", + "GENEMIND", + "TAPESTRI" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "instrument_model", + "cardinality": "mandatory", + "description": "Model of the sequencing instrument.", + "units": "", + "regex": "", + "cv": [ + "454 GS", + "454 GS 20", + "454 GS FLX", + "454 GS FLX Titanium", + "454 GS FLX+", + "454 GS Junior", + "AB 310 Genetic Analyzer", + "AB 3130 Genetic Analyzer", + "AB 3130xL Genetic Analyzer", + "AB 3500 Genetic Analyzer", + "AB 3500xL Genetic Analyzer", + "AB 3730 Genetic Analyzer", + "AB 3730xL Genetic Analyzer", + "AB 5500 Genetic Analyzer", + "AB 5500xl Genetic Analyzer", + "AB 5500xl-W Genetic Analysis System", + "AB SOLiD 3 Plus System", + "AB SOLiD 4 System", + "AB SOLiD 4hq System", + "AB SOLiD PI System", + "AB SOLiD System", + "AB SOLiD System 2.0", + "AB SOLiD System 3.0", + "BGISEQ-50", + "BGISEQ-500", + "Complete Genomics", + "DNBSEQ-G400", + "DNBSEQ-G400 FAST", + "DNBSEQ-G50", + "DNBSEQ-T7", + "Element AVITI", + "FASTASeq 300", + "GENIUS", + "GS111", + "Genapsys Sequencer", + "GenoCare 1600", + "GenoLab M", + "GridION", + "Helicos HeliScope", + "HiSeq X Five", + "HiSeq X Ten", + "Illumina Genome Analyzer", + "Illumina Genome Analyzer II", + "Illumina Genome Analyzer IIx", + "Illumina HiScanSQ", + "Illumina HiSeq 1000", + "Illumina HiSeq 1500", + "Illumina HiSeq 2000", + "Illumina HiSeq 2500", + "Illumina HiSeq 3000", + "Illumina HiSeq 4000", + "Illumina HiSeq X", + "Illumina MiSeq", + "Illumina MiniSeq", + "Illumina NovaSeq 6000", + "Illumina NovaSeq X", + "Illumina iSeq 100", + "Ion GeneStudio S5", + "Ion GeneStudio S5 Plus", + "Ion GeneStudio S5 Prime", + "Ion Torrent Genexus", + "Ion Torrent PGM", + "Ion Torrent Proton", + "Ion Torrent S5", + "Ion Torrent S5 XL", + "MGISEQ-2000RS", + "MinION", + "NextSeq 1000", + "NextSeq 2000", + "NextSeq 500", + "NextSeq 550", + "Onso", + "PacBio RS", + "PacBio RS II", + "PromethION", + "Revio", + "Sentosa SQ301", + "Sequel", + "Sequel II", + "Sequel IIe", + "Tapestri", + "UG 100", + "unspecified" + ], + "field_type": "TEXT_CHOICE_FIELD" + } + ] + }, + "run": { + "description": "A run contains a group of reads generated for a particular experiment.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for each run.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "experiment_alias", + "cardinality": "mandatory", + "description": "From_experiment_metadata", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "file_name", + "cardinality": "mandatory", + "description": "The name or relative pathname of a run data file.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "file_format", + "cardinality": "mandatory", + "description": "The run data file model.", + "units": "", + "regex": "", + "cv": [ + "sra", + "srf", + "sff", + "fastq", + "fasta", + "tab", + "454_native", + "454_native_seq", + "454_native_qual", + "Helicos_native", + "Illumina_native", + "Illumina_native_seq", + "Illumina_native_prb", + "Illumina_native_int", + "Illumina_native_qseq", + "Illumina_native_scarf", + "SOLiD_native", + "SOLiD_native_csfasta", + "SOLiD_native_qual", + "PacBio_HDF5", + "bam", + "cram", + "CompleteGenomics_native", + "OxfordNanopore_native" + ], + "field_type": "TEXT_CHOICE_FIELD" + } + ] + }, + "sample": { + "description": "A Sample defines an isolate of sequenceable material upon which sequencing experiments can be based. The Sample object may be a surrogate for taxonomy accession or an anonymized individual identifier. Or, it may fully specify provenance and isolation method of the starting material.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for each run.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "title", + "cardinality": "mandatory", + "description": "Short text that can be used to call out sample records in search results or in displays.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "taxon_id", + "cardinality": "mandatory", + "description": "NCBI Taxonomy Identifier. This is appropriate for individual organisms and some environmental samples.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "sample_description", + "cardinality": "optional", + "description": "Free-form text describing the sample, its origin, and its method of isolation.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_AREA_FIELD" + }, + { + "name": "biotic relationship [deprecated]", + "cardinality": "optional", + "description": "free text description of relationship(s) between the subject organism and other organism(s) it is associate with, e.g., parasite on species X; mutualist with species Y, the target organism is the subject of the relationship, and the other organism(s) is the object", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "trophic level", + "cardinality": "optional", + "description": "Trophic levels are the feeding position in a food chain. Microbes can be a range of producers (e.g. chemolithotroph)", + "cv": [ + "autotroph", + "carboxydotroph", + "chemoautotroph", + "chemoheterotroph", + "chemolithoautotroph", + "chemolithotroph", + "chemoorganoheterotroph", + "chemoorganotroph", + "chemosynthetic", + "chemotroph", + "copiotroph", + "diazotroph", + "facultative autotroph", + "heterotroph", + "lithoautotroph", + "lithoheterotroph", + "lithotroph", + "methanotroph", + "methylotroph", + "mixotroph", + "obligate chemoautolithotroph", + "oligotroph", + "organoheterotroph", + "organotroph", + "photoautotroph", + "photoheterotroph", + "photolithoautotroph", + "photolithotroph", + "photosynthetic", + "phototroph" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "known pathogenicity", + "cardinality": "optional", + "description": "To what is the entity pathogenic, for instance plant, fungi, bacteria", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "relationship to oxygen", + "cardinality": "optional", + "description": "Is this organism an aerobe, anaerobe? Please note that aerobic and anaerobic are valid descriptors for microbial environments", + "cv": [ + "aerobe", + "anaerobe", + "facultative", + "microaerophilic", + "microanaerobe", + "obligate aerobe", + "obligate anaerobe" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "propagation", + "cardinality": "optional", + "description": "The type of reproduction from the parent stock. Values for this field is specific to different taxa. For phage or virus: lytic/lysogenic/temperate/obligately lytic. For plasmids: incompatibility group. For eukaryotes: sexual/asexual. Mandatory for MIGs of eukayotes, plasmids and viruses.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "observed host symbionts", + "cardinality": "optional", + "description": "The taxonomic name of the organism(s) found living in mutualistic, commensalistic, or parasitic symbiosis with the specific host.", + "cv": [], + "units": "", + "field_type": "TAXON_FIELD", + "regex": "" + }, + { + "name": "sample collection device", + "cardinality": "optional", + "description": "The device used to collect an environmental sample. It is recommended to use terms listed under environmental sampling device (http://purl.obolibrary.org/obo/ENVO) and/or terms listed under specimen collection device (http://purl.obolibrary.org/obo/GENEPIO_0002094).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample collection method", + "cardinality": "optional", + "description": "The method employed for collecting the sample. Can be provided in the form of a PMID, DOI, url or text.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample storage temperature", + "cardinality": "optional", + "description": "temperature at which sample was stored, e.g. -80", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "sample storage location", + "cardinality": "optional", + "description": "Location at which sample was stored, usually name of a specific freezer/room. Indicate the location name.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "size-fraction lower threshold", + "cardinality": "optional", + "description": "Refers to the mesh/pore size used to retain the sample. Materials smaller than the size threshold are excluded from the sample", + "cv": [], + "units": "\u00b5m", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "size-fraction upper threshold", + "cardinality": "optional", + "description": "Refers to the mesh/pore size used to pre-filter/pre-sort the sample. Materials larger than the size threshold are excluded from the sample", + "cv": [], + "units": "\u00b5m", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "soil_taxonomic/FAO classification", + "cardinality": "optional", + "description": "soil classification from the FAO World Reference Database for Soil Resources", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "soil_taxonomic/local classification", + "cardinality": "optional", + "description": "soil classification based on local soil classification system", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "soil_taxonomic/local classification method", + "cardinality": "optional", + "description": "reference or method used in determining the local soil classification", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "soil type", + "cardinality": "optional", + "description": "Description of the soil type or classification. This field accepts terms under soil (http://purl.obolibrary.org/obo/ENVO_00001998). Multiple terms can be separated by pipes.", + "cv": [ + "Acrisol", + "Albeluvisol", + "Alisol", + "Andosol", + "Anthrosol", + "Arenosol", + "Calcisol", + "Cambisol", + "Chernozem", + "Cryosol", + "Durisol", + "Ferralsol", + "Fluvisol", + "Gleysol", + "Gypsisol", + "Histosol", + "Kastanozem", + "Leptosol", + "Lixisol", + "Luvisol", + "Nitisol", + "Phaeozem", + "Planosol", + "Plinthosol", + "Podzol", + "Regosol", + "Solonchak", + "Solonetz", + "Stagnosol", + "Technosol", + "Umbrisol", + "Vertisol" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "soil type method", + "cardinality": "optional", + "description": "reference or method used in determining soil series name or other lower-level classification", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "soil texture measurement", + "cardinality": "optional", + "description": "the relative proportion of different grain sizes of mineral particles in a soil, as described using a standard system; express as % sand (50 um to 2 mm), silt (2 um to 50 um), and clay (<2 um) with textural name (e.g., silty clay loam) optional.", + "cv": [], + "units": "% sand/silt/clay", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "soil texture method", + "cardinality": "optional", + "description": "reference or method used in determining soil texture", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "soil pH", + "cardinality": "optional", + "description": "pH measurement of the soil; e.g. 6.2", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "soil cover", + "cardinality": "optional", + "description": "Description of the material covering the sampled soil. This field accepts terms under ENVO:00010483, environmental material.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "oxygenation status of sample", + "cardinality": "optional", + "description": "oxygenation status of sample", + "cv": [ + "aerobic", + "anaerobic" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "microbial biomass", + "cardinality": "optional", + "description": "the part of the organic matter in the soil that constitutes living microorganisms smaller than 5-10 \u00b5m. IF you keep this, you would need to have correction factors used for conversion to the final units, which should be mg C (or N)/kg soil).", + "cv": [], + "units": "g/kg", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "project name", + "cardinality": "optional", + "description": "Name of the project within which the sequencing was organized", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "farm equipment sanitization", + "cardinality": "optional", + "description": "Method used to sanitize growing and harvesting equipment. This can including type and concentration of sanitizing solution. Multiple terms can be separated by one or more pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "equipment shared with other farms", + "cardinality": "optional", + "description": "List of planting, growing or harvesting equipment shared with other farms. This field accepts terms listed under agricultural implement (http://purl.obolibrary.org/obo/AGRO_00000416). Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "farm equipment used", + "cardinality": "optional", + "description": "List of equipment used for planting, fertilization, harvesting, irrigation, land levelling, residue management, weeding or transplanting during the growing season. This field accepts terms listed under agricultural implement (http://purl.obolibrary.org/obo/AGRO_00000416). Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "farm watering water source", + "cardinality": "optional", + "description": "Source of water used on the farm for irrigation of crops or watering of livestock.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food production system characteristics", + "cardinality": "optional", + "description": "Descriptors of the food production system or of the agricultural environment and growing conditions related to the farm production system, such as wild caught, organic, free-range, industrial, dairy, beef, domestic or cultivated food production. This field accepts terms listed under food production (http://purl.obolibrary.org/obo/FOODON_03530206). Multiple terms may apply and can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "animal water delivery method", + "cardinality": "optional", + "description": "Description of the equipment or method used to distribute water to livestock. This field accepts termed listed under water delivery equipment (http://opendata.inra.fr/EOL/EOL_0001653). Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "plant water delivery method", + "cardinality": "optional", + "description": "Description of the equipment or method used to distribute water to crops. This field accepts termed listed under irrigation process (http://purl.obolibrary.org/obo/AGRO_00000006). Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food harvesting process", + "cardinality": "optional", + "description": "A harvesting process is a process which takes in some food material from an individual or community of plant or animal organisms in a given context and time, and outputs a precursor or consumable food product. This may include a part of an organism or the whole, and may involve killing the organism.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food production characteristics", + "cardinality": "optional", + "description": "Descriptors of the food production system such as wild caught, free-range, organic, free-range, industrial, dairy, beef.", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "fertilizer administration date", + "cardinality": "optional", + "description": "Date of administration of soil amendment or fertilizer. Multiple terms may apply and can be separated by pipes, listing in reverse chronological order.", + "cv": [], + "units": "", + "field_type": "DATE_FIELD", + "regex": "" + }, + { + "name": "crop yield", + "cardinality": "optional", + "description": "Amount of crop produced per unit or area of land.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "ploidy", + "cardinality": "optional", + "description": "The ploidy level of the genome (e.g. allopolyploid, haploid, diploid, triploid, tetraploid). It has implications for the downstream study of duplicated gene and regions of the genomes (and perhaps for difficulties in assembly). For terms, please select terms listed under class ploidy (PATO:001374) of Phenotypic Quality Ontology (PATO), and for a browser of PATO (v 2018-03-27) please refer to http://purl.bioontology.org/ontology/PATO", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "number of replicons", + "cardinality": "optional", + "description": "Reports the number of replicons in a nuclear genome of eukaryotes, in the genome of a bacterium or archaea or the number of segments in a segmented virus. Always applied to the haploid chromosome count of a eukaryote. Mandatory for MIGS of eukaryotes, bacteria, archaea and segmented virus.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "extrachromosomal elements", + "cardinality": "optional", + "description": "Do plasmids exist of significant phenotypic consequence (e.g. ones that determine virulence or antibiotic resistance). Megaplasmids? Other plasmids (borrelia has 15+ plasmids).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "estimated size", + "cardinality": "optional", + "description": "The estimated size of the genome (in bp) prior to sequencing. Of particular importance in the sequencing of (eukaryotic) genome which could remain in draft form for a long or unspecified period. Mandatory for MIGS of eukaryotes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "target gene", + "cardinality": "optional", + "description": "Targeted gene or locus name for marker gene studies", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "target subfragment", + "cardinality": "optional", + "description": "Name of subfragment of a gene or locus. Important to e.g. identify special regions on marker genes like V6 on 16S rRNA", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "multiplex identifiers", + "cardinality": "optional", + "description": "Molecular barcodes, called Multiplex Identifiers (MIDs), that are used to specifically tag unique samples in a sequencing run. Sequence should be reported in uppercase letters", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sequence quality check", + "cardinality": "optional", + "description": "Indicate if the sequence has been called by automatic systems (none) or undergone a manual editing procedure (e.g. by inspecting the raw data or chromatograms). Applied only for sequences that are not submitted to SRA or DRA", + "cv": [ + "manual", + "none", + "software" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "chimera check software", + "cardinality": "optional", + "description": "Tool(s) used for chimera checking, including version number and parameters, to discover and remove chimeric sequences. A chimeric sequence is comprised of two or more phylogenetically distinct parent sequences.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "relevant electronic resources", + "cardinality": "optional", + "description": "A related resource that is referenced, cited, or otherwise associated to the sequence in the format of a PMID, DOI or URL", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "relevant standard operating procedures", + "cardinality": "optional", + "description": "Standard operating procedures used in assembly and/or annotation of genomes, metagenomes or environmental sequences in the format of a PMID, DOI or URL", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "16s recovered", + "cardinality": "optional", + "description": "Can a 16S gene be recovered from the submitted bin, SAG or MAG?", + "cv": [ + "No", + "Yes" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "16S recovery software", + "cardinality": "optional", + "description": "Tools used for 16S rRNA gene extraction. Add names and versions of software(s), parameters used", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "collection date", + "cardinality": "mandatory", + "description": "The date the sample was collected with the intention of sequencing, either as an instance (single point in time) or interval. In case no exact time is available, the date/time can be right truncated i.e. all of these are valid ISO8601 compliant times: 2008-01-23T19:23:10+00:00; 2008-01-23T19:23:10; 2008-01-23; 2008-01; 2008.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "(^[12][0-9]{3}(-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01])(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?(/[0-9]{4}(-[0-9]{2}(-[0-9]{2}(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?)?$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)" + }, + { + "name": "altitude", + "cardinality": "optional", + "description": "The altitude of the sample is the vertical distance between Earth's surface above Sea Level and the sampled position in the air.", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "((0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "geographic location (country and/or sea)", + "cardinality": "mandatory", + "description": "The geographical origin of where the sample was collected from, with the intention of sequencing, as defined by the country or sea name. Country or sea names should be chosen from the INSDC country list (http://insdc.org/country.html).", + "cv": [ + "Afghanistan", + "Albania", + "Algeria", + "American Samoa", + "Andorra", + "Angola", + "Anguilla", + "Antarctica", + "Antigua and Barbuda", + "Arctic Ocean", + "Argentina", + "Armenia", + "Aruba", + "Ashmore and Cartier Islands", + "Atlantic Ocean", + "Australia", + "Austria", + "Azerbaijan", + "Bahamas", + "Bahrain", + "Baker Island", + "Baltic Sea", + "Bangladesh", + "Barbados", + "Bassas da India", + "Belarus", + "Belgium", + "Belize", + "Benin", + "Bermuda", + "Bhutan", + "Bolivia", + "Borneo", + "Bosnia and Herzegovina", + "Botswana", + "Bouvet Island", + "Brazil", + "British Virgin Islands", + "Brunei", + "Bulgaria", + "Burkina Faso", + "Burundi", + "Cambodia", + "Cameroon", + "Canada", + "Cape Verde", + "Cayman Islands", + "Central African Republic", + "Chad", + "Chile", + "China", + "Christmas Island", + "Clipperton Island", + "Cocos Islands", + "Colombia", + "Comoros", + "Cook Islands", + "Coral Sea Islands", + "Costa Rica", + "Cote d'Ivoire", + "Croatia", + "Cuba", + "Curacao", + "Cyprus", + "Czechia", + "Czech Republic", + "Democratic Republic of the Congo", + "Denmark", + "Djibouti", + "Dominica", + "Dominican Republic", + "East Timor", + "Ecuador", + "Egypt", + "El Salvador", + "Equatorial Guinea", + "Eritrea", + "Estonia", + "Ethiopia", + "Europa Island", + "Falkland Islands (Islas Malvinas)", + "Faroe Islands", + "Fiji", + "Finland", + "France", + "French Guiana", + "French Polynesia", + "French Southern and Antarctic Lands", + "Gabon", + "Gambia", + "Gaza Strip", + "Georgia", + "Germany", + "Ghana", + "Gibraltar", + "Glorioso Islands", + "Greece", + "Greenland", + "Grenada", + "Guadeloupe", + "Guam", + "Guatemala", + "Guernsey", + "Guinea", + "Guinea-Bissau", + "Guyana", + "Haiti", + "Heard Island and McDonald Islands", + "Honduras", + "Hong Kong", + "Howland Island", + "Hungary", + "Iceland", + "India", + "Indian Ocean", + "Indonesia", + "Iran", + "Iraq", + "Ireland", + "Isle of Man", + "Israel", + "Italy", + "Jamaica", + "Jan Mayen", + "Japan", + "Jarvis Island", + "Jersey", + "Johnston Atoll", + "Jordan", + "Juan de Nova Island", + "Kazakhstan", + "Kenya", + "Kerguelen Archipelago", + "Kingman Reef", + "Kiribati", + "Kosovo", + "Kuwait", + "Kyrgyzstan", + "Laos", + "Latvia", + "Lebanon", + "Lesotho", + "Liberia", + "Libya", + "Liechtenstein", + "Lithuania", + "Luxembourg", + "Macau", + "Macedonia", + "Madagascar", + "Malawi", + "Malaysia", + "Maldives", + "Mali", + "Malta", + "Marshall Islands", + "Martinique", + "Mauritania", + "Mauritius", + "Mayotte", + "Mediterranean Sea", + "Mexico", + "Micronesia", + "Midway Islands", + "Moldova", + "Monaco", + "Mongolia", + "Montenegro", + "Montserrat", + "Morocco", + "Mozambique", + "Myanmar", + "Namibia", + "Nauru", + "Navassa Island", + "Nepal", + "Netherlands", + "New Caledonia", + "New Zealand", + "Nicaragua", + "Niger", + "Nigeria", + "Niue", + "Norfolk Island", + "North Korea", + "North Sea", + "Northern Mariana Islands", + "Norway", + "Oman", + "Pacific Ocean", + "Pakistan", + "Palau", + "Palmyra Atoll", + "Panama", + "Papua New Guinea", + "Paracel Islands", + "Paraguay", + "Peru", + "Philippines", + "Pitcairn Islands", + "Poland", + "Portugal", + "Puerto Rico", + "Qatar", + "Republic of the Congo", + "Reunion", + "Romania", + "Ross Sea", + "Russia", + "Rwanda", + "Saint Helena", + "Saint Kitts and Nevis", + "Saint Lucia", + "Saint Pierre and Miquelon", + "Saint Vincent and the Grenadines", + "Samoa", + "San Marino", + "Sao Tome and Principe", + "Saudi Arabia", + "Senegal", + "Serbia", + "Seychelles", + "Sierra Leone", + "Singapore", + "Sint Maarten", + "Slovakia", + "Slovenia", + "Solomon Islands", + "Somalia", + "South Africa", + "South Georgia and the South Sandwich Islands", + "South Korea", + "Southern Ocean", + "Spain", + "Spratly Islands", + "Sri Lanka", + "Sudan", + "Suriname", + "Svalbard", + "Swaziland", + "Sweden", + "Switzerland", + "Syria", + "Taiwan", + "Tajikistan", + "Tanzania", + "Tasman Sea", + "Thailand", + "Togo", + "Tokelau", + "Tonga", + "Trinidad and Tobago", + "Tromelin Island", + "Tunisia", + "Turkey", + "Turkmenistan", + "Turks and Caicos Islands", + "Tuvalu", + "USA", + "Uganda", + "Ukraine", + "United Arab Emirates", + "United Kingdom", + "Uruguay", + "Uzbekistan", + "Vanuatu", + "Venezuela", + "Viet Nam", + "Virgin Islands", + "Wake Island", + "Wallis and Futuna", + "West Bank", + "Western Sahara", + "Yemen", + "Zambia", + "Zimbabwe", + "missing: control sample", + "missing: data agreement established pre-2023", + "missing: endangered species", + "missing: human-identifiable", + "missing: lab stock", + "missing: sample group", + "missing: synthetic construct", + "missing: third party data", + "not applicable", + "not collected", + "not provided", + "restricted access" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "geographic location (latitude)", + "cardinality": "optional", + "description": "The geographical origin of the sample as defined by latitude. The values should be reported in decimal degrees and in WGS84 system", + "cv": [], + "units": "DD", + "field_type": "TEXT_FIELD", + "regex": "(^[+-]?[0-9]+.?[0-9]{0,8}$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)" + }, + { + "name": "geographic location (longitude)", + "cardinality": "optional", + "description": "The geographical origin of the sample as defined by longitude. The values should be reported in decimal degrees and in WGS84 system", + "cv": [], + "units": "DD", + "field_type": "TEXT_FIELD", + "regex": "(^[+-]?[0-9]+.?[0-9]{0,8}$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)" + }, + { + "name": "geographic location (region and locality)", + "cardinality": "optional", + "description": "The geographical origin of the sample as defined by the specific region name followed by the locality name.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "broad-scale environmental context", + "cardinality": "optional", + "description": "Report the major environmental system the sample or specimen came from. The system(s) identified should have a coarse spatial grain, to provide the general environmental context of where the sampling was done (e.g. in the desert or a rainforest). We recommend using subclasses of EnvO\u2019s biome class: http://purl.obolibrary.org/obo/ENVO_00000428. EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "local environmental context", + "cardinality": "optional", + "description": "Report the entity or entities which are in the sample or specimen\u2019s local vicinity and which you believe have significant causal influences on your sample or specimen. We recommend using EnvO terms which are of smaller spatial grain than your entry for \"broad-scale environmental context\". Terms, such as anatomical sites, from other OBO Library ontologies which interoperate with EnvO (e.g. UBERON) are accepted in this field. EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "environmental medium", + "cardinality": "optional", + "description": "Report the environmental material(s) immediately surrounding the sample or specimen at the time of sampling. We recommend using subclasses of 'environmental material' (http://purl.obolibrary.org/obo/ENVO_00010483). EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS . Terms from other OBO ontologies are permissible as long as they reference mass/volume nouns (e.g. air, water, blood) and not discrete, countable entities (e.g. a tree, a leaf, a table top).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "elevation", + "cardinality": "optional", + "description": "The elevation of the sampling site as measured by the vertical distance from mean sea level.", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "([+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "culture isolation date", + "cardinality": "optional", + "description": "A culture isolation date is a date-time entity marking the end of a process in which a sample yields a positive result for the target microbial analyte(s) in the form of an isolated colony or colonies.", + "cv": [], + "units": "", + "field_type": "DATE_FIELD", + "regex": "" + }, + { + "name": "sieving", + "cardinality": "optional", + "description": "Collection design of pooled samples and/or sieve size and amount of sample sieved", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "microbial biomass method", + "cardinality": "optional", + "description": "Reference or method used in determining microbial biomass", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "organism count", + "cardinality": "optional", + "description": "Total cell count of any organism (or group of organisms) per gram, volume or area of sample, should include name of organism followed by count. The method that was used for the enumeration (e.g. qPCR, atp, mpn, etc.) Should also be provided. (example: total prokaryotes; 3.5e7 cells per ml; qpcr)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "horizon method", + "cardinality": "optional", + "description": "Reference or method used in determining the horizon", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "extreme_unusual_properties/heavy metals", + "cardinality": "optional", + "description": "heavy metals present and concentrations of any drug used by subject and the frequency of usage; can include multiple heavy metals and concentrations", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "extreme_unusual_properties/heavy metals method", + "cardinality": "optional", + "description": "reference or method used in determining heavy metals", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "plant structure", + "cardinality": "optional", + "description": "name of plant structure that the sample was obtained from; for Plant Ontology (PO) terms see http://purl.bioontology.org/ontology/PO, e.g. petiole epidermis (PO_0000051); if an individual flower is sampled the sex of it can be recorded here", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host disease status", + "cardinality": "optional", + "description": "list of diseases with which the host has been diagnosed; can include multiple diagnoses. The value of the field depends on host; for humans the terms should be chosen from DO (Disease Ontology) at http://www.disease-ontology.org, other hosts are free text", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host common name", + "cardinality": "optional", + "description": "common name of the host, e.g. human", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host age", + "cardinality": "optional", + "description": "age of host at the time of sampling; relevant scale depends on species and study, e.g. could be seconds for amoebae or centuries for trees", + "cv": [], + "units": "years", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "host taxid", + "cardinality": "optional", + "description": "NCBI taxon id of the host, e.g. 9606", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "host life stage", + "cardinality": "optional", + "description": "description of life stage of host", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host height", + "cardinality": "optional", + "description": "the height of subject", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "((0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "host length", + "cardinality": "optional", + "description": "the length of subject", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "host total mass", + "cardinality": "optional", + "description": "total mass of the host at collection, the unit depends on host", + "cv": [], + "units": "kg", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "host phenotype", + "cardinality": "optional", + "description": "phenotype of host. For Phenotypic quality Ontology (PATO) (v 2013-10-28) terms, please see http://purl.bioontology.org/ontology/PATO", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host scientific name", + "cardinality": "optional", + "description": "Scientific name of the natural (as opposed to laboratory) host to the organism from which sample was obtained.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host subspecific genetic lineage", + "cardinality": "optional", + "description": "Information about the genetic distinctness of the host organism below the subspecies level e.g., serovar, serotype, biotype, ecotype, variety, cultivar, or any relevant genetic typing schemes like Group I plasmid. Subspecies should not be recorded in this term, but in the NCBI taxonomy. Supply both the lineage name and the lineage rank separated by a colon, e.g., biovar:abc123.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "link to climate information", + "cardinality": "optional", + "description": "link to climate resource", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "link to classification information", + "cardinality": "optional", + "description": "link to digitized soil maps or other soil classification information", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "climate environment", + "cardinality": "optional", + "description": "treatment involving an exposure to a particular climate; can include multiple climates", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "presence of pets, animals, or insects", + "cardinality": "optional", + "description": "The type and number of animals or insects present in the sampling space.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "current vegetation", + "cardinality": "optional", + "description": "vegetation classification from one or more standard classification systems, or agricultural crop", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "gaseous environment", + "cardinality": "optional", + "description": "use of conditions with differing gaseous environments; should include the name of gaseous compound, amount administered, treatment duration, interval and total experimental duration; can include multiple gaseous environment regimens", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "humidity", + "cardinality": "optional", + "description": "amount of water vapour in the air, at the time of sampling", + "cv": [], + "units": "g/m3", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "current vegetation method", + "cardinality": "optional", + "description": "reference or method used in vegetation classification", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "seasonal environment", + "cardinality": "optional", + "description": "treatment involving an exposure to a particular season (e.g. winter, summer, rabi, rainy etc.)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "soil horizon", + "cardinality": "optional", + "description": "specific layer in the land area which measures parallel to the soil surface and possesses physical characteristics which differ from the layers above and beneath", + "cv": [ + "A horizon", + "B horizon", + "E horizon", + "O horizon", + "Permafrost", + "R layer" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "solar irradiance", + "cardinality": "optional", + "description": "the amount of solar energy that arrives at a specific area of a surface during a specific time interval", + "cv": [], + "units": "W/m2", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "drainage classification", + "cardinality": "optional", + "description": "drainage classification from a standard system such as the USDA system", + "cv": [ + "excessively drained", + "moderately well", + "poorly", + "somewhat poorly", + "very poorly", + "well" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "temperature", + "cardinality": "optional", + "description": "temperature of the sample at time of sampling", + "cv": [], + "units": "\u00baC", + "field_type": "TEXT_FIELD", + "regex": "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "pH method", + "cardinality": "optional", + "description": "reference or method used in determining pH", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "slope gradient", + "cardinality": "optional", + "description": "commonly called slope. The angle between ground surface and a horizontal line (in percent). This is the direction that overland water would flow. This measure is usually taken with a hand level meter or clinometer.", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "slope aspect", + "cardinality": "optional", + "description": "the direction a slope faces. While looking down a slope use a compass to record the direction you are facing (direction or degrees); e.g., NW or 315\u00b0. This measure provides an indication of sun and wind exposure that will influence soil temperature and evapotranspiration.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "profile position", + "cardinality": "optional", + "description": "cross-sectional position in the hillslope where sample was collected.sample area position in relation to surrounding areas", + "cv": [ + "backslope", + "footslope", + "shoulder", + "summit", + "toeslope" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "total organic carbon method", + "cardinality": "optional", + "description": "Reference or method used in determining total organic carbon", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "total nitrogen content method", + "cardinality": "optional", + "description": "Reference or method used in determining the total nitrogen", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "total phosphate", + "cardinality": "optional", + "description": "total amount or concentration of phosphate", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "total nitrogen concentration", + "cardinality": "optional", + "description": "Concentration of nitrogen (total). Total nitrogen concentration of water samples, calculated by: total nitrogen = total dissolved nitrogen + particulate nitrogen. Can also be measured without filtering, reported as nitrogen", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "total carbon", + "cardinality": "optional", + "description": "total carbon content", + "cv": [], + "units": "\u00b5g/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "total organic carbon", + "cardinality": "optional", + "description": "Definition for soil: total organic C content of the soil units of g C/kg soil. Definition otherwise: total organic carbon content", + "cv": [], + "units": "g/kg", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "water pH", + "cardinality": "optional", + "description": "pH measurement of the sample, or liquid portion of sample, or aqueous phase of the fluid.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[\\d][0-4]?(\\.[\\d]{1,10})?" + }, + { + "name": "photosynthetic activity method", + "cardinality": "optional", + "description": "Reference or method used in measurement of photosythentic activity", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "photosynthetic activity", + "cardinality": "optional", + "description": "Measurement of photosythetic activity (i.e. leaf gas exchange / chlorophyll fluorescence emissions / reflectance / transpiration) Please also include the term method term detailing the method of activity measurement.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "source material identifiers", + "cardinality": "optional", + "description": "A unique identifier assigned to a material sample (as defined by http://rs.tdwg.org/dwc/terms/materialSampleID, and as opposed to a particular digital record of a material sample) used for extracting nucleic acids, and subsequent sequencing. The identifier can refer either to the original material collected or to any derived sub-samples. The INSDC qualifiers /specimen_voucher, /bio_material, or /culture_collection may or may not share the same value as the source_mat_id field. For instance, the /specimen_voucher qualifier and source_mat_id may both contain 'UAM:Herps:14' , referring to both the specimen voucher and sampled tissue with the same identifier. However, the /culture_collection qualifier may refer to a value from an initial culture (e.g. ATCC:11775) while source_mat_id would refer to an identifier from some derived culture from which the nucleic acids were extracted (e.g. xatc123 or ark:/2154/R2).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "history/previous land use", + "cardinality": "optional", + "description": "previous land use and dates", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "previous land use method", + "cardinality": "optional", + "description": "Reference or method used in determining previous land use and dates", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "history/crop rotation", + "cardinality": "optional", + "description": "whether or not crop is rotated, and if yes, rotation schedule", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "history/agrochemical additions", + "cardinality": "optional", + "description": "addition of fertilizers, pesticides, etc. - amount and time of applications", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "history/tillage", + "cardinality": "optional", + "description": "note method(s) used for tilling", + "cv": [ + "chisel", + "cutting disc", + "disc plough", + "drill", + "mouldboard", + "ridge till", + "strip tillage", + "tined", + "zonal tillage" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "history/fire", + "cardinality": "optional", + "description": "historical and/or physical evidence of fire", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "history/flooding", + "cardinality": "optional", + "description": "historical and/or physical evidence of flooding", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "history/extreme events", + "cardinality": "optional", + "description": "unusual physical events that may have affected microbial populations", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "mean seasonal humidity", + "cardinality": "optional", + "description": "Average humidity of the region throughout the growing season.", + "cv": [], + "units": "g/m3", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "mean seasonal temperature", + "cardinality": "optional", + "description": "Mean seasonal temperature", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "mean seasonal precipitation", + "cardinality": "optional", + "description": "The average of all seasonal precipitation values known, or an estimated equivalent value derived by such methods as regional indexes or Isohyetal maps.", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "season", + "cardinality": "optional", + "description": "The season when sampling occurred. Any of the four periods into which the year is divided by the equinoxes and solstices. This field accepts terms listed under season (http://purl.obolibrary.org/obo/NCIT_C94729).", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "mean annual precipitation", + "cardinality": "optional", + "description": "The average of all annual precipitation values known, or an estimated equivalent value derived by such methods as regional indexes or Isohyetal maps.", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "mean annual temperature", + "cardinality": "optional", + "description": "Mean annual temperature", + "cv": [], + "units": "\u00baC", + "field_type": "TEXT_FIELD", + "regex": "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "host genotype", + "cardinality": "optional", + "description": "observed genotype", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host specificity or range", + "cardinality": "optional", + "description": "The range and diversity of host species that an organism is capable of infecting, defined by NCBI taxonomy identifier.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "host dry mass", + "cardinality": "optional", + "description": "measurement of dry mass", + "cv": [], + "units": "mg", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "spike-in microbial strain", + "cardinality": "optional", + "description": "Taxonomic information about the spike-in organism(s) at the strain level. This field accepts terms under organism (http://purl.obolibrary.org/obo/NCIT_C14250). This field also accepts identification numbers from NCBI under https://www.ncbi.nlm.nih.gov/taxonomy. Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "TAXON_FIELD", + "regex": "" + }, + { + "name": "perturbation", + "cardinality": "optional", + "description": "type of perturbation, e.g. chemical administration, physical disturbance, etc., coupled with time that perturbation occurred; can include multiple perturbation types", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "negative control type", + "cardinality": "optional", + "description": "The substance or equipment used as a negative control in an investigation", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "positive control type", + "cardinality": "optional", + "description": "The substance, mixture, product, or apparatus used to verify that a process which is part of an investigation delivers a true positive.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "experimental factor", + "cardinality": "optional", + "description": "Experimental factors are essentially the variable aspects of an experiment design which can be used to describe an experiment, or set of experiments, in an increasingly detailed manner. This field accepts ontology terms from Experimental Factor Ontology (EFO) and/or Ontology for Biomedical Investigations (OBI). For a browser of EFO (v 2.95) terms, please see http://purl.bioontology.org/ontology/EFO; for a browser of OBI (v 2018-02-12) terms please see http://purl.bioontology.org/ontology/OBI. E.g. time series design [EFO:EFO_0001779]", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "encoded traits", + "cardinality": "optional", + "description": "Should include key traits like antibiotic resistance or xenobiotic degradation phenotypes for plasmids, converting genes for phage", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "genetic modification", + "cardinality": "optional", + "description": "A genetic modification of the genome of an organism which may occur naturally by spontaneous mutation, or be introduced by some experimental means. Examples of genetic modification include specification of a transgene or the gene knocked-out or details of transient transfection.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "subspecific genetic lineage", + "cardinality": "optional", + "description": "Information about the genetic distinctness of the sequenced organism below the subspecies level, e.g., serovar, serotype, biotype, ecotype, or any relevant genetic typing schemes like Group I plasmid. Subspecies should not be recorded in this term, but in the NCBI taxonomy. Supply both the lineage name and the lineage rank separated by a colon, e.g., biovar:abc123.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "ancestral data", + "cardinality": "optional", + "description": "information about either pedigree or other description of ancestral information (e.g. parental variety in case of mutant or selection), e.g. A/3*B (meaning [(A x B) x B] x B)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "taxonomic classification", + "cardinality": "optional", + "description": "Method used for taxonomic classification, along with reference database used, classification rank, and thresholds used to classify new genomes. Expected values are: classification method, database name, and other parameters e.g. vConTACT vContact2 (references from NCBI RefSeq v83, genus rank classification, default parameters)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "plant growth medium", + "cardinality": "optional", + "description": "Specification of the media for growing the plants or tissue cultured samples, e.g. soil, aeroponic, hydroponic, in vitro solid culture medium, in vitro liquid culture medium. Recommended value is a specific value from EO:plant growth medium (follow this link for terms http://purl.obolibrary.org/obo/EO_0007147).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "rooting medium macronutrients", + "cardinality": "optional", + "description": "measurement of the culture rooting medium macronutrients (N,P, K, Ca, Mg, S); e.g. KH2PO4 (170mg/L)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "rooting medium carbon", + "cardinality": "optional", + "description": "source of organic carbon in the culture rooting medium; e.g. sucrose", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "isolation and growth condition", + "cardinality": "optional", + "description": "Publication reference in the form of pubmed ID (pmid), digital object identifier (doi) or url for isolation and growth condition specifications of the organism/material. Mandatory for MIGS and MIMARKS Specimen.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "annotation source", + "cardinality": "optional", + "description": "For cases where annotation was provided by a community jamboree or model organism database rather than by a specific submitter", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "reference for biomaterial", + "cardinality": "optional", + "description": "Primary publication if isolated before genome publication; otherwise, primary genome report. Mandatory for MIGS of bacteria and archaea.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sequencing location", + "cardinality": "optional", + "description": "The location the sequencing run was performed. Indicate the name of the lab or core facility where samples were sequenced.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "enrichment protocol", + "cardinality": "optional", + "description": "The microbiological workflow or protocol followed to test for the presence or enumeration of the target microbial analyte(s). Please provide a PubMed or DOI reference for published protocols.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "library preparation kit", + "cardinality": "optional", + "description": "Packaged kits (containing adapters, indexes, enzymes, buffers etc.), tailored for specific sequencing workflows, which allow the simplified preparation of sequencing-ready libraries for small genomes, amplicons, and plasmids.", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample pooling", + "cardinality": "optional", + "description": "Physical combination of several instances of like material, e.g. RNA extracted from samples or dishes of cell cultures into one big aliquot of cells. Please provide a short description of the samples that were pooled.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "lot number", + "cardinality": "optional", + "description": "A distinctive alpha-numeric identification code assigned by the manufacturer or distributor to a specific quantity of manufactured material or product within a batch. Synonym: Batch Number. The submitter should provide lot number of the item followed by the item name for which the lot number was provided.", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "single cell or viral particle lysis approach", + "cardinality": "optional", + "description": "Method used to free DNA from interior of the cell(s) or particle(s)", + "cv": [ + "chemical", + "combination", + "enzymatic", + "physical" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "single cell or viral particle lysis kit protocol", + "cardinality": "optional", + "description": "Name of the kit or standard protocol used for cell(s) or particle(s) lysis", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pooled DNA extract total", + "cardinality": "optional", + "description": "Indicate whether multiple DNA extractions were mixed. If the answer yes, the number of extracts that were pooled should be given. [ENA version of MIxS term: pooling of DNA extracts (if done). ]", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "([0-9]*)" + }, + { + "name": "sample material processing", + "cardinality": "optional", + "description": "A brief description of any processing applied to the sample during or after retrieving the sample from environment, or a link to the relevant protocol(s) performed.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample volume or weight for DNA extraction", + "cardinality": "optional", + "description": "Volume (ml) or mass (g) of total collected sample processed for DNA extraction. Note: total sample collected should be entered under the term 'sample size'.", + "cv": [], + "units": "ng", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "nucleic acid extraction", + "cardinality": "optional", + "description": "A link to a literature reference, electronic resource or a standard operating procedure (SOP), that describes the material separation to recover the nucleic acid fraction from a sample", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "nucleic acid amplification", + "cardinality": "optional", + "description": "A link to a literature reference, electronic resource or a standard operating procedure (SOP), that describes the enzymatic amplification (PCR, TMA, NASBA) of specific nucleic acids", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "library size", + "cardinality": "optional", + "description": "Total number of clones in the library prepared for the project", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "library reads sequenced", + "cardinality": "optional", + "description": "Total number of clones sequenced from the library", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "library construction method", + "cardinality": "optional", + "description": "Library construction method used for clone libraries", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "library vector", + "cardinality": "optional", + "description": "Cloning vector type(s) used in construction of libraries", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "library screening strategy", + "cardinality": "optional", + "description": "Specific enrichment or screening methods applied before and/or after creating clone libraries in order to select a specific group of sequences", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pcr conditions", + "cardinality": "optional", + "description": "Description of reaction conditions and components for PCR in the form of 'initial denaturation:94degC_1.5min; annealing=...'", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pcr primers", + "cardinality": "optional", + "description": "PCR primers that were used to amplify the sequence of the targeted gene, locus or subfragment. This field should contain all the primers used for a single PCR reaction if multiple forward or reverse primers are present in a single PCR reaction. The primer sequence should be reported in uppercase letters", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "adapters", + "cardinality": "optional", + "description": "Adapters provide priming sequences for both amplification and sequencing of the sample-library fragments. Both adapters should be reported; in uppercase letters", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food shipping transportation vehicle", + "cardinality": "optional", + "description": "A descriptor for the mobile machine which is used to transport food commodities along the food distribution system. This field accepts terms listed under vehicle (http://purl.obolibrary.org/obo/ENVO_01000604). If the proper descrptor is not listed please use text to describe the mode of travel. Multiple terms can be separated by one or more pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "water source shared", + "cardinality": "optional", + "description": "Other users sharing access to the same water source. Multiple terms can be separated by one or more pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food source", + "cardinality": "optional", + "description": "Type of plant or animal from which the food product or its major ingredient is derived or a chemical food source [FDA CFSAN 1995].", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food shipping transportation method", + "cardinality": "optional", + "description": "A descriptor for the method of movement of food commodity along the food distribution system. This field accepts terms listed under travel mode (http://purl.obolibrary.org/obo/GENEPIO_0001064). If the proper descrptor is not listed please use text to describe the mode of travel. Multiple terms can be separated by one or more pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food product type", + "cardinality": "optional", + "description": "A food product type is a class of food products that is differentiated by its food composition (e.g., single- or multi-ingredient), processing and/or consumption characteristics. This does not include brand name products but it may include generic food dish categories. This field accepts terms under food product type (http://purl.obolibrary.org/obo/FOODON:03400361). For terms related to food product for an animal, consult food product for animal (http://purl.obolibrary.org/obo/FOODON_03309997). If the proper descriptor is not listed please use text to describe the food type. Multiple terms can be separated by one or more pipes.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "relative location of sample", + "cardinality": "optional", + "description": "Location of sampled soil to other parts of the farm e.g. under crop plant, near irrigation ditch, from the dirt road.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "porosity", + "cardinality": "optional", + "description": "Porosity of deposited sediment is volume of voids divided by the total volume of sample", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[0-9]+" + }, + { + "name": "depth", + "cardinality": "optional", + "description": "The vertical distance below local surface, e.g. for sediment or soil samples depth is measured from sediment or soil surface, respectively. Depth can be reported as an interval for subsurface samples.", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "((0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "environment adjacent to site", + "cardinality": "optional", + "description": "Description of the environmental system or features that are adjacent to the sampling site. This field accepts terms under ecosystem (http://purl.obolibrary.org/obo/ENVO_01001110) and human construction (http://purl.obolibrary.org/obo/ENVO_00000070). Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "fungicide regimen", + "cardinality": "optional", + "description": "information about treatment involving use of fungicides; should include the name of fungicide, amount administered, treatment duration, interval and total experimental duration; can include multiple fungicide regimens", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "herbicide regimen", + "cardinality": "optional", + "description": "information about treatment involving use of herbicides; information about treatment involving use of growth hormones; should include the name of herbicide, amount administered, treatment duration, interval and total experimental duration; can include multiple regimens", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "non-mineral nutrient regimen", + "cardinality": "optional", + "description": "information about treatment involving the exposure of plant to non-mineral nutrient such as oxygen, hydrogen or carbon; should include the name of non-mineral nutrient, amount administered, treatment duration, interval and total experimental duration; can include multiple non-mineral nutrient regimens", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pesticide regimen", + "cardinality": "optional", + "description": "information about treatment involving use of insecticides; should include the name of pesticide, amount administered, treatment duration, interval and total experimental duration; can include multiple pesticide regimens", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pH regimen", + "cardinality": "optional", + "description": "information about treatment involving exposure of plants to varying levels of pH of the growth media; can include multiple regimen", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "salt regimen", + "cardinality": "optional", + "description": "information about treatment involving use of salts as supplement to liquid and soil growth media; should include the name of salt, amount administered, treatment duration, interval and total experimental duration; can include multiple salt regimens", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "standing water regimen", + "cardinality": "optional", + "description": "treatment involving an exposure to standing water during a plant's life span, types can be flood water or standing water; can include multiple regimens", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "watering regimen", + "cardinality": "optional", + "description": "information about treatment involving an exposure to watering frequencies; can include multiple regimens", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "water temperature regimen", + "cardinality": "optional", + "description": "information about treatment involving an exposure to water with varying degree of temperature; can include multiple regimens", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "chemical administration", + "cardinality": "optional", + "description": "list of chemical compounds administered to the host or site where sampling occurred, and when (e.g. antibiotics, N fertilizer, air filter); can include multiple compounds. For Chemical Entities of Biological Interest ontology (CHEBI) (v111), please see http://purl.bioontology.org/ontology/CHEBI", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + } + ] + } +} \ No newline at end of file diff --git a/templates/ERC000055/README.md b/templates/ERC000055/README.md new file mode 100644 index 0000000..21837c6 --- /dev/null +++ b/templates/ERC000055/README.md @@ -0,0 +1,235 @@ +# ERC000055: GSC MIxS agriculture + +Genomic Standards Consortium package extension for reporting of measurements and observations obtained from the environment where the sample was obtained. By choosing the environmental package, a selection of fields can be made from a relevant subsets of the GSC terms. + +## Study + +A Study is a container for a sequencing investigation that may comprise multiple experiments. The Study has an overall goal, but is otherwise minimally defined in the SRA. A Study is composed of a descriptor, zero or more experiments, and zero or more analyses. The submitter may decorate the Study with web links and properties. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:---------------|:--------------|:---------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for a study. this is used to link experiments to the study. | | +| title | mandatory | Title of the study as would be used in a publication. | | +| study_type | mandatory | The study_type presents a controlled vocabulary for expressing the overall purpose of the study. | Whole Genome Sequencing, Metagenomics, Transcriptome Analysis, Resequencing, Epigenetics, Synthetic Genomics, Forensic or Paleo-genomics, Gene Regulation Study, Cancer Genomics, Population Genomics, RNASeq, Exome Sequencing, Pooled Clone Sequencing, Transcriptome Sequencing, Other | +| new_study_type | optional | Optional if 'study_type' is not 'other'. to propose a new term, select other and enter a new study type. | | +| study_abstract | optional | Briefly describes the goals, purpose, and scope of the study. this need not be listed if it can be inherited from a referenced publication. | | + +## Experiment + +An experiment object serves as a metadata record encapsulating essential details about a sequencing experiment, including the experimental design, sequencing type, and relevant parameters. This information enhances the interpretation and contextual understanding of nucleotide sequences submitted to the archive. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:------------------------------|:--------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for each experiment. this is used to link runs to experiments. | | +| title | optional | Short text that can be used to call out experiment records in searches or in displays. this element is technically optional but should be used for all new records. | | +| study_alias | mandatory | Identifies the parent study. (from study metadata) | | +| sample_alias | mandatory | (from sample metadata) | | +| design_description | optional | Goal and setup of the individual library including library was constructed. | | +| library_name | optional | The submitter's name for this library. | | +| library_strategy | mandatory | Sequencing technique intended for this library. | WGS, WGA, WXS, RNA-Seq, ssRNA-seq, snRNA-seq, miRNA-Seq, ncRNA-Seq, FL-cDNA, EST, Hi-C, ATAC-seq, WCS, RAD-Seq, CLONE, POOLCLONE, AMPLICON, CLONEEND, FINISHING, ChIP-Seq, MNase-Seq, DNase-Hypersensitivity, Bisulfite-Seq, CTS, MRE-Seq, MeDIP-Seq, MBD-Seq, Tn-Seq, VALIDATION, FAIRE-seq, SELEX, RIP-Seq, ChIA-PET, Synthetic-Long-Read, Targeted-Capture, Tethered Chromatin Conformation Capture, NOMe-Seq, ChM-Seq, GBS, Ribo-Seq, OTHER | +| library_source | mandatory | The library_source specifies the type of source material that is being sequenced. | GENOMIC, GENOMIC SINGLE CELL, TRANSCRIPTOMIC, TRANSCRIPTOMIC SINGLE CELL, METAGENOMIC, METATRANSCRIPTOMIC, SYNTHETIC, VIRAL RNA, OTHER | +| library_selection | mandatory | Method used to enrich the target in the sequence library preparation | RANDOM, PCR, RANDOM PCR, RT-PCR, HMPR, MF, repeat fractionation, size fractionation, MSLL, cDNA, cDNA_randomPriming, cDNA_oligo_dT, PolyA, Oligo-dT, Inverse rRNA, Inverse rRNA selection, ChIP, ChIP-Seq, MNase, DNase, Hybrid Selection, Reduced Representation, Restriction Digest, 5-methylcytidine antibody, MBD2 protein methyl-CpG binding domain, CAGE, RACE, MDA, padlock probes capture method, other, unspecified | +| library_layout | mandatory | Library_layout specifies whether to expect single, paired, or other configuration of reads. in the case of paired reads, information about the relative distance and orientation is specified. | | +| insert_size | optional | Insert size for paired reads | | +| library_construction_protocol | optional | Free form text describing the protocol by which the sequencing library was constructed. | | +| platform | mandatory | The platform record selects which sequencing platform and platform-specific runtime parameters. this will be determined by the center. optional if 'instrument_model' is provided. | LS454, ILLUMINA, HELICOS, ABI_SOLID, COMPLETE_GENOMICS, BGISEQ, OXFORD_NANOPORE, PACBIO_SMRT, ION_TORRENT, CAPILLARY, DNBSEQ, ELEMENT, ULTIMA, VELA_DIAGNOSTICS, GENAPSYS, GENEMIND, TAPESTRI | +| instrument_model | mandatory | Model of the sequencing instrument. | 454 GS, 454 GS 20, 454 GS FLX, 454 GS FLX Titanium, 454 GS FLX+, 454 GS Junior, AB 310 Genetic Analyzer, AB 3130 Genetic Analyzer, AB 3130xL Genetic Analyzer, AB 3500 Genetic Analyzer, AB 3500xL Genetic Analyzer, AB 3730 Genetic Analyzer, AB 3730xL Genetic Analyzer, AB 5500 Genetic Analyzer, AB 5500xl Genetic Analyzer, AB 5500xl-W Genetic Analysis System, AB SOLiD 3 Plus System, AB SOLiD 4 System, AB SOLiD 4hq System, AB SOLiD PI System, AB SOLiD System, AB SOLiD System 2.0, AB SOLiD System 3.0, BGISEQ-50, BGISEQ-500, Complete Genomics, DNBSEQ-G400, DNBSEQ-G400 FAST, DNBSEQ-G50, DNBSEQ-T7, Element AVITI, FASTASeq 300, GENIUS, GS111, Genapsys Sequencer, GenoCare 1600, GenoLab M, GridION, Helicos HeliScope, HiSeq X Five, HiSeq X Ten, Illumina Genome Analyzer, Illumina Genome Analyzer II, Illumina Genome Analyzer IIx, Illumina HiScanSQ, Illumina HiSeq 1000, Illumina HiSeq 1500, Illumina HiSeq 2000, Illumina HiSeq 2500, Illumina HiSeq 3000, Illumina HiSeq 4000, Illumina HiSeq X, Illumina MiSeq, Illumina MiniSeq, Illumina NovaSeq 6000, Illumina NovaSeq X, Illumina iSeq 100, Ion GeneStudio S5, Ion GeneStudio S5 Plus, Ion GeneStudio S5 Prime, Ion Torrent Genexus, Ion Torrent PGM, Ion Torrent Proton, Ion Torrent S5, Ion Torrent S5 XL, MGISEQ-2000RS, MinION, NextSeq 1000, NextSeq 2000, NextSeq 500, NextSeq 550, Onso, PacBio RS, PacBio RS II, PromethION, Revio, Sentosa SQ301, Sequel, Sequel II, Sequel IIe, Tapestri, UG 100, unspecified | + +## Run + +A run contains a group of reads generated for a particular experiment. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:-----------------|:--------------|:--------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for each run. | | +| experiment_alias | mandatory | From_experiment_metadata | | +| file_name | mandatory | The name or relative pathname of a run data file. | | +| file_format | mandatory | The run data file model. | sra, srf, sff, fastq, fasta, tab, 454_native, 454_native_seq, 454_native_qual, Helicos_native, Illumina_native, Illumina_native_seq, Illumina_native_prb, Illumina_native_int, Illumina_native_qseq, Illumina_native_scarf, SOLiD_native, SOLiD_native_csfasta, SOLiD_native_qual, PacBio_HDF5, bam, cram, CompleteGenomics_native, OxfordNanopore_native | + +## Sample + +A Sample defines an isolate of sequenceable material upon which sequencing experiments can be based. The Sample object may be a surrogate for taxonomy accession or an anonymized individual identifier. Or, it may fully specify provenance and isolation method of the starting material. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:-------------------------------------------------|:--------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for each run. | | +| title | mandatory | Short text that can be used to call out sample records in search results or in displays. | | +| taxon_id | mandatory | Ncbi taxonomy identifier. this is appropriate for individual organisms and some environmental samples. | | +| sample_description | optional | Free-form text describing the sample, its origin, and its method of isolation. | | +| biotic relationship [deprecated] | optional | Free text description of relationship(s) between the subject organism and other organism(s) it is associate with, e.g., parasite on species x; mutualist with species y, the target organism is the subject of the relationship, and the other organism(s) is the object | | +| trophic level | optional | Trophic levels are the feeding position in a food chain. microbes can be a range of producers (e.g. chemolithotroph) | autotroph, carboxydotroph, chemoautotroph, chemoheterotroph, chemolithoautotroph, chemolithotroph, chemoorganoheterotroph, chemoorganotroph, chemosynthetic, chemotroph, copiotroph, diazotroph, facultative autotroph, heterotroph, lithoautotroph, lithoheterotroph, lithotroph, methanotroph, methylotroph, mixotroph, obligate chemoautolithotroph, oligotroph, organoheterotroph, organotroph, photoautotroph, photoheterotroph, photolithoautotroph, photolithotroph, photosynthetic, phototroph | +| known pathogenicity | optional | To what is the entity pathogenic, for instance plant, fungi, bacteria | | +| relationship to oxygen | optional | Is this organism an aerobe, anaerobe? please note that aerobic and anaerobic are valid descriptors for microbial environments | aerobe, anaerobe, facultative, microaerophilic, microanaerobe, obligate aerobe, obligate anaerobe | +| propagation | optional | The type of reproduction from the parent stock. values for this field is specific to different taxa. for phage or virus: lytic/lysogenic/temperate/obligately lytic. for plasmids: incompatibility group. for eukaryotes: sexual/asexual. mandatory for migs of eukayotes, plasmids and viruses. | | +| observed host symbionts | optional | The taxonomic name of the organism(s) found living in mutualistic, commensalistic, or parasitic symbiosis with the specific host. | | +| sample collection device | optional | The device used to collect an environmental sample. it is recommended to use terms listed under environmental sampling device (http://purl.obolibrary.org/obo/envo) and/or terms listed under specimen collection device (http://purl.obolibrary.org/obo/genepio_0002094). | | +| sample collection method | optional | The method employed for collecting the sample. can be provided in the form of a pmid, doi, url or text. | | +| sample storage temperature | optional | Temperature at which sample was stored, e.g. -80 (Units: °C) | | +| sample storage location | optional | Location at which sample was stored, usually name of a specific freezer/room. indicate the location name. | | +| size-fraction lower threshold | optional | Refers to the mesh/pore size used to retain the sample. materials smaller than the size threshold are excluded from the sample (Units: µm) | | +| size-fraction upper threshold | optional | Refers to the mesh/pore size used to pre-filter/pre-sort the sample. materials larger than the size threshold are excluded from the sample (Units: µm) | | +| soil_taxonomic/FAO classification | optional | Soil classification from the fao world reference database for soil resources | | +| soil_taxonomic/local classification | optional | Soil classification based on local soil classification system | | +| soil_taxonomic/local classification method | optional | Reference or method used in determining the local soil classification | | +| soil type | optional | Description of the soil type or classification. this field accepts terms under soil (http://purl.obolibrary.org/obo/envo_00001998). multiple terms can be separated by pipes. | Acrisol, Albeluvisol, Alisol, Andosol, Anthrosol, Arenosol, Calcisol, Cambisol, Chernozem, Cryosol, Durisol, Ferralsol, Fluvisol, Gleysol, Gypsisol, Histosol, Kastanozem, Leptosol, Lixisol, Luvisol, Nitisol, Phaeozem, Planosol, Plinthosol, Podzol, Regosol, Solonchak, Solonetz, Stagnosol, Technosol, Umbrisol, Vertisol | +| soil type method | optional | Reference or method used in determining soil series name or other lower-level classification | | +| soil texture measurement | optional | The relative proportion of different grain sizes of mineral particles in a soil, as described using a standard system; express as % sand (50 um to 2 mm), silt (2 um to 50 um), and clay (<2 um) with textural name (e.g., silty clay loam) optional. (Units: % sand/silt/clay) | | +| soil texture method | optional | Reference or method used in determining soil texture | | +| soil pH | optional | Ph measurement of the soil; e.g. 6.2 | | +| soil cover | optional | Description of the material covering the sampled soil. this field accepts terms under envo:00010483, environmental material. | | +| oxygenation status of sample | optional | Oxygenation status of sample | aerobic, anaerobic | +| microbial biomass | optional | The part of the organic matter in the soil that constitutes living microorganisms smaller than 5-10 µm. if you keep this, you would need to have correction factors used for conversion to the final units, which should be mg c (or n)/kg soil). (Units: g/kg) | | +| project name | optional | Name of the project within which the sequencing was organized | | +| farm equipment sanitization | optional | Method used to sanitize growing and harvesting equipment. this can including type and concentration of sanitizing solution. multiple terms can be separated by one or more pipes. | | +| equipment shared with other farms | optional | List of planting, growing or harvesting equipment shared with other farms. this field accepts terms listed under agricultural implement (http://purl.obolibrary.org/obo/agro_00000416). multiple terms can be separated by pipes. | | +| farm equipment used | optional | List of equipment used for planting, fertilization, harvesting, irrigation, land levelling, residue management, weeding or transplanting during the growing season. this field accepts terms listed under agricultural implement (http://purl.obolibrary.org/obo/agro_00000416). multiple terms can be separated by pipes. | | +| farm watering water source | optional | Source of water used on the farm for irrigation of crops or watering of livestock. | | +| food production system characteristics | optional | Descriptors of the food production system or of the agricultural environment and growing conditions related to the farm production system, such as wild caught, organic, free-range, industrial, dairy, beef, domestic or cultivated food production. this field accepts terms listed under food production (http://purl.obolibrary.org/obo/foodon_03530206). multiple terms may apply and can be separated by pipes. | | +| animal water delivery method | optional | Description of the equipment or method used to distribute water to livestock. this field accepts termed listed under water delivery equipment (http://opendata.inra.fr/eol/eol_0001653). multiple terms can be separated by pipes. | | +| plant water delivery method | optional | Description of the equipment or method used to distribute water to crops. this field accepts termed listed under irrigation process (http://purl.obolibrary.org/obo/agro_00000006). multiple terms can be separated by pipes. | | +| food harvesting process | optional | A harvesting process is a process which takes in some food material from an individual or community of plant or animal organisms in a given context and time, and outputs a precursor or consumable food product. this may include a part of an organism or the whole, and may involve killing the organism. | | +| food production characteristics | optional | Descriptors of the food production system such as wild caught, free-range, organic, free-range, industrial, dairy, beef. (Units: °C) | | +| fertilizer administration date | optional | Date of administration of soil amendment or fertilizer. multiple terms may apply and can be separated by pipes, listing in reverse chronological order. | | +| crop yield | optional | Amount of crop produced per unit or area of land. | | +| ploidy | optional | The ploidy level of the genome (e.g. allopolyploid, haploid, diploid, triploid, tetraploid). it has implications for the downstream study of duplicated gene and regions of the genomes (and perhaps for difficulties in assembly). for terms, please select terms listed under class ploidy (pato:001374) of phenotypic quality ontology (pato), and for a browser of pato (v 2018-03-27) please refer to http://purl.bioontology.org/ontology/pato | | +| number of replicons | optional | Reports the number of replicons in a nuclear genome of eukaryotes, in the genome of a bacterium or archaea or the number of segments in a segmented virus. always applied to the haploid chromosome count of a eukaryote. mandatory for migs of eukaryotes, bacteria, archaea and segmented virus. | | +| extrachromosomal elements | optional | Do plasmids exist of significant phenotypic consequence (e.g. ones that determine virulence or antibiotic resistance). megaplasmids? other plasmids (borrelia has 15+ plasmids). | | +| estimated size | optional | The estimated size of the genome (in bp) prior to sequencing. of particular importance in the sequencing of (eukaryotic) genome which could remain in draft form for a long or unspecified period. mandatory for migs of eukaryotes. | | +| target gene | optional | Targeted gene or locus name for marker gene studies | | +| target subfragment | optional | Name of subfragment of a gene or locus. important to e.g. identify special regions on marker genes like v6 on 16s rrna | | +| multiplex identifiers | optional | Molecular barcodes, called multiplex identifiers (mids), that are used to specifically tag unique samples in a sequencing run. sequence should be reported in uppercase letters | | +| sequence quality check | optional | Indicate if the sequence has been called by automatic systems (none) or undergone a manual editing procedure (e.g. by inspecting the raw data or chromatograms). applied only for sequences that are not submitted to sra or dra | manual, none, software | +| chimera check software | optional | Tool(s) used for chimera checking, including version number and parameters, to discover and remove chimeric sequences. a chimeric sequence is comprised of two or more phylogenetically distinct parent sequences. | | +| relevant electronic resources | optional | A related resource that is referenced, cited, or otherwise associated to the sequence in the format of a pmid, doi or url | | +| relevant standard operating procedures | optional | Standard operating procedures used in assembly and/or annotation of genomes, metagenomes or environmental sequences in the format of a pmid, doi or url | | +| 16s recovered | optional | Can a 16s gene be recovered from the submitted bin, sag or mag? | No, Yes | +| 16S recovery software | optional | Tools used for 16s rrna gene extraction. add names and versions of software(s), parameters used | | +| collection date | mandatory | The date the sample was collected with the intention of sequencing, either as an instance (single point in time) or interval. in case no exact time is available, the date/time can be right truncated i.e. all of these are valid iso8601 compliant times: 2008-01-23t19:23:10+00:00; 2008-01-23t19:23:10; 2008-01-23; 2008-01; 2008. | | +| altitude | optional | The altitude of the sample is the vertical distance between earth's surface above sea level and the sampled position in the air. (Units: m) | | +| geographic location (country and/or sea) | mandatory | The geographical origin of where the sample was collected from, with the intention of sequencing, as defined by the country or sea name. country or sea names should be chosen from the insdc country list (http://insdc.org/country.html). | Afghanistan, Albania, Algeria, American Samoa, Andorra, Angola, Anguilla, Antarctica, Antigua and Barbuda, Arctic Ocean, Argentina, Armenia, Aruba, Ashmore and Cartier Islands, Atlantic Ocean, Australia, Austria, Azerbaijan, Bahamas, Bahrain, Baker Island, Baltic Sea, Bangladesh, Barbados, Bassas da India, Belarus, Belgium, Belize, Benin, Bermuda, Bhutan, Bolivia, Borneo, Bosnia and Herzegovina, Botswana, Bouvet Island, Brazil, British Virgin Islands, Brunei, Bulgaria, Burkina Faso, Burundi, Cambodia, Cameroon, Canada, Cape Verde, Cayman Islands, Central African Republic, Chad, Chile, China, Christmas Island, Clipperton Island, Cocos Islands, Colombia, Comoros, Cook Islands, Coral Sea Islands, Costa Rica, Cote d'Ivoire, Croatia, Cuba, Curacao, Cyprus, Czechia, Czech Republic, Democratic Republic of the Congo, Denmark, Djibouti, Dominica, Dominican Republic, East Timor, Ecuador, Egypt, El Salvador, Equatorial Guinea, Eritrea, Estonia, Ethiopia, Europa Island, Falkland Islands (Islas Malvinas), Faroe Islands, Fiji, Finland, France, French Guiana, French Polynesia, French Southern and Antarctic Lands, Gabon, Gambia, Gaza Strip, Georgia, Germany, Ghana, Gibraltar, Glorioso Islands, Greece, Greenland, Grenada, Guadeloupe, Guam, Guatemala, Guernsey, Guinea, Guinea-Bissau, Guyana, Haiti, Heard Island and McDonald Islands, Honduras, Hong Kong, Howland Island, Hungary, Iceland, India, Indian Ocean, Indonesia, Iran, Iraq, Ireland, Isle of Man, Israel, Italy, Jamaica, Jan Mayen, Japan, Jarvis Island, Jersey, Johnston Atoll, Jordan, Juan de Nova Island, Kazakhstan, Kenya, Kerguelen Archipelago, Kingman Reef, Kiribati, Kosovo, Kuwait, Kyrgyzstan, Laos, Latvia, Lebanon, Lesotho, Liberia, Libya, Liechtenstein, Lithuania, Luxembourg, Macau, Macedonia, Madagascar, Malawi, Malaysia, Maldives, Mali, Malta, Marshall Islands, Martinique, Mauritania, Mauritius, Mayotte, Mediterranean Sea, Mexico, Micronesia, Midway Islands, Moldova, Monaco, Mongolia, Montenegro, Montserrat, Morocco, Mozambique, Myanmar, Namibia, Nauru, Navassa Island, Nepal, Netherlands, New Caledonia, New Zealand, Nicaragua, Niger, Nigeria, Niue, Norfolk Island, North Korea, North Sea, Northern Mariana Islands, Norway, Oman, Pacific Ocean, Pakistan, Palau, Palmyra Atoll, Panama, Papua New Guinea, Paracel Islands, Paraguay, Peru, Philippines, Pitcairn Islands, Poland, Portugal, Puerto Rico, Qatar, Republic of the Congo, Reunion, Romania, Ross Sea, Russia, Rwanda, Saint Helena, Saint Kitts and Nevis, Saint Lucia, Saint Pierre and Miquelon, Saint Vincent and the Grenadines, Samoa, San Marino, Sao Tome and Principe, Saudi Arabia, Senegal, Serbia, Seychelles, Sierra Leone, Singapore, Sint Maarten, Slovakia, Slovenia, Solomon Islands, Somalia, South Africa, South Georgia and the South Sandwich Islands, South Korea, Southern Ocean, Spain, Spratly Islands, Sri Lanka, Sudan, Suriname, Svalbard, Swaziland, Sweden, Switzerland, Syria, Taiwan, Tajikistan, Tanzania, Tasman Sea, Thailand, Togo, Tokelau, Tonga, Trinidad and Tobago, Tromelin Island, Tunisia, Turkey, Turkmenistan, Turks and Caicos Islands, Tuvalu, USA, Uganda, Ukraine, United Arab Emirates, United Kingdom, Uruguay, Uzbekistan, Vanuatu, Venezuela, Viet Nam, Virgin Islands, Wake Island, Wallis and Futuna, West Bank, Western Sahara, Yemen, Zambia, Zimbabwe, missing: control sample, missing: data agreement established pre-2023, missing: endangered species, missing: human-identifiable, missing: lab stock, missing: sample group, missing: synthetic construct, missing: third party data, not applicable, not collected, not provided, restricted access | +| geographic location (latitude) | optional | The geographical origin of the sample as defined by latitude. the values should be reported in decimal degrees and in wgs84 system (Units: DD) | | +| geographic location (longitude) | optional | The geographical origin of the sample as defined by longitude. the values should be reported in decimal degrees and in wgs84 system (Units: DD) | | +| geographic location (region and locality) | optional | The geographical origin of the sample as defined by the specific region name followed by the locality name. | | +| broad-scale environmental context | optional | Report the major environmental system the sample or specimen came from. the system(s) identified should have a coarse spatial grain, to provide the general environmental context of where the sampling was done (e.g. in the desert or a rainforest). we recommend using subclasses of envo’s biome class: http://purl.obolibrary.org/obo/envo_00000428. envo documentation about how to use the field: https://github.com/environmentontology/envo/wiki/using-envo-with-mixs. | | +| local environmental context | optional | Report the entity or entities which are in the sample or specimen’s local vicinity and which you believe have significant causal influences on your sample or specimen. we recommend using envo terms which are of smaller spatial grain than your entry for "broad-scale environmental context". terms, such as anatomical sites, from other obo library ontologies which interoperate with envo (e.g. uberon) are accepted in this field. envo documentation about how to use the field: https://github.com/environmentontology/envo/wiki/using-envo-with-mixs. | | +| environmental medium | optional | Report the environmental material(s) immediately surrounding the sample or specimen at the time of sampling. we recommend using subclasses of 'environmental material' (http://purl.obolibrary.org/obo/envo_00010483). envo documentation about how to use the field: https://github.com/environmentontology/envo/wiki/using-envo-with-mixs . terms from other obo ontologies are permissible as long as they reference mass/volume nouns (e.g. air, water, blood) and not discrete, countable entities (e.g. a tree, a leaf, a table top). | | +| elevation | optional | The elevation of the sampling site as measured by the vertical distance from mean sea level. (Units: m) | | +| culture isolation date | optional | A culture isolation date is a date-time entity marking the end of a process in which a sample yields a positive result for the target microbial analyte(s) in the form of an isolated colony or colonies. | | +| sieving | optional | Collection design of pooled samples and/or sieve size and amount of sample sieved | | +| microbial biomass method | optional | Reference or method used in determining microbial biomass | | +| organism count | optional | Total cell count of any organism (or group of organisms) per gram, volume or area of sample, should include name of organism followed by count. the method that was used for the enumeration (e.g. qpcr, atp, mpn, etc.) should also be provided. (example: total prokaryotes; 3.5e7 cells per ml; qpcr) | | +| horizon method | optional | Reference or method used in determining the horizon | | +| extreme_unusual_properties/heavy metals | optional | Heavy metals present and concentrations of any drug used by subject and the frequency of usage; can include multiple heavy metals and concentrations | | +| extreme_unusual_properties/heavy metals method | optional | Reference or method used in determining heavy metals | | +| plant structure | optional | Name of plant structure that the sample was obtained from; for plant ontology (po) terms see http://purl.bioontology.org/ontology/po, e.g. petiole epidermis (po_0000051); if an individual flower is sampled the sex of it can be recorded here | | +| host disease status | optional | List of diseases with which the host has been diagnosed; can include multiple diagnoses. the value of the field depends on host; for humans the terms should be chosen from do (disease ontology) at http://www.disease-ontology.org, other hosts are free text | | +| host common name | optional | Common name of the host, e.g. human | | +| host age | optional | Age of host at the time of sampling; relevant scale depends on species and study, e.g. could be seconds for amoebae or centuries for trees (Units: years) | | +| host taxid | optional | Ncbi taxon id of the host, e.g. 9606 | | +| host life stage | optional | Description of life stage of host | | +| host height | optional | The height of subject (Units: mm) | | +| host length | optional | The length of subject (Units: mm) | | +| host total mass | optional | Total mass of the host at collection, the unit depends on host (Units: kg) | | +| host phenotype | optional | Phenotype of host. for phenotypic quality ontology (pato) (v 2013-10-28) terms, please see http://purl.bioontology.org/ontology/pato | | +| host scientific name | optional | Scientific name of the natural (as opposed to laboratory) host to the organism from which sample was obtained. | | +| host subspecific genetic lineage | optional | Information about the genetic distinctness of the host organism below the subspecies level e.g., serovar, serotype, biotype, ecotype, variety, cultivar, or any relevant genetic typing schemes like group i plasmid. subspecies should not be recorded in this term, but in the ncbi taxonomy. supply both the lineage name and the lineage rank separated by a colon, e.g., biovar:abc123. | | +| link to climate information | optional | Link to climate resource | | +| link to classification information | optional | Link to digitized soil maps or other soil classification information | | +| climate environment | optional | Treatment involving an exposure to a particular climate; can include multiple climates | | +| presence of pets, animals, or insects | optional | The type and number of animals or insects present in the sampling space. | | +| current vegetation | optional | Vegetation classification from one or more standard classification systems, or agricultural crop | | +| gaseous environment | optional | Use of conditions with differing gaseous environments; should include the name of gaseous compound, amount administered, treatment duration, interval and total experimental duration; can include multiple gaseous environment regimens | | +| humidity | optional | Amount of water vapour in the air, at the time of sampling (Units: g/m3) | | +| current vegetation method | optional | Reference or method used in vegetation classification | | +| seasonal environment | optional | Treatment involving an exposure to a particular season (e.g. winter, summer, rabi, rainy etc.) | | +| soil horizon | optional | Specific layer in the land area which measures parallel to the soil surface and possesses physical characteristics which differ from the layers above and beneath | A horizon, B horizon, E horizon, O horizon, Permafrost, R layer | +| solar irradiance | optional | The amount of solar energy that arrives at a specific area of a surface during a specific time interval (Units: W/m2) | | +| drainage classification | optional | Drainage classification from a standard system such as the usda system | excessively drained, moderately well, poorly, somewhat poorly, very poorly, well | +| temperature | optional | Temperature of the sample at time of sampling (Units: ºC) | | +| pH method | optional | Reference or method used in determining ph | | +| slope gradient | optional | Commonly called slope. the angle between ground surface and a horizontal line (in percent). this is the direction that overland water would flow. this measure is usually taken with a hand level meter or clinometer. (Units: %) | | +| slope aspect | optional | The direction a slope faces. while looking down a slope use a compass to record the direction you are facing (direction or degrees); e.g., nw or 315°. this measure provides an indication of sun and wind exposure that will influence soil temperature and evapotranspiration. | | +| profile position | optional | Cross-sectional position in the hillslope where sample was collected.sample area position in relation to surrounding areas | backslope, footslope, shoulder, summit, toeslope | +| total organic carbon method | optional | Reference or method used in determining total organic carbon | | +| total nitrogen content method | optional | Reference or method used in determining the total nitrogen | | +| total phosphate | optional | Total amount or concentration of phosphate (Units: µmol/L) | | +| total nitrogen concentration | optional | Concentration of nitrogen (total). total nitrogen concentration of water samples, calculated by: total nitrogen = total dissolved nitrogen + particulate nitrogen. can also be measured without filtering, reported as nitrogen (Units: µmol/L) | | +| total carbon | optional | Total carbon content (Units: µg/L) | | +| total organic carbon | optional | Definition for soil: total organic c content of the soil units of g c/kg soil. definition otherwise: total organic carbon content (Units: g/kg) | | +| water pH | optional | Ph measurement of the sample, or liquid portion of sample, or aqueous phase of the fluid. | | +| photosynthetic activity method | optional | Reference or method used in measurement of photosythentic activity | | +| photosynthetic activity | optional | Measurement of photosythetic activity (i.e. leaf gas exchange / chlorophyll fluorescence emissions / reflectance / transpiration) please also include the term method term detailing the method of activity measurement. | | +| source material identifiers | optional | A unique identifier assigned to a material sample (as defined by http://rs.tdwg.org/dwc/terms/materialsampleid, and as opposed to a particular digital record of a material sample) used for extracting nucleic acids, and subsequent sequencing. the identifier can refer either to the original material collected or to any derived sub-samples. the insdc qualifiers /specimen_voucher, /bio_material, or /culture_collection may or may not share the same value as the source_mat_id field. for instance, the /specimen_voucher qualifier and source_mat_id may both contain 'uam:herps:14' , referring to both the specimen voucher and sampled tissue with the same identifier. however, the /culture_collection qualifier may refer to a value from an initial culture (e.g. atcc:11775) while source_mat_id would refer to an identifier from some derived culture from which the nucleic acids were extracted (e.g. xatc123 or ark:/2154/r2). | | +| history/previous land use | optional | Previous land use and dates | | +| previous land use method | optional | Reference or method used in determining previous land use and dates | | +| history/crop rotation | optional | Whether or not crop is rotated, and if yes, rotation schedule | | +| history/agrochemical additions | optional | Addition of fertilizers, pesticides, etc. - amount and time of applications | | +| history/tillage | optional | Note method(s) used for tilling | chisel, cutting disc, disc plough, drill, mouldboard, ridge till, strip tillage, tined, zonal tillage | +| history/fire | optional | Historical and/or physical evidence of fire | | +| history/flooding | optional | Historical and/or physical evidence of flooding | | +| history/extreme events | optional | Unusual physical events that may have affected microbial populations | | +| mean seasonal humidity | optional | Average humidity of the region throughout the growing season. (Units: g/m3) | | +| mean seasonal temperature | optional | Mean seasonal temperature (Units: °C) | | +| mean seasonal precipitation | optional | The average of all seasonal precipitation values known, or an estimated equivalent value derived by such methods as regional indexes or isohyetal maps. (Units: mm) | | +| season | optional | The season when sampling occurred. any of the four periods into which the year is divided by the equinoxes and solstices. this field accepts terms listed under season (http://purl.obolibrary.org/obo/ncit_c94729). | | +| mean annual precipitation | optional | The average of all annual precipitation values known, or an estimated equivalent value derived by such methods as regional indexes or isohyetal maps. (Units: mm) | | +| mean annual temperature | optional | Mean annual temperature (Units: ºC) | | +| host genotype | optional | Observed genotype | | +| host specificity or range | optional | The range and diversity of host species that an organism is capable of infecting, defined by ncbi taxonomy identifier. | | +| host dry mass | optional | Measurement of dry mass (Units: mg) | | +| spike-in microbial strain | optional | Taxonomic information about the spike-in organism(s) at the strain level. this field accepts terms under organism (http://purl.obolibrary.org/obo/ncit_c14250). this field also accepts identification numbers from ncbi under https://www.ncbi.nlm.nih.gov/taxonomy. multiple terms can be separated by pipes. | | +| perturbation | optional | Type of perturbation, e.g. chemical administration, physical disturbance, etc., coupled with time that perturbation occurred; can include multiple perturbation types | | +| negative control type | optional | The substance or equipment used as a negative control in an investigation | | +| positive control type | optional | The substance, mixture, product, or apparatus used to verify that a process which is part of an investigation delivers a true positive. | | +| experimental factor | optional | Experimental factors are essentially the variable aspects of an experiment design which can be used to describe an experiment, or set of experiments, in an increasingly detailed manner. this field accepts ontology terms from experimental factor ontology (efo) and/or ontology for biomedical investigations (obi). for a browser of efo (v 2.95) terms, please see http://purl.bioontology.org/ontology/efo; for a browser of obi (v 2018-02-12) terms please see http://purl.bioontology.org/ontology/obi. e.g. time series design [efo:efo_0001779] | | +| encoded traits | optional | Should include key traits like antibiotic resistance or xenobiotic degradation phenotypes for plasmids, converting genes for phage | | +| genetic modification | optional | A genetic modification of the genome of an organism which may occur naturally by spontaneous mutation, or be introduced by some experimental means. examples of genetic modification include specification of a transgene or the gene knocked-out or details of transient transfection. | | +| subspecific genetic lineage | optional | Information about the genetic distinctness of the sequenced organism below the subspecies level, e.g., serovar, serotype, biotype, ecotype, or any relevant genetic typing schemes like group i plasmid. subspecies should not be recorded in this term, but in the ncbi taxonomy. supply both the lineage name and the lineage rank separated by a colon, e.g., biovar:abc123. | | +| ancestral data | optional | Information about either pedigree or other description of ancestral information (e.g. parental variety in case of mutant or selection), e.g. a/3*b (meaning [(a x b) x b] x b) | | +| taxonomic classification | optional | Method used for taxonomic classification, along with reference database used, classification rank, and thresholds used to classify new genomes. expected values are: classification method, database name, and other parameters e.g. vcontact vcontact2 (references from ncbi refseq v83, genus rank classification, default parameters) | | +| plant growth medium | optional | Specification of the media for growing the plants or tissue cultured samples, e.g. soil, aeroponic, hydroponic, in vitro solid culture medium, in vitro liquid culture medium. recommended value is a specific value from eo:plant growth medium (follow this link for terms http://purl.obolibrary.org/obo/eo_0007147). | | +| rooting medium macronutrients | optional | Measurement of the culture rooting medium macronutrients (n,p, k, ca, mg, s); e.g. kh2po4 (170mg/l) | | +| rooting medium carbon | optional | Source of organic carbon in the culture rooting medium; e.g. sucrose | | +| isolation and growth condition | optional | Publication reference in the form of pubmed id (pmid), digital object identifier (doi) or url for isolation and growth condition specifications of the organism/material. mandatory for migs and mimarks specimen. | | +| annotation source | optional | For cases where annotation was provided by a community jamboree or model organism database rather than by a specific submitter | | +| reference for biomaterial | optional | Primary publication if isolated before genome publication; otherwise, primary genome report. mandatory for migs of bacteria and archaea. | | +| sequencing location | optional | The location the sequencing run was performed. indicate the name of the lab or core facility where samples were sequenced. | | +| enrichment protocol | optional | The microbiological workflow or protocol followed to test for the presence or enumeration of the target microbial analyte(s). please provide a pubmed or doi reference for published protocols. | | +| library preparation kit | optional | Packaged kits (containing adapters, indexes, enzymes, buffers etc.), tailored for specific sequencing workflows, which allow the simplified preparation of sequencing-ready libraries for small genomes, amplicons, and plasmids. (Units: %) | | +| sample pooling | optional | Physical combination of several instances of like material, e.g. rna extracted from samples or dishes of cell cultures into one big aliquot of cells. please provide a short description of the samples that were pooled. | | +| lot number | optional | A distinctive alpha-numeric identification code assigned by the manufacturer or distributor to a specific quantity of manufactured material or product within a batch. synonym: batch number. the submitter should provide lot number of the item followed by the item name for which the lot number was provided. (Units: %) | | +| single cell or viral particle lysis approach | optional | Method used to free dna from interior of the cell(s) or particle(s) | chemical, combination, enzymatic, physical | +| single cell or viral particle lysis kit protocol | optional | Name of the kit or standard protocol used for cell(s) or particle(s) lysis | | +| pooled DNA extract total | optional | Indicate whether multiple dna extractions were mixed. if the answer yes, the number of extracts that were pooled should be given. [ena version of mixs term: pooling of dna extracts (if done). ] | | +| sample material processing | optional | A brief description of any processing applied to the sample during or after retrieving the sample from environment, or a link to the relevant protocol(s) performed. | | +| sample volume or weight for DNA extraction | optional | Volume (ml) or mass (g) of total collected sample processed for dna extraction. note: total sample collected should be entered under the term 'sample size'. (Units: ng) | | +| nucleic acid extraction | optional | A link to a literature reference, electronic resource or a standard operating procedure (sop), that describes the material separation to recover the nucleic acid fraction from a sample | | +| nucleic acid amplification | optional | A link to a literature reference, electronic resource or a standard operating procedure (sop), that describes the enzymatic amplification (pcr, tma, nasba) of specific nucleic acids | | +| library size | optional | Total number of clones in the library prepared for the project | | +| library reads sequenced | optional | Total number of clones sequenced from the library | | +| library construction method | optional | Library construction method used for clone libraries | | +| library vector | optional | Cloning vector type(s) used in construction of libraries | | +| library screening strategy | optional | Specific enrichment or screening methods applied before and/or after creating clone libraries in order to select a specific group of sequences | | +| pcr conditions | optional | Description of reaction conditions and components for pcr in the form of 'initial denaturation:94degc_1.5min; annealing=...' | | +| pcr primers | optional | Pcr primers that were used to amplify the sequence of the targeted gene, locus or subfragment. this field should contain all the primers used for a single pcr reaction if multiple forward or reverse primers are present in a single pcr reaction. the primer sequence should be reported in uppercase letters | | +| adapters | optional | Adapters provide priming sequences for both amplification and sequencing of the sample-library fragments. both adapters should be reported; in uppercase letters | | +| food shipping transportation vehicle | optional | A descriptor for the mobile machine which is used to transport food commodities along the food distribution system. this field accepts terms listed under vehicle (http://purl.obolibrary.org/obo/envo_01000604). if the proper descrptor is not listed please use text to describe the mode of travel. multiple terms can be separated by one or more pipes. | | +| water source shared | optional | Other users sharing access to the same water source. multiple terms can be separated by one or more pipes. | | +| food source | optional | Type of plant or animal from which the food product or its major ingredient is derived or a chemical food source [fda cfsan 1995]. | | +| food shipping transportation method | optional | A descriptor for the method of movement of food commodity along the food distribution system. this field accepts terms listed under travel mode (http://purl.obolibrary.org/obo/genepio_0001064). if the proper descrptor is not listed please use text to describe the mode of travel. multiple terms can be separated by one or more pipes. | | +| food product type | optional | A food product type is a class of food products that is differentiated by its food composition (e.g., single- or multi-ingredient), processing and/or consumption characteristics. this does not include brand name products but it may include generic food dish categories. this field accepts terms under food product type (http://purl.obolibrary.org/obo/foodon:03400361). for terms related to food product for an animal, consult food product for animal (http://purl.obolibrary.org/obo/foodon_03309997). if the proper descriptor is not listed please use text to describe the food type. multiple terms can be separated by one or more pipes. | | +| relative location of sample | optional | Location of sampled soil to other parts of the farm e.g. under crop plant, near irrigation ditch, from the dirt road. | | +| porosity | optional | Porosity of deposited sediment is volume of voids divided by the total volume of sample | | +| depth | optional | The vertical distance below local surface, e.g. for sediment or soil samples depth is measured from sediment or soil surface, respectively. depth can be reported as an interval for subsurface samples. (Units: mm) | | +| environment adjacent to site | optional | Description of the environmental system or features that are adjacent to the sampling site. this field accepts terms under ecosystem (http://purl.obolibrary.org/obo/envo_01001110) and human construction (http://purl.obolibrary.org/obo/envo_00000070). multiple terms can be separated by pipes. | | +| fungicide regimen | optional | Information about treatment involving use of fungicides; should include the name of fungicide, amount administered, treatment duration, interval and total experimental duration; can include multiple fungicide regimens | | +| herbicide regimen | optional | Information about treatment involving use of herbicides; information about treatment involving use of growth hormones; should include the name of herbicide, amount administered, treatment duration, interval and total experimental duration; can include multiple regimens | | +| non-mineral nutrient regimen | optional | Information about treatment involving the exposure of plant to non-mineral nutrient such as oxygen, hydrogen or carbon; should include the name of non-mineral nutrient, amount administered, treatment duration, interval and total experimental duration; can include multiple non-mineral nutrient regimens | | +| pesticide regimen | optional | Information about treatment involving use of insecticides; should include the name of pesticide, amount administered, treatment duration, interval and total experimental duration; can include multiple pesticide regimens | | +| pH regimen | optional | Information about treatment involving exposure of plants to varying levels of ph of the growth media; can include multiple regimen | | +| salt regimen | optional | Information about treatment involving use of salts as supplement to liquid and soil growth media; should include the name of salt, amount administered, treatment duration, interval and total experimental duration; can include multiple salt regimens | | +| standing water regimen | optional | Treatment involving an exposure to standing water during a plant's life span, types can be flood water or standing water; can include multiple regimens | | +| watering regimen | optional | Information about treatment involving an exposure to watering frequencies; can include multiple regimens | | +| water temperature regimen | optional | Information about treatment involving an exposure to water with varying degree of temperature; can include multiple regimens | | +| chemical administration | optional | List of chemical compounds administered to the host or site where sampling occurred, and when (e.g. antibiotics, n fertilizer, air filter); can include multiple compounds. for chemical entities of biological interest ontology (chebi) (v111), please see http://purl.bioontology.org/ontology/chebi | | + diff --git a/templates/ERC000055/experiment.tsv b/templates/ERC000055/experiment.tsv new file mode 100644 index 0000000..55beb83 --- /dev/null +++ b/templates/ERC000055/experiment.tsv @@ -0,0 +1 @@ +"alias" "title" "study_alias" "sample_alias" "design_description" "library_name" "library_strategy" "library_source" "library_selection" "library_layout" "insert_size" "library_construction_protocol" "platform" "instrument_model" diff --git a/templates/ERC000055/metadata_template_ERC000055.xlsx b/templates/ERC000055/metadata_template_ERC000055.xlsx new file mode 100644 index 0000000..47a460c Binary files /dev/null and b/templates/ERC000055/metadata_template_ERC000055.xlsx differ diff --git a/templates/ERC000055/run.tsv b/templates/ERC000055/run.tsv new file mode 100644 index 0000000..e752173 --- /dev/null +++ b/templates/ERC000055/run.tsv @@ -0,0 +1 @@ +"alias" "experiment_alias" "file_name" "file_format" diff --git a/templates/ERC000055/sample.tsv b/templates/ERC000055/sample.tsv new file mode 100644 index 0000000..486c9d3 --- /dev/null +++ b/templates/ERC000055/sample.tsv @@ -0,0 +1 @@ +"alias" "title" "taxon_id" "sample_description" "biotic relationship [deprecated]" "trophic level" "known pathogenicity" "relationship to oxygen" "propagation" "observed host symbionts" "sample collection device" "sample collection method" "sample storage temperature" "sample storage location" "size-fraction lower threshold" "size-fraction upper threshold" "soil_taxonomic/FAO classification" "soil_taxonomic/local classification" "soil_taxonomic/local classification method" "soil type" "soil type method" "soil texture measurement" "soil texture method" "soil pH" "soil cover" "oxygenation status of sample" "microbial biomass" "project name" "farm equipment sanitization" "equipment shared with other farms" "farm equipment used" "farm watering water source" "food production system characteristics" "animal water delivery method" "plant water delivery method" "food harvesting process" "food production characteristics" "fertilizer administration date" "crop yield" "ploidy" "number of replicons" "extrachromosomal elements" "estimated size" "target gene" "target subfragment" "multiplex identifiers" "sequence quality check" "chimera check software" "relevant electronic resources" "relevant standard operating procedures" "16s recovered" "16S recovery software" "collection date" "altitude" "geographic location (country and/or sea)" "geographic location (latitude)" "geographic location (longitude)" "geographic location (region and locality)" "broad-scale environmental context" "local environmental context" "environmental medium" "elevation" "culture isolation date" "sieving" "microbial biomass method" "organism count" "horizon method" "extreme_unusual_properties/heavy metals" "extreme_unusual_properties/heavy metals method" "plant structure" "host disease status" "host common name" "host age" "host taxid" "host life stage" "host height" "host length" "host total mass" "host phenotype" "host scientific name" "host subspecific genetic lineage" "link to climate information" "link to classification information" "climate environment" "presence of pets, animals, or insects" "current vegetation" "gaseous environment" "humidity" "current vegetation method" "seasonal environment" "soil horizon" "solar irradiance" "drainage classification" "temperature" "pH method" "slope gradient" "slope aspect" "profile position" "total organic carbon method" "total nitrogen content method" "total phosphate" "total nitrogen concentration" "total carbon" "total organic carbon" "water pH" "photosynthetic activity method" "photosynthetic activity" "source material identifiers" "history/previous land use" "previous land use method" "history/crop rotation" "history/agrochemical additions" "history/tillage" "history/fire" "history/flooding" "history/extreme events" "mean seasonal humidity" "mean seasonal temperature" "mean seasonal precipitation" "season" "mean annual precipitation" "mean annual temperature" "host genotype" "host specificity or range" "host dry mass" "spike-in microbial strain" "perturbation" "negative control type" "positive control type" "experimental factor" "encoded traits" "genetic modification" "subspecific genetic lineage" "ancestral data" "taxonomic classification" "plant growth medium" "rooting medium macronutrients" "rooting medium carbon" "isolation and growth condition" "annotation source" "reference for biomaterial" "sequencing location" "enrichment protocol" "library preparation kit" "sample pooling" "lot number" "single cell or viral particle lysis approach" "single cell or viral particle lysis kit protocol" "pooled DNA extract total" "sample material processing" "sample volume or weight for DNA extraction" "nucleic acid extraction" "nucleic acid amplification" "library size" "library reads sequenced" "library construction method" "library vector" "library screening strategy" "pcr conditions" "pcr primers" "adapters" "food shipping transportation vehicle" "water source shared" "food source" "food shipping transportation method" "food product type" "relative location of sample" "porosity" "depth" "environment adjacent to site" "fungicide regimen" "herbicide regimen" "non-mineral nutrient regimen" "pesticide regimen" "pH regimen" "salt regimen" "standing water regimen" "watering regimen" "water temperature regimen" "chemical administration" diff --git a/templates/ERC000055/study.tsv b/templates/ERC000055/study.tsv new file mode 100644 index 0000000..fd9fd79 --- /dev/null +++ b/templates/ERC000055/study.tsv @@ -0,0 +1 @@ +"alias" "title" "study_type" "new_study_type" "study_abstract" diff --git a/templates/ERC000056/ERC000056.json b/templates/ERC000056/ERC000056.json new file mode 100644 index 0000000..c699329 --- /dev/null +++ b/templates/ERC000056/ERC000056.json @@ -0,0 +1,3390 @@ +{ + "study": { + "description": "A Study is a container for a sequencing investigation that may comprise multiple experiments. The Study has an overall goal, but is otherwise minimally defined in the SRA. A Study is composed of a descriptor, zero or more experiments, and zero or more analyses. The submitter may decorate the Study with web links and properties.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for a study. This is used to link experiments to the study.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "title", + "cardinality": "mandatory", + "description": "Title of the study as would be used in a publication.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "study_type", + "cardinality": "mandatory", + "description": "The STUDY_TYPE presents a controlled vocabulary for expressing the overall purpose of the study.", + "units": "", + "regex": "", + "cv": [ + "Whole Genome Sequencing", + "Metagenomics", + "Transcriptome Analysis", + "Resequencing", + "Epigenetics", + "Synthetic Genomics", + "Forensic or Paleo-genomics", + "Gene Regulation Study", + "Cancer Genomics", + "Population Genomics", + "RNASeq", + "Exome Sequencing", + "Pooled Clone Sequencing", + "Transcriptome Sequencing", + "Other" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "new_study_type", + "cardinality": "optional", + "description": "Optional if 'study_type' is not 'other'. To propose a new term, select Other and enter a new study type.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "study_abstract", + "cardinality": "optional", + "description": "Briefly describes the goals, purpose, and scope of the Study. This need not be listed if it can be inherited from a referenced publication.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_AREA_FIELD" + } + ] + }, + "experiment": { + "description": "An experiment object serves as a metadata record encapsulating essential details about a sequencing experiment, including the experimental design, sequencing type, and relevant parameters. This information enhances the interpretation and contextual understanding of nucleotide sequences submitted to the archive.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for each experiment. This is used to link runs to experiments.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "title", + "cardinality": "optional", + "description": "Short text that can be used to call out experiment records in searches or in displays. This element is technically optional but should be used for all new records.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "study_alias", + "cardinality": "mandatory", + "description": "Identifies the parent study. (From study metadata)", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "sample_alias", + "cardinality": "mandatory", + "description": "(From sample metadata)", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "design_description", + "cardinality": "optional", + "description": "Goal and setup of the individual library including library was constructed.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_AREA_FIELD" + }, + { + "name": "library_name", + "cardinality": "optional", + "description": "The submitter's name for this library.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "library_strategy", + "cardinality": "mandatory", + "description": "Sequencing technique intended for this library.", + "units": "", + "regex": "", + "cv": [ + "WGS", + "WGA", + "WXS", + "RNA-Seq", + "ssRNA-seq", + "snRNA-seq", + "miRNA-Seq", + "ncRNA-Seq", + "FL-cDNA", + "EST", + "Hi-C", + "ATAC-seq", + "WCS", + "RAD-Seq", + "CLONE", + "POOLCLONE", + "AMPLICON", + "CLONEEND", + "FINISHING", + "ChIP-Seq", + "MNase-Seq", + "DNase-Hypersensitivity", + "Bisulfite-Seq", + "CTS", + "MRE-Seq", + "MeDIP-Seq", + "MBD-Seq", + "Tn-Seq", + "VALIDATION", + "FAIRE-seq", + "SELEX", + "RIP-Seq", + "ChIA-PET", + "Synthetic-Long-Read", + "Targeted-Capture", + "Tethered Chromatin Conformation Capture", + "NOMe-Seq", + "ChM-Seq", + "GBS", + "Ribo-Seq", + "OTHER" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "library_source", + "cardinality": "mandatory", + "description": "The LIBRARY_SOURCE specifies the type of source material that is being sequenced.", + "units": "", + "regex": "", + "cv": [ + "GENOMIC", + "GENOMIC SINGLE CELL", + "TRANSCRIPTOMIC", + "TRANSCRIPTOMIC SINGLE CELL", + "METAGENOMIC", + "METATRANSCRIPTOMIC", + "SYNTHETIC", + "VIRAL RNA", + "OTHER" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "library_selection", + "cardinality": "mandatory", + "description": "Method used to enrich the target in the sequence library preparation", + "units": "", + "regex": "", + "cv": [ + "RANDOM", + "PCR", + "RANDOM PCR", + "RT-PCR", + "HMPR", + "MF", + "repeat fractionation", + "size fractionation", + "MSLL", + "cDNA", + "cDNA_randomPriming", + "cDNA_oligo_dT", + "PolyA", + "Oligo-dT", + "Inverse rRNA", + "Inverse rRNA selection", + "ChIP", + "ChIP-Seq", + "MNase", + "DNase", + "Hybrid Selection", + "Reduced Representation", + "Restriction Digest", + "5-methylcytidine antibody", + "MBD2 protein methyl-CpG binding domain", + "CAGE", + "RACE", + "MDA", + "padlock probes capture method", + "other", + "unspecified" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "library_layout", + "cardinality": "mandatory", + "description": "LIBRARY_LAYOUT specifies whether to expect single, paired, or other configuration of reads. In the case of paired reads, information about the relative distance and orientation is specified.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "insert_size", + "cardinality": "optional", + "description": "Insert size for paired reads", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "library_construction_protocol", + "cardinality": "optional", + "description": "Free form text describing the protocol by which the sequencing library was constructed.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "platform", + "cardinality": "mandatory", + "description": "The PLATFORM record selects which sequencing platform and platform-specific runtime parameters. This will be determined by the Center. optional if 'instrument_model' is provided.", + "units": "", + "regex": "", + "cv": [ + "LS454", + "ILLUMINA", + "HELICOS", + "ABI_SOLID", + "COMPLETE_GENOMICS", + "BGISEQ", + "OXFORD_NANOPORE", + "PACBIO_SMRT", + "ION_TORRENT", + "CAPILLARY", + "DNBSEQ", + "ELEMENT", + "ULTIMA", + "VELA_DIAGNOSTICS", + "GENAPSYS", + "GENEMIND", + "TAPESTRI" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "instrument_model", + "cardinality": "mandatory", + "description": "Model of the sequencing instrument.", + "units": "", + "regex": "", + "cv": [ + "454 GS", + "454 GS 20", + "454 GS FLX", + "454 GS FLX Titanium", + "454 GS FLX+", + "454 GS Junior", + "AB 310 Genetic Analyzer", + "AB 3130 Genetic Analyzer", + "AB 3130xL Genetic Analyzer", + "AB 3500 Genetic Analyzer", + "AB 3500xL Genetic Analyzer", + "AB 3730 Genetic Analyzer", + "AB 3730xL Genetic Analyzer", + "AB 5500 Genetic Analyzer", + "AB 5500xl Genetic Analyzer", + "AB 5500xl-W Genetic Analysis System", + "AB SOLiD 3 Plus System", + "AB SOLiD 4 System", + "AB SOLiD 4hq System", + "AB SOLiD PI System", + "AB SOLiD System", + "AB SOLiD System 2.0", + "AB SOLiD System 3.0", + "BGISEQ-50", + "BGISEQ-500", + "Complete Genomics", + "DNBSEQ-G400", + "DNBSEQ-G400 FAST", + "DNBSEQ-G50", + "DNBSEQ-T7", + "Element AVITI", + "FASTASeq 300", + "GENIUS", + "GS111", + "Genapsys Sequencer", + "GenoCare 1600", + "GenoLab M", + "GridION", + "Helicos HeliScope", + "HiSeq X Five", + "HiSeq X Ten", + "Illumina Genome Analyzer", + "Illumina Genome Analyzer II", + "Illumina Genome Analyzer IIx", + "Illumina HiScanSQ", + "Illumina HiSeq 1000", + "Illumina HiSeq 1500", + "Illumina HiSeq 2000", + "Illumina HiSeq 2500", + "Illumina HiSeq 3000", + "Illumina HiSeq 4000", + "Illumina HiSeq X", + "Illumina MiSeq", + "Illumina MiniSeq", + "Illumina NovaSeq 6000", + "Illumina NovaSeq X", + "Illumina iSeq 100", + "Ion GeneStudio S5", + "Ion GeneStudio S5 Plus", + "Ion GeneStudio S5 Prime", + "Ion Torrent Genexus", + "Ion Torrent PGM", + "Ion Torrent Proton", + "Ion Torrent S5", + "Ion Torrent S5 XL", + "MGISEQ-2000RS", + "MinION", + "NextSeq 1000", + "NextSeq 2000", + "NextSeq 500", + "NextSeq 550", + "Onso", + "PacBio RS", + "PacBio RS II", + "PromethION", + "Revio", + "Sentosa SQ301", + "Sequel", + "Sequel II", + "Sequel IIe", + "Tapestri", + "UG 100", + "unspecified" + ], + "field_type": "TEXT_CHOICE_FIELD" + } + ] + }, + "run": { + "description": "A run contains a group of reads generated for a particular experiment.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for each run.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "experiment_alias", + "cardinality": "mandatory", + "description": "From_experiment_metadata", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "file_name", + "cardinality": "mandatory", + "description": "The name or relative pathname of a run data file.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "file_format", + "cardinality": "mandatory", + "description": "The run data file model.", + "units": "", + "regex": "", + "cv": [ + "sra", + "srf", + "sff", + "fastq", + "fasta", + "tab", + "454_native", + "454_native_seq", + "454_native_qual", + "Helicos_native", + "Illumina_native", + "Illumina_native_seq", + "Illumina_native_prb", + "Illumina_native_int", + "Illumina_native_qseq", + "Illumina_native_scarf", + "SOLiD_native", + "SOLiD_native_csfasta", + "SOLiD_native_qual", + "PacBio_HDF5", + "bam", + "cram", + "CompleteGenomics_native", + "OxfordNanopore_native" + ], + "field_type": "TEXT_CHOICE_FIELD" + } + ] + }, + "sample": { + "description": "A Sample defines an isolate of sequenceable material upon which sequencing experiments can be based. The Sample object may be a surrogate for taxonomy accession or an anonymized individual identifier. Or, it may fully specify provenance and isolation method of the starting material.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for each run.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "title", + "cardinality": "mandatory", + "description": "Short text that can be used to call out sample records in search results or in displays.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "taxon_id", + "cardinality": "mandatory", + "description": "NCBI Taxonomy Identifier. This is appropriate for individual organisms and some environmental samples.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "sample_description", + "cardinality": "optional", + "description": "Free-form text describing the sample, its origin, and its method of isolation.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_AREA_FIELD" + }, + { + "name": "culture result", + "cardinality": "optional", + "description": "Any result of a bacterial culture experiment reported as a binary assessment such as positive/negative, active/inactive.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "culture result organism", + "cardinality": "optional", + "description": "Taxonomic information about the cultured organism(s).", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "culture target microbial analyte", + "cardinality": "optional", + "description": "The target microbial analyte in terms of investigation scope. This field accepts terms under organism (http://purl.obolibrary.org/obo/NCIT_C14250). This field also accepts identification numbers from NCBI under https://www.ncbi.nlm.nih.gov/taxonomy.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "biological sample replicate", + "cardinality": "optional", + "description": "Measurements of biologically distinct samples that show biological variation.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "technical sample replicate", + "cardinality": "optional", + "description": "Repeated measurements of the same sample that show independent measures of the noise associated with the equipment and the protocols.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "purpose of sampling", + "cardinality": "optional", + "description": "The reason that the sample was collected.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "trophic level", + "cardinality": "optional", + "description": "Trophic levels are the feeding position in a food chain. Microbes can be a range of producers (e.g. chemolithotroph)", + "cv": [ + "autotroph", + "carboxydotroph", + "chemoautotroph", + "chemoheterotroph", + "chemolithoautotroph", + "chemolithotroph", + "chemoorganoheterotroph", + "chemoorganotroph", + "chemosynthetic", + "chemotroph", + "copiotroph", + "diazotroph", + "facultative autotroph", + "heterotroph", + "lithoautotroph", + "lithoheterotroph", + "lithotroph", + "methanotroph", + "methylotroph", + "mixotroph", + "obligate chemoautolithotroph", + "oligotroph", + "organoheterotroph", + "organotroph", + "photoautotroph", + "photoheterotroph", + "photolithoautotroph", + "photolithotroph", + "photosynthetic", + "phototroph" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "observed biotic relationship", + "cardinality": "optional", + "description": "Description of relationship(s) between the subject organism and other organism(s) it is associated with. E.g., parasite on species X; mutualist with species Y. The target organism is the subject of the relationship, and the other organism(s) is the object.", + "cv": [ + "commensal", + "free living", + "mutualism", + "parasite", + "symbiont" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "known pathogenicity", + "cardinality": "optional", + "description": "To what is the entity pathogenic, for instance plant, fungi, bacteria", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "relationship to oxygen", + "cardinality": "optional", + "description": "Is this organism an aerobe, anaerobe? Please note that aerobic and anaerobic are valid descriptors for microbial environments", + "cv": [ + "aerobe", + "anaerobe", + "facultative", + "microaerophilic", + "microanaerobe", + "obligate aerobe", + "obligate anaerobe" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "propagation", + "cardinality": "optional", + "description": "The type of reproduction from the parent stock. Values for this field is specific to different taxa. For phage or virus: lytic/lysogenic/temperate/obligately lytic. For plasmids: incompatibility group. For eukaryotes: sexual/asexual. Mandatory for MIGs of eukayotes, plasmids and viruses.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample transportation temperature", + "cardinality": "optional", + "description": "Temperature at which sample was transported, e.g. -20 or 4 degree Celsius.", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample transport container", + "cardinality": "optional", + "description": "Container in which the sample was stored during transport. Indicate the location name.", + "cv": [], + "units": "J/\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample transport duration", + "cardinality": "optional", + "description": "The duration of time from when the sample was collected until processed. Indicate the duration for which the sample was stored written in ISO 8601 format.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "sample collection device", + "cardinality": "optional", + "description": "The device used to collect an environmental sample. It is recommended to use terms listed under environmental sampling device (http://purl.obolibrary.org/obo/ENVO) and/or terms listed under specimen collection device (http://purl.obolibrary.org/obo/GENEPIO_0002094).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample collection method", + "cardinality": "optional", + "description": "The method employed for collecting the sample. Can be provided in the form of a PMID, DOI, url or text.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample storage temperature", + "cardinality": "optional", + "description": "temperature at which sample was stored, e.g. -80", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "sample storage device", + "cardinality": "optional", + "description": "The container used to store the sample. This field accepts terms listed under container (http://purl.obolibrary.org/obo/NCIT_C43186). If the proper descriptor is not listed please use text to describe the storage device.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample storage location", + "cardinality": "optional", + "description": "Location at which sample was stored, usually name of a specific freezer/room. Indicate the location name.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "size-fraction lower threshold", + "cardinality": "optional", + "description": "Refers to the mesh/pore size used to retain the sample. Materials smaller than the size threshold are excluded from the sample", + "cv": [], + "units": "\u00b5m", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "size-fraction upper threshold", + "cardinality": "optional", + "description": "Refers to the mesh/pore size used to pre-filter/pre-sort the sample. Materials larger than the size threshold are excluded from the sample", + "cv": [], + "units": "\u00b5m", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "soil type", + "cardinality": "optional", + "description": "Description of the soil type or classification. This field accepts terms under soil (http://purl.obolibrary.org/obo/ENVO_00001998). Multiple terms can be separated by pipes.", + "cv": [ + "Acrisol", + "Albeluvisol", + "Alisol", + "Andosol", + "Anthrosol", + "Arenosol", + "Calcisol", + "Cambisol", + "Chernozem", + "Cryosol", + "Durisol", + "Ferralsol", + "Fluvisol", + "Gleysol", + "Gypsisol", + "Histosol", + "Kastanozem", + "Leptosol", + "Lixisol", + "Luvisol", + "Nitisol", + "Phaeozem", + "Planosol", + "Plinthosol", + "Podzol", + "Regosol", + "Solonchak", + "Solonetz", + "Stagnosol", + "Technosol", + "Umbrisol", + "Vertisol" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "soil type method", + "cardinality": "optional", + "description": "reference or method used in determining soil series name or other lower-level classification", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "soil texture method", + "cardinality": "optional", + "description": "reference or method used in determining soil texture", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "soil pH", + "cardinality": "optional", + "description": "pH measurement of the soil; e.g. 6.2", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "soil cover", + "cardinality": "optional", + "description": "Description of the material covering the sampled soil. This field accepts terms under ENVO:00010483, environmental material.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "soil texture classification", + "cardinality": "optional", + "description": "One of the 12 soil texture classes use to describe soil texture based on the relative proportion of different grain sizes of mineral particles [sand (50 um to 2 mm), silt (2 um to 50 um), and clay (<2 um)] in a soil.", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "soil sediment porosity", + "cardinality": "optional", + "description": "Porosity of soil or deposited sediment is volume of voids divided by the total volume of sample.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "soil conductivity", + "cardinality": "optional", + "description": "Conductivity of soil at time of sampling.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "facility type", + "cardinality": "optional", + "description": "Establishment details about the type of facility where the sample was taken. This is independent of the specific product(s) within the facility.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "collection site geographic feature", + "cardinality": "optional", + "description": "Text or terms that describe the geographic feature where the food sample was obtained by the researcher. This field accepts selected terms listed under the following ontologies: anthropogenic geographic feature (http://purl.obolibrary.org/obo/ENVO_00000002), for example agricultural fairground [ENVO:01000986]; garden [ENVO:00000011} or any of its subclasses; market [ENVO:01000987]; water well [ENVO:01000002]; or human construction (http://purl.obolibrary.org/obo/ENVO_00000070).", + "cv": [], + "units": "m2", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "area sampled size", + "cardinality": "optional", + "description": "The total amount or size (volume (ml), mass (g) or area (m2) ) of sample collected.", + "cv": [], + "units": "ml", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "sample name", + "cardinality": "optional", + "description": "Sample Name is a name that you choose for the sample. It can have any format, but we suggest that you make it concise, unique and consistent within your lab, and as informative as possible. Every Sample Name from a single Submitter must be unique.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "study design", + "cardinality": "optional", + "description": "A plan specification comprised of protocols (which may specify how and what kinds of data will be gathered) that are executed as part of an investigation and is realized during a study design execution. This field accepts terms under study design (http://purl.obolibrary.org/obo/OBI_0500000). If the proper descriptor is not listed please use text to describe the study design. Multiple terms can be separated by pipes.", + "cv": [], + "units": "kg s\u22123", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "project name", + "cardinality": "optional", + "description": "Name of the project within which the sequencing was organized", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "farm equipment sanitization", + "cardinality": "optional", + "description": "Method used to sanitize growing and harvesting equipment. This can including type and concentration of sanitizing solution. Multiple terms can be separated by one or more pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "equipment shared with other farms", + "cardinality": "optional", + "description": "List of planting, growing or harvesting equipment shared with other farms. This field accepts terms listed under agricultural implement (http://purl.obolibrary.org/obo/AGRO_00000416). Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "farm equipment used", + "cardinality": "optional", + "description": "List of equipment used for planting, fertilization, harvesting, irrigation, land levelling, residue management, weeding or transplanting during the growing season. This field accepts terms listed under agricultural implement (http://purl.obolibrary.org/obo/AGRO_00000416). Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "farm equipment sanitization frequency", + "cardinality": "optional", + "description": "The number of times farm equipment is cleaned. Frequency of cleaning might be on a Daily basis, Weekly, Monthly, Quarterly or Annually.", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "farm watering water source", + "cardinality": "optional", + "description": "Source of water used on the farm for irrigation of crops or watering of livestock.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food production system characteristics", + "cardinality": "optional", + "description": "Descriptors of the food production system or of the agricultural environment and growing conditions related to the farm production system, such as wild caught, organic, free-range, industrial, dairy, beef, domestic or cultivated food production. This field accepts terms listed under food production (http://purl.obolibrary.org/obo/FOODON_03530206). Multiple terms may apply and can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "animal water delivery method", + "cardinality": "optional", + "description": "Description of the equipment or method used to distribute water to livestock. This field accepts termed listed under water delivery equipment (http://opendata.inra.fr/EOL/EOL_0001653). Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "plant water delivery method", + "cardinality": "optional", + "description": "Description of the equipment or method used to distribute water to crops. This field accepts termed listed under irrigation process (http://purl.obolibrary.org/obo/AGRO_00000006). Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food harvesting process", + "cardinality": "optional", + "description": "A harvesting process is a process which takes in some food material from an individual or community of plant or animal organisms in a given context and time, and outputs a precursor or consumable food product. This may include a part of an organism or the whole, and may involve killing the organism.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food animal source diet", + "cardinality": "optional", + "description": "If the isolate is from a food animal, the type of diet eaten by the food animal. Please list the main food staple and the setting, if appropriate. For a list of acceptable animal feed terms or categories, please see http://www.feedipedia.org. Multiple terms may apply and can be separated by pipes |Food product for animal covers foods intended for consumption by domesticated animals. Consult http://purl.obolibrary.org/obo/FOODON_03309997. If the proper descriptor is not listed please use text to describe the food type. Multiple terms can be separated by one or more pipes. If the proper descriptor is not listed please use text to describe the food product type.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food production characteristics", + "cardinality": "optional", + "description": "Descriptors of the food production system such as wild caught, free-range, organic, free-range, industrial, dairy, beef.", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food animal group size", + "cardinality": "optional", + "description": "The number of food animals of the same species that are maintained together as a unit, i.e. a herd or flock.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "fertilizer administration date", + "cardinality": "optional", + "description": "Date of administration of soil amendment or fertilizer. Multiple terms may apply and can be separated by pipes, listing in reverse chronological order.", + "cv": [], + "units": "", + "field_type": "DATE_FIELD", + "regex": "" + }, + { + "name": "animal feeding equipment", + "cardinality": "optional", + "description": "Description of the feeding equipment used for livestock. This field accepts terms listed under feed delivery (http://opendata.inra.fr/EOL/EOL_0001757). Multiple terms can be separated by one or more pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "crop yield", + "cardinality": "optional", + "description": "Amount of crop produced per unit or area of land.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "water delivery frequency", + "cardinality": "optional", + "description": "Number of water delivery events within a given period of time.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "animal housing system", + "cardinality": "optional", + "description": "Description of the housing system of the livestock. This field accepts terms listed under terrestrial management housing system (http://opendata.inra.fr/EOL/EOL_0001605).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "environmental feature adjacent water source", + "cardinality": "optional", + "description": "Description of the environmental features that are adjacent to the farm water source. This field accepts terms under ecosystem (http://purl.obolibrary.org/obo/ENVO_01001110) and human construction (http://purl.obolibrary.org/obo/ENVO_00000070). Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "ploidy", + "cardinality": "optional", + "description": "The ploidy level of the genome (e.g. allopolyploid, haploid, diploid, triploid, tetraploid). It has implications for the downstream study of duplicated gene and regions of the genomes (and perhaps for difficulties in assembly). For terms, please select terms listed under class ploidy (PATO:001374) of Phenotypic Quality Ontology (PATO), and for a browser of PATO (v 2018-03-27) please refer to http://purl.bioontology.org/ontology/PATO", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "number of replicons", + "cardinality": "optional", + "description": "Reports the number of replicons in a nuclear genome of eukaryotes, in the genome of a bacterium or archaea or the number of segments in a segmented virus. Always applied to the haploid chromosome count of a eukaryote. Mandatory for MIGS of eukaryotes, bacteria, archaea and segmented virus.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "extrachromosomal elements", + "cardinality": "optional", + "description": "Do plasmids exist of significant phenotypic consequence (e.g. ones that determine virulence or antibiotic resistance). Megaplasmids? Other plasmids (borrelia has 15+ plasmids).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "estimated size", + "cardinality": "optional", + "description": "The estimated size of the genome (in bp) prior to sequencing. Of particular importance in the sequencing of (eukaryotic) genome which could remain in draft form for a long or unspecified period. Mandatory for MIGS of eukaryotes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "target gene", + "cardinality": "optional", + "description": "Targeted gene or locus name for marker gene studies", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "target subfragment", + "cardinality": "optional", + "description": "Name of subfragment of a gene or locus. Important to e.g. identify special regions on marker genes like V6 on 16S rRNA", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "multiplex identifiers", + "cardinality": "optional", + "description": "Molecular barcodes, called Multiplex Identifiers (MIDs), that are used to specifically tag unique samples in a sequencing run. Sequence should be reported in uppercase letters", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sequence quality check", + "cardinality": "optional", + "description": "Indicate if the sequence has been called by automatic systems (none) or undergone a manual editing procedure (e.g. by inspecting the raw data or chromatograms). Applied only for sequences that are not submitted to SRA or DRA", + "cv": [ + "manual", + "none", + "software" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "chimera check software", + "cardinality": "optional", + "description": "Tool(s) used for chimera checking, including version number and parameters, to discover and remove chimeric sequences. A chimeric sequence is comprised of two or more phylogenetically distinct parent sequences.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "relevant electronic resources", + "cardinality": "optional", + "description": "A related resource that is referenced, cited, or otherwise associated to the sequence in the format of a PMID, DOI or URL", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "relevant standard operating procedures", + "cardinality": "optional", + "description": "Standard operating procedures used in assembly and/or annotation of genomes, metagenomes or environmental sequences in the format of a PMID, DOI or URL", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "16s recovered", + "cardinality": "optional", + "description": "Can a 16S gene be recovered from the submitted bin, SAG or MAG?", + "cv": [ + "No", + "Yes" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "16S recovery software", + "cardinality": "optional", + "description": "Tools used for 16S rRNA gene extraction. Add names and versions of software(s), parameters used", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "completeness score", + "cardinality": "optional", + "description": "Completeness score is typically based on either the fraction of markers found as compared to a database or the percent of a genome found as compared to a closely related reference genome. Completeness score is one of 3 attributes which in combination reflect the standard quality of a MAG, see here for more information: https://ena-docs.readthedocs.io/en/latest/faq_metagenomes.html. Mandatory for all samples directly linked with SAGs or MAGs.", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "^(\\d|[1-9]\\d|\\d\\.\\d{1,2}|[1-9]\\d\\.\\d{1,2}|100)$" + }, + { + "name": "completeness software", + "cardinality": "optional", + "description": "Tools used for completion estimate, i.e. checkm, anvi'o, busco. Mandatory for all samples directly linked with SAGs or MAGs.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "completeness approach", + "cardinality": "optional", + "description": "The approach used to determine the completeness of a given bin, SAG or MAG, which would typically make use of a set of conserved marker genes or a closely related reference genome. For UViG completeness, include reference genome or group used, and contig feature suggesting a complete genome", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "assembly quality", + "cardinality": "optional", + "description": "The assembly quality category is based on sets of criteria outlined for each assembly quality category. For MISAG/MIMAG; Finished: Single, validated, contiguous sequence per replicon without gaps or ambiguities with a consensus error rate equivalent to Q50 or better. High Quality Draft:Multiple fragments where gaps span repetitive regions. Presence of the 23S, 16S and 5S rRNA genes and at least 18 tRNAs. Medium Quality Draft:Many fragments with little to no review of assembly other than reporting of standard assembly statistics. Low Quality Draft:Many fragments with little to no review of assembly other than reporting of standard assembly statistics. Assembly statistics include, but are not limited to total assembly size, number of contigs, contig N50/L50, and maximum contig length. For MIUVIG; Finished: Single, validated, contiguous sequence per replicon without gaps or ambiguities, with extensive manual review and editing to annotate putative gene functions and transcriptional units. High-quality draft genome: One or multiple fragments, totaling \u2265 90% of the expected genome or replicon sequence or predicted complete. Genome fragment(s): One or multiple fragments, totalling < 90% of the expected genome or replicon sequence, or for which no genome size could be estimated.", + "cv": [ + "Many fragments with little to no review of assembly other than reporting of standard assembly statistics", + "Multiple fragments where gaps span repetitive regions. Presence of the 23S, 16S, and 5S rRNA genes and at least 18 tRNAs", + "Single contiguous sequence without gaps or ambiguities with a consensus error rate equivalent to Q50 or better" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "assembly name", + "cardinality": "optional", + "description": "Name/version of the assembly provided by the submitter that is used in the genome browsers and in the community", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "collection date", + "cardinality": "optional", + "description": "The date the sample was collected with the intention of sequencing, either as an instance (single point in time) or interval. In case no exact time is available, the date/time can be right truncated i.e. all of these are valid ISO8601 compliant times: 2008-01-23T19:23:10+00:00; 2008-01-23T19:23:10; 2008-01-23; 2008-01; 2008.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "(^[12][0-9]{3}(-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01])(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?(/[0-9]{4}(-[0-9]{2}(-[0-9]{2}(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?)?$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)" + }, + { + "name": "altitude", + "cardinality": "optional", + "description": "The altitude of the sample is the vertical distance between Earth's surface above Sea Level and the sampled position in the air.", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "((0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "geographic location (country and/or sea)", + "cardinality": "optional", + "description": "The geographical origin of where the sample was collected from, with the intention of sequencing, as defined by the country or sea name. Country or sea names should be chosen from the INSDC country list (http://insdc.org/country.html).", + "cv": [ + "Afghanistan", + "Albania", + "Algeria", + "American Samoa", + "Andorra", + "Angola", + "Anguilla", + "Antarctica", + "Antigua and Barbuda", + "Arctic Ocean", + "Argentina", + "Armenia", + "Aruba", + "Ashmore and Cartier Islands", + "Atlantic Ocean", + "Australia", + "Austria", + "Azerbaijan", + "Bahamas", + "Bahrain", + "Baker Island", + "Baltic Sea", + "Bangladesh", + "Barbados", + "Bassas da India", + "Belarus", + "Belgium", + "Belize", + "Benin", + "Bermuda", + "Bhutan", + "Bolivia", + "Borneo", + "Bosnia and Herzegovina", + "Botswana", + "Bouvet Island", + "Brazil", + "British Virgin Islands", + "Brunei", + "Bulgaria", + "Burkina Faso", + "Burundi", + "Cambodia", + "Cameroon", + "Canada", + "Cape Verde", + "Cayman Islands", + "Central African Republic", + "Chad", + "Chile", + "China", + "Christmas Island", + "Clipperton Island", + "Cocos Islands", + "Colombia", + "Comoros", + "Cook Islands", + "Coral Sea Islands", + "Costa Rica", + "Cote d'Ivoire", + "Croatia", + "Cuba", + "Curacao", + "Cyprus", + "Czechia", + "Czech Republic", + "Democratic Republic of the Congo", + "Denmark", + "Djibouti", + "Dominica", + "Dominican Republic", + "East Timor", + "Ecuador", + "Egypt", + "El Salvador", + "Equatorial Guinea", + "Eritrea", + "Estonia", + "Ethiopia", + "Europa Island", + "Falkland Islands (Islas Malvinas)", + "Faroe Islands", + "Fiji", + "Finland", + "France", + "French Guiana", + "French Polynesia", + "French Southern and Antarctic Lands", + "Gabon", + "Gambia", + "Gaza Strip", + "Georgia", + "Germany", + "Ghana", + "Gibraltar", + "Glorioso Islands", + "Greece", + "Greenland", + "Grenada", + "Guadeloupe", + "Guam", + "Guatemala", + "Guernsey", + "Guinea", + "Guinea-Bissau", + "Guyana", + "Haiti", + "Heard Island and McDonald Islands", + "Honduras", + "Hong Kong", + "Howland Island", + "Hungary", + "Iceland", + "India", + "Indian Ocean", + "Indonesia", + "Iran", + "Iraq", + "Ireland", + "Isle of Man", + "Israel", + "Italy", + "Jamaica", + "Jan Mayen", + "Japan", + "Jarvis Island", + "Jersey", + "Johnston Atoll", + "Jordan", + "Juan de Nova Island", + "Kazakhstan", + "Kenya", + "Kerguelen Archipelago", + "Kingman Reef", + "Kiribati", + "Kosovo", + "Kuwait", + "Kyrgyzstan", + "Laos", + "Latvia", + "Lebanon", + "Lesotho", + "Liberia", + "Libya", + "Liechtenstein", + "Lithuania", + "Luxembourg", + "Macau", + "Macedonia", + "Madagascar", + "Malawi", + "Malaysia", + "Maldives", + "Mali", + "Malta", + "Marshall Islands", + "Martinique", + "Mauritania", + "Mauritius", + "Mayotte", + "Mediterranean Sea", + "Mexico", + "Micronesia", + "Midway Islands", + "Moldova", + "Monaco", + "Mongolia", + "Montenegro", + "Montserrat", + "Morocco", + "Mozambique", + "Myanmar", + "Namibia", + "Nauru", + "Navassa Island", + "Nepal", + "Netherlands", + "New Caledonia", + "New Zealand", + "Nicaragua", + "Niger", + "Nigeria", + "Niue", + "Norfolk Island", + "North Korea", + "North Sea", + "Northern Mariana Islands", + "Norway", + "Oman", + "Pacific Ocean", + "Pakistan", + "Palau", + "Palmyra Atoll", + "Panama", + "Papua New Guinea", + "Paracel Islands", + "Paraguay", + "Peru", + "Philippines", + "Pitcairn Islands", + "Poland", + "Portugal", + "Puerto Rico", + "Qatar", + "Republic of the Congo", + "Reunion", + "Romania", + "Ross Sea", + "Russia", + "Rwanda", + "Saint Helena", + "Saint Kitts and Nevis", + "Saint Lucia", + "Saint Pierre and Miquelon", + "Saint Vincent and the Grenadines", + "Samoa", + "San Marino", + "Sao Tome and Principe", + "Saudi Arabia", + "Senegal", + "Serbia", + "Seychelles", + "Sierra Leone", + "Singapore", + "Sint Maarten", + "Slovakia", + "Slovenia", + "Solomon Islands", + "Somalia", + "South Africa", + "South Georgia and the South Sandwich Islands", + "South Korea", + "Southern Ocean", + "Spain", + "Spratly Islands", + "Sri Lanka", + "Sudan", + "Suriname", + "Svalbard", + "Swaziland", + "Sweden", + "Switzerland", + "Syria", + "Taiwan", + "Tajikistan", + "Tanzania", + "Tasman Sea", + "Thailand", + "Togo", + "Tokelau", + "Tonga", + "Trinidad and Tobago", + "Tromelin Island", + "Tunisia", + "Turkey", + "Turkmenistan", + "Turks and Caicos Islands", + "Tuvalu", + "USA", + "Uganda", + "Ukraine", + "United Arab Emirates", + "United Kingdom", + "Uruguay", + "Uzbekistan", + "Vanuatu", + "Venezuela", + "Viet Nam", + "Virgin Islands", + "Wake Island", + "Wallis and Futuna", + "West Bank", + "Western Sahara", + "Yemen", + "Zambia", + "Zimbabwe", + "missing: control sample", + "missing: data agreement established pre-2023", + "missing: endangered species", + "missing: human-identifiable", + "missing: lab stock", + "missing: sample group", + "missing: synthetic construct", + "missing: third party data", + "not applicable", + "not collected", + "not provided", + "restricted access" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "geographic location (latitude)", + "cardinality": "optional", + "description": "The geographical origin of the sample as defined by latitude. The values should be reported in decimal degrees and in WGS84 system", + "cv": [], + "units": "DD", + "field_type": "TEXT_FIELD", + "regex": "(^[+-]?[0-9]+.?[0-9]{0,8}$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)" + }, + { + "name": "geographic location (longitude)", + "cardinality": "optional", + "description": "The geographical origin of the sample as defined by longitude. The values should be reported in decimal degrees and in WGS84 system", + "cv": [], + "units": "DD", + "field_type": "TEXT_FIELD", + "regex": "(^[+-]?[0-9]+.?[0-9]{0,8}$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)" + }, + { + "name": "geographic location (region and locality)", + "cardinality": "optional", + "description": "The geographical origin of the sample as defined by the specific region name followed by the locality name.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "broad-scale environmental context", + "cardinality": "optional", + "description": "Report the major environmental system the sample or specimen came from. The system(s) identified should have a coarse spatial grain, to provide the general environmental context of where the sampling was done (e.g. in the desert or a rainforest). We recommend using subclasses of EnvO\u2019s biome class: http://purl.obolibrary.org/obo/ENVO_00000428. EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "local environmental context", + "cardinality": "optional", + "description": "Report the entity or entities which are in the sample or specimen\u2019s local vicinity and which you believe have significant causal influences on your sample or specimen. We recommend using EnvO terms which are of smaller spatial grain than your entry for \"broad-scale environmental context\". Terms, such as anatomical sites, from other OBO Library ontologies which interoperate with EnvO (e.g. UBERON) are accepted in this field. EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "environmental medium", + "cardinality": "optional", + "description": "Report the environmental material(s) immediately surrounding the sample or specimen at the time of sampling. We recommend using subclasses of 'environmental material' (http://purl.obolibrary.org/obo/ENVO_00010483). EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS . Terms from other OBO ontologies are permissible as long as they reference mass/volume nouns (e.g. air, water, blood) and not discrete, countable entities (e.g. a tree, a leaf, a table top).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "elevation", + "cardinality": "optional", + "description": "The elevation of the sampling site as measured by the vertical distance from mean sea level.", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "([+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "culture isolation date", + "cardinality": "optional", + "description": "A culture isolation date is a date-time entity marking the end of a process in which a sample yields a positive result for the target microbial analyte(s) in the form of an isolated colony or colonies.", + "cv": [], + "units": "", + "field_type": "DATE_FIELD", + "regex": "" + }, + { + "name": "time course duration", + "cardinality": "optional", + "description": "For time-course research studies involving samples of the food commodity, indicate the total duration of the time-course study.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "number of samples collected", + "cardinality": "optional", + "description": "The number of samples collected during the current sampling event.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "surface material", + "cardinality": "optional", + "description": "surface materials at the point of sampling", + "cv": [ + "adobe", + "carpet", + "cinder blocks", + "concrete", + "glass", + "hay bales", + "metal", + "paint", + "plastic", + "stainless steel", + "stone", + "stucco", + "tile", + "vinyl", + "wood" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "ventilation rate", + "cardinality": "optional", + "description": "ventilation rate of the system in the sampled premises", + "cv": [], + "units": "m3/min", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "indoor surface", + "cardinality": "optional", + "description": "type of indoor surface", + "cv": [ + "cabinet", + "ceiling", + "counter top", + "door", + "shelving", + "vent cover", + "wall", + "window" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "ventilation type", + "cardinality": "optional", + "description": "The intentional movement of air from outside a building to the inside through forced or natural movement of air", + "cv": [ + "forced ventilation", + "mechanical ventilation", + "natural ventilation" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "sampling room sterilization method", + "cardinality": "optional", + "description": "The method used to sterilize the sampling room. This field accepts terms listed under electromagnetic radiation (http://purl.obolibrary.org/obo/ENVO_01001026). If the proper descriptor is not listed, please use text to describe the sampling room sterilization method. Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "sampling floor", + "cardinality": "optional", + "description": "The floor of the building, where the sampling room is located", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "average daily occupancy", + "cardinality": "optional", + "description": "Daily average occupancy of room. Indicate the number of person(s) daily occupying the sampling room.", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "sample surface moisture", + "cardinality": "optional", + "description": "Degree of water held on a sampled surface. If present, user can state the degree of water held on surface (intermittent moisture, submerged). If no surface moisture is present indicate not present.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sampling room id or name", + "cardinality": "optional", + "description": "Explain how and for how long the soil sample was stored before DNA extraction (fresh/frozen/other).", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "fermentation relative humidity", + "cardinality": "optional", + "description": "The relative humidity of the fermented food fermentation process.", + "cv": [], + "units": "g/m3", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "room dimensions", + "cardinality": "optional", + "description": "The length, width and height of sampling room", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "amount or size of sample collected", + "cardinality": "optional", + "description": "The total amount or size (volume (ml), mass (g) or area (m2) ) of sample collected.", + "cv": [], + "units": "m3", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "organism count", + "cardinality": "optional", + "description": "Total cell count of any organism (or group of organisms) per gram, volume or area of sample, should include name of organism followed by count. The method that was used for the enumeration (e.g. qPCR, atp, mpn, etc.) Should also be provided. (example: total prokaryotes; 3.5e7 cells per ml; qpcr)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sampling time point", + "cardinality": "optional", + "description": "Time point at which a sample or observation is made or taken from a biomaterial as measured from some reference point. Indicate the timepoint written in ISO 8601 format.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "growth habit", + "cardinality": "optional", + "description": "characteristic shape, appearance or growth form of a plant species", + "cv": [ + "erect", + "prostrate", + "semi-erect", + "spreading" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "sample storage duration", + "cardinality": "optional", + "description": "Duration for which the sample was stored. Indicate the duration for which the sample was stored written in ISO 8601 format.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sequencing kit", + "cardinality": "optional", + "description": "Pre-filled, ready-to-use reagent cartridges. Used to produce improved chemistry, cluster density and read length as well as improve quality (Q) scores. Reagent components are encoded to interact with the sequencing system to validate compatibility with user-defined applications. Indicate name of the sequencing kit.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host disease status", + "cardinality": "optional", + "description": "list of diseases with which the host has been diagnosed; can include multiple diagnoses. The value of the field depends on host; for humans the terms should be chosen from DO (Disease Ontology) at http://www.disease-ontology.org, other hosts are free text", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host age", + "cardinality": "optional", + "description": "age of host at the time of sampling; relevant scale depends on species and study, e.g. could be seconds for amoebae or centuries for trees", + "cv": [], + "units": "years", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "host taxid", + "cardinality": "optional", + "description": "NCBI taxon id of the host, e.g. 9606", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "host height", + "cardinality": "optional", + "description": "the height of subject", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "((0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "host length", + "cardinality": "optional", + "description": "the length of subject", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "host total mass", + "cardinality": "optional", + "description": "total mass of the host at collection, the unit depends on host", + "cv": [], + "units": "kg", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "host phenotype", + "cardinality": "optional", + "description": "phenotype of host. For Phenotypic quality Ontology (PATO) (v 2013-10-28) terms, please see http://purl.bioontology.org/ontology/PATO", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host scientific name", + "cardinality": "optional", + "description": "Scientific name of the natural (as opposed to laboratory) host to the organism from which sample was obtained.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host subspecific genetic lineage", + "cardinality": "optional", + "description": "Information about the genetic distinctness of the host organism below the subspecies level e.g., serovar, serotype, biotype, ecotype, variety, cultivar, or any relevant genetic typing schemes like Group I plasmid. Subspecies should not be recorded in this term, but in the NCBI taxonomy. Supply both the lineage name and the lineage rank separated by a colon, e.g., biovar:abc123.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "serovar or serotype", + "cardinality": "optional", + "description": "A characterization of a cell or microorganism based on the antigenic properties of the molecules on its surface. Indicate the name of a serovar or serotype of interest. This field accepts terms under organism (http://purl.obolibrary.org/obo/NCIT_C14250). This field also accepts identification numbers from NCBI under https://www.ncbi.nlm.nih.gov/taxonomy.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "humidity", + "cardinality": "optional", + "description": "amount of water vapour in the air, at the time of sampling", + "cv": [], + "units": "g/m3", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "conductivity", + "cardinality": "optional", + "description": "electrical conductivity of water", + "cv": [], + "units": "mS/cm", + "field_type": "TEXT_FIELD", + "regex": "[1-9][0-9]*\\.?[0-9]*([Ee][+-]?[0-9]+)?" + }, + { + "name": "solar irradiance", + "cardinality": "optional", + "description": "the amount of solar energy that arrives at a specific area of a surface during a specific time interval", + "cv": [], + "units": "W/m2", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "wind direction", + "cardinality": "optional", + "description": "wind direction is the direction from which a wind originates", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "wind speed", + "cardinality": "optional", + "description": "speed of wind measured at the time of sampling", + "cv": [], + "units": "m/s", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "temperature", + "cardinality": "optional", + "description": "temperature of the sample at time of sampling", + "cv": [], + "units": "\u00baC", + "field_type": "TEXT_FIELD", + "regex": "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "turbidity", + "cardinality": "optional", + "description": "turbidity measurement", + "cv": [], + "units": "NTU", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "pH", + "cardinality": "optional", + "description": "pH measurement", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "pH method", + "cardinality": "optional", + "description": "reference or method used in determining pH", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "fermentation vessel", + "cardinality": "optional", + "description": "The type of vessel used for containment of the fermentation.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "fermentation headspace oxygen", + "cardinality": "optional", + "description": "The amount of headspace oxygen in a fermentation vessel.", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "frequency of cleaning", + "cardinality": "optional", + "description": "The number of times the sample location is cleaned. Frequency of cleaning might be on a Daily basis, Weekly, Monthly, Quarterly or Annually.", + "cv": [ + "Annually", + "Daily", + "Monthly", + "Quarterly", + "Weekly" + ], + "units": "year", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "total organic carbon method", + "cardinality": "optional", + "description": "Reference or method used in determining total organic carbon", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "air particulate matter concentration", + "cardinality": "optional", + "description": "Concentration of substances that remain suspended in the air, and comprise mixtures of organic and inorganic substances (PM10 and PM2.5); can report multiple PM's by entering numeric values preceded by name of PM", + "cv": [], + "units": "\u00b5g/m3", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "total nitrogen content method", + "cardinality": "optional", + "description": "Reference or method used in determining the total nitrogen", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "total nitrogen concentration", + "cardinality": "optional", + "description": "Concentration of nitrogen (total). Total nitrogen concentration of water samples, calculated by: total nitrogen = total dissolved nitrogen + particulate nitrogen. Can also be measured without filtering, reported as nitrogen", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "salinity", + "cardinality": "optional", + "description": "The total concentration of all dissolved salts in a liquid or solid sample. While salinity can be measured by a complete chemical analysis, this method is difficult and time consuming. More often, it is instead derived from the conductivity measurement. This is known as practical salinity. These derivations compare the specific conductance of the sample to a salinity standard such as seawater.", + "cv": [], + "units": "psu", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "total carbon", + "cardinality": "optional", + "description": "total carbon content", + "cv": [], + "units": "\u00b5g/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "total organic carbon", + "cardinality": "optional", + "description": "Definition for soil: total organic C content of the soil units of g C/kg soil. Definition otherwise: total organic carbon content", + "cv": [], + "units": "g/kg", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "total nitrogen content", + "cardinality": "optional", + "description": "Total nitrogen content of the sample", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "water pH", + "cardinality": "optional", + "description": "pH measurement of the sample, or liquid portion of sample, or aqueous phase of the fluid.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[\\d][0-4]?(\\.[\\d]{1,10})?" + }, + { + "name": "fermentation ph", + "cardinality": "optional", + "description": "The pH of the fermented food fermentation process.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[\\d][0-4]?(\\.[\\d]{1,10})?" + }, + { + "name": "bacteria density", + "cardinality": "optional", + "description": "Number of bacteria in sample, as defined by bacteria density (http://purl.obolibrary.org/obo/GENEPIO_0000043).", + "cv": [], + "units": "g/m3", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "salinity method", + "cardinality": "optional", + "description": "reference or method used in determining salinity", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "bio_material", + "cardinality": "optional", + "description": "Unique identifier that references the biological material from which the sample was obtained and that ideally exists in a curated collection (e.g. stock centres, seed banks, DNA banks). The ID should have the following structure: name of the institution (institution code) followed by the collection code (if available) and the voucher id (institution_code:collection_code:voucher_id). Please note institution codes and collection codes are taken from a controlled vocabulary maintained by the INSDC: https://ftp.ncbi.nih.gov/pub/taxonomy/biocollections/", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "source material identifiers", + "cardinality": "optional", + "description": "A unique identifier assigned to a material sample (as defined by http://rs.tdwg.org/dwc/terms/materialSampleID, and as opposed to a particular digital record of a material sample) used for extracting nucleic acids, and subsequent sequencing. The identifier can refer either to the original material collected or to any derived sub-samples. The INSDC qualifiers /specimen_voucher, /bio_material, or /culture_collection may or may not share the same value as the source_mat_id field. For instance, the /specimen_voucher qualifier and source_mat_id may both contain 'UAM:Herps:14' , referring to both the specimen voucher and sampled tissue with the same identifier. However, the /culture_collection qualifier may refer to a value from an initial culture (e.g. ATCC:11775) while source_mat_id would refer to an identifier from some derived culture from which the nucleic acids were extracted (e.g. xatc123 or ark:/2154/R2).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample source material category", + "cardinality": "optional", + "description": "This is the scientific role or category that the subject organism or material has with respect to an investigation. This field accepts terms listed under specimen source material category (http://purl.obolibrary.org/obo/GENEPIO_0001237 or http://purl.obolibrary.org/obo/OBI_0100051).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "history/previous land use", + "cardinality": "optional", + "description": "previous land use and dates", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "history/crop rotation", + "cardinality": "optional", + "description": "whether or not crop is rotated, and if yes, rotation schedule", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "history/tillage", + "cardinality": "optional", + "description": "note method(s) used for tilling", + "cv": [ + "chisel", + "cutting disc", + "disc plough", + "drill", + "mouldboard", + "ridge till", + "strip tillage", + "tined", + "zonal tillage" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "mean seasonal humidity", + "cardinality": "optional", + "description": "Average humidity of the region throughout the growing season.", + "cv": [], + "units": "g/m3", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "mean seasonal temperature", + "cardinality": "optional", + "description": "Mean seasonal temperature", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "mean seasonal precipitation", + "cardinality": "optional", + "description": "The average of all seasonal precipitation values known, or an estimated equivalent value derived by such methods as regional indexes or Isohyetal maps.", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "extreme weather date", + "cardinality": "optional", + "description": "Date of unusual weather events that may have affected microbial populations. Multiple terms can be separated by pipes, listed in reverse chronological order.", + "cv": [], + "units": "J/\u00b0C", + "field_type": "DATE_FIELD", + "regex": "" + }, + { + "name": "extreme weather event", + "cardinality": "optional", + "description": "Unusual weather events that may have affected microbial populations. Multiple terms can be separated by pipes, listed in reverse chronological order.", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "season", + "cardinality": "optional", + "description": "The season when sampling occurred. Any of the four periods into which the year is divided by the equinoxes and solstices. This field accepts terms listed under season (http://purl.obolibrary.org/obo/NCIT_C94729).", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "host genotype", + "cardinality": "optional", + "description": "observed genotype", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host specificity or range", + "cardinality": "optional", + "description": "The range and diversity of host species that an organism is capable of infecting, defined by NCBI taxonomy identifier.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "host dry mass", + "cardinality": "optional", + "description": "measurement of dry mass", + "cv": [], + "units": "mg", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "host prediction approach", + "cardinality": "optional", + "description": "Tool or approach used for host prediction", + "cv": [ + "CRISPR spacer match", + "co-occurrence", + "combination", + "host sequence similarity", + "kmer similarity", + "other", + "provirus" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "host prediction estimated accuracy", + "cardinality": "optional", + "description": "For each tool or approach used for host prediction, estimated false discovery rates should be included, either computed de novo or from the literature", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "spike-in microbial strain", + "cardinality": "optional", + "description": "Taxonomic information about the spike-in organism(s) at the strain level. This field accepts terms under organism (http://purl.obolibrary.org/obo/NCIT_C14250). This field also accepts identification numbers from NCBI under https://www.ncbi.nlm.nih.gov/taxonomy. Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "TAXON_FIELD", + "regex": "" + }, + { + "name": "fermentation chemical additives", + "cardinality": "optional", + "description": "Any chemicals that are added to the fermentation process to achieve the desired final product.", + "cv": [], + "units": "J/\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "fermentation chemical additives percentage", + "cardinality": "optional", + "description": "The amount of chemical added to the fermentation process.", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*)))" + }, + { + "name": "study treatment", + "cardinality": "optional", + "description": "A process in which the act is intended to modify or alter some other material entity. From the study design, each treatment is comprised of one level of one or multiple factors. This field accepts terms listed under treatment (http://purl.obolibrary.org/obo/MCO_0000866). If the proper descriptor is not listed please use text to describe the study treatment. Multiple terms can be separated by one or more pipes.", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "spike-in organism", + "cardinality": "optional", + "description": "Taxonomic information about the spike-in organism(s). This field accepts terms under organism (http://purl.obolibrary.org/obo/NCIT_C14250). This field also accepts identification numbers from NCBI under https://www.ncbi.nlm.nih.gov/taxonomy. Multiple terms can be separated by pipes.", + "cv": [], + "units": "g/m3", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "spike-in organism count", + "cardinality": "optional", + "description": "Total cell count of any organism (or group of organisms) per gram, volume or area of sample, should include name of organism followed by count. The method that was used for the enumeration (e.g. qPCR, atp, mpn, etc.) should also be provided (example: total prokaryotes; 3.5e7 cells per ml; qPCR).", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "fermentation temperature", + "cardinality": "optional", + "description": "The temperature of the fermented food fermentation process.", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "spike-in with heavy metals", + "cardinality": "optional", + "description": "Heavy metals used in research study to assess effects of exposure on microbiome of a specific site. Please list heavy metals and concentration used for spike-in.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "microbial starter inoculation", + "cardinality": "optional", + "description": "The amount of starter culture used to inoculate a new batch.", + "cv": [], + "units": "m3/day", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "microbial starter source", + "cardinality": "optional", + "description": "The source from which the microbial starter culture was sourced. If commercially supplied, list supplier.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "microbial starter preparation", + "cardinality": "optional", + "description": "Information about the protocol or method used to prepare the starter inoculum.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "spike-in bacterial serovar or serotype", + "cardinality": "optional", + "description": "Taxonomic information about the spike-in organism(s) at the serovar or serotype level. This field accepts terms under organism (http://purl.obolibrary.org/obo/NCIT_C14250). This field also accepts identification numbers from NCBI under https://www.ncbi.nlm.nih.gov/taxonomy. Multiple terms can be separated by pipes.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "antimicrobial phenotype of spike-in bacteria", + "cardinality": "optional", + "description": "Qualitative description of a microbial response to antimicrobial agents. Bacteria may be susceptible or resistant to a broad range of antibiotic drugs or drug classes, with several intermediate states or phases. This field accepts terms under antimicrobial phenotype (http://purl.obolibrary.org/obo/ARO_3004299).", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "fermentation time", + "cardinality": "optional", + "description": "The time duration of the fermented food fermentation process.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "microbial starter organism count", + "cardinality": "optional", + "description": "Total cell count of starter culture per gram, volume or area of sample and the method that was used for the enumeration (e.g. qPCR, atp, mpn, etc.) should also be provided. (example : total prokaryotes; 3.5e7 cells per ml; qPCR).", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "spike-in with antibiotics", + "cardinality": "optional", + "description": "Antimicrobials used in research study to assess effects of exposure on microbiome of a specific site. Please list antimicrobial, common name and/or class and concentration used for spike-in.", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "study incubation temperature", + "cardinality": "optional", + "description": "Sample incubation temperature if unpublished or unvalidated method is used.", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "perturbation", + "cardinality": "optional", + "description": "type of perturbation, e.g. chemical administration, physical disturbance, etc., coupled with time that perturbation occurred; can include multiple perturbation types", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "study incubation duration", + "cardinality": "optional", + "description": "Sample incubation duration if unpublished or unvalidated method is used. Indicate the timepoint written in ISO 8601 format.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "biocide", + "cardinality": "optional", + "description": "Substance intended for preventing, neutralizing, destroying, repelling, or mitigating the effects of any pest or microorganism; that inhibits the growth, reproduction, and activity of organisms, including fungal cells; decreases the number of fungi or pests present; deters microbial growth and degradation of other ingredients in the formulation. Indicate the biocide used on the location where the sample was taken. Multiple terms can be separated by pipes.", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "negative control type", + "cardinality": "optional", + "description": "The substance or equipment used as a negative control in an investigation", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "positive control type", + "cardinality": "optional", + "description": "The substance, mixture, product, or apparatus used to verify that a process which is part of an investigation delivers a true positive.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "experimental factor", + "cardinality": "optional", + "description": "Experimental factors are essentially the variable aspects of an experiment design which can be used to describe an experiment, or set of experiments, in an increasingly detailed manner. This field accepts ontology terms from Experimental Factor Ontology (EFO) and/or Ontology for Biomedical Investigations (OBI). For a browser of EFO (v 2.95) terms, please see http://purl.bioontology.org/ontology/EFO; for a browser of OBI (v 2018-02-12) terms please see http://purl.bioontology.org/ontology/OBI. E.g. time series design [EFO:EFO_0001779]", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "encoded traits", + "cardinality": "optional", + "description": "Should include key traits like antibiotic resistance or xenobiotic degradation phenotypes for plasmids, converting genes for phage", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "genetic modification", + "cardinality": "optional", + "description": "A genetic modification of the genome of an organism which may occur naturally by spontaneous mutation, or be introduced by some experimental means. Examples of genetic modification include specification of a transgene or the gene knocked-out or details of transient transfection.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "subspecific genetic lineage", + "cardinality": "optional", + "description": "Information about the genetic distinctness of the sequenced organism below the subspecies level, e.g., serovar, serotype, biotype, ecotype, or any relevant genetic typing schemes like Group I plasmid. Subspecies should not be recorded in this term, but in the NCBI taxonomy. Supply both the lineage name and the lineage rank separated by a colon, e.g., biovar:abc123.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "ancestral data", + "cardinality": "optional", + "description": "information about either pedigree or other description of ancestral information (e.g. parental variety in case of mutant or selection), e.g. A/3*B (meaning [(A x B) x B] x B)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "taxonomic classification", + "cardinality": "optional", + "description": "Method used for taxonomic classification, along with reference database used, classification rank, and thresholds used to classify new genomes. Expected values are: classification method, database name, and other parameters e.g. vConTACT vContact2 (references from NCBI RefSeq v83, genus rank classification, default parameters)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "plant growth medium", + "cardinality": "optional", + "description": "Specification of the media for growing the plants or tissue cultured samples, e.g. soil, aeroponic, hydroponic, in vitro solid culture medium, in vitro liquid culture medium. Recommended value is a specific value from EO:plant growth medium (follow this link for terms http://purl.obolibrary.org/obo/EO_0007147).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "rooting conditions", + "cardinality": "optional", + "description": "relevant rooting conditions, such as field plot size, sowing density, container dimensions, number of plants per container", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "rooting medium macronutrients", + "cardinality": "optional", + "description": "measurement of the culture rooting medium macronutrients (N,P, K, Ca, Mg, S); e.g. KH2PO4 (170mg/L)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "rooting medium micronutrients", + "cardinality": "optional", + "description": "measurement of the culture rooting medium micronutrients (Fe, Mn, Zn, B, Cu, Mo); e.g. H3BO3 (6.2mg/L)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "rooting medium carbon", + "cardinality": "optional", + "description": "source of organic carbon in the culture rooting medium; e.g. sucrose", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "rooting medium pH", + "cardinality": "optional", + "description": "pH measurement of the culture rooting medium; e.g. 5.5", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "microbiological culture medium", + "cardinality": "optional", + "description": "A culture medium used to select for, grow, and maintain prokaryotic microorganisms. Can be in either liquid (broth) or solidified (e.g. with agar) forms. This field accepts terms listed under microbiological culture medium (http://purl.obolibrary.org/obo/MICRO_0000067). If the proper descriptor is not listed please use text to describe the culture medium.", + "cv": [], + "units": "Pa", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "spike-in growth medium", + "cardinality": "optional", + "description": "A liquid or gel containing nutrients, salts, and other factors formulated to support the growth of microorganisms, cells, or plants (National Cancer Institute Thesaurus). A growth medium is a culture medium which has the disposition to encourage growth of particular bacteria to the exclusion of others in the same growth environment. In this case, list the culture medium used to propagate the spike-in bacteria during preparation of spike-in inoculum. This field accepts terms listed under microbiological culture medium (http://purl.obolibrary.org/obo/MICRO_0000067). If the proper descriptor is not listed please use text to describe the spike in growth media.", + "cv": [], + "units": "W/m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "fermentation medium", + "cardinality": "optional", + "description": "The growth medium used for the fermented food fermentation process, which supplies the required nutrients. Usually this includes a carbon and nitrogen source, water, micronutrients and chemical additives.", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "growth medium", + "cardinality": "optional", + "description": "A liquid or gel containing nutrients, salts, and other factors formulated to support the growth of microorganisms, cells, or plants (National Cancer Institute Thesaurus). The name of the medium used to grow the microorganism.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "isolation and growth condition", + "cardinality": "optional", + "description": "Publication reference in the form of pubmed ID (pmid), digital object identifier (doi) or url for isolation and growth condition specifications of the organism/material. Mandatory for MIGS and MIMARKS Specimen.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "annotation source", + "cardinality": "optional", + "description": "For cases where annotation was provided by a community jamboree or model organism database rather than by a specific submitter", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "reference for biomaterial", + "cardinality": "optional", + "description": "Primary publication if isolated before genome publication; otherwise, primary genome report. Mandatory for MIGS of bacteria and archaea.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sequencing location", + "cardinality": "optional", + "description": "The location the sequencing run was performed. Indicate the name of the lab or core facility where samples were sequenced.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "enrichment protocol", + "cardinality": "optional", + "description": "The microbiological workflow or protocol followed to test for the presence or enumeration of the target microbial analyte(s). Please provide a PubMed or DOI reference for published protocols.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "library preparation kit", + "cardinality": "optional", + "description": "Packaged kits (containing adapters, indexes, enzymes, buffers etc.), tailored for specific sequencing workflows, which allow the simplified preparation of sequencing-ready libraries for small genomes, amplicons, and plasmids.", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "nucleic acid extraction kit", + "cardinality": "optional", + "description": "The name of the extraction kit used to recover the nucleic acid fraction of an input material is performed.", + "cv": [], + "units": "ppm", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample pooling", + "cardinality": "optional", + "description": "Physical combination of several instances of like material, e.g. RNA extracted from samples or dishes of cell cultures into one big aliquot of cells. Please provide a short description of the samples that were pooled.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "lot number", + "cardinality": "optional", + "description": "A distinctive alpha-numeric identification code assigned by the manufacturer or distributor to a specific quantity of manufactured material or product within a batch. Synonym: Batch Number. The submitter should provide lot number of the item followed by the item name for which the lot number was provided.", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "single cell or viral particle lysis approach", + "cardinality": "optional", + "description": "Method used to free DNA from interior of the cell(s) or particle(s)", + "cv": [ + "chemical", + "combination", + "enzymatic", + "physical" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "single cell or viral particle lysis kit protocol", + "cardinality": "optional", + "description": "Name of the kit or standard protocol used for cell(s) or particle(s) lysis", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pooled DNA extract total", + "cardinality": "optional", + "description": "Indicate whether multiple DNA extractions were mixed. If the answer yes, the number of extracts that were pooled should be given. [ENA version of MIxS term: pooling of DNA extracts (if done). ]", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "([0-9]*)" + }, + { + "name": "sample material processing", + "cardinality": "optional", + "description": "A brief description of any processing applied to the sample during or after retrieving the sample from environment, or a link to the relevant protocol(s) performed.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample volume or weight for DNA extraction", + "cardinality": "optional", + "description": "Volume (ml) or mass (g) of total collected sample processed for DNA extraction. Note: total sample collected should be entered under the term 'sample size'.", + "cv": [], + "units": "ng", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "nucleic acid extraction", + "cardinality": "optional", + "description": "A link to a literature reference, electronic resource or a standard operating procedure (SOP), that describes the material separation to recover the nucleic acid fraction from a sample", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "nucleic acid amplification", + "cardinality": "optional", + "description": "A link to a literature reference, electronic resource or a standard operating procedure (SOP), that describes the enzymatic amplification (PCR, TMA, NASBA) of specific nucleic acids", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "library size", + "cardinality": "optional", + "description": "Total number of clones in the library prepared for the project", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "library reads sequenced", + "cardinality": "optional", + "description": "Total number of clones sequenced from the library", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "library vector", + "cardinality": "optional", + "description": "Cloning vector type(s) used in construction of libraries", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "library screening strategy", + "cardinality": "optional", + "description": "Specific enrichment or screening methods applied before and/or after creating clone libraries in order to select a specific group of sequences", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pcr conditions", + "cardinality": "optional", + "description": "Description of reaction conditions and components for PCR in the form of 'initial denaturation:94degC_1.5min; annealing=...'", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "assembly software", + "cardinality": "optional", + "description": "Tool(s) used for assembly, including version number and parameters in the format {software};{version};{parameters} e.g. metaSPAdes;3.11.0;kmer set 21,33,55,77,99,121, default parameters otherwise", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pcr primers", + "cardinality": "optional", + "description": "PCR primers that were used to amplify the sequence of the targeted gene, locus or subfragment. This field should contain all the primers used for a single PCR reaction if multiple forward or reverse primers are present in a single PCR reaction. The primer sequence should be reported in uppercase letters", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "adapters", + "cardinality": "optional", + "description": "Adapters provide priming sequences for both amplification and sequencing of the sample-library fragments. Both adapters should be reported; in uppercase letters", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food animal antimicrobial", + "cardinality": "optional", + "description": "The name(s) (generic or brand) of the antimicrobial(s) given to the food animal within the last 30 days.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food shipping transportation vehicle", + "cardinality": "optional", + "description": "A descriptor for the mobile machine which is used to transport food commodities along the food distribution system. This field accepts terms listed under vehicle (http://purl.obolibrary.org/obo/ENVO_01000604). If the proper descrptor is not listed please use text to describe the mode of travel. Multiple terms can be separated by one or more pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "water source shared", + "cardinality": "optional", + "description": "Other users sharing access to the same water source. Multiple terms can be separated by one or more pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food source", + "cardinality": "optional", + "description": "Type of plant or animal from which the food product or its major ingredient is derived or a chemical food source [FDA CFSAN 1995].", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food shipping transportation method", + "cardinality": "optional", + "description": "A descriptor for the method of movement of food commodity along the food distribution system. This field accepts terms listed under travel mode (http://purl.obolibrary.org/obo/GENEPIO_0001064). If the proper descrptor is not listed please use text to describe the mode of travel. Multiple terms can be separated by one or more pipes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "material of contact prior to food packaging", + "cardinality": "optional", + "description": "The material the food contacted (e.g., was processed in) prior to packaging. This field accepts terms listed under material of contact prior to food packaging (http://purl.obolibrary.org/obo/FOODON_03530077). If the proper descriptor is not listed please use text to describe the material of contact prior to food packaging.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "food product name legal status", + "cardinality": "optional", + "description": "A datum indicating that use of a food product name is regulated in some legal jurisdiction. This field accepts terms listed under food product name legal status (http://purl.obolibrary.org/obo/FOODON_03530087).", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "food quality date", + "cardinality": "optional", + "description": "The date recommended for the use of the product while at peak quality, this date is not a reflection of safety unless used on infant formula this date is not a reflection of safety and is typically labeled on a food product as \"best if used by,\" best by,\" \"use by,\" or \"freeze by.\"", + "cv": [], + "units": "", + "field_type": "DATE_FIELD", + "regex": "" + }, + { + "name": "food cleaning process", + "cardinality": "optional", + "description": "The process of cleaning food to separate other environmental materials from the food source. Multiple terms can be separated by pipes.", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "hygienic food production area", + "cardinality": "optional", + "description": "The subdivision of areas within a food production facility according to hygienic requirements. This field accepts terms listed under hygienic food production area (http://purl.obolibrary.org/obo/ENVO). Please add a term that most accurately indicates the hygienic area your sample was taken from according to the definitions provided.", + "cv": [], + "units": "kg s\u22123", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "food contact surface", + "cardinality": "optional", + "description": "The specific container or coating materials in direct contact with the food. Multiple values can be assigned. This field accepts terms listed under food contact surface (http://purl.obolibrary.org/obo/FOODON_03500010).", + "cv": [], + "units": "J/\u00b0C", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "food cooking process", + "cardinality": "optional", + "description": "The transformation of raw food by the application of heat. This field accepts terms listed under food cooking (http://purl.obolibrary.org/obo/FOODON_03450002).", + "cv": [], + "units": "%", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "food product by quality", + "cardinality": "optional", + "description": "Descriptors for describing food visually or via other senses, which is useful for tasks like food inspection where little prior knowledge of how the food came to be is available. Some terms like \"food (frozen)\" are both a quality descriptor and the output of a process. This field accepts terms listed under food product by quality (http://purl.obolibrary.org/obo/FOODON_00002454).", + "cv": [], + "units": "year", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "food animal antimicrobial route of administration", + "cardinality": "optional", + "description": "The route by which the antimicrobial is administered into the body of the food animal.", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food allergen labeling", + "cardinality": "optional", + "description": "A label indication that the product contains a recognized allergen. This field accepts terms listed under dietary claim or use (http://purl.obolibrary.org/obo/FOODON_03510213).", + "cv": [], + "units": "W/m2", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "food product type", + "cardinality": "optional", + "description": "A food product type is a class of food products that is differentiated by its food composition (e.g., single- or multi-ingredient), processing and/or consumption characteristics. This does not include brand name products but it may include generic food dish categories. This field accepts terms under food product type (http://purl.obolibrary.org/obo/FOODON:03400361). For terms related to food product for an animal, consult food product for animal (http://purl.obolibrary.org/obo/FOODON_03309997). If the proper descriptor is not listed please use text to describe the food type. Multiple terms can be separated by one or more pipes.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "food animal source sex category", + "cardinality": "optional", + "description": "The sex and reproductive status of the food animal.", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "animal intrusion near sample source", + "cardinality": "optional", + "description": "Identification of animals intruding on the sample or sample site including invertebrates (such as pests or pollinators) and vertebrates (such as wildlife or domesticated animals). This field accepts terms under organism (http://purl.obolibrary.org/obo/NCIT_C14250). This field also accepts identification numbers from NCBI under https://www.ncbi.nlm.nih.gov/taxonomy. Multiple terms can be separated by pipes.", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food packing medium integrity", + "cardinality": "optional", + "description": "A term label and term id to describe the state of the packing material and text to explain the exact condition. This field accepts terms listed under food packing medium integrity (http://purl.obolibrary.org/obo/FOODON_03530218).", + "cv": [], + "units": "\u00b0C", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "microbial starter", + "cardinality": "optional", + "description": "Any type of microorganisms used in food production. This field accepts terms listed under live organisms for food production (http://purl.obolibrary.org/obo/FOODON_0344453).", + "cv": [], + "units": "\u00b0C", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "food treatment process", + "cardinality": "optional", + "description": "Used to specifically characterize a food product based on the treatment or processes applied to the product or any indexed ingredient. The processes include adding, substituting or removing components or modifying the food or component, e.g., through fermentation. Multiple values can be assigned. This fields accepts terms listed under food treatment process (http://purl.obolibrary.org/obo/FOODON_03460111).", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "food preservation process", + "cardinality": "optional", + "description": "The methods contributing to the prevention or retardation of microbial, enzymatic or oxidative spoilage and thus to the extension of shelf life. This field accepts terms listed under food preservation process (http://purl.obolibrary.org/obo/FOODON_03470107).", + "cv": [], + "units": "J/\u00b0C", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "microbial starter ncbi taxonomy id", + "cardinality": "optional", + "description": "Please include Genus species and strain ID, if known of microorganisms used in food production. For complex communities, pipes can be used to separate two or more microbes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "interagency food safety analytics collaboration (ifsac) category", + "cardinality": "optional", + "description": "The IFSAC food categorization scheme has five distinct levels to which foods can be assigned, depending upon the type of food. First, foods are assigned to one of four food groups (aquatic animals, land animals, plants, and other). Food groups include increasingly specific food categories; dairy, eggs, meat and poultry, and game are in the land animal food group, and the category meat and poultry is further subdivided into more specific categories of meat (beef, pork, other meat) and poultry (chicken, turkey, other poultry). Finally, foods are differentiated by differences in food processing (such as pasteurized fluid dairy products, unpasteurized fluid dairy products, pasteurized solid and semi-solid dairy products, and unpasteurized solid and semi-solid dairy products. An IFSAC food category chart is available from https://www.cdc.gov/foodsafety/ifsac/projects/food-categorization-scheme.html PMID: 28926300.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food animal body condition", + "cardinality": "optional", + "description": "Body condition scoring is a production management tool used to evaluate overall health and nutritional needs of a food animal. Because there are different scoring systems, this field is restricted to three categories.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food product synonym", + "cardinality": "optional", + "description": "Other names by which the food product is known by (e.g., regional or non-English names).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food ingredient", + "cardinality": "optional", + "description": "In this field, please list individual ingredients for multi-component food [FOODON:00002501] and simple foods that is not captured in food_type. Please use terms that are present in FoodOn. Multiple terms can be separated by one or more pipes |, but please consider limiting this list to the top 5 ingredients listed in order as on the food label. See also, https://www.fda.gov/food/food-ingredients-packaging/overview-food-ingredients-additives-colors.", + "cv": [], + "units": "year", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "food stored by consumer (storage duration)", + "cardinality": "optional", + "description": "The storage duration of the food commodity by the consumer, prior to onset of illness or sample collection. Indicate the timepoint written in ISO 8601 format.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "food animal antimicrobial duration", + "cardinality": "optional", + "description": "The duration of time (days) that the antimicrobial was administered to the food animal.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "part of plant or animal", + "cardinality": "optional", + "description": "The anatomical part of the organism being involved in food production or consumption; e.g., a carrot is the root of the plant (root vegetable). This field accepts terms listed under part of plant or animal (http://purl.obolibrary.org/obo/FOODON_03420116).", + "cv": [], + "units": "year", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "hazard analysis critical control points (haccp) guide food safety term", + "cardinality": "optional", + "description": "Hazard Analysis Critical Control Points (HACCP) food safety terms; This field accepts terms listed under HACCP guide food safety term (http://purl.obolibrary.org/obo/FOODON_03530221).", + "cv": [], + "units": "year", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "dietary claim or use", + "cardinality": "optional", + "description": "These descriptors are used either for foods intended for special dietary use as defined in 21 CFR 105 or for foods that have special characteristics indicated in the name or labeling. This field accepts terms listed under dietary claim or use (http://purl.obolibrary.org/obo/FOODON_03510023). Multiple terms can be separated by one or more pipes, but please consider limiting this list to the most prominent dietary claim or use.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "degree of plant part maturity", + "cardinality": "optional", + "description": "A description of the stage of development of a plant or plant part based on maturity or ripeness. This field accepts terms listed under degree of plant maturity (http://purl.obolibrary.org/obo/FOODON_03530050).", + "cv": [], + "units": "year", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "food production environmental monitoring zone", + "cardinality": "optional", + "description": "An environmental monitoring zone is a formal designation as part of an environmental monitoring program, in which areas of a food production facility are categorized, commonly as zones 1-4, based on likelihood or risk of foodborne pathogen contamination. This field accepts terms listed under food production environmental monitoring zone (http://purl.obolibrary.org/obo/ENVO). Please add a term to indicate the environmental monitoring zone the sample was taken from.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "plant reproductive part", + "cardinality": "optional", + "description": "Plant reproductive part used in the field during planting to start the crop.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food traceability list category", + "cardinality": "optional", + "description": "The FDA is proposing to establish additional traceability recordkeeping requirements (beyond what is already required in existing regulations) for persons who manufacture, process, pack, or hold foods the Agency has designated for inclusion on the Food Traceability List. The Food Traceability List (FTL) identifies the foods for which the additional traceability records described in the proposed rule would be required. The term \u201cFood Traceability List\u201d (FTL) refers not only to the foods specifically listed (https://www.fda.gov/media/142303/download), but also to any foods that contain listed foods as ingredients.", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food animal antimicrobial frequency", + "cardinality": "optional", + "description": "The frequency per day that the antimicrobial was administered to the food animal.", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "intended consumer", + "cardinality": "optional", + "description": "Food consumer type, human or animal, for which the food product is produced and marketed. This field accepts terms listed under food consumer group (http://purl.obolibrary.org/obo/FOODON_03510136) or NCBI taxid.", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "quantity purchased", + "cardinality": "optional", + "description": "The quantity of food purchased by consumer.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food container or wrapping", + "cardinality": "optional", + "description": "Type of container or wrapping defined by the main container material, the container form, and the material of the liner lids or ends. Also type of container or wrapping by form; prefer description by material first, then by form. This field accepts terms listed under food container or wrapping (http://purl.obolibrary.org/obo/FOODON_03490100).", + "cv": [], + "units": "\u00b0C", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "food additive", + "cardinality": "optional", + "description": "A substance or substances added to food to maintain or improve safety and freshness, to improve or maintain nutritional value, or improve taste, texture and appearance. This field accepts terms listed under food additive (http://purl.obolibrary.org/obo/FOODON_03412972). Multiple terms can be separated by one or more pipes, but please consider limiting this list to the top 5 ingredients listed in order as on the food label. See also, https://www.fda.gov/food/food-ingredients-packaging/overview-food-ingredients-additives-colors.", + "cv": [], + "units": "g/m3", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food source age", + "cardinality": "optional", + "description": "The age of the food source host organism. Depending on the type of host organism, age may be more appropriate to report in days, weeks, or years.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "food animal antimicrobial intended use", + "cardinality": "optional", + "description": "The prescribed intended use of or the condition treated by the antimicrobial given to the food animal by any route of administration.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food packing medium", + "cardinality": "optional", + "description": "The medium in which the food is packed for preservation and handling or the medium surrounding homemade foods, e.g., peaches cooked in sugar syrup. The packing medium may provide a controlled environment for the food. It may also serve to improve palatability and consumer appeal. This includes edible packing media (e.g. fruit juice), gas other than air (e.g. carbon dioxide), vacuum packed, or packed with aerosol propellant. This field accepts terms under food packing medium (http://purl.obolibrary.org/obo/FOODON_03480020). Multiple terms may apply and can be separated by pipes.", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "specific intended consumer", + "cardinality": "optional", + "description": "Food consumer type, human or animal, for which the food product is produced and marketed. This field accepts terms listed under food consumer group (http://purl.obolibrary.org/obo/FOODON_03510136).", + "cv": [], + "units": "m2", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "purchase date", + "cardinality": "optional", + "description": "The date a food product was purchased by consumer.", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food stored by consumer (storage temperature)", + "cardinality": "optional", + "description": "Temperature at which food commodity was stored by the consumer, prior to onset of illness or sample collection.", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "food package capacity", + "cardinality": "optional", + "description": "The maximum number of product units within a package", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "food distribution point geographic location (city)", + "cardinality": "optional", + "description": "A reference to a place on the Earth, by its name or by its geographical location that refers to a distribution point along the food chain. This field accepts terms listed under geographic location (http://purl.obolibrary.org/obo/GAZ_00000448). Reference: Adam Diamond, James Barham. Moving Food Along the Value Chain: Innovations in Regional Food Distribution. U.S. Dept. of Agriculture, Agricultural Marketing Service. Washington, DC. March 2012. http://dx.doi.org/10.9752/MS045.03-2012.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food product origin geographic location", + "cardinality": "optional", + "description": "A reference to a place on the Earth, by its name or by its geographical location that describes the origin of the food commodity, either in terms of its cultivation or production. This field accepts terms listed under geographic location (http://purl.obolibrary.org/obo/GAZ_00000448).", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "food distribution point geographic location", + "cardinality": "optional", + "description": "A reference to a place on the Earth, by its name or by its geographical location that refers to a distribution point along the food chain. This field accepts terms listed under geographic location (http://purl.obolibrary.org/obo/GAZ_00000448). Reference: Adam Diamond, James Barham. Moving Food Along the Value Chain: Innovations in Regional Food Distribution. U.S. Dept. of Agriculture, Agricultural Marketing Service. Washington, DC. March 2012. http://dx.doi.org/10.9752/MS045.03-2012.", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "production labeling claims", + "cardinality": "optional", + "description": "Labeling claims containing descriptors such as wild caught, free-range, organic, free-range, industrial, hormone-free, antibiotic free, cage free. Can include more than one term, separated by \";\"", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "relative location of sample", + "cardinality": "optional", + "description": "Location of sampled soil to other parts of the farm e.g. under crop plant, near irrigation ditch, from the dirt road.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "depth", + "cardinality": "optional", + "description": "The vertical distance below local surface, e.g. for sediment or soil samples depth is measured from sediment or soil surface, respectively. Depth can be reported as an interval for subsurface samples.", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "((0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "environment adjacent to site", + "cardinality": "optional", + "description": "Description of the environmental system or features that are adjacent to the sampling site. This field accepts terms under ecosystem (http://purl.obolibrary.org/obo/ENVO_01001110) and human construction (http://purl.obolibrary.org/obo/ENVO_00000070). Multiple terms can be separated by pipes.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "fertilizer administration", + "cardinality": "optional", + "description": "Type of fertilizer or amendment added to the soil or water for the purpose of improving substrate health and quality for plant growth. This field accepts terms listed under agronomic fertilizer (http://purl.obolibrary.org/obo/AGRO_00002062). Multiple terms may apply and can be separated by pipes, listing in reverse chronological order. N.B. Old ENA definition as \"fertilizer regimen\": information about treatment involving the use of fertilizers; should include the name fertilizer, amount administered, treatment duration, interval and total experimental duration; can include multiple fertilizer regimens", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "biotic regimen", + "cardinality": "optional", + "description": "information about treatment involving use of biotic factors, such as bacteria, viruses or fungi", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "mechanical damage", + "cardinality": "optional", + "description": "information about any mechanical damage exerted on the plant; can include multiple damages and sites", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "chemical administration", + "cardinality": "optional", + "description": "list of chemical compounds administered to the host or site where sampling occurred, and when (e.g. antibiotics, N fertilizer, air filter); can include multiple compounds. For Chemical Entities of Biological Interest ontology (CHEBI) (v111), please see http://purl.bioontology.org/ontology/CHEBI", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + } + ] + } +} \ No newline at end of file diff --git a/templates/ERC000056/README.md b/templates/ERC000056/README.md new file mode 100644 index 0000000..9391edc --- /dev/null +++ b/templates/ERC000056/README.md @@ -0,0 +1,332 @@ +# ERC000056: GSC MIxS Food and Production + +Genomic Standards Consortium package extension for reporting of measurements and observations obtained from the environment where the sample was obtained. By choosing the environmental package, a selection of fields can be made from a relevant subsets of the GSC terms. This package is a combination of the four food extensions (MIxS-food-animal and animal feed, MIxS-food-farm environment, MIxS-food-food production facility, MIxS-food-human foods). + +## Study + +A Study is a container for a sequencing investigation that may comprise multiple experiments. The Study has an overall goal, but is otherwise minimally defined in the SRA. A Study is composed of a descriptor, zero or more experiments, and zero or more analyses. The submitter may decorate the Study with web links and properties. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:---------------|:--------------|:---------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for a study. this is used to link experiments to the study. | | +| title | mandatory | Title of the study as would be used in a publication. | | +| study_type | mandatory | The study_type presents a controlled vocabulary for expressing the overall purpose of the study. | Whole Genome Sequencing, Metagenomics, Transcriptome Analysis, Resequencing, Epigenetics, Synthetic Genomics, Forensic or Paleo-genomics, Gene Regulation Study, Cancer Genomics, Population Genomics, RNASeq, Exome Sequencing, Pooled Clone Sequencing, Transcriptome Sequencing, Other | +| new_study_type | optional | Optional if 'study_type' is not 'other'. to propose a new term, select other and enter a new study type. | | +| study_abstract | optional | Briefly describes the goals, purpose, and scope of the study. this need not be listed if it can be inherited from a referenced publication. | | + +## Experiment + +An experiment object serves as a metadata record encapsulating essential details about a sequencing experiment, including the experimental design, sequencing type, and relevant parameters. This information enhances the interpretation and contextual understanding of nucleotide sequences submitted to the archive. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:------------------------------|:--------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for each experiment. this is used to link runs to experiments. | | +| title | optional | Short text that can be used to call out experiment records in searches or in displays. this element is technically optional but should be used for all new records. | | +| study_alias | mandatory | Identifies the parent study. (from study metadata) | | +| sample_alias | mandatory | (from sample metadata) | | +| design_description | optional | Goal and setup of the individual library including library was constructed. | | +| library_name | optional | The submitter's name for this library. | | +| library_strategy | mandatory | Sequencing technique intended for this library. | WGS, WGA, WXS, RNA-Seq, ssRNA-seq, snRNA-seq, miRNA-Seq, ncRNA-Seq, FL-cDNA, EST, Hi-C, ATAC-seq, WCS, RAD-Seq, CLONE, POOLCLONE, AMPLICON, CLONEEND, FINISHING, ChIP-Seq, MNase-Seq, DNase-Hypersensitivity, Bisulfite-Seq, CTS, MRE-Seq, MeDIP-Seq, MBD-Seq, Tn-Seq, VALIDATION, FAIRE-seq, SELEX, RIP-Seq, ChIA-PET, Synthetic-Long-Read, Targeted-Capture, Tethered Chromatin Conformation Capture, NOMe-Seq, ChM-Seq, GBS, Ribo-Seq, OTHER | +| library_source | mandatory | The library_source specifies the type of source material that is being sequenced. | GENOMIC, GENOMIC SINGLE CELL, TRANSCRIPTOMIC, TRANSCRIPTOMIC SINGLE CELL, METAGENOMIC, METATRANSCRIPTOMIC, SYNTHETIC, VIRAL RNA, OTHER | +| library_selection | mandatory | Method used to enrich the target in the sequence library preparation | RANDOM, PCR, RANDOM PCR, RT-PCR, HMPR, MF, repeat fractionation, size fractionation, MSLL, cDNA, cDNA_randomPriming, cDNA_oligo_dT, PolyA, Oligo-dT, Inverse rRNA, Inverse rRNA selection, ChIP, ChIP-Seq, MNase, DNase, Hybrid Selection, Reduced Representation, Restriction Digest, 5-methylcytidine antibody, MBD2 protein methyl-CpG binding domain, CAGE, RACE, MDA, padlock probes capture method, other, unspecified | +| library_layout | mandatory | Library_layout specifies whether to expect single, paired, or other configuration of reads. in the case of paired reads, information about the relative distance and orientation is specified. | | +| insert_size | optional | Insert size for paired reads | | +| library_construction_protocol | optional | Free form text describing the protocol by which the sequencing library was constructed. | | +| platform | mandatory | The platform record selects which sequencing platform and platform-specific runtime parameters. this will be determined by the center. optional if 'instrument_model' is provided. | LS454, ILLUMINA, HELICOS, ABI_SOLID, COMPLETE_GENOMICS, BGISEQ, OXFORD_NANOPORE, PACBIO_SMRT, ION_TORRENT, CAPILLARY, DNBSEQ, ELEMENT, ULTIMA, VELA_DIAGNOSTICS, GENAPSYS, GENEMIND, TAPESTRI | +| instrument_model | mandatory | Model of the sequencing instrument. | 454 GS, 454 GS 20, 454 GS FLX, 454 GS FLX Titanium, 454 GS FLX+, 454 GS Junior, AB 310 Genetic Analyzer, AB 3130 Genetic Analyzer, AB 3130xL Genetic Analyzer, AB 3500 Genetic Analyzer, AB 3500xL Genetic Analyzer, AB 3730 Genetic Analyzer, AB 3730xL Genetic Analyzer, AB 5500 Genetic Analyzer, AB 5500xl Genetic Analyzer, AB 5500xl-W Genetic Analysis System, AB SOLiD 3 Plus System, AB SOLiD 4 System, AB SOLiD 4hq System, AB SOLiD PI System, AB SOLiD System, AB SOLiD System 2.0, AB SOLiD System 3.0, BGISEQ-50, BGISEQ-500, Complete Genomics, DNBSEQ-G400, DNBSEQ-G400 FAST, DNBSEQ-G50, DNBSEQ-T7, Element AVITI, FASTASeq 300, GENIUS, GS111, Genapsys Sequencer, GenoCare 1600, GenoLab M, GridION, Helicos HeliScope, HiSeq X Five, HiSeq X Ten, Illumina Genome Analyzer, Illumina Genome Analyzer II, Illumina Genome Analyzer IIx, Illumina HiScanSQ, Illumina HiSeq 1000, Illumina HiSeq 1500, Illumina HiSeq 2000, Illumina HiSeq 2500, Illumina HiSeq 3000, Illumina HiSeq 4000, Illumina HiSeq X, Illumina MiSeq, Illumina MiniSeq, Illumina NovaSeq 6000, Illumina NovaSeq X, Illumina iSeq 100, Ion GeneStudio S5, Ion GeneStudio S5 Plus, Ion GeneStudio S5 Prime, Ion Torrent Genexus, Ion Torrent PGM, Ion Torrent Proton, Ion Torrent S5, Ion Torrent S5 XL, MGISEQ-2000RS, MinION, NextSeq 1000, NextSeq 2000, NextSeq 500, NextSeq 550, Onso, PacBio RS, PacBio RS II, PromethION, Revio, Sentosa SQ301, Sequel, Sequel II, Sequel IIe, Tapestri, UG 100, unspecified | + +## Run + +A run contains a group of reads generated for a particular experiment. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:-----------------|:--------------|:--------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for each run. | | +| experiment_alias | mandatory | From_experiment_metadata | | +| file_name | mandatory | The name or relative pathname of a run data file. | | +| file_format | mandatory | The run data file model. | sra, srf, sff, fastq, fasta, tab, 454_native, 454_native_seq, 454_native_qual, Helicos_native, Illumina_native, Illumina_native_seq, Illumina_native_prb, Illumina_native_int, Illumina_native_qseq, Illumina_native_scarf, SOLiD_native, SOLiD_native_csfasta, SOLiD_native_qual, PacBio_HDF5, bam, cram, CompleteGenomics_native, OxfordNanopore_native | + +## Sample + +A Sample defines an isolate of sequenceable material upon which sequencing experiments can be based. The Sample object may be a surrogate for taxonomy accession or an anonymized individual identifier. Or, it may fully specify provenance and isolation method of the starting material. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:-----------------------------------------------------------------------|:--------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for each run. | | +| title | mandatory | Short text that can be used to call out sample records in search results or in displays. | | +| taxon_id | mandatory | Ncbi taxonomy identifier. this is appropriate for individual organisms and some environmental samples. | | +| sample_description | optional | Free-form text describing the sample, its origin, and its method of isolation. | | +| culture result | optional | Any result of a bacterial culture experiment reported as a binary assessment such as positive/negative, active/inactive. | | +| culture result organism | optional | Taxonomic information about the cultured organism(s). (Units: m2) | | +| culture target microbial analyte | optional | The target microbial analyte in terms of investigation scope. this field accepts terms under organism (http://purl.obolibrary.org/obo/ncit_c14250). this field also accepts identification numbers from ncbi under https://www.ncbi.nlm.nih.gov/taxonomy. | | +| biological sample replicate | optional | Measurements of biologically distinct samples that show biological variation. (Units: year) | | +| technical sample replicate | optional | Repeated measurements of the same sample that show independent measures of the noise associated with the equipment and the protocols. | | +| purpose of sampling | optional | The reason that the sample was collected. | | +| trophic level | optional | Trophic levels are the feeding position in a food chain. microbes can be a range of producers (e.g. chemolithotroph) | autotroph, carboxydotroph, chemoautotroph, chemoheterotroph, chemolithoautotroph, chemolithotroph, chemoorganoheterotroph, chemoorganotroph, chemosynthetic, chemotroph, copiotroph, diazotroph, facultative autotroph, heterotroph, lithoautotroph, lithoheterotroph, lithotroph, methanotroph, methylotroph, mixotroph, obligate chemoautolithotroph, oligotroph, organoheterotroph, organotroph, photoautotroph, photoheterotroph, photolithoautotroph, photolithotroph, photosynthetic, phototroph | +| observed biotic relationship | optional | Description of relationship(s) between the subject organism and other organism(s) it is associated with. e.g., parasite on species x; mutualist with species y. the target organism is the subject of the relationship, and the other organism(s) is the object. | commensal, free living, mutualism, parasite, symbiont | +| known pathogenicity | optional | To what is the entity pathogenic, for instance plant, fungi, bacteria | | +| relationship to oxygen | optional | Is this organism an aerobe, anaerobe? please note that aerobic and anaerobic are valid descriptors for microbial environments | aerobe, anaerobe, facultative, microaerophilic, microanaerobe, obligate aerobe, obligate anaerobe | +| propagation | optional | The type of reproduction from the parent stock. values for this field is specific to different taxa. for phage or virus: lytic/lysogenic/temperate/obligately lytic. for plasmids: incompatibility group. for eukaryotes: sexual/asexual. mandatory for migs of eukayotes, plasmids and viruses. | | +| sample transportation temperature | optional | Temperature at which sample was transported, e.g. -20 or 4 degree celsius. (Units: °C) | | +| sample transport container | optional | Container in which the sample was stored during transport. indicate the location name. (Units: J/°C) | | +| sample transport duration | optional | The duration of time from when the sample was collected until processed. indicate the duration for which the sample was stored written in iso 8601 format. (Units: year) | | +| sample collection device | optional | The device used to collect an environmental sample. it is recommended to use terms listed under environmental sampling device (http://purl.obolibrary.org/obo/envo) and/or terms listed under specimen collection device (http://purl.obolibrary.org/obo/genepio_0002094). | | +| sample collection method | optional | The method employed for collecting the sample. can be provided in the form of a pmid, doi, url or text. | | +| sample storage temperature | optional | Temperature at which sample was stored, e.g. -80 (Units: °C) | | +| sample storage device | optional | The container used to store the sample. this field accepts terms listed under container (http://purl.obolibrary.org/obo/ncit_c43186). if the proper descriptor is not listed please use text to describe the storage device. | | +| sample storage location | optional | Location at which sample was stored, usually name of a specific freezer/room. indicate the location name. | | +| size-fraction lower threshold | optional | Refers to the mesh/pore size used to retain the sample. materials smaller than the size threshold are excluded from the sample (Units: µm) | | +| size-fraction upper threshold | optional | Refers to the mesh/pore size used to pre-filter/pre-sort the sample. materials larger than the size threshold are excluded from the sample (Units: µm) | | +| soil type | optional | Description of the soil type or classification. this field accepts terms under soil (http://purl.obolibrary.org/obo/envo_00001998). multiple terms can be separated by pipes. | Acrisol, Albeluvisol, Alisol, Andosol, Anthrosol, Arenosol, Calcisol, Cambisol, Chernozem, Cryosol, Durisol, Ferralsol, Fluvisol, Gleysol, Gypsisol, Histosol, Kastanozem, Leptosol, Lixisol, Luvisol, Nitisol, Phaeozem, Planosol, Plinthosol, Podzol, Regosol, Solonchak, Solonetz, Stagnosol, Technosol, Umbrisol, Vertisol | +| soil type method | optional | Reference or method used in determining soil series name or other lower-level classification | | +| soil texture method | optional | Reference or method used in determining soil texture | | +| soil pH | optional | Ph measurement of the soil; e.g. 6.2 | | +| soil cover | optional | Description of the material covering the sampled soil. this field accepts terms under envo:00010483, environmental material. | | +| soil texture classification | optional | One of the 12 soil texture classes use to describe soil texture based on the relative proportion of different grain sizes of mineral particles [sand (50 um to 2 mm), silt (2 um to 50 um), and clay (<2 um)] in a soil. (Units: °C) | | +| soil sediment porosity | optional | Porosity of soil or deposited sediment is volume of voids divided by the total volume of sample. | | +| soil conductivity | optional | Conductivity of soil at time of sampling. | | +| facility type | optional | Establishment details about the type of facility where the sample was taken. this is independent of the specific product(s) within the facility. | | +| collection site geographic feature | optional | Text or terms that describe the geographic feature where the food sample was obtained by the researcher. this field accepts selected terms listed under the following ontologies: anthropogenic geographic feature (http://purl.obolibrary.org/obo/envo_00000002), for example agricultural fairground [envo:01000986]; garden [envo:00000011} or any of its subclasses; market [envo:01000987]; water well [envo:01000002]; or human construction (http://purl.obolibrary.org/obo/envo_00000070). (Units: m2) | | +| area sampled size | optional | The total amount or size (volume (ml), mass (g) or area (m2) ) of sample collected. (Units: ml) | | +| sample name | optional | Sample name is a name that you choose for the sample. it can have any format, but we suggest that you make it concise, unique and consistent within your lab, and as informative as possible. every sample name from a single submitter must be unique. | | +| study design | optional | A plan specification comprised of protocols (which may specify how and what kinds of data will be gathered) that are executed as part of an investigation and is realized during a study design execution. this field accepts terms under study design (http://purl.obolibrary.org/obo/obi_0500000). if the proper descriptor is not listed please use text to describe the study design. multiple terms can be separated by pipes. (Units: kg s−3) | | +| project name | optional | Name of the project within which the sequencing was organized | | +| farm equipment sanitization | optional | Method used to sanitize growing and harvesting equipment. this can including type and concentration of sanitizing solution. multiple terms can be separated by one or more pipes. | | +| equipment shared with other farms | optional | List of planting, growing or harvesting equipment shared with other farms. this field accepts terms listed under agricultural implement (http://purl.obolibrary.org/obo/agro_00000416). multiple terms can be separated by pipes. | | +| farm equipment used | optional | List of equipment used for planting, fertilization, harvesting, irrigation, land levelling, residue management, weeding or transplanting during the growing season. this field accepts terms listed under agricultural implement (http://purl.obolibrary.org/obo/agro_00000416). multiple terms can be separated by pipes. | | +| farm equipment sanitization frequency | optional | The number of times farm equipment is cleaned. frequency of cleaning might be on a daily basis, weekly, monthly, quarterly or annually. (Units: m2) | | +| farm watering water source | optional | Source of water used on the farm for irrigation of crops or watering of livestock. | | +| food production system characteristics | optional | Descriptors of the food production system or of the agricultural environment and growing conditions related to the farm production system, such as wild caught, organic, free-range, industrial, dairy, beef, domestic or cultivated food production. this field accepts terms listed under food production (http://purl.obolibrary.org/obo/foodon_03530206). multiple terms may apply and can be separated by pipes. | | +| animal water delivery method | optional | Description of the equipment or method used to distribute water to livestock. this field accepts termed listed under water delivery equipment (http://opendata.inra.fr/eol/eol_0001653). multiple terms can be separated by pipes. | | +| plant water delivery method | optional | Description of the equipment or method used to distribute water to crops. this field accepts termed listed under irrigation process (http://purl.obolibrary.org/obo/agro_00000006). multiple terms can be separated by pipes. | | +| food harvesting process | optional | A harvesting process is a process which takes in some food material from an individual or community of plant or animal organisms in a given context and time, and outputs a precursor or consumable food product. this may include a part of an organism or the whole, and may involve killing the organism. | | +| food animal source diet | optional | If the isolate is from a food animal, the type of diet eaten by the food animal. please list the main food staple and the setting, if appropriate. for a list of acceptable animal feed terms or categories, please see http://www.feedipedia.org. multiple terms may apply and can be separated by pipes |food product for animal covers foods intended for consumption by domesticated animals. consult http://purl.obolibrary.org/obo/foodon_03309997. if the proper descriptor is not listed please use text to describe the food type. multiple terms can be separated by one or more pipes. if the proper descriptor is not listed please use text to describe the food product type. | | +| food production characteristics | optional | Descriptors of the food production system such as wild caught, free-range, organic, free-range, industrial, dairy, beef. (Units: °C) | | +| food animal group size | optional | The number of food animals of the same species that are maintained together as a unit, i.e. a herd or flock. (Units: year) | | +| fertilizer administration date | optional | Date of administration of soil amendment or fertilizer. multiple terms may apply and can be separated by pipes, listing in reverse chronological order. | | +| animal feeding equipment | optional | Description of the feeding equipment used for livestock. this field accepts terms listed under feed delivery (http://opendata.inra.fr/eol/eol_0001757). multiple terms can be separated by one or more pipes. | | +| crop yield | optional | Amount of crop produced per unit or area of land. | | +| water delivery frequency | optional | Number of water delivery events within a given period of time. | | +| animal housing system | optional | Description of the housing system of the livestock. this field accepts terms listed under terrestrial management housing system (http://opendata.inra.fr/eol/eol_0001605). | | +| environmental feature adjacent water source | optional | Description of the environmental features that are adjacent to the farm water source. this field accepts terms under ecosystem (http://purl.obolibrary.org/obo/envo_01001110) and human construction (http://purl.obolibrary.org/obo/envo_00000070). multiple terms can be separated by pipes. | | +| ploidy | optional | The ploidy level of the genome (e.g. allopolyploid, haploid, diploid, triploid, tetraploid). it has implications for the downstream study of duplicated gene and regions of the genomes (and perhaps for difficulties in assembly). for terms, please select terms listed under class ploidy (pato:001374) of phenotypic quality ontology (pato), and for a browser of pato (v 2018-03-27) please refer to http://purl.bioontology.org/ontology/pato | | +| number of replicons | optional | Reports the number of replicons in a nuclear genome of eukaryotes, in the genome of a bacterium or archaea or the number of segments in a segmented virus. always applied to the haploid chromosome count of a eukaryote. mandatory for migs of eukaryotes, bacteria, archaea and segmented virus. | | +| extrachromosomal elements | optional | Do plasmids exist of significant phenotypic consequence (e.g. ones that determine virulence or antibiotic resistance). megaplasmids? other plasmids (borrelia has 15+ plasmids). | | +| estimated size | optional | The estimated size of the genome (in bp) prior to sequencing. of particular importance in the sequencing of (eukaryotic) genome which could remain in draft form for a long or unspecified period. mandatory for migs of eukaryotes. | | +| target gene | optional | Targeted gene or locus name for marker gene studies | | +| target subfragment | optional | Name of subfragment of a gene or locus. important to e.g. identify special regions on marker genes like v6 on 16s rrna | | +| multiplex identifiers | optional | Molecular barcodes, called multiplex identifiers (mids), that are used to specifically tag unique samples in a sequencing run. sequence should be reported in uppercase letters | | +| sequence quality check | optional | Indicate if the sequence has been called by automatic systems (none) or undergone a manual editing procedure (e.g. by inspecting the raw data or chromatograms). applied only for sequences that are not submitted to sra or dra | manual, none, software | +| chimera check software | optional | Tool(s) used for chimera checking, including version number and parameters, to discover and remove chimeric sequences. a chimeric sequence is comprised of two or more phylogenetically distinct parent sequences. | | +| relevant electronic resources | optional | A related resource that is referenced, cited, or otherwise associated to the sequence in the format of a pmid, doi or url | | +| relevant standard operating procedures | optional | Standard operating procedures used in assembly and/or annotation of genomes, metagenomes or environmental sequences in the format of a pmid, doi or url | | +| 16s recovered | optional | Can a 16s gene be recovered from the submitted bin, sag or mag? | No, Yes | +| 16S recovery software | optional | Tools used for 16s rrna gene extraction. add names and versions of software(s), parameters used | | +| completeness score | optional | Completeness score is typically based on either the fraction of markers found as compared to a database or the percent of a genome found as compared to a closely related reference genome. completeness score is one of 3 attributes which in combination reflect the standard quality of a mag, see here for more information: https://ena-docs.readthedocs.io/en/latest/faq_metagenomes.html. mandatory for all samples directly linked with sags or mags. (Units: %) | | +| completeness software | optional | Tools used for completion estimate, i.e. checkm, anvi'o, busco. mandatory for all samples directly linked with sags or mags. | | +| completeness approach | optional | The approach used to determine the completeness of a given bin, sag or mag, which would typically make use of a set of conserved marker genes or a closely related reference genome. for uvig completeness, include reference genome or group used, and contig feature suggesting a complete genome | | +| assembly quality | optional | The assembly quality category is based on sets of criteria outlined for each assembly quality category. for misag/mimag; finished: single, validated, contiguous sequence per replicon without gaps or ambiguities with a consensus error rate equivalent to q50 or better. high quality draft:multiple fragments where gaps span repetitive regions. presence of the 23s, 16s and 5s rrna genes and at least 18 trnas. medium quality draft:many fragments with little to no review of assembly other than reporting of standard assembly statistics. low quality draft:many fragments with little to no review of assembly other than reporting of standard assembly statistics. assembly statistics include, but are not limited to total assembly size, number of contigs, contig n50/l50, and maximum contig length. for miuvig; finished: single, validated, contiguous sequence per replicon without gaps or ambiguities, with extensive manual review and editing to annotate putative gene functions and transcriptional units. high-quality draft genome: one or multiple fragments, totaling ≥ 90% of the expected genome or replicon sequence or predicted complete. genome fragment(s): one or multiple fragments, totalling < 90% of the expected genome or replicon sequence, or for which no genome size could be estimated. | Many fragments with little to no review of assembly other than reporting of standard assembly statistics, Multiple fragments where gaps span repetitive regions. Presence of the 23S, 16S, and 5S rRNA genes and at least 18 tRNAs, Single contiguous sequence without gaps or ambiguities with a consensus error rate equivalent to Q50 or better | +| assembly name | optional | Name/version of the assembly provided by the submitter that is used in the genome browsers and in the community | | +| collection date | optional | The date the sample was collected with the intention of sequencing, either as an instance (single point in time) or interval. in case no exact time is available, the date/time can be right truncated i.e. all of these are valid iso8601 compliant times: 2008-01-23t19:23:10+00:00; 2008-01-23t19:23:10; 2008-01-23; 2008-01; 2008. | | +| altitude | optional | The altitude of the sample is the vertical distance between earth's surface above sea level and the sampled position in the air. (Units: m) | | +| geographic location (country and/or sea) | optional | The geographical origin of where the sample was collected from, with the intention of sequencing, as defined by the country or sea name. country or sea names should be chosen from the insdc country list (http://insdc.org/country.html). | Afghanistan, Albania, Algeria, American Samoa, Andorra, Angola, Anguilla, Antarctica, Antigua and Barbuda, Arctic Ocean, Argentina, Armenia, Aruba, Ashmore and Cartier Islands, Atlantic Ocean, Australia, Austria, Azerbaijan, Bahamas, Bahrain, Baker Island, Baltic Sea, Bangladesh, Barbados, Bassas da India, Belarus, Belgium, Belize, Benin, Bermuda, Bhutan, Bolivia, Borneo, Bosnia and Herzegovina, Botswana, Bouvet Island, Brazil, British Virgin Islands, Brunei, Bulgaria, Burkina Faso, Burundi, Cambodia, Cameroon, Canada, Cape Verde, Cayman Islands, Central African Republic, Chad, Chile, China, Christmas Island, Clipperton Island, Cocos Islands, Colombia, Comoros, Cook Islands, Coral Sea Islands, Costa Rica, Cote d'Ivoire, Croatia, Cuba, Curacao, Cyprus, Czechia, Czech Republic, Democratic Republic of the Congo, Denmark, Djibouti, Dominica, Dominican Republic, East Timor, Ecuador, Egypt, El Salvador, Equatorial Guinea, Eritrea, Estonia, Ethiopia, Europa Island, Falkland Islands (Islas Malvinas), Faroe Islands, Fiji, Finland, France, French Guiana, French Polynesia, French Southern and Antarctic Lands, Gabon, Gambia, Gaza Strip, Georgia, Germany, Ghana, Gibraltar, Glorioso Islands, Greece, Greenland, Grenada, Guadeloupe, Guam, Guatemala, Guernsey, Guinea, Guinea-Bissau, Guyana, Haiti, Heard Island and McDonald Islands, Honduras, Hong Kong, Howland Island, Hungary, Iceland, India, Indian Ocean, Indonesia, Iran, Iraq, Ireland, Isle of Man, Israel, Italy, Jamaica, Jan Mayen, Japan, Jarvis Island, Jersey, Johnston Atoll, Jordan, Juan de Nova Island, Kazakhstan, Kenya, Kerguelen Archipelago, Kingman Reef, Kiribati, Kosovo, Kuwait, Kyrgyzstan, Laos, Latvia, Lebanon, Lesotho, Liberia, Libya, Liechtenstein, Lithuania, Luxembourg, Macau, Macedonia, Madagascar, Malawi, Malaysia, Maldives, Mali, Malta, Marshall Islands, Martinique, Mauritania, Mauritius, Mayotte, Mediterranean Sea, Mexico, Micronesia, Midway Islands, Moldova, Monaco, Mongolia, Montenegro, Montserrat, Morocco, Mozambique, Myanmar, Namibia, Nauru, Navassa Island, Nepal, Netherlands, New Caledonia, New Zealand, Nicaragua, Niger, Nigeria, Niue, Norfolk Island, North Korea, North Sea, Northern Mariana Islands, Norway, Oman, Pacific Ocean, Pakistan, Palau, Palmyra Atoll, Panama, Papua New Guinea, Paracel Islands, Paraguay, Peru, Philippines, Pitcairn Islands, Poland, Portugal, Puerto Rico, Qatar, Republic of the Congo, Reunion, Romania, Ross Sea, Russia, Rwanda, Saint Helena, Saint Kitts and Nevis, Saint Lucia, Saint Pierre and Miquelon, Saint Vincent and the Grenadines, Samoa, San Marino, Sao Tome and Principe, Saudi Arabia, Senegal, Serbia, Seychelles, Sierra Leone, Singapore, Sint Maarten, Slovakia, Slovenia, Solomon Islands, Somalia, South Africa, South Georgia and the South Sandwich Islands, South Korea, Southern Ocean, Spain, Spratly Islands, Sri Lanka, Sudan, Suriname, Svalbard, Swaziland, Sweden, Switzerland, Syria, Taiwan, Tajikistan, Tanzania, Tasman Sea, Thailand, Togo, Tokelau, Tonga, Trinidad and Tobago, Tromelin Island, Tunisia, Turkey, Turkmenistan, Turks and Caicos Islands, Tuvalu, USA, Uganda, Ukraine, United Arab Emirates, United Kingdom, Uruguay, Uzbekistan, Vanuatu, Venezuela, Viet Nam, Virgin Islands, Wake Island, Wallis and Futuna, West Bank, Western Sahara, Yemen, Zambia, Zimbabwe, missing: control sample, missing: data agreement established pre-2023, missing: endangered species, missing: human-identifiable, missing: lab stock, missing: sample group, missing: synthetic construct, missing: third party data, not applicable, not collected, not provided, restricted access | +| geographic location (latitude) | optional | The geographical origin of the sample as defined by latitude. the values should be reported in decimal degrees and in wgs84 system (Units: DD) | | +| geographic location (longitude) | optional | The geographical origin of the sample as defined by longitude. the values should be reported in decimal degrees and in wgs84 system (Units: DD) | | +| geographic location (region and locality) | optional | The geographical origin of the sample as defined by the specific region name followed by the locality name. | | +| broad-scale environmental context | optional | Report the major environmental system the sample or specimen came from. the system(s) identified should have a coarse spatial grain, to provide the general environmental context of where the sampling was done (e.g. in the desert or a rainforest). we recommend using subclasses of envo’s biome class: http://purl.obolibrary.org/obo/envo_00000428. envo documentation about how to use the field: https://github.com/environmentontology/envo/wiki/using-envo-with-mixs. | | +| local environmental context | optional | Report the entity or entities which are in the sample or specimen’s local vicinity and which you believe have significant causal influences on your sample or specimen. we recommend using envo terms which are of smaller spatial grain than your entry for "broad-scale environmental context". terms, such as anatomical sites, from other obo library ontologies which interoperate with envo (e.g. uberon) are accepted in this field. envo documentation about how to use the field: https://github.com/environmentontology/envo/wiki/using-envo-with-mixs. | | +| environmental medium | optional | Report the environmental material(s) immediately surrounding the sample or specimen at the time of sampling. we recommend using subclasses of 'environmental material' (http://purl.obolibrary.org/obo/envo_00010483). envo documentation about how to use the field: https://github.com/environmentontology/envo/wiki/using-envo-with-mixs . terms from other obo ontologies are permissible as long as they reference mass/volume nouns (e.g. air, water, blood) and not discrete, countable entities (e.g. a tree, a leaf, a table top). | | +| elevation | optional | The elevation of the sampling site as measured by the vertical distance from mean sea level. (Units: m) | | +| culture isolation date | optional | A culture isolation date is a date-time entity marking the end of a process in which a sample yields a positive result for the target microbial analyte(s) in the form of an isolated colony or colonies. | | +| time course duration | optional | For time-course research studies involving samples of the food commodity, indicate the total duration of the time-course study. (Units: year) | | +| number of samples collected | optional | The number of samples collected during the current sampling event. | | +| surface material | optional | Surface materials at the point of sampling | adobe, carpet, cinder blocks, concrete, glass, hay bales, metal, paint, plastic, stainless steel, stone, stucco, tile, vinyl, wood | +| ventilation rate | optional | Ventilation rate of the system in the sampled premises (Units: m3/min) | | +| indoor surface | optional | Type of indoor surface | cabinet, ceiling, counter top, door, shelving, vent cover, wall, window | +| ventilation type | optional | The intentional movement of air from outside a building to the inside through forced or natural movement of air | forced ventilation, mechanical ventilation, natural ventilation | +| sampling room sterilization method | optional | The method used to sterilize the sampling room. this field accepts terms listed under electromagnetic radiation (http://purl.obolibrary.org/obo/envo_01001026). if the proper descriptor is not listed, please use text to describe the sampling room sterilization method. multiple terms can be separated by pipes. | | +| sampling floor | optional | The floor of the building, where the sampling room is located (Units: °C) | | +| average daily occupancy | optional | Daily average occupancy of room. indicate the number of person(s) daily occupying the sampling room. (Units: °C) | | +| sample surface moisture | optional | Degree of water held on a sampled surface. if present, user can state the degree of water held on surface (intermittent moisture, submerged). if no surface moisture is present indicate not present. (Units: year) | | +| sampling room id or name | optional | Explain how and for how long the soil sample was stored before dna extraction (fresh/frozen/other). (Units: year) | | +| fermentation relative humidity | optional | The relative humidity of the fermented food fermentation process. (Units: g/m3) | | +| room dimensions | optional | The length, width and height of sampling room | | +| amount or size of sample collected | optional | The total amount or size (volume (ml), mass (g) or area (m2) ) of sample collected. (Units: m3) | | +| organism count | optional | Total cell count of any organism (or group of organisms) per gram, volume or area of sample, should include name of organism followed by count. the method that was used for the enumeration (e.g. qpcr, atp, mpn, etc.) should also be provided. (example: total prokaryotes; 3.5e7 cells per ml; qpcr) | | +| sampling time point | optional | Time point at which a sample or observation is made or taken from a biomaterial as measured from some reference point. indicate the timepoint written in iso 8601 format. | | +| growth habit | optional | Characteristic shape, appearance or growth form of a plant species | erect, prostrate, semi-erect, spreading | +| sample storage duration | optional | Duration for which the sample was stored. indicate the duration for which the sample was stored written in iso 8601 format. | | +| sequencing kit | optional | Pre-filled, ready-to-use reagent cartridges. used to produce improved chemistry, cluster density and read length as well as improve quality (q) scores. reagent components are encoded to interact with the sequencing system to validate compatibility with user-defined applications. indicate name of the sequencing kit. | | +| host disease status | optional | List of diseases with which the host has been diagnosed; can include multiple diagnoses. the value of the field depends on host; for humans the terms should be chosen from do (disease ontology) at http://www.disease-ontology.org, other hosts are free text | | +| host age | optional | Age of host at the time of sampling; relevant scale depends on species and study, e.g. could be seconds for amoebae or centuries for trees (Units: years) | | +| host taxid | optional | Ncbi taxon id of the host, e.g. 9606 | | +| host height | optional | The height of subject (Units: mm) | | +| host length | optional | The length of subject (Units: mm) | | +| host total mass | optional | Total mass of the host at collection, the unit depends on host (Units: kg) | | +| host phenotype | optional | Phenotype of host. for phenotypic quality ontology (pato) (v 2013-10-28) terms, please see http://purl.bioontology.org/ontology/pato | | +| host scientific name | optional | Scientific name of the natural (as opposed to laboratory) host to the organism from which sample was obtained. | | +| host subspecific genetic lineage | optional | Information about the genetic distinctness of the host organism below the subspecies level e.g., serovar, serotype, biotype, ecotype, variety, cultivar, or any relevant genetic typing schemes like group i plasmid. subspecies should not be recorded in this term, but in the ncbi taxonomy. supply both the lineage name and the lineage rank separated by a colon, e.g., biovar:abc123. | | +| serovar or serotype | optional | A characterization of a cell or microorganism based on the antigenic properties of the molecules on its surface. indicate the name of a serovar or serotype of interest. this field accepts terms under organism (http://purl.obolibrary.org/obo/ncit_c14250). this field also accepts identification numbers from ncbi under https://www.ncbi.nlm.nih.gov/taxonomy. | | +| humidity | optional | Amount of water vapour in the air, at the time of sampling (Units: g/m3) | | +| conductivity | optional | Electrical conductivity of water (Units: mS/cm) | | +| solar irradiance | optional | The amount of solar energy that arrives at a specific area of a surface during a specific time interval (Units: W/m2) | | +| wind direction | optional | Wind direction is the direction from which a wind originates | | +| wind speed | optional | Speed of wind measured at the time of sampling (Units: m/s) | | +| temperature | optional | Temperature of the sample at time of sampling (Units: ºC) | | +| turbidity | optional | Turbidity measurement (Units: NTU) | | +| pH | optional | Ph measurement | | +| pH method | optional | Reference or method used in determining ph | | +| fermentation vessel | optional | The type of vessel used for containment of the fermentation. | | +| fermentation headspace oxygen | optional | The amount of headspace oxygen in a fermentation vessel. (Units: m2) | | +| frequency of cleaning | optional | The number of times the sample location is cleaned. frequency of cleaning might be on a daily basis, weekly, monthly, quarterly or annually. (Units: year) | Annually, Daily, Monthly, Quarterly, Weekly | +| total organic carbon method | optional | Reference or method used in determining total organic carbon | | +| air particulate matter concentration | optional | Concentration of substances that remain suspended in the air, and comprise mixtures of organic and inorganic substances (pm10 and pm2.5); can report multiple pm's by entering numeric values preceded by name of pm (Units: µg/m3) | | +| total nitrogen content method | optional | Reference or method used in determining the total nitrogen | | +| total nitrogen concentration | optional | Concentration of nitrogen (total). total nitrogen concentration of water samples, calculated by: total nitrogen = total dissolved nitrogen + particulate nitrogen. can also be measured without filtering, reported as nitrogen (Units: µmol/L) | | +| salinity | optional | The total concentration of all dissolved salts in a liquid or solid sample. while salinity can be measured by a complete chemical analysis, this method is difficult and time consuming. more often, it is instead derived from the conductivity measurement. this is known as practical salinity. these derivations compare the specific conductance of the sample to a salinity standard such as seawater. (Units: psu) | | +| total carbon | optional | Total carbon content (Units: µg/L) | | +| total organic carbon | optional | Definition for soil: total organic c content of the soil units of g c/kg soil. definition otherwise: total organic carbon content (Units: g/kg) | | +| total nitrogen content | optional | Total nitrogen content of the sample (Units: µmol/L) | | +| water pH | optional | Ph measurement of the sample, or liquid portion of sample, or aqueous phase of the fluid. | | +| fermentation ph | optional | The ph of the fermented food fermentation process. | | +| bacteria density | optional | Number of bacteria in sample, as defined by bacteria density (http://purl.obolibrary.org/obo/genepio_0000043). (Units: g/m3) | | +| salinity method | optional | Reference or method used in determining salinity | | +| bio_material | optional | Unique identifier that references the biological material from which the sample was obtained and that ideally exists in a curated collection (e.g. stock centres, seed banks, dna banks). the id should have the following structure: name of the institution (institution code) followed by the collection code (if available) and the voucher id (institution_code:collection_code:voucher_id). please note institution codes and collection codes are taken from a controlled vocabulary maintained by the insdc: https://ftp.ncbi.nih.gov/pub/taxonomy/biocollections/ | | +| source material identifiers | optional | A unique identifier assigned to a material sample (as defined by http://rs.tdwg.org/dwc/terms/materialsampleid, and as opposed to a particular digital record of a material sample) used for extracting nucleic acids, and subsequent sequencing. the identifier can refer either to the original material collected or to any derived sub-samples. the insdc qualifiers /specimen_voucher, /bio_material, or /culture_collection may or may not share the same value as the source_mat_id field. for instance, the /specimen_voucher qualifier and source_mat_id may both contain 'uam:herps:14' , referring to both the specimen voucher and sampled tissue with the same identifier. however, the /culture_collection qualifier may refer to a value from an initial culture (e.g. atcc:11775) while source_mat_id would refer to an identifier from some derived culture from which the nucleic acids were extracted (e.g. xatc123 or ark:/2154/r2). | | +| sample source material category | optional | This is the scientific role or category that the subject organism or material has with respect to an investigation. this field accepts terms listed under specimen source material category (http://purl.obolibrary.org/obo/genepio_0001237 or http://purl.obolibrary.org/obo/obi_0100051). | | +| history/previous land use | optional | Previous land use and dates | | +| history/crop rotation | optional | Whether or not crop is rotated, and if yes, rotation schedule | | +| history/tillage | optional | Note method(s) used for tilling | chisel, cutting disc, disc plough, drill, mouldboard, ridge till, strip tillage, tined, zonal tillage | +| mean seasonal humidity | optional | Average humidity of the region throughout the growing season. (Units: g/m3) | | +| mean seasonal temperature | optional | Mean seasonal temperature (Units: °C) | | +| mean seasonal precipitation | optional | The average of all seasonal precipitation values known, or an estimated equivalent value derived by such methods as regional indexes or isohyetal maps. (Units: mm) | | +| extreme weather date | optional | Date of unusual weather events that may have affected microbial populations. multiple terms can be separated by pipes, listed in reverse chronological order. (Units: J/°C) | | +| extreme weather event | optional | Unusual weather events that may have affected microbial populations. multiple terms can be separated by pipes, listed in reverse chronological order. (Units: m) | | +| season | optional | The season when sampling occurred. any of the four periods into which the year is divided by the equinoxes and solstices. this field accepts terms listed under season (http://purl.obolibrary.org/obo/ncit_c94729). | | +| host genotype | optional | Observed genotype | | +| host specificity or range | optional | The range and diversity of host species that an organism is capable of infecting, defined by ncbi taxonomy identifier. | | +| host dry mass | optional | Measurement of dry mass (Units: mg) | | +| host prediction approach | optional | Tool or approach used for host prediction | CRISPR spacer match, co-occurrence, combination, host sequence similarity, kmer similarity, other, provirus | +| host prediction estimated accuracy | optional | For each tool or approach used for host prediction, estimated false discovery rates should be included, either computed de novo or from the literature | | +| spike-in microbial strain | optional | Taxonomic information about the spike-in organism(s) at the strain level. this field accepts terms under organism (http://purl.obolibrary.org/obo/ncit_c14250). this field also accepts identification numbers from ncbi under https://www.ncbi.nlm.nih.gov/taxonomy. multiple terms can be separated by pipes. | | +| fermentation chemical additives | optional | Any chemicals that are added to the fermentation process to achieve the desired final product. (Units: J/°C) | | +| fermentation chemical additives percentage | optional | The amount of chemical added to the fermentation process. (Units: %) | | +| study treatment | optional | A process in which the act is intended to modify or alter some other material entity. from the study design, each treatment is comprised of one level of one or multiple factors. this field accepts terms listed under treatment (http://purl.obolibrary.org/obo/mco_0000866). if the proper descriptor is not listed please use text to describe the study treatment. multiple terms can be separated by one or more pipes. (Units: %) | | +| spike-in organism | optional | Taxonomic information about the spike-in organism(s). this field accepts terms under organism (http://purl.obolibrary.org/obo/ncit_c14250). this field also accepts identification numbers from ncbi under https://www.ncbi.nlm.nih.gov/taxonomy. multiple terms can be separated by pipes. (Units: g/m3) | | +| spike-in organism count | optional | Total cell count of any organism (or group of organisms) per gram, volume or area of sample, should include name of organism followed by count. the method that was used for the enumeration (e.g. qpcr, atp, mpn, etc.) should also be provided (example: total prokaryotes; 3.5e7 cells per ml; qpcr). (Units: mm) | | +| fermentation temperature | optional | The temperature of the fermented food fermentation process. (Units: °C) | | +| spike-in with heavy metals | optional | Heavy metals used in research study to assess effects of exposure on microbiome of a specific site. please list heavy metals and concentration used for spike-in. (Units: year) | | +| microbial starter inoculation | optional | The amount of starter culture used to inoculate a new batch. (Units: m3/day) | | +| microbial starter source | optional | The source from which the microbial starter culture was sourced. if commercially supplied, list supplier. (Units: year) | | +| microbial starter preparation | optional | Information about the protocol or method used to prepare the starter inoculum. (Units: year) | | +| spike-in bacterial serovar or serotype | optional | Taxonomic information about the spike-in organism(s) at the serovar or serotype level. this field accepts terms under organism (http://purl.obolibrary.org/obo/ncit_c14250). this field also accepts identification numbers from ncbi under https://www.ncbi.nlm.nih.gov/taxonomy. multiple terms can be separated by pipes. (Units: year) | | +| antimicrobial phenotype of spike-in bacteria | optional | Qualitative description of a microbial response to antimicrobial agents. bacteria may be susceptible or resistant to a broad range of antibiotic drugs or drug classes, with several intermediate states or phases. this field accepts terms under antimicrobial phenotype (http://purl.obolibrary.org/obo/aro_3004299). | | +| fermentation time | optional | The time duration of the fermented food fermentation process. (Units: year) | | +| microbial starter organism count | optional | Total cell count of starter culture per gram, volume or area of sample and the method that was used for the enumeration (e.g. qpcr, atp, mpn, etc.) should also be provided. (example : total prokaryotes; 3.5e7 cells per ml; qpcr). (Units: m2) | | +| spike-in with antibiotics | optional | Antimicrobials used in research study to assess effects of exposure on microbiome of a specific site. please list antimicrobial, common name and/or class and concentration used for spike-in. (Units: m2) | | +| study incubation temperature | optional | Sample incubation temperature if unpublished or unvalidated method is used. (Units: °C) | | +| perturbation | optional | Type of perturbation, e.g. chemical administration, physical disturbance, etc., coupled with time that perturbation occurred; can include multiple perturbation types | | +| study incubation duration | optional | Sample incubation duration if unpublished or unvalidated method is used. indicate the timepoint written in iso 8601 format. (Units: year) | | +| biocide | optional | Substance intended for preventing, neutralizing, destroying, repelling, or mitigating the effects of any pest or microorganism; that inhibits the growth, reproduction, and activity of organisms, including fungal cells; decreases the number of fungi or pests present; deters microbial growth and degradation of other ingredients in the formulation. indicate the biocide used on the location where the sample was taken. multiple terms can be separated by pipes. (Units: °C) | | +| negative control type | optional | The substance or equipment used as a negative control in an investigation | | +| positive control type | optional | The substance, mixture, product, or apparatus used to verify that a process which is part of an investigation delivers a true positive. | | +| experimental factor | optional | Experimental factors are essentially the variable aspects of an experiment design which can be used to describe an experiment, or set of experiments, in an increasingly detailed manner. this field accepts ontology terms from experimental factor ontology (efo) and/or ontology for biomedical investigations (obi). for a browser of efo (v 2.95) terms, please see http://purl.bioontology.org/ontology/efo; for a browser of obi (v 2018-02-12) terms please see http://purl.bioontology.org/ontology/obi. e.g. time series design [efo:efo_0001779] | | +| encoded traits | optional | Should include key traits like antibiotic resistance or xenobiotic degradation phenotypes for plasmids, converting genes for phage | | +| genetic modification | optional | A genetic modification of the genome of an organism which may occur naturally by spontaneous mutation, or be introduced by some experimental means. examples of genetic modification include specification of a transgene or the gene knocked-out or details of transient transfection. | | +| subspecific genetic lineage | optional | Information about the genetic distinctness of the sequenced organism below the subspecies level, e.g., serovar, serotype, biotype, ecotype, or any relevant genetic typing schemes like group i plasmid. subspecies should not be recorded in this term, but in the ncbi taxonomy. supply both the lineage name and the lineage rank separated by a colon, e.g., biovar:abc123. | | +| ancestral data | optional | Information about either pedigree or other description of ancestral information (e.g. parental variety in case of mutant or selection), e.g. a/3*b (meaning [(a x b) x b] x b) | | +| taxonomic classification | optional | Method used for taxonomic classification, along with reference database used, classification rank, and thresholds used to classify new genomes. expected values are: classification method, database name, and other parameters e.g. vcontact vcontact2 (references from ncbi refseq v83, genus rank classification, default parameters) | | +| plant growth medium | optional | Specification of the media for growing the plants or tissue cultured samples, e.g. soil, aeroponic, hydroponic, in vitro solid culture medium, in vitro liquid culture medium. recommended value is a specific value from eo:plant growth medium (follow this link for terms http://purl.obolibrary.org/obo/eo_0007147). | | +| rooting conditions | optional | Relevant rooting conditions, such as field plot size, sowing density, container dimensions, number of plants per container | | +| rooting medium macronutrients | optional | Measurement of the culture rooting medium macronutrients (n,p, k, ca, mg, s); e.g. kh2po4 (170mg/l) | | +| rooting medium micronutrients | optional | Measurement of the culture rooting medium micronutrients (fe, mn, zn, b, cu, mo); e.g. h3bo3 (6.2mg/l) | | +| rooting medium carbon | optional | Source of organic carbon in the culture rooting medium; e.g. sucrose | | +| rooting medium pH | optional | Ph measurement of the culture rooting medium; e.g. 5.5 | | +| microbiological culture medium | optional | A culture medium used to select for, grow, and maintain prokaryotic microorganisms. can be in either liquid (broth) or solidified (e.g. with agar) forms. this field accepts terms listed under microbiological culture medium (http://purl.obolibrary.org/obo/micro_0000067). if the proper descriptor is not listed please use text to describe the culture medium. (Units: Pa) | | +| spike-in growth medium | optional | A liquid or gel containing nutrients, salts, and other factors formulated to support the growth of microorganisms, cells, or plants (national cancer institute thesaurus). a growth medium is a culture medium which has the disposition to encourage growth of particular bacteria to the exclusion of others in the same growth environment. in this case, list the culture medium used to propagate the spike-in bacteria during preparation of spike-in inoculum. this field accepts terms listed under microbiological culture medium (http://purl.obolibrary.org/obo/micro_0000067). if the proper descriptor is not listed please use text to describe the spike in growth media. (Units: W/m2) | | +| fermentation medium | optional | The growth medium used for the fermented food fermentation process, which supplies the required nutrients. usually this includes a carbon and nitrogen source, water, micronutrients and chemical additives. (Units: m) | | +| growth medium | optional | A liquid or gel containing nutrients, salts, and other factors formulated to support the growth of microorganisms, cells, or plants (national cancer institute thesaurus). the name of the medium used to grow the microorganism. (Units: year) | | +| isolation and growth condition | optional | Publication reference in the form of pubmed id (pmid), digital object identifier (doi) or url for isolation and growth condition specifications of the organism/material. mandatory for migs and mimarks specimen. | | +| annotation source | optional | For cases where annotation was provided by a community jamboree or model organism database rather than by a specific submitter | | +| reference for biomaterial | optional | Primary publication if isolated before genome publication; otherwise, primary genome report. mandatory for migs of bacteria and archaea. | | +| sequencing location | optional | The location the sequencing run was performed. indicate the name of the lab or core facility where samples were sequenced. | | +| enrichment protocol | optional | The microbiological workflow or protocol followed to test for the presence or enumeration of the target microbial analyte(s). please provide a pubmed or doi reference for published protocols. | | +| library preparation kit | optional | Packaged kits (containing adapters, indexes, enzymes, buffers etc.), tailored for specific sequencing workflows, which allow the simplified preparation of sequencing-ready libraries for small genomes, amplicons, and plasmids. (Units: %) | | +| nucleic acid extraction kit | optional | The name of the extraction kit used to recover the nucleic acid fraction of an input material is performed. (Units: ppm) | | +| sample pooling | optional | Physical combination of several instances of like material, e.g. rna extracted from samples or dishes of cell cultures into one big aliquot of cells. please provide a short description of the samples that were pooled. | | +| lot number | optional | A distinctive alpha-numeric identification code assigned by the manufacturer or distributor to a specific quantity of manufactured material or product within a batch. synonym: batch number. the submitter should provide lot number of the item followed by the item name for which the lot number was provided. (Units: %) | | +| single cell or viral particle lysis approach | optional | Method used to free dna from interior of the cell(s) or particle(s) | chemical, combination, enzymatic, physical | +| single cell or viral particle lysis kit protocol | optional | Name of the kit or standard protocol used for cell(s) or particle(s) lysis | | +| pooled DNA extract total | optional | Indicate whether multiple dna extractions were mixed. if the answer yes, the number of extracts that were pooled should be given. [ena version of mixs term: pooling of dna extracts (if done). ] | | +| sample material processing | optional | A brief description of any processing applied to the sample during or after retrieving the sample from environment, or a link to the relevant protocol(s) performed. | | +| sample volume or weight for DNA extraction | optional | Volume (ml) or mass (g) of total collected sample processed for dna extraction. note: total sample collected should be entered under the term 'sample size'. (Units: ng) | | +| nucleic acid extraction | optional | A link to a literature reference, electronic resource or a standard operating procedure (sop), that describes the material separation to recover the nucleic acid fraction from a sample | | +| nucleic acid amplification | optional | A link to a literature reference, electronic resource or a standard operating procedure (sop), that describes the enzymatic amplification (pcr, tma, nasba) of specific nucleic acids | | +| library size | optional | Total number of clones in the library prepared for the project | | +| library reads sequenced | optional | Total number of clones sequenced from the library | | +| library vector | optional | Cloning vector type(s) used in construction of libraries | | +| library screening strategy | optional | Specific enrichment or screening methods applied before and/or after creating clone libraries in order to select a specific group of sequences | | +| pcr conditions | optional | Description of reaction conditions and components for pcr in the form of 'initial denaturation:94degc_1.5min; annealing=...' | | +| assembly software | optional | Tool(s) used for assembly, including version number and parameters in the format {software};{version};{parameters} e.g. metaspades;3.11.0;kmer set 21,33,55,77,99,121, default parameters otherwise | | +| pcr primers | optional | Pcr primers that were used to amplify the sequence of the targeted gene, locus or subfragment. this field should contain all the primers used for a single pcr reaction if multiple forward or reverse primers are present in a single pcr reaction. the primer sequence should be reported in uppercase letters | | +| adapters | optional | Adapters provide priming sequences for both amplification and sequencing of the sample-library fragments. both adapters should be reported; in uppercase letters | | +| food animal antimicrobial | optional | The name(s) (generic or brand) of the antimicrobial(s) given to the food animal within the last 30 days. | | +| food shipping transportation vehicle | optional | A descriptor for the mobile machine which is used to transport food commodities along the food distribution system. this field accepts terms listed under vehicle (http://purl.obolibrary.org/obo/envo_01000604). if the proper descrptor is not listed please use text to describe the mode of travel. multiple terms can be separated by one or more pipes. | | +| water source shared | optional | Other users sharing access to the same water source. multiple terms can be separated by one or more pipes. | | +| food source | optional | Type of plant or animal from which the food product or its major ingredient is derived or a chemical food source [fda cfsan 1995]. | | +| food shipping transportation method | optional | A descriptor for the method of movement of food commodity along the food distribution system. this field accepts terms listed under travel mode (http://purl.obolibrary.org/obo/genepio_0001064). if the proper descrptor is not listed please use text to describe the mode of travel. multiple terms can be separated by one or more pipes. | | +| material of contact prior to food packaging | optional | The material the food contacted (e.g., was processed in) prior to packaging. this field accepts terms listed under material of contact prior to food packaging (http://purl.obolibrary.org/obo/foodon_03530077). if the proper descriptor is not listed please use text to describe the material of contact prior to food packaging. | | +| food product name legal status | optional | A datum indicating that use of a food product name is regulated in some legal jurisdiction. this field accepts terms listed under food product name legal status (http://purl.obolibrary.org/obo/foodon_03530087). | | +| food quality date | optional | The date recommended for the use of the product while at peak quality, this date is not a reflection of safety unless used on infant formula this date is not a reflection of safety and is typically labeled on a food product as "best if used by," best by," "use by," or "freeze by." | | +| food cleaning process | optional | The process of cleaning food to separate other environmental materials from the food source. multiple terms can be separated by pipes. (Units: m) | | +| hygienic food production area | optional | The subdivision of areas within a food production facility according to hygienic requirements. this field accepts terms listed under hygienic food production area (http://purl.obolibrary.org/obo/envo). please add a term that most accurately indicates the hygienic area your sample was taken from according to the definitions provided. (Units: kg s−3) | | +| food contact surface | optional | The specific container or coating materials in direct contact with the food. multiple values can be assigned. this field accepts terms listed under food contact surface (http://purl.obolibrary.org/obo/foodon_03500010). (Units: J/°C) | | +| food cooking process | optional | The transformation of raw food by the application of heat. this field accepts terms listed under food cooking (http://purl.obolibrary.org/obo/foodon_03450002). (Units: %) | | +| food product by quality | optional | Descriptors for describing food visually or via other senses, which is useful for tasks like food inspection where little prior knowledge of how the food came to be is available. some terms like "food (frozen)" are both a quality descriptor and the output of a process. this field accepts terms listed under food product by quality (http://purl.obolibrary.org/obo/foodon_00002454). (Units: year) | | +| food animal antimicrobial route of administration | optional | The route by which the antimicrobial is administered into the body of the food animal. (Units: m2) | | +| food allergen labeling | optional | A label indication that the product contains a recognized allergen. this field accepts terms listed under dietary claim or use (http://purl.obolibrary.org/obo/foodon_03510213). (Units: W/m2) | | +| food product type | optional | A food product type is a class of food products that is differentiated by its food composition (e.g., single- or multi-ingredient), processing and/or consumption characteristics. this does not include brand name products but it may include generic food dish categories. this field accepts terms under food product type (http://purl.obolibrary.org/obo/foodon:03400361). for terms related to food product for an animal, consult food product for animal (http://purl.obolibrary.org/obo/foodon_03309997). if the proper descriptor is not listed please use text to describe the food type. multiple terms can be separated by one or more pipes. | | +| food animal source sex category | optional | The sex and reproductive status of the food animal. (Units: °C) | | +| animal intrusion near sample source | optional | Identification of animals intruding on the sample or sample site including invertebrates (such as pests or pollinators) and vertebrates (such as wildlife or domesticated animals). this field accepts terms under organism (http://purl.obolibrary.org/obo/ncit_c14250). this field also accepts identification numbers from ncbi under https://www.ncbi.nlm.nih.gov/taxonomy. multiple terms can be separated by pipes. (Units: °C) | | +| food packing medium integrity | optional | A term label and term id to describe the state of the packing material and text to explain the exact condition. this field accepts terms listed under food packing medium integrity (http://purl.obolibrary.org/obo/foodon_03530218). (Units: °C) | | +| microbial starter | optional | Any type of microorganisms used in food production. this field accepts terms listed under live organisms for food production (http://purl.obolibrary.org/obo/foodon_0344453). (Units: °C) | | +| food treatment process | optional | Used to specifically characterize a food product based on the treatment or processes applied to the product or any indexed ingredient. the processes include adding, substituting or removing components or modifying the food or component, e.g., through fermentation. multiple values can be assigned. this fields accepts terms listed under food treatment process (http://purl.obolibrary.org/obo/foodon_03460111). | | +| food preservation process | optional | The methods contributing to the prevention or retardation of microbial, enzymatic or oxidative spoilage and thus to the extension of shelf life. this field accepts terms listed under food preservation process (http://purl.obolibrary.org/obo/foodon_03470107). (Units: J/°C) | | +| microbial starter ncbi taxonomy id | optional | Please include genus species and strain id, if known of microorganisms used in food production. for complex communities, pipes can be used to separate two or more microbes. | | +| interagency food safety analytics collaboration (ifsac) category | optional | The ifsac food categorization scheme has five distinct levels to which foods can be assigned, depending upon the type of food. first, foods are assigned to one of four food groups (aquatic animals, land animals, plants, and other). food groups include increasingly specific food categories; dairy, eggs, meat and poultry, and game are in the land animal food group, and the category meat and poultry is further subdivided into more specific categories of meat (beef, pork, other meat) and poultry (chicken, turkey, other poultry). finally, foods are differentiated by differences in food processing (such as pasteurized fluid dairy products, unpasteurized fluid dairy products, pasteurized solid and semi-solid dairy products, and unpasteurized solid and semi-solid dairy products. an ifsac food category chart is available from https://www.cdc.gov/foodsafety/ifsac/projects/food-categorization-scheme.html pmid: 28926300. | | +| food animal body condition | optional | Body condition scoring is a production management tool used to evaluate overall health and nutritional needs of a food animal. because there are different scoring systems, this field is restricted to three categories. | | +| food product synonym | optional | Other names by which the food product is known by (e.g., regional or non-english names). | | +| food ingredient | optional | In this field, please list individual ingredients for multi-component food [foodon:00002501] and simple foods that is not captured in food_type. please use terms that are present in foodon. multiple terms can be separated by one or more pipes |, but please consider limiting this list to the top 5 ingredients listed in order as on the food label. see also, https://www.fda.gov/food/food-ingredients-packaging/overview-food-ingredients-additives-colors. (Units: year) | | +| food stored by consumer (storage duration) | optional | The storage duration of the food commodity by the consumer, prior to onset of illness or sample collection. indicate the timepoint written in iso 8601 format. (Units: year) | | +| food animal antimicrobial duration | optional | The duration of time (days) that the antimicrobial was administered to the food animal. (Units: year) | | +| part of plant or animal | optional | The anatomical part of the organism being involved in food production or consumption; e.g., a carrot is the root of the plant (root vegetable). this field accepts terms listed under part of plant or animal (http://purl.obolibrary.org/obo/foodon_03420116). (Units: year) | | +| hazard analysis critical control points (haccp) guide food safety term | optional | Hazard analysis critical control points (haccp) food safety terms; this field accepts terms listed under haccp guide food safety term (http://purl.obolibrary.org/obo/foodon_03530221). (Units: year) | | +| dietary claim or use | optional | These descriptors are used either for foods intended for special dietary use as defined in 21 cfr 105 or for foods that have special characteristics indicated in the name or labeling. this field accepts terms listed under dietary claim or use (http://purl.obolibrary.org/obo/foodon_03510023). multiple terms can be separated by one or more pipes, but please consider limiting this list to the most prominent dietary claim or use. | | +| degree of plant part maturity | optional | A description of the stage of development of a plant or plant part based on maturity or ripeness. this field accepts terms listed under degree of plant maturity (http://purl.obolibrary.org/obo/foodon_03530050). (Units: year) | | +| food production environmental monitoring zone | optional | An environmental monitoring zone is a formal designation as part of an environmental monitoring program, in which areas of a food production facility are categorized, commonly as zones 1-4, based on likelihood or risk of foodborne pathogen contamination. this field accepts terms listed under food production environmental monitoring zone (http://purl.obolibrary.org/obo/envo). please add a term to indicate the environmental monitoring zone the sample was taken from. | | +| plant reproductive part | optional | Plant reproductive part used in the field during planting to start the crop. | | +| food traceability list category | optional | The fda is proposing to establish additional traceability recordkeeping requirements (beyond what is already required in existing regulations) for persons who manufacture, process, pack, or hold foods the agency has designated for inclusion on the food traceability list. the food traceability list (ftl) identifies the foods for which the additional traceability records described in the proposed rule would be required. the term “food traceability list” (ftl) refers not only to the foods specifically listed (https://www.fda.gov/media/142303/download), but also to any foods that contain listed foods as ingredients. (Units: mm) | | +| food animal antimicrobial frequency | optional | The frequency per day that the antimicrobial was administered to the food animal. (Units: m2) | | +| intended consumer | optional | Food consumer type, human or animal, for which the food product is produced and marketed. this field accepts terms listed under food consumer group (http://purl.obolibrary.org/obo/foodon_03510136) or ncbi taxid. (Units: m2) | | +| quantity purchased | optional | The quantity of food purchased by consumer. | | +| food container or wrapping | optional | Type of container or wrapping defined by the main container material, the container form, and the material of the liner lids or ends. also type of container or wrapping by form; prefer description by material first, then by form. this field accepts terms listed under food container or wrapping (http://purl.obolibrary.org/obo/foodon_03490100). (Units: °C) | | +| food additive | optional | A substance or substances added to food to maintain or improve safety and freshness, to improve or maintain nutritional value, or improve taste, texture and appearance. this field accepts terms listed under food additive (http://purl.obolibrary.org/obo/foodon_03412972). multiple terms can be separated by one or more pipes, but please consider limiting this list to the top 5 ingredients listed in order as on the food label. see also, https://www.fda.gov/food/food-ingredients-packaging/overview-food-ingredients-additives-colors. (Units: g/m3) | | +| food source age | optional | The age of the food source host organism. depending on the type of host organism, age may be more appropriate to report in days, weeks, or years. (Units: year) | | +| food animal antimicrobial intended use | optional | The prescribed intended use of or the condition treated by the antimicrobial given to the food animal by any route of administration. (Units: year) | | +| food packing medium | optional | The medium in which the food is packed for preservation and handling or the medium surrounding homemade foods, e.g., peaches cooked in sugar syrup. the packing medium may provide a controlled environment for the food. it may also serve to improve palatability and consumer appeal. this includes edible packing media (e.g. fruit juice), gas other than air (e.g. carbon dioxide), vacuum packed, or packed with aerosol propellant. this field accepts terms under food packing medium (http://purl.obolibrary.org/obo/foodon_03480020). multiple terms may apply and can be separated by pipes. (Units: m2) | | +| specific intended consumer | optional | Food consumer type, human or animal, for which the food product is produced and marketed. this field accepts terms listed under food consumer group (http://purl.obolibrary.org/obo/foodon_03510136). (Units: m2) | | +| purchase date | optional | The date a food product was purchased by consumer. (Units: m2) | | +| food stored by consumer (storage temperature) | optional | Temperature at which food commodity was stored by the consumer, prior to onset of illness or sample collection. (Units: °C) | | +| food package capacity | optional | The maximum number of product units within a package (Units: year) | | +| food distribution point geographic location (city) | optional | A reference to a place on the earth, by its name or by its geographical location that refers to a distribution point along the food chain. this field accepts terms listed under geographic location (http://purl.obolibrary.org/obo/gaz_00000448). reference: adam diamond, james barham. moving food along the value chain: innovations in regional food distribution. u.s. dept. of agriculture, agricultural marketing service. washington, dc. march 2012. http://dx.doi.org/10.9752/ms045.03-2012. | | +| food product origin geographic location | optional | A reference to a place on the earth, by its name or by its geographical location that describes the origin of the food commodity, either in terms of its cultivation or production. this field accepts terms listed under geographic location (http://purl.obolibrary.org/obo/gaz_00000448). (Units: m) | | +| food distribution point geographic location | optional | A reference to a place on the earth, by its name or by its geographical location that refers to a distribution point along the food chain. this field accepts terms listed under geographic location (http://purl.obolibrary.org/obo/gaz_00000448). reference: adam diamond, james barham. moving food along the value chain: innovations in regional food distribution. u.s. dept. of agriculture, agricultural marketing service. washington, dc. march 2012. http://dx.doi.org/10.9752/ms045.03-2012. (Units: m) | | +| production labeling claims | optional | Labeling claims containing descriptors such as wild caught, free-range, organic, free-range, industrial, hormone-free, antibiotic free, cage free. can include more than one term, separated by ";" | | +| relative location of sample | optional | Location of sampled soil to other parts of the farm e.g. under crop plant, near irrigation ditch, from the dirt road. | | +| depth | optional | The vertical distance below local surface, e.g. for sediment or soil samples depth is measured from sediment or soil surface, respectively. depth can be reported as an interval for subsurface samples. (Units: mm) | | +| environment adjacent to site | optional | Description of the environmental system or features that are adjacent to the sampling site. this field accepts terms under ecosystem (http://purl.obolibrary.org/obo/envo_01001110) and human construction (http://purl.obolibrary.org/obo/envo_00000070). multiple terms can be separated by pipes. | | +| fertilizer administration | optional | Type of fertilizer or amendment added to the soil or water for the purpose of improving substrate health and quality for plant growth. this field accepts terms listed under agronomic fertilizer (http://purl.obolibrary.org/obo/agro_00002062). multiple terms may apply and can be separated by pipes, listing in reverse chronological order. n.b. old ena definition as "fertilizer regimen": information about treatment involving the use of fertilizers; should include the name fertilizer, amount administered, treatment duration, interval and total experimental duration; can include multiple fertilizer regimens | | +| biotic regimen | optional | Information about treatment involving use of biotic factors, such as bacteria, viruses or fungi | | +| mechanical damage | optional | Information about any mechanical damage exerted on the plant; can include multiple damages and sites | | +| chemical administration | optional | List of chemical compounds administered to the host or site where sampling occurred, and when (e.g. antibiotics, n fertilizer, air filter); can include multiple compounds. for chemical entities of biological interest ontology (chebi) (v111), please see http://purl.bioontology.org/ontology/chebi | | + diff --git a/templates/ERC000056/experiment.tsv b/templates/ERC000056/experiment.tsv new file mode 100644 index 0000000..55beb83 --- /dev/null +++ b/templates/ERC000056/experiment.tsv @@ -0,0 +1 @@ +"alias" "title" "study_alias" "sample_alias" "design_description" "library_name" "library_strategy" "library_source" "library_selection" "library_layout" "insert_size" "library_construction_protocol" "platform" "instrument_model" diff --git a/templates/ERC000056/metadata_template_ERC000056.xlsx b/templates/ERC000056/metadata_template_ERC000056.xlsx new file mode 100644 index 0000000..0daa14e Binary files /dev/null and b/templates/ERC000056/metadata_template_ERC000056.xlsx differ diff --git a/templates/ERC000056/run.tsv b/templates/ERC000056/run.tsv new file mode 100644 index 0000000..e752173 --- /dev/null +++ b/templates/ERC000056/run.tsv @@ -0,0 +1 @@ +"alias" "experiment_alias" "file_name" "file_format" diff --git a/templates/ERC000056/sample.tsv b/templates/ERC000056/sample.tsv new file mode 100644 index 0000000..a44dac6 --- /dev/null +++ b/templates/ERC000056/sample.tsv @@ -0,0 +1 @@ +"alias" "title" "taxon_id" "sample_description" "culture result" "culture result organism" "culture target microbial analyte" "biological sample replicate" "technical sample replicate" "purpose of sampling" "trophic level" "observed biotic relationship" "known pathogenicity" "relationship to oxygen" "propagation" "sample transportation temperature" "sample transport container" "sample transport duration" "sample collection device" "sample collection method" "sample storage temperature" "sample storage device" "sample storage location" "size-fraction lower threshold" "size-fraction upper threshold" "soil type" "soil type method" "soil texture method" "soil pH" "soil cover" "soil texture classification" "soil sediment porosity" "soil conductivity" "facility type" "collection site geographic feature" "area sampled size" "sample name" "study design" "project name" "farm equipment sanitization" "equipment shared with other farms" "farm equipment used" "farm equipment sanitization frequency" "farm watering water source" "food production system characteristics" "animal water delivery method" "plant water delivery method" "food harvesting process" "food animal source diet" "food production characteristics" "food animal group size" "fertilizer administration date" "animal feeding equipment" "crop yield" "water delivery frequency" "animal housing system" "environmental feature adjacent water source" "ploidy" "number of replicons" "extrachromosomal elements" "estimated size" "target gene" "target subfragment" "multiplex identifiers" "sequence quality check" "chimera check software" "relevant electronic resources" "relevant standard operating procedures" "16s recovered" "16S recovery software" "completeness score" "completeness software" "completeness approach" "assembly quality" "assembly name" "collection date" "altitude" "geographic location (country and/or sea)" "geographic location (latitude)" "geographic location (longitude)" "geographic location (region and locality)" "broad-scale environmental context" "local environmental context" "environmental medium" "elevation" "culture isolation date" "time course duration" "number of samples collected" "surface material" "ventilation rate" "indoor surface" "ventilation type" "sampling room sterilization method" "sampling floor" "average daily occupancy" "sample surface moisture" "sampling room id or name" "fermentation relative humidity" "room dimensions" "amount or size of sample collected" "organism count" "sampling time point" "growth habit" "sample storage duration" "sequencing kit" "host disease status" "host age" "host taxid" "host height" "host length" "host total mass" "host phenotype" "host scientific name" "host subspecific genetic lineage" "serovar or serotype" "humidity" "conductivity" "solar irradiance" "wind direction" "wind speed" "temperature" "turbidity" "pH" "pH method" "fermentation vessel" "fermentation headspace oxygen" "frequency of cleaning" "total organic carbon method" "air particulate matter concentration" "total nitrogen content method" "total nitrogen concentration" "salinity" "total carbon" "total organic carbon" "total nitrogen content" "water pH" "fermentation ph" "bacteria density" "salinity method" "bio_material" "source material identifiers" "sample source material category" "history/previous land use" "history/crop rotation" "history/tillage" "mean seasonal humidity" "mean seasonal temperature" "mean seasonal precipitation" "extreme weather date" "extreme weather event" "season" "host genotype" "host specificity or range" "host dry mass" "host prediction approach" "host prediction estimated accuracy" "spike-in microbial strain" "fermentation chemical additives" "fermentation chemical additives percentage" "study treatment" "spike-in organism" "spike-in organism count" "fermentation temperature" "spike-in with heavy metals" "microbial starter inoculation" "microbial starter source" "microbial starter preparation" "spike-in bacterial serovar or serotype" "antimicrobial phenotype of spike-in bacteria" "fermentation time" "microbial starter organism count" "spike-in with antibiotics" "study incubation temperature" "perturbation" "study incubation duration" "biocide" "negative control type" "positive control type" "experimental factor" "encoded traits" "genetic modification" "subspecific genetic lineage" "ancestral data" "taxonomic classification" "plant growth medium" "rooting conditions" "rooting medium macronutrients" "rooting medium micronutrients" "rooting medium carbon" "rooting medium pH" "microbiological culture medium" "spike-in growth medium" "fermentation medium" "growth medium" "isolation and growth condition" "annotation source" "reference for biomaterial" "sequencing location" "enrichment protocol" "library preparation kit" "nucleic acid extraction kit" "sample pooling" "lot number" "single cell or viral particle lysis approach" "single cell or viral particle lysis kit protocol" "pooled DNA extract total" "sample material processing" "sample volume or weight for DNA extraction" "nucleic acid extraction" "nucleic acid amplification" "library size" "library reads sequenced" "library vector" "library screening strategy" "pcr conditions" "assembly software" "pcr primers" "adapters" "food animal antimicrobial" "food shipping transportation vehicle" "water source shared" "food source" "food shipping transportation method" "material of contact prior to food packaging" "food product name legal status" "food quality date" "food cleaning process" "hygienic food production area" "food contact surface" "food cooking process" "food product by quality" "food animal antimicrobial route of administration" "food allergen labeling" "food product type" "food animal source sex category" "animal intrusion near sample source" "food packing medium integrity" "microbial starter" "food treatment process" "food preservation process" "microbial starter ncbi taxonomy id" "interagency food safety analytics collaboration (ifsac) category" "food animal body condition" "food product synonym" "food ingredient" "food stored by consumer (storage duration)" "food animal antimicrobial duration" "part of plant or animal" "hazard analysis critical control points (haccp) guide food safety term" "dietary claim or use" "degree of plant part maturity" "food production environmental monitoring zone" "plant reproductive part" "food traceability list category" "food animal antimicrobial frequency" "intended consumer" "quantity purchased" "food container or wrapping" "food additive" "food source age" "food animal antimicrobial intended use" "food packing medium" "specific intended consumer" "purchase date" "food stored by consumer (storage temperature)" "food package capacity" "food distribution point geographic location (city)" "food product origin geographic location" "food distribution point geographic location" "production labeling claims" "relative location of sample" "depth" "environment adjacent to site" "fertilizer administration" "biotic regimen" "mechanical damage" "chemical administration" diff --git a/templates/ERC000056/study.tsv b/templates/ERC000056/study.tsv new file mode 100644 index 0000000..fd9fd79 --- /dev/null +++ b/templates/ERC000056/study.tsv @@ -0,0 +1 @@ +"alias" "title" "study_type" "new_study_type" "study_abstract" diff --git a/templates/ERC000057/ERC000057.json b/templates/ERC000057/ERC000057.json new file mode 100644 index 0000000..314176c --- /dev/null +++ b/templates/ERC000057/ERC000057.json @@ -0,0 +1,1867 @@ +{ + "study": { + "description": "A Study is a container for a sequencing investigation that may comprise multiple experiments. The Study has an overall goal, but is otherwise minimally defined in the SRA. A Study is composed of a descriptor, zero or more experiments, and zero or more analyses. The submitter may decorate the Study with web links and properties.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for a study. This is used to link experiments to the study.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "title", + "cardinality": "mandatory", + "description": "Title of the study as would be used in a publication.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "study_type", + "cardinality": "mandatory", + "description": "The STUDY_TYPE presents a controlled vocabulary for expressing the overall purpose of the study.", + "units": "", + "regex": "", + "cv": [ + "Whole Genome Sequencing", + "Metagenomics", + "Transcriptome Analysis", + "Resequencing", + "Epigenetics", + "Synthetic Genomics", + "Forensic or Paleo-genomics", + "Gene Regulation Study", + "Cancer Genomics", + "Population Genomics", + "RNASeq", + "Exome Sequencing", + "Pooled Clone Sequencing", + "Transcriptome Sequencing", + "Other" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "new_study_type", + "cardinality": "optional", + "description": "Optional if 'study_type' is not 'other'. To propose a new term, select Other and enter a new study type.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "study_abstract", + "cardinality": "optional", + "description": "Briefly describes the goals, purpose, and scope of the Study. This need not be listed if it can be inherited from a referenced publication.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_AREA_FIELD" + } + ] + }, + "experiment": { + "description": "An experiment object serves as a metadata record encapsulating essential details about a sequencing experiment, including the experimental design, sequencing type, and relevant parameters. This information enhances the interpretation and contextual understanding of nucleotide sequences submitted to the archive.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for each experiment. This is used to link runs to experiments.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "title", + "cardinality": "optional", + "description": "Short text that can be used to call out experiment records in searches or in displays. This element is technically optional but should be used for all new records.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "study_alias", + "cardinality": "mandatory", + "description": "Identifies the parent study. (From study metadata)", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "sample_alias", + "cardinality": "mandatory", + "description": "(From sample metadata)", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "design_description", + "cardinality": "optional", + "description": "Goal and setup of the individual library including library was constructed.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_AREA_FIELD" + }, + { + "name": "library_name", + "cardinality": "optional", + "description": "The submitter's name for this library.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "library_strategy", + "cardinality": "mandatory", + "description": "Sequencing technique intended for this library.", + "units": "", + "regex": "", + "cv": [ + "WGS", + "WGA", + "WXS", + "RNA-Seq", + "ssRNA-seq", + "snRNA-seq", + "miRNA-Seq", + "ncRNA-Seq", + "FL-cDNA", + "EST", + "Hi-C", + "ATAC-seq", + "WCS", + "RAD-Seq", + "CLONE", + "POOLCLONE", + "AMPLICON", + "CLONEEND", + "FINISHING", + "ChIP-Seq", + "MNase-Seq", + "DNase-Hypersensitivity", + "Bisulfite-Seq", + "CTS", + "MRE-Seq", + "MeDIP-Seq", + "MBD-Seq", + "Tn-Seq", + "VALIDATION", + "FAIRE-seq", + "SELEX", + "RIP-Seq", + "ChIA-PET", + "Synthetic-Long-Read", + "Targeted-Capture", + "Tethered Chromatin Conformation Capture", + "NOMe-Seq", + "ChM-Seq", + "GBS", + "Ribo-Seq", + "OTHER" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "library_source", + "cardinality": "mandatory", + "description": "The LIBRARY_SOURCE specifies the type of source material that is being sequenced.", + "units": "", + "regex": "", + "cv": [ + "GENOMIC", + "GENOMIC SINGLE CELL", + "TRANSCRIPTOMIC", + "TRANSCRIPTOMIC SINGLE CELL", + "METAGENOMIC", + "METATRANSCRIPTOMIC", + "SYNTHETIC", + "VIRAL RNA", + "OTHER" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "library_selection", + "cardinality": "mandatory", + "description": "Method used to enrich the target in the sequence library preparation", + "units": "", + "regex": "", + "cv": [ + "RANDOM", + "PCR", + "RANDOM PCR", + "RT-PCR", + "HMPR", + "MF", + "repeat fractionation", + "size fractionation", + "MSLL", + "cDNA", + "cDNA_randomPriming", + "cDNA_oligo_dT", + "PolyA", + "Oligo-dT", + "Inverse rRNA", + "Inverse rRNA selection", + "ChIP", + "ChIP-Seq", + "MNase", + "DNase", + "Hybrid Selection", + "Reduced Representation", + "Restriction Digest", + "5-methylcytidine antibody", + "MBD2 protein methyl-CpG binding domain", + "CAGE", + "RACE", + "MDA", + "padlock probes capture method", + "other", + "unspecified" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "library_layout", + "cardinality": "mandatory", + "description": "LIBRARY_LAYOUT specifies whether to expect single, paired, or other configuration of reads. In the case of paired reads, information about the relative distance and orientation is specified.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "insert_size", + "cardinality": "optional", + "description": "Insert size for paired reads", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "library_construction_protocol", + "cardinality": "optional", + "description": "Free form text describing the protocol by which the sequencing library was constructed.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "platform", + "cardinality": "mandatory", + "description": "The PLATFORM record selects which sequencing platform and platform-specific runtime parameters. This will be determined by the Center. optional if 'instrument_model' is provided.", + "units": "", + "regex": "", + "cv": [ + "LS454", + "ILLUMINA", + "HELICOS", + "ABI_SOLID", + "COMPLETE_GENOMICS", + "BGISEQ", + "OXFORD_NANOPORE", + "PACBIO_SMRT", + "ION_TORRENT", + "CAPILLARY", + "DNBSEQ", + "ELEMENT", + "ULTIMA", + "VELA_DIAGNOSTICS", + "GENAPSYS", + "GENEMIND", + "TAPESTRI" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "instrument_model", + "cardinality": "mandatory", + "description": "Model of the sequencing instrument.", + "units": "", + "regex": "", + "cv": [ + "454 GS", + "454 GS 20", + "454 GS FLX", + "454 GS FLX Titanium", + "454 GS FLX+", + "454 GS Junior", + "AB 310 Genetic Analyzer", + "AB 3130 Genetic Analyzer", + "AB 3130xL Genetic Analyzer", + "AB 3500 Genetic Analyzer", + "AB 3500xL Genetic Analyzer", + "AB 3730 Genetic Analyzer", + "AB 3730xL Genetic Analyzer", + "AB 5500 Genetic Analyzer", + "AB 5500xl Genetic Analyzer", + "AB 5500xl-W Genetic Analysis System", + "AB SOLiD 3 Plus System", + "AB SOLiD 4 System", + "AB SOLiD 4hq System", + "AB SOLiD PI System", + "AB SOLiD System", + "AB SOLiD System 2.0", + "AB SOLiD System 3.0", + "BGISEQ-50", + "BGISEQ-500", + "Complete Genomics", + "DNBSEQ-G400", + "DNBSEQ-G400 FAST", + "DNBSEQ-G50", + "DNBSEQ-T7", + "Element AVITI", + "FASTASeq 300", + "GENIUS", + "GS111", + "Genapsys Sequencer", + "GenoCare 1600", + "GenoLab M", + "GridION", + "Helicos HeliScope", + "HiSeq X Five", + "HiSeq X Ten", + "Illumina Genome Analyzer", + "Illumina Genome Analyzer II", + "Illumina Genome Analyzer IIx", + "Illumina HiScanSQ", + "Illumina HiSeq 1000", + "Illumina HiSeq 1500", + "Illumina HiSeq 2000", + "Illumina HiSeq 2500", + "Illumina HiSeq 3000", + "Illumina HiSeq 4000", + "Illumina HiSeq X", + "Illumina MiSeq", + "Illumina MiniSeq", + "Illumina NovaSeq 6000", + "Illumina NovaSeq X", + "Illumina iSeq 100", + "Ion GeneStudio S5", + "Ion GeneStudio S5 Plus", + "Ion GeneStudio S5 Prime", + "Ion Torrent Genexus", + "Ion Torrent PGM", + "Ion Torrent Proton", + "Ion Torrent S5", + "Ion Torrent S5 XL", + "MGISEQ-2000RS", + "MinION", + "NextSeq 1000", + "NextSeq 2000", + "NextSeq 500", + "NextSeq 550", + "Onso", + "PacBio RS", + "PacBio RS II", + "PromethION", + "Revio", + "Sentosa SQ301", + "Sequel", + "Sequel II", + "Sequel IIe", + "Tapestri", + "UG 100", + "unspecified" + ], + "field_type": "TEXT_CHOICE_FIELD" + } + ] + }, + "run": { + "description": "A run contains a group of reads generated for a particular experiment.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for each run.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "experiment_alias", + "cardinality": "mandatory", + "description": "From_experiment_metadata", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "file_name", + "cardinality": "mandatory", + "description": "The name or relative pathname of a run data file.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "file_format", + "cardinality": "mandatory", + "description": "The run data file model.", + "units": "", + "regex": "", + "cv": [ + "sra", + "srf", + "sff", + "fastq", + "fasta", + "tab", + "454_native", + "454_native_seq", + "454_native_qual", + "Helicos_native", + "Illumina_native", + "Illumina_native_seq", + "Illumina_native_prb", + "Illumina_native_int", + "Illumina_native_qseq", + "Illumina_native_scarf", + "SOLiD_native", + "SOLiD_native_csfasta", + "SOLiD_native_qual", + "PacBio_HDF5", + "bam", + "cram", + "CompleteGenomics_native", + "OxfordNanopore_native" + ], + "field_type": "TEXT_CHOICE_FIELD" + } + ] + }, + "sample": { + "description": "A Sample defines an isolate of sequenceable material upon which sequencing experiments can be based. The Sample object may be a surrogate for taxonomy accession or an anonymized individual identifier. Or, it may fully specify provenance and isolation method of the starting material.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for each run.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "title", + "cardinality": "mandatory", + "description": "Short text that can be used to call out sample records in search results or in displays.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "taxon_id", + "cardinality": "mandatory", + "description": "NCBI Taxonomy Identifier. This is appropriate for individual organisms and some environmental samples.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "sample_description", + "cardinality": "optional", + "description": "Free-form text describing the sample, its origin, and its method of isolation.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_AREA_FIELD" + }, + { + "name": "trophic level", + "cardinality": "optional", + "description": "Trophic levels are the feeding position in a food chain. Microbes can be a range of producers (e.g. chemolithotroph)", + "cv": [ + "autotroph", + "carboxydotroph", + "chemoautotroph", + "chemoheterotroph", + "chemolithoautotroph", + "chemolithotroph", + "chemoorganoheterotroph", + "chemoorganotroph", + "chemosynthetic", + "chemotroph", + "copiotroph", + "diazotroph", + "facultative autotroph", + "heterotroph", + "lithoautotroph", + "lithoheterotroph", + "lithotroph", + "methanotroph", + "methylotroph", + "mixotroph", + "obligate chemoautolithotroph", + "oligotroph", + "organoheterotroph", + "organotroph", + "photoautotroph", + "photoheterotroph", + "photolithoautotroph", + "photolithotroph", + "photosynthetic", + "phototroph" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "observed biotic relationship", + "cardinality": "optional", + "description": "Description of relationship(s) between the subject organism and other organism(s) it is associated with. E.g., parasite on species X; mutualist with species Y. The target organism is the subject of the relationship, and the other organism(s) is the object.", + "cv": [ + "commensal", + "free living", + "mutualism", + "parasite", + "symbiont" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "known pathogenicity", + "cardinality": "optional", + "description": "To what is the entity pathogenic, for instance plant, fungi, bacteria", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "relationship to oxygen", + "cardinality": "optional", + "description": "Is this organism an aerobe, anaerobe? Please note that aerobic and anaerobic are valid descriptors for microbial environments", + "cv": [ + "aerobe", + "anaerobe", + "facultative", + "microaerophilic", + "microanaerobe", + "obligate aerobe", + "obligate anaerobe" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "propagation", + "cardinality": "optional", + "description": "The type of reproduction from the parent stock. Values for this field is specific to different taxa. For phage or virus: lytic/lysogenic/temperate/obligately lytic. For plasmids: incompatibility group. For eukaryotes: sexual/asexual. Mandatory for MIGs of eukayotes, plasmids and viruses.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host of the symbiont role", + "cardinality": "optional", + "description": "Role of the host in the life cycle of the symbiotic organism.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample symbiont of", + "cardinality": "optional", + "description": "Reference to host sample from symbiont. The referenced sample should already be registered in INSDC. E.g. ERSxxxxxx", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "(^[ESD]RS\\d{6,}$)|(^SAM[END][AG]?\\d+$)|(^EGAN\\d{11}$)" + }, + { + "name": "sample collection method", + "cardinality": "optional", + "description": "The method employed for collecting the sample. Can be provided in the form of a PMID, DOI, url or text.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample storage temperature", + "cardinality": "optional", + "description": "temperature at which sample was stored, e.g. -80", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "sample storage location", + "cardinality": "optional", + "description": "Location at which sample was stored, usually name of a specific freezer/room. Indicate the location name.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample storage solution", + "cardinality": "optional", + "description": "Solution within which sample was stored, if any.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "oxygenation status of sample", + "cardinality": "optional", + "description": "oxygenation status of sample", + "cv": [ + "aerobic", + "anaerobic" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "project name", + "cardinality": "optional", + "description": "Name of the project within which the sequencing was organized", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "ploidy", + "cardinality": "optional", + "description": "The ploidy level of the genome (e.g. allopolyploid, haploid, diploid, triploid, tetraploid). It has implications for the downstream study of duplicated gene and regions of the genomes (and perhaps for difficulties in assembly). For terms, please select terms listed under class ploidy (PATO:001374) of Phenotypic Quality Ontology (PATO), and for a browser of PATO (v 2018-03-27) please refer to http://purl.bioontology.org/ontology/PATO", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "number of replicons", + "cardinality": "optional", + "description": "Reports the number of replicons in a nuclear genome of eukaryotes, in the genome of a bacterium or archaea or the number of segments in a segmented virus. Always applied to the haploid chromosome count of a eukaryote. Mandatory for MIGS of eukaryotes, bacteria, archaea and segmented virus.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "extrachromosomal elements", + "cardinality": "optional", + "description": "Do plasmids exist of significant phenotypic consequence (e.g. ones that determine virulence or antibiotic resistance). Megaplasmids? Other plasmids (borrelia has 15+ plasmids).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "estimated size", + "cardinality": "optional", + "description": "The estimated size of the genome (in bp) prior to sequencing. Of particular importance in the sequencing of (eukaryotic) genome which could remain in draft form for a long or unspecified period. Mandatory for MIGS of eukaryotes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "target gene", + "cardinality": "optional", + "description": "Targeted gene or locus name for marker gene studies", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "target subfragment", + "cardinality": "optional", + "description": "Name of subfragment of a gene or locus. Important to e.g. identify special regions on marker genes like V6 on 16S rRNA", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "multiplex identifiers", + "cardinality": "optional", + "description": "Molecular barcodes, called Multiplex Identifiers (MIDs), that are used to specifically tag unique samples in a sequencing run. Sequence should be reported in uppercase letters", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sequence quality check", + "cardinality": "optional", + "description": "Indicate if the sequence has been called by automatic systems (none) or undergone a manual editing procedure (e.g. by inspecting the raw data or chromatograms). Applied only for sequences that are not submitted to SRA or DRA", + "cv": [ + "manual", + "none", + "software" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "chimera check software", + "cardinality": "optional", + "description": "Tool(s) used for chimera checking, including version number and parameters, to discover and remove chimeric sequences. A chimeric sequence is comprised of two or more phylogenetically distinct parent sequences.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "relevant electronic resources", + "cardinality": "optional", + "description": "A related resource that is referenced, cited, or otherwise associated to the sequence in the format of a PMID, DOI or URL", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "relevant standard operating procedures", + "cardinality": "optional", + "description": "Standard operating procedures used in assembly and/or annotation of genomes, metagenomes or environmental sequences in the format of a PMID, DOI or URL", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "16s recovered", + "cardinality": "optional", + "description": "Can a 16S gene be recovered from the submitted bin, SAG or MAG?", + "cv": [ + "No", + "Yes" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "16S recovery software", + "cardinality": "optional", + "description": "Tools used for 16S rRNA gene extraction. Add names and versions of software(s), parameters used", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "collection date", + "cardinality": "optional", + "description": "The date the sample was collected with the intention of sequencing, either as an instance (single point in time) or interval. In case no exact time is available, the date/time can be right truncated i.e. all of these are valid ISO8601 compliant times: 2008-01-23T19:23:10+00:00; 2008-01-23T19:23:10; 2008-01-23; 2008-01; 2008.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "(^[12][0-9]{3}(-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01])(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?(/[0-9]{4}(-[0-9]{2}(-[0-9]{2}(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?)?$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)" + }, + { + "name": "altitude", + "cardinality": "optional", + "description": "The altitude of the sample is the vertical distance between Earth's surface above Sea Level and the sampled position in the air.", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "((0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "geographic location (country and/or sea)", + "cardinality": "optional", + "description": "The geographical origin of where the sample was collected from, with the intention of sequencing, as defined by the country or sea name. Country or sea names should be chosen from the INSDC country list (http://insdc.org/country.html).", + "cv": [ + "Afghanistan", + "Albania", + "Algeria", + "American Samoa", + "Andorra", + "Angola", + "Anguilla", + "Antarctica", + "Antigua and Barbuda", + "Arctic Ocean", + "Argentina", + "Armenia", + "Aruba", + "Ashmore and Cartier Islands", + "Atlantic Ocean", + "Australia", + "Austria", + "Azerbaijan", + "Bahamas", + "Bahrain", + "Baker Island", + "Baltic Sea", + "Bangladesh", + "Barbados", + "Bassas da India", + "Belarus", + "Belgium", + "Belize", + "Benin", + "Bermuda", + "Bhutan", + "Bolivia", + "Borneo", + "Bosnia and Herzegovina", + "Botswana", + "Bouvet Island", + "Brazil", + "British Virgin Islands", + "Brunei", + "Bulgaria", + "Burkina Faso", + "Burundi", + "Cambodia", + "Cameroon", + "Canada", + "Cape Verde", + "Cayman Islands", + "Central African Republic", + "Chad", + "Chile", + "China", + "Christmas Island", + "Clipperton Island", + "Cocos Islands", + "Colombia", + "Comoros", + "Cook Islands", + "Coral Sea Islands", + "Costa Rica", + "Cote d'Ivoire", + "Croatia", + "Cuba", + "Curacao", + "Cyprus", + "Czechia", + "Czech Republic", + "Democratic Republic of the Congo", + "Denmark", + "Djibouti", + "Dominica", + "Dominican Republic", + "East Timor", + "Ecuador", + "Egypt", + "El Salvador", + "Equatorial Guinea", + "Eritrea", + "Estonia", + "Ethiopia", + "Europa Island", + "Falkland Islands (Islas Malvinas)", + "Faroe Islands", + "Fiji", + "Finland", + "France", + "French Guiana", + "French Polynesia", + "French Southern and Antarctic Lands", + "Gabon", + "Gambia", + "Gaza Strip", + "Georgia", + "Germany", + "Ghana", + "Gibraltar", + "Glorioso Islands", + "Greece", + "Greenland", + "Grenada", + "Guadeloupe", + "Guam", + "Guatemala", + "Guernsey", + "Guinea", + "Guinea-Bissau", + "Guyana", + "Haiti", + "Heard Island and McDonald Islands", + "Honduras", + "Hong Kong", + "Howland Island", + "Hungary", + "Iceland", + "India", + "Indian Ocean", + "Indonesia", + "Iran", + "Iraq", + "Ireland", + "Isle of Man", + "Israel", + "Italy", + "Jamaica", + "Jan Mayen", + "Japan", + "Jarvis Island", + "Jersey", + "Johnston Atoll", + "Jordan", + "Juan de Nova Island", + "Kazakhstan", + "Kenya", + "Kerguelen Archipelago", + "Kingman Reef", + "Kiribati", + "Kosovo", + "Kuwait", + "Kyrgyzstan", + "Laos", + "Latvia", + "Lebanon", + "Lesotho", + "Liberia", + "Libya", + "Liechtenstein", + "Lithuania", + "Luxembourg", + "Macau", + "Macedonia", + "Madagascar", + "Malawi", + "Malaysia", + "Maldives", + "Mali", + "Malta", + "Marshall Islands", + "Martinique", + "Mauritania", + "Mauritius", + "Mayotte", + "Mediterranean Sea", + "Mexico", + "Micronesia", + "Midway Islands", + "Moldova", + "Monaco", + "Mongolia", + "Montenegro", + "Montserrat", + "Morocco", + "Mozambique", + "Myanmar", + "Namibia", + "Nauru", + "Navassa Island", + "Nepal", + "Netherlands", + "New Caledonia", + "New Zealand", + "Nicaragua", + "Niger", + "Nigeria", + "Niue", + "Norfolk Island", + "North Korea", + "North Sea", + "Northern Mariana Islands", + "Norway", + "Oman", + "Pacific Ocean", + "Pakistan", + "Palau", + "Palmyra Atoll", + "Panama", + "Papua New Guinea", + "Paracel Islands", + "Paraguay", + "Peru", + "Philippines", + "Pitcairn Islands", + "Poland", + "Portugal", + "Puerto Rico", + "Qatar", + "Republic of the Congo", + "Reunion", + "Romania", + "Ross Sea", + "Russia", + "Rwanda", + "Saint Helena", + "Saint Kitts and Nevis", + "Saint Lucia", + "Saint Pierre and Miquelon", + "Saint Vincent and the Grenadines", + "Samoa", + "San Marino", + "Sao Tome and Principe", + "Saudi Arabia", + "Senegal", + "Serbia", + "Seychelles", + "Sierra Leone", + "Singapore", + "Sint Maarten", + "Slovakia", + "Slovenia", + "Solomon Islands", + "Somalia", + "South Africa", + "South Georgia and the South Sandwich Islands", + "South Korea", + "Southern Ocean", + "Spain", + "Spratly Islands", + "Sri Lanka", + "Sudan", + "Suriname", + "Svalbard", + "Swaziland", + "Sweden", + "Switzerland", + "Syria", + "Taiwan", + "Tajikistan", + "Tanzania", + "Tasman Sea", + "Thailand", + "Togo", + "Tokelau", + "Tonga", + "Trinidad and Tobago", + "Tromelin Island", + "Tunisia", + "Turkey", + "Turkmenistan", + "Turks and Caicos Islands", + "Tuvalu", + "USA", + "Uganda", + "Ukraine", + "United Arab Emirates", + "United Kingdom", + "Uruguay", + "Uzbekistan", + "Vanuatu", + "Venezuela", + "Viet Nam", + "Virgin Islands", + "Wake Island", + "Wallis and Futuna", + "West Bank", + "Western Sahara", + "Yemen", + "Zambia", + "Zimbabwe", + "missing: control sample", + "missing: data agreement established pre-2023", + "missing: endangered species", + "missing: human-identifiable", + "missing: lab stock", + "missing: sample group", + "missing: synthetic construct", + "missing: third party data", + "not applicable", + "not collected", + "not provided", + "restricted access" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "geographic location (latitude)", + "cardinality": "optional", + "description": "The geographical origin of the sample as defined by latitude. The values should be reported in decimal degrees and in WGS84 system", + "cv": [], + "units": "DD", + "field_type": "TEXT_FIELD", + "regex": "(^[+-]?[0-9]+.?[0-9]{0,8}$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)" + }, + { + "name": "geographic location (longitude)", + "cardinality": "optional", + "description": "The geographical origin of the sample as defined by longitude. The values should be reported in decimal degrees and in WGS84 system", + "cv": [], + "units": "DD", + "field_type": "TEXT_FIELD", + "regex": "(^[+-]?[0-9]+.?[0-9]{0,8}$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)" + }, + { + "name": "geographic location (region and locality)", + "cardinality": "optional", + "description": "The geographical origin of the sample as defined by the specific region name followed by the locality name.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "broad-scale environmental context", + "cardinality": "optional", + "description": "Report the major environmental system the sample or specimen came from. The system(s) identified should have a coarse spatial grain, to provide the general environmental context of where the sampling was done (e.g. in the desert or a rainforest). We recommend using subclasses of EnvO\u2019s biome class: http://purl.obolibrary.org/obo/ENVO_00000428. EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "local environmental context", + "cardinality": "optional", + "description": "Report the entity or entities which are in the sample or specimen\u2019s local vicinity and which you believe have significant causal influences on your sample or specimen. We recommend using EnvO terms which are of smaller spatial grain than your entry for \"broad-scale environmental context\". Terms, such as anatomical sites, from other OBO Library ontologies which interoperate with EnvO (e.g. UBERON) are accepted in this field. EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "environmental medium", + "cardinality": "optional", + "description": "Report the environmental material(s) immediately surrounding the sample or specimen at the time of sampling. We recommend using subclasses of 'environmental material' (http://purl.obolibrary.org/obo/ENVO_00010483). EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS . Terms from other OBO ontologies are permissible as long as they reference mass/volume nouns (e.g. air, water, blood) and not discrete, countable entities (e.g. a tree, a leaf, a table top).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "elevation", + "cardinality": "optional", + "description": "The elevation of the sampling site as measured by the vertical distance from mean sea level.", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "([+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "amount or size of sample collected", + "cardinality": "optional", + "description": "The total amount or size (volume (ml), mass (g) or area (m2) ) of sample collected.", + "cv": [], + "units": "m3", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "organism count", + "cardinality": "optional", + "description": "Total cell count of any organism (or group of organisms) per gram, volume or area of sample, should include name of organism followed by count. The method that was used for the enumeration (e.g. qPCR, atp, mpn, etc.) Should also be provided. (example: total prokaryotes; 3.5e7 cells per ml; qpcr)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample storage duration", + "cardinality": "optional", + "description": "Duration for which the sample was stored. Indicate the duration for which the sample was stored written in ISO 8601 format.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host disease status", + "cardinality": "optional", + "description": "list of diseases with which the host has been diagnosed; can include multiple diagnoses. The value of the field depends on host; for humans the terms should be chosen from DO (Disease Ontology) at http://www.disease-ontology.org, other hosts are free text", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host of the symbiotic host disease status", + "cardinality": "optional", + "description": "List of diseases with which the host of the symbiotic host organism has been diagnosed; can include multiple diagnoses. The value of the field depends on host; for humans the terms should be chosen from the DO (Human Disease Ontology) at https://www.disease-ontology.org, non-human host diseases are free text.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host common name", + "cardinality": "optional", + "description": "common name of the host, e.g. human", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host subject id", + "cardinality": "optional", + "description": "a unique identifier by which each subject can be referred to, de-identified, e.g. #131", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host age", + "cardinality": "optional", + "description": "age of host at the time of sampling; relevant scale depends on species and study, e.g. could be seconds for amoebae or centuries for trees", + "cv": [], + "units": "years", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "host taxid", + "cardinality": "optional", + "description": "NCBI taxon id of the host, e.g. 9606", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "host body habitat", + "cardinality": "optional", + "description": "original body habitat where the sample was obtained from", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host body site", + "cardinality": "optional", + "description": "name of body site where the sample was obtained from, such as a specific organ or tissue (tongue, lung etc...). For Foundational Model of Anatomy Ontology (FMA) (v 3.1) terms, please see http://purl.bioontology.org/ontology/FMA", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host life stage", + "cardinality": "optional", + "description": "description of life stage of host", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host height", + "cardinality": "optional", + "description": "the height of subject", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "((0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "host length", + "cardinality": "optional", + "description": "the length of subject", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "host growth conditions", + "cardinality": "optional", + "description": "literature reference giving growth conditions of the host", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host substrate", + "cardinality": "optional", + "description": "the growth substrate of the host", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host total mass", + "cardinality": "optional", + "description": "total mass of the host at collection, the unit depends on host", + "cv": [], + "units": "kg", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "host infra-specific name", + "cardinality": "optional", + "description": "taxonomic information about the host below subspecies level", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host infra-specific rank", + "cardinality": "optional", + "description": "taxonomic rank information about the host below subspecies level, such as variety, form, rank etc.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host phenotype", + "cardinality": "optional", + "description": "phenotype of host. For Phenotypic quality Ontology (PATO) (v 2013-10-28) terms, please see http://purl.bioontology.org/ontology/PATO", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host color", + "cardinality": "optional", + "description": "the color of host", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host shape", + "cardinality": "optional", + "description": "morphological shape of host", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host sex", + "cardinality": "optional", + "description": "Gender or sex of the host.", + "cv": [ + "female", + "hermaphrodite", + "male", + "missing: control sample", + "missing: data agreement established pre-2023", + "missing: endangered species", + "missing: human-identifiable", + "missing: lab stock", + "missing: sample group", + "missing: synthetic construct", + "missing: third party data", + "neuter", + "not applicable", + "not collected", + "not provided", + "other", + "restricted access" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "host scientific name", + "cardinality": "optional", + "description": "Scientific name of the natural (as opposed to laboratory) host to the organism from which sample was obtained.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host of the symbiotic host subject id", + "cardinality": "optional", + "description": "A unique identifier by which each host of the symbiotic host organism subject can be referred to, de-identified, e.g. #H14.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host of the symbiotic host taxon id", + "cardinality": "optional", + "description": "NCBI taxon id of the host of the symbiotic host organism.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "duration of association with the host", + "cardinality": "optional", + "description": "Time spent in host of the symbiotic organism at the time of sampling; relevant scale depends on symbiotic organism and study.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "temperature", + "cardinality": "optional", + "description": "temperature of the sample at time of sampling", + "cv": [], + "units": "\u00baC", + "field_type": "TEXT_FIELD", + "regex": "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "sample salinity", + "cardinality": "optional", + "description": "Salinity is the total concentration of all dissolved salts in a liquid or solid (in the form of an extract obtained by centrifugation) sample. While salinity can be measured by a complete chemical analysis, this method is difficult and time consuming. More often, it is instead derived from the conductivity measurement. This is known as practical salinity. These derivations compare the specific conductance of the sample to a salinity standard such as seawater", + "cv": [], + "units": "psu", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "source material identifiers", + "cardinality": "optional", + "description": "A unique identifier assigned to a material sample (as defined by http://rs.tdwg.org/dwc/terms/materialSampleID, and as opposed to a particular digital record of a material sample) used for extracting nucleic acids, and subsequent sequencing. The identifier can refer either to the original material collected or to any derived sub-samples. The INSDC qualifiers /specimen_voucher, /bio_material, or /culture_collection may or may not share the same value as the source_mat_id field. For instance, the /specimen_voucher qualifier and source_mat_id may both contain 'UAM:Herps:14' , referring to both the specimen voucher and sampled tissue with the same identifier. However, the /culture_collection qualifier may refer to a value from an initial culture (e.g. ATCC:11775) while source_mat_id would refer to an identifier from some derived culture from which the nucleic acids were extracted (e.g. xatc123 or ark:/2154/R2).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host family relationship", + "cardinality": "optional", + "description": "Familial relationships to other hosts in the same study; can include multiple relationships", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host genotype", + "cardinality": "optional", + "description": "observed genotype", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "gravidity", + "cardinality": "optional", + "description": "Whether or not the subject is gravid. If so, report date due or date post-conception and specify which of these two dates is being reported.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host specificity or range", + "cardinality": "optional", + "description": "The range and diversity of host species that an organism is capable of infecting, defined by NCBI taxonomy identifier.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "host of the symbiotic host phenotype", + "cardinality": "optional", + "description": "Phenotype of the host of the symbiotic host organism. For phenotypic quality ontology (PATO) terms, see http://purl.bioontology.org/ontology/pato.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "mode of transmission", + "cardinality": "optional", + "description": "The process through which the symbiotic host organism entered the host from which it was sampled.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "symbiotic host organism life cycle type", + "cardinality": "optional", + "description": "Type of life cycle of the symbiotic host species (the thing being sampled). Simple life cycles occur within a single host, complex ones within multiple different hosts over the course of their normal life cycle.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host specificity", + "cardinality": "optional", + "description": "Level of specificity of symbiont-host interaction: e.g. generalist (symbiont able to establish associations with distantly related hosts) or species-specific.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host cellular location", + "cardinality": "optional", + "description": "The localization of the symbiotic host organism within the host from which it was sampled: e.g. intracellular if the symbiotic host organism is localized within the cells or extracellular if the symbiotic host organism is localized outside of cells.", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host of the symbiotic host infra-specific rank", + "cardinality": "optional", + "description": "Taxonomic rank information about the host of the symbiotic host organism below subspecies level, such as variety, form, rank etc.", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "type of symbiosis", + "cardinality": "optional", + "description": "Type of biological interaction established between the symbiotic host organism being sampled and its respective host", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "observed coinfecting organisms in host of host", + "cardinality": "optional", + "description": "The taxonomic name of any coinfecting organism observed in a symbiotic relationship with the host of the sampled host organism. e.g. where a sample collected from a host trematode species (A) which was collected from a host_of_host fish (B) that was also infected with a nematode (C), the value here would be (C) the nematode {species name} or {common name}. Multiple co-infecting species may be added in a comma-separated list. For listing symbiotic organisms associated with the host (A) use the term Observed host symbiont.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host of the symbiotic host infra-specific name", + "cardinality": "optional", + "description": "Taxonomic name information of the host of the symbiotic host organism below subspecies level.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host of the symbiotic host total mass", + "cardinality": "optional", + "description": "Total mass of the host of the symbiotic host organism at collection, the unit depends on the host.", + "cv": [], + "units": "\u00b5g", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "host of the symbiotic host local environmental context", + "cardinality": "optional", + "description": "For a symbiotic host organism the local anatomical environment within its host may have causal influences. Report the anatomical entity(s) which are in the direct environment of the symbiotic host organism being sampled and which you believe have significant causal influences on your sample or specimen. For example, if the symbiotic host organism being sampled is an intestinal worm, its local environmental context will be the term for intestine from UBERON (http://uberon.github.io/).", + "cv": [], + "units": "g/m3", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host of the symbiotic host common name", + "cardinality": "optional", + "description": "Common name of the host of the symbiotic host organism.", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host of the symbiotic host genotype", + "cardinality": "optional", + "description": "Observed genotype of the host of the symbiotic host organism.", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "route of transmission", + "cardinality": "optional", + "description": "Description of path taken by the symbiotic host organism being sampled in order to establish a symbiotic relationship with the host (with which it was observed at the time of sampling) via a mode of transmission (specified in mode_transmission).", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host dry mass", + "cardinality": "optional", + "description": "measurement of dry mass", + "cv": [], + "units": "mg", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "host body product", + "cardinality": "optional", + "description": "substance produced by the body, e.g. stool, mucus, where the sample was obtained from. For Foundational Model of Anatomy Ontology (FMA) (v 3.1) terms, please see http://purl.bioontology.org/ontology/FMA", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host number individual", + "cardinality": "optional", + "description": "Number of symbiotic host individuals pooled at the time of collection.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "perturbation", + "cardinality": "optional", + "description": "type of perturbation, e.g. chemical administration, physical disturbance, etc., coupled with time that perturbation occurred; can include multiple perturbation types", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "negative control type", + "cardinality": "optional", + "description": "The substance or equipment used as a negative control in an investigation", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "positive control type", + "cardinality": "optional", + "description": "The substance, mixture, product, or apparatus used to verify that a process which is part of an investigation delivers a true positive.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "experimental factor", + "cardinality": "optional", + "description": "Experimental factors are essentially the variable aspects of an experiment design which can be used to describe an experiment, or set of experiments, in an increasingly detailed manner. This field accepts ontology terms from Experimental Factor Ontology (EFO) and/or Ontology for Biomedical Investigations (OBI). For a browser of EFO (v 2.95) terms, please see http://purl.bioontology.org/ontology/EFO; for a browser of OBI (v 2018-02-12) terms please see http://purl.bioontology.org/ontology/OBI. E.g. time series design [EFO:EFO_0001779]", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "encoded traits", + "cardinality": "optional", + "description": "Should include key traits like antibiotic resistance or xenobiotic degradation phenotypes for plasmids, converting genes for phage", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "subspecific genetic lineage", + "cardinality": "optional", + "description": "Information about the genetic distinctness of the sequenced organism below the subspecies level, e.g., serovar, serotype, biotype, ecotype, or any relevant genetic typing schemes like Group I plasmid. Subspecies should not be recorded in this term, but in the NCBI taxonomy. Supply both the lineage name and the lineage rank separated by a colon, e.g., biovar:abc123.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "taxonomic classification", + "cardinality": "optional", + "description": "Method used for taxonomic classification, along with reference database used, classification rank, and thresholds used to classify new genomes. Expected values are: classification method, database name, and other parameters e.g. vConTACT vContact2 (references from NCBI RefSeq v83, genus rank classification, default parameters)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "isolation and growth condition", + "cardinality": "optional", + "description": "Publication reference in the form of pubmed ID (pmid), digital object identifier (doi) or url for isolation and growth condition specifications of the organism/material. Mandatory for MIGS and MIMARKS Specimen.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "annotation source", + "cardinality": "optional", + "description": "For cases where annotation was provided by a community jamboree or model organism database rather than by a specific submitter", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "reference for biomaterial", + "cardinality": "optional", + "description": "Primary publication if isolated before genome publication; otherwise, primary genome report. Mandatory for MIGS of bacteria and archaea.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "single cell or viral particle lysis approach", + "cardinality": "optional", + "description": "Method used to free DNA from interior of the cell(s) or particle(s)", + "cv": [ + "chemical", + "combination", + "enzymatic", + "physical" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "single cell or viral particle lysis kit protocol", + "cardinality": "optional", + "description": "Name of the kit or standard protocol used for cell(s) or particle(s) lysis", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample material processing", + "cardinality": "optional", + "description": "A brief description of any processing applied to the sample during or after retrieving the sample from environment, or a link to the relevant protocol(s) performed.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample volume or weight for DNA extraction", + "cardinality": "optional", + "description": "Volume (ml) or mass (g) of total collected sample processed for DNA extraction. Note: total sample collected should be entered under the term 'sample size'.", + "cv": [], + "units": "ng", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "nucleic acid extraction", + "cardinality": "optional", + "description": "A link to a literature reference, electronic resource or a standard operating procedure (SOP), that describes the material separation to recover the nucleic acid fraction from a sample", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "nucleic acid amplification", + "cardinality": "optional", + "description": "A link to a literature reference, electronic resource or a standard operating procedure (SOP), that describes the enzymatic amplification (PCR, TMA, NASBA) of specific nucleic acids", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "library size", + "cardinality": "optional", + "description": "Total number of clones in the library prepared for the project", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "library reads sequenced", + "cardinality": "optional", + "description": "Total number of clones sequenced from the library", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "library vector", + "cardinality": "optional", + "description": "Cloning vector type(s) used in construction of libraries", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "library screening strategy", + "cardinality": "optional", + "description": "Specific enrichment or screening methods applied before and/or after creating clone libraries in order to select a specific group of sequences", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pcr conditions", + "cardinality": "optional", + "description": "Description of reaction conditions and components for PCR in the form of 'initial denaturation:94degC_1.5min; annealing=...'", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pcr primers", + "cardinality": "optional", + "description": "PCR primers that were used to amplify the sequence of the targeted gene, locus or subfragment. This field should contain all the primers used for a single PCR reaction if multiple forward or reverse primers are present in a single PCR reaction. The primer sequence should be reported in uppercase letters", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "adapters", + "cardinality": "optional", + "description": "Adapters provide priming sequences for both amplification and sequencing of the sample-library fragments. Both adapters should be reported; in uppercase letters", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "depth", + "cardinality": "optional", + "description": "The vertical distance below local surface, e.g. for sediment or soil samples depth is measured from sediment or soil surface, respectively. Depth can be reported as an interval for subsurface samples.", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "((0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "chemical administration", + "cardinality": "optional", + "description": "list of chemical compounds administered to the host or site where sampling occurred, and when (e.g. antibiotics, N fertilizer, air filter); can include multiple compounds. For Chemical Entities of Biological Interest ontology (CHEBI) (v111), please see http://purl.bioontology.org/ontology/CHEBI", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + } + ] + } +} \ No newline at end of file diff --git a/templates/ERC000057/README.md b/templates/ERC000057/README.md new file mode 100644 index 0000000..b42ebfa --- /dev/null +++ b/templates/ERC000057/README.md @@ -0,0 +1,171 @@ +# ERC000057: GSC MIxS Symbiont + +Genomic Standards Consortium package extension for reporting of measurements and observations obtained from the environment where the sample was obtained. By choosing the environmental package, a selection of fields can be made from a relevant subsets of the GSC terms. + +## Study + +A Study is a container for a sequencing investigation that may comprise multiple experiments. The Study has an overall goal, but is otherwise minimally defined in the SRA. A Study is composed of a descriptor, zero or more experiments, and zero or more analyses. The submitter may decorate the Study with web links and properties. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:---------------|:--------------|:---------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for a study. this is used to link experiments to the study. | | +| title | mandatory | Title of the study as would be used in a publication. | | +| study_type | mandatory | The study_type presents a controlled vocabulary for expressing the overall purpose of the study. | Whole Genome Sequencing, Metagenomics, Transcriptome Analysis, Resequencing, Epigenetics, Synthetic Genomics, Forensic or Paleo-genomics, Gene Regulation Study, Cancer Genomics, Population Genomics, RNASeq, Exome Sequencing, Pooled Clone Sequencing, Transcriptome Sequencing, Other | +| new_study_type | optional | Optional if 'study_type' is not 'other'. to propose a new term, select other and enter a new study type. | | +| study_abstract | optional | Briefly describes the goals, purpose, and scope of the study. this need not be listed if it can be inherited from a referenced publication. | | + +## Experiment + +An experiment object serves as a metadata record encapsulating essential details about a sequencing experiment, including the experimental design, sequencing type, and relevant parameters. This information enhances the interpretation and contextual understanding of nucleotide sequences submitted to the archive. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:------------------------------|:--------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for each experiment. this is used to link runs to experiments. | | +| title | optional | Short text that can be used to call out experiment records in searches or in displays. this element is technically optional but should be used for all new records. | | +| study_alias | mandatory | Identifies the parent study. (from study metadata) | | +| sample_alias | mandatory | (from sample metadata) | | +| design_description | optional | Goal and setup of the individual library including library was constructed. | | +| library_name | optional | The submitter's name for this library. | | +| library_strategy | mandatory | Sequencing technique intended for this library. | WGS, WGA, WXS, RNA-Seq, ssRNA-seq, snRNA-seq, miRNA-Seq, ncRNA-Seq, FL-cDNA, EST, Hi-C, ATAC-seq, WCS, RAD-Seq, CLONE, POOLCLONE, AMPLICON, CLONEEND, FINISHING, ChIP-Seq, MNase-Seq, DNase-Hypersensitivity, Bisulfite-Seq, CTS, MRE-Seq, MeDIP-Seq, MBD-Seq, Tn-Seq, VALIDATION, FAIRE-seq, SELEX, RIP-Seq, ChIA-PET, Synthetic-Long-Read, Targeted-Capture, Tethered Chromatin Conformation Capture, NOMe-Seq, ChM-Seq, GBS, Ribo-Seq, OTHER | +| library_source | mandatory | The library_source specifies the type of source material that is being sequenced. | GENOMIC, GENOMIC SINGLE CELL, TRANSCRIPTOMIC, TRANSCRIPTOMIC SINGLE CELL, METAGENOMIC, METATRANSCRIPTOMIC, SYNTHETIC, VIRAL RNA, OTHER | +| library_selection | mandatory | Method used to enrich the target in the sequence library preparation | RANDOM, PCR, RANDOM PCR, RT-PCR, HMPR, MF, repeat fractionation, size fractionation, MSLL, cDNA, cDNA_randomPriming, cDNA_oligo_dT, PolyA, Oligo-dT, Inverse rRNA, Inverse rRNA selection, ChIP, ChIP-Seq, MNase, DNase, Hybrid Selection, Reduced Representation, Restriction Digest, 5-methylcytidine antibody, MBD2 protein methyl-CpG binding domain, CAGE, RACE, MDA, padlock probes capture method, other, unspecified | +| library_layout | mandatory | Library_layout specifies whether to expect single, paired, or other configuration of reads. in the case of paired reads, information about the relative distance and orientation is specified. | | +| insert_size | optional | Insert size for paired reads | | +| library_construction_protocol | optional | Free form text describing the protocol by which the sequencing library was constructed. | | +| platform | mandatory | The platform record selects which sequencing platform and platform-specific runtime parameters. this will be determined by the center. optional if 'instrument_model' is provided. | LS454, ILLUMINA, HELICOS, ABI_SOLID, COMPLETE_GENOMICS, BGISEQ, OXFORD_NANOPORE, PACBIO_SMRT, ION_TORRENT, CAPILLARY, DNBSEQ, ELEMENT, ULTIMA, VELA_DIAGNOSTICS, GENAPSYS, GENEMIND, TAPESTRI | +| instrument_model | mandatory | Model of the sequencing instrument. | 454 GS, 454 GS 20, 454 GS FLX, 454 GS FLX Titanium, 454 GS FLX+, 454 GS Junior, AB 310 Genetic Analyzer, AB 3130 Genetic Analyzer, AB 3130xL Genetic Analyzer, AB 3500 Genetic Analyzer, AB 3500xL Genetic Analyzer, AB 3730 Genetic Analyzer, AB 3730xL Genetic Analyzer, AB 5500 Genetic Analyzer, AB 5500xl Genetic Analyzer, AB 5500xl-W Genetic Analysis System, AB SOLiD 3 Plus System, AB SOLiD 4 System, AB SOLiD 4hq System, AB SOLiD PI System, AB SOLiD System, AB SOLiD System 2.0, AB SOLiD System 3.0, BGISEQ-50, BGISEQ-500, Complete Genomics, DNBSEQ-G400, DNBSEQ-G400 FAST, DNBSEQ-G50, DNBSEQ-T7, Element AVITI, FASTASeq 300, GENIUS, GS111, Genapsys Sequencer, GenoCare 1600, GenoLab M, GridION, Helicos HeliScope, HiSeq X Five, HiSeq X Ten, Illumina Genome Analyzer, Illumina Genome Analyzer II, Illumina Genome Analyzer IIx, Illumina HiScanSQ, Illumina HiSeq 1000, Illumina HiSeq 1500, Illumina HiSeq 2000, Illumina HiSeq 2500, Illumina HiSeq 3000, Illumina HiSeq 4000, Illumina HiSeq X, Illumina MiSeq, Illumina MiniSeq, Illumina NovaSeq 6000, Illumina NovaSeq X, Illumina iSeq 100, Ion GeneStudio S5, Ion GeneStudio S5 Plus, Ion GeneStudio S5 Prime, Ion Torrent Genexus, Ion Torrent PGM, Ion Torrent Proton, Ion Torrent S5, Ion Torrent S5 XL, MGISEQ-2000RS, MinION, NextSeq 1000, NextSeq 2000, NextSeq 500, NextSeq 550, Onso, PacBio RS, PacBio RS II, PromethION, Revio, Sentosa SQ301, Sequel, Sequel II, Sequel IIe, Tapestri, UG 100, unspecified | + +## Run + +A run contains a group of reads generated for a particular experiment. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:-----------------|:--------------|:--------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for each run. | | +| experiment_alias | mandatory | From_experiment_metadata | | +| file_name | mandatory | The name or relative pathname of a run data file. | | +| file_format | mandatory | The run data file model. | sra, srf, sff, fastq, fasta, tab, 454_native, 454_native_seq, 454_native_qual, Helicos_native, Illumina_native, Illumina_native_seq, Illumina_native_prb, Illumina_native_int, Illumina_native_qseq, Illumina_native_scarf, SOLiD_native, SOLiD_native_csfasta, SOLiD_native_qual, PacBio_HDF5, bam, cram, CompleteGenomics_native, OxfordNanopore_native | + +## Sample + +A Sample defines an isolate of sequenceable material upon which sequencing experiments can be based. The Sample object may be a surrogate for taxonomy accession or an anonymized individual identifier. Or, it may fully specify provenance and isolation method of the starting material. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:-------------------------------------------------------|:--------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for each run. | | +| title | mandatory | Short text that can be used to call out sample records in search results or in displays. | | +| taxon_id | mandatory | Ncbi taxonomy identifier. this is appropriate for individual organisms and some environmental samples. | | +| sample_description | optional | Free-form text describing the sample, its origin, and its method of isolation. | | +| trophic level | optional | Trophic levels are the feeding position in a food chain. microbes can be a range of producers (e.g. chemolithotroph) | autotroph, carboxydotroph, chemoautotroph, chemoheterotroph, chemolithoautotroph, chemolithotroph, chemoorganoheterotroph, chemoorganotroph, chemosynthetic, chemotroph, copiotroph, diazotroph, facultative autotroph, heterotroph, lithoautotroph, lithoheterotroph, lithotroph, methanotroph, methylotroph, mixotroph, obligate chemoautolithotroph, oligotroph, organoheterotroph, organotroph, photoautotroph, photoheterotroph, photolithoautotroph, photolithotroph, photosynthetic, phototroph | +| observed biotic relationship | optional | Description of relationship(s) between the subject organism and other organism(s) it is associated with. e.g., parasite on species x; mutualist with species y. the target organism is the subject of the relationship, and the other organism(s) is the object. | commensal, free living, mutualism, parasite, symbiont | +| known pathogenicity | optional | To what is the entity pathogenic, for instance plant, fungi, bacteria | | +| relationship to oxygen | optional | Is this organism an aerobe, anaerobe? please note that aerobic and anaerobic are valid descriptors for microbial environments | aerobe, anaerobe, facultative, microaerophilic, microanaerobe, obligate aerobe, obligate anaerobe | +| propagation | optional | The type of reproduction from the parent stock. values for this field is specific to different taxa. for phage or virus: lytic/lysogenic/temperate/obligately lytic. for plasmids: incompatibility group. for eukaryotes: sexual/asexual. mandatory for migs of eukayotes, plasmids and viruses. | | +| host of the symbiont role | optional | Role of the host in the life cycle of the symbiotic organism. | | +| sample symbiont of | optional | Reference to host sample from symbiont. the referenced sample should already be registered in insdc. e.g. ersxxxxxx | | +| sample collection method | optional | The method employed for collecting the sample. can be provided in the form of a pmid, doi, url or text. | | +| sample storage temperature | optional | Temperature at which sample was stored, e.g. -80 (Units: °C) | | +| sample storage location | optional | Location at which sample was stored, usually name of a specific freezer/room. indicate the location name. | | +| sample storage solution | optional | Solution within which sample was stored, if any. | | +| oxygenation status of sample | optional | Oxygenation status of sample | aerobic, anaerobic | +| project name | optional | Name of the project within which the sequencing was organized | | +| ploidy | optional | The ploidy level of the genome (e.g. allopolyploid, haploid, diploid, triploid, tetraploid). it has implications for the downstream study of duplicated gene and regions of the genomes (and perhaps for difficulties in assembly). for terms, please select terms listed under class ploidy (pato:001374) of phenotypic quality ontology (pato), and for a browser of pato (v 2018-03-27) please refer to http://purl.bioontology.org/ontology/pato | | +| number of replicons | optional | Reports the number of replicons in a nuclear genome of eukaryotes, in the genome of a bacterium or archaea or the number of segments in a segmented virus. always applied to the haploid chromosome count of a eukaryote. mandatory for migs of eukaryotes, bacteria, archaea and segmented virus. | | +| extrachromosomal elements | optional | Do plasmids exist of significant phenotypic consequence (e.g. ones that determine virulence or antibiotic resistance). megaplasmids? other plasmids (borrelia has 15+ plasmids). | | +| estimated size | optional | The estimated size of the genome (in bp) prior to sequencing. of particular importance in the sequencing of (eukaryotic) genome which could remain in draft form for a long or unspecified period. mandatory for migs of eukaryotes. | | +| target gene | optional | Targeted gene or locus name for marker gene studies | | +| target subfragment | optional | Name of subfragment of a gene or locus. important to e.g. identify special regions on marker genes like v6 on 16s rrna | | +| multiplex identifiers | optional | Molecular barcodes, called multiplex identifiers (mids), that are used to specifically tag unique samples in a sequencing run. sequence should be reported in uppercase letters | | +| sequence quality check | optional | Indicate if the sequence has been called by automatic systems (none) or undergone a manual editing procedure (e.g. by inspecting the raw data or chromatograms). applied only for sequences that are not submitted to sra or dra | manual, none, software | +| chimera check software | optional | Tool(s) used for chimera checking, including version number and parameters, to discover and remove chimeric sequences. a chimeric sequence is comprised of two or more phylogenetically distinct parent sequences. | | +| relevant electronic resources | optional | A related resource that is referenced, cited, or otherwise associated to the sequence in the format of a pmid, doi or url | | +| relevant standard operating procedures | optional | Standard operating procedures used in assembly and/or annotation of genomes, metagenomes or environmental sequences in the format of a pmid, doi or url | | +| 16s recovered | optional | Can a 16s gene be recovered from the submitted bin, sag or mag? | No, Yes | +| 16S recovery software | optional | Tools used for 16s rrna gene extraction. add names and versions of software(s), parameters used | | +| collection date | optional | The date the sample was collected with the intention of sequencing, either as an instance (single point in time) or interval. in case no exact time is available, the date/time can be right truncated i.e. all of these are valid iso8601 compliant times: 2008-01-23t19:23:10+00:00; 2008-01-23t19:23:10; 2008-01-23; 2008-01; 2008. | | +| altitude | optional | The altitude of the sample is the vertical distance between earth's surface above sea level and the sampled position in the air. (Units: m) | | +| geographic location (country and/or sea) | optional | The geographical origin of where the sample was collected from, with the intention of sequencing, as defined by the country or sea name. country or sea names should be chosen from the insdc country list (http://insdc.org/country.html). | Afghanistan, Albania, Algeria, American Samoa, Andorra, Angola, Anguilla, Antarctica, Antigua and Barbuda, Arctic Ocean, Argentina, Armenia, Aruba, Ashmore and Cartier Islands, Atlantic Ocean, Australia, Austria, Azerbaijan, Bahamas, Bahrain, Baker Island, Baltic Sea, Bangladesh, Barbados, Bassas da India, Belarus, Belgium, Belize, Benin, Bermuda, Bhutan, Bolivia, Borneo, Bosnia and Herzegovina, Botswana, Bouvet Island, Brazil, British Virgin Islands, Brunei, Bulgaria, Burkina Faso, Burundi, Cambodia, Cameroon, Canada, Cape Verde, Cayman Islands, Central African Republic, Chad, Chile, China, Christmas Island, Clipperton Island, Cocos Islands, Colombia, Comoros, Cook Islands, Coral Sea Islands, Costa Rica, Cote d'Ivoire, Croatia, Cuba, Curacao, Cyprus, Czechia, Czech Republic, Democratic Republic of the Congo, Denmark, Djibouti, Dominica, Dominican Republic, East Timor, Ecuador, Egypt, El Salvador, Equatorial Guinea, Eritrea, Estonia, Ethiopia, Europa Island, Falkland Islands (Islas Malvinas), Faroe Islands, Fiji, Finland, France, French Guiana, French Polynesia, French Southern and Antarctic Lands, Gabon, Gambia, Gaza Strip, Georgia, Germany, Ghana, Gibraltar, Glorioso Islands, Greece, Greenland, Grenada, Guadeloupe, Guam, Guatemala, Guernsey, Guinea, Guinea-Bissau, Guyana, Haiti, Heard Island and McDonald Islands, Honduras, Hong Kong, Howland Island, Hungary, Iceland, India, Indian Ocean, Indonesia, Iran, Iraq, Ireland, Isle of Man, Israel, Italy, Jamaica, Jan Mayen, Japan, Jarvis Island, Jersey, Johnston Atoll, Jordan, Juan de Nova Island, Kazakhstan, Kenya, Kerguelen Archipelago, Kingman Reef, Kiribati, Kosovo, Kuwait, Kyrgyzstan, Laos, Latvia, Lebanon, Lesotho, Liberia, Libya, Liechtenstein, Lithuania, Luxembourg, Macau, Macedonia, Madagascar, Malawi, Malaysia, Maldives, Mali, Malta, Marshall Islands, Martinique, Mauritania, Mauritius, Mayotte, Mediterranean Sea, Mexico, Micronesia, Midway Islands, Moldova, Monaco, Mongolia, Montenegro, Montserrat, Morocco, Mozambique, Myanmar, Namibia, Nauru, Navassa Island, Nepal, Netherlands, New Caledonia, New Zealand, Nicaragua, Niger, Nigeria, Niue, Norfolk Island, North Korea, North Sea, Northern Mariana Islands, Norway, Oman, Pacific Ocean, Pakistan, Palau, Palmyra Atoll, Panama, Papua New Guinea, Paracel Islands, Paraguay, Peru, Philippines, Pitcairn Islands, Poland, Portugal, Puerto Rico, Qatar, Republic of the Congo, Reunion, Romania, Ross Sea, Russia, Rwanda, Saint Helena, Saint Kitts and Nevis, Saint Lucia, Saint Pierre and Miquelon, Saint Vincent and the Grenadines, Samoa, San Marino, Sao Tome and Principe, Saudi Arabia, Senegal, Serbia, Seychelles, Sierra Leone, Singapore, Sint Maarten, Slovakia, Slovenia, Solomon Islands, Somalia, South Africa, South Georgia and the South Sandwich Islands, South Korea, Southern Ocean, Spain, Spratly Islands, Sri Lanka, Sudan, Suriname, Svalbard, Swaziland, Sweden, Switzerland, Syria, Taiwan, Tajikistan, Tanzania, Tasman Sea, Thailand, Togo, Tokelau, Tonga, Trinidad and Tobago, Tromelin Island, Tunisia, Turkey, Turkmenistan, Turks and Caicos Islands, Tuvalu, USA, Uganda, Ukraine, United Arab Emirates, United Kingdom, Uruguay, Uzbekistan, Vanuatu, Venezuela, Viet Nam, Virgin Islands, Wake Island, Wallis and Futuna, West Bank, Western Sahara, Yemen, Zambia, Zimbabwe, missing: control sample, missing: data agreement established pre-2023, missing: endangered species, missing: human-identifiable, missing: lab stock, missing: sample group, missing: synthetic construct, missing: third party data, not applicable, not collected, not provided, restricted access | +| geographic location (latitude) | optional | The geographical origin of the sample as defined by latitude. the values should be reported in decimal degrees and in wgs84 system (Units: DD) | | +| geographic location (longitude) | optional | The geographical origin of the sample as defined by longitude. the values should be reported in decimal degrees and in wgs84 system (Units: DD) | | +| geographic location (region and locality) | optional | The geographical origin of the sample as defined by the specific region name followed by the locality name. | | +| broad-scale environmental context | optional | Report the major environmental system the sample or specimen came from. the system(s) identified should have a coarse spatial grain, to provide the general environmental context of where the sampling was done (e.g. in the desert or a rainforest). we recommend using subclasses of envo’s biome class: http://purl.obolibrary.org/obo/envo_00000428. envo documentation about how to use the field: https://github.com/environmentontology/envo/wiki/using-envo-with-mixs. | | +| local environmental context | optional | Report the entity or entities which are in the sample or specimen’s local vicinity and which you believe have significant causal influences on your sample or specimen. we recommend using envo terms which are of smaller spatial grain than your entry for "broad-scale environmental context". terms, such as anatomical sites, from other obo library ontologies which interoperate with envo (e.g. uberon) are accepted in this field. envo documentation about how to use the field: https://github.com/environmentontology/envo/wiki/using-envo-with-mixs. | | +| environmental medium | optional | Report the environmental material(s) immediately surrounding the sample or specimen at the time of sampling. we recommend using subclasses of 'environmental material' (http://purl.obolibrary.org/obo/envo_00010483). envo documentation about how to use the field: https://github.com/environmentontology/envo/wiki/using-envo-with-mixs . terms from other obo ontologies are permissible as long as they reference mass/volume nouns (e.g. air, water, blood) and not discrete, countable entities (e.g. a tree, a leaf, a table top). | | +| elevation | optional | The elevation of the sampling site as measured by the vertical distance from mean sea level. (Units: m) | | +| amount or size of sample collected | optional | The total amount or size (volume (ml), mass (g) or area (m2) ) of sample collected. (Units: m3) | | +| organism count | optional | Total cell count of any organism (or group of organisms) per gram, volume or area of sample, should include name of organism followed by count. the method that was used for the enumeration (e.g. qpcr, atp, mpn, etc.) should also be provided. (example: total prokaryotes; 3.5e7 cells per ml; qpcr) | | +| sample storage duration | optional | Duration for which the sample was stored. indicate the duration for which the sample was stored written in iso 8601 format. | | +| host disease status | optional | List of diseases with which the host has been diagnosed; can include multiple diagnoses. the value of the field depends on host; for humans the terms should be chosen from do (disease ontology) at http://www.disease-ontology.org, other hosts are free text | | +| host of the symbiotic host disease status | optional | List of diseases with which the host of the symbiotic host organism has been diagnosed; can include multiple diagnoses. the value of the field depends on host; for humans the terms should be chosen from the do (human disease ontology) at https://www.disease-ontology.org, non-human host diseases are free text. | | +| host common name | optional | Common name of the host, e.g. human | | +| host subject id | optional | A unique identifier by which each subject can be referred to, de-identified, e.g. #131 | | +| host age | optional | Age of host at the time of sampling; relevant scale depends on species and study, e.g. could be seconds for amoebae or centuries for trees (Units: years) | | +| host taxid | optional | Ncbi taxon id of the host, e.g. 9606 | | +| host body habitat | optional | Original body habitat where the sample was obtained from | | +| host body site | optional | Name of body site where the sample was obtained from, such as a specific organ or tissue (tongue, lung etc...). for foundational model of anatomy ontology (fma) (v 3.1) terms, please see http://purl.bioontology.org/ontology/fma | | +| host life stage | optional | Description of life stage of host | | +| host height | optional | The height of subject (Units: mm) | | +| host length | optional | The length of subject (Units: mm) | | +| host growth conditions | optional | Literature reference giving growth conditions of the host | | +| host substrate | optional | The growth substrate of the host | | +| host total mass | optional | Total mass of the host at collection, the unit depends on host (Units: kg) | | +| host infra-specific name | optional | Taxonomic information about the host below subspecies level | | +| host infra-specific rank | optional | Taxonomic rank information about the host below subspecies level, such as variety, form, rank etc. | | +| host phenotype | optional | Phenotype of host. for phenotypic quality ontology (pato) (v 2013-10-28) terms, please see http://purl.bioontology.org/ontology/pato | | +| host color | optional | The color of host | | +| host shape | optional | Morphological shape of host | | +| host sex | optional | Gender or sex of the host. | female, hermaphrodite, male, missing: control sample, missing: data agreement established pre-2023, missing: endangered species, missing: human-identifiable, missing: lab stock, missing: sample group, missing: synthetic construct, missing: third party data, neuter, not applicable, not collected, not provided, other, restricted access | +| host scientific name | optional | Scientific name of the natural (as opposed to laboratory) host to the organism from which sample was obtained. | | +| host of the symbiotic host subject id | optional | A unique identifier by which each host of the symbiotic host organism subject can be referred to, de-identified, e.g. #h14. (Units: year) | | +| host of the symbiotic host taxon id | optional | Ncbi taxon id of the host of the symbiotic host organism. | | +| duration of association with the host | optional | Time spent in host of the symbiotic organism at the time of sampling; relevant scale depends on symbiotic organism and study. (Units: year) | | +| temperature | optional | Temperature of the sample at time of sampling (Units: ºC) | | +| sample salinity | optional | Salinity is the total concentration of all dissolved salts in a liquid or solid (in the form of an extract obtained by centrifugation) sample. while salinity can be measured by a complete chemical analysis, this method is difficult and time consuming. more often, it is instead derived from the conductivity measurement. this is known as practical salinity. these derivations compare the specific conductance of the sample to a salinity standard such as seawater (Units: psu) | | +| source material identifiers | optional | A unique identifier assigned to a material sample (as defined by http://rs.tdwg.org/dwc/terms/materialsampleid, and as opposed to a particular digital record of a material sample) used for extracting nucleic acids, and subsequent sequencing. the identifier can refer either to the original material collected or to any derived sub-samples. the insdc qualifiers /specimen_voucher, /bio_material, or /culture_collection may or may not share the same value as the source_mat_id field. for instance, the /specimen_voucher qualifier and source_mat_id may both contain 'uam:herps:14' , referring to both the specimen voucher and sampled tissue with the same identifier. however, the /culture_collection qualifier may refer to a value from an initial culture (e.g. atcc:11775) while source_mat_id would refer to an identifier from some derived culture from which the nucleic acids were extracted (e.g. xatc123 or ark:/2154/r2). | | +| host family relationship | optional | Familial relationships to other hosts in the same study; can include multiple relationships | | +| host genotype | optional | Observed genotype | | +| gravidity | optional | Whether or not the subject is gravid. if so, report date due or date post-conception and specify which of these two dates is being reported. | | +| host specificity or range | optional | The range and diversity of host species that an organism is capable of infecting, defined by ncbi taxonomy identifier. | | +| host of the symbiotic host phenotype | optional | Phenotype of the host of the symbiotic host organism. for phenotypic quality ontology (pato) terms, see http://purl.bioontology.org/ontology/pato. | | +| mode of transmission | optional | The process through which the symbiotic host organism entered the host from which it was sampled. | | +| symbiotic host organism life cycle type | optional | Type of life cycle of the symbiotic host species (the thing being sampled). simple life cycles occur within a single host, complex ones within multiple different hosts over the course of their normal life cycle. | | +| host specificity | optional | Level of specificity of symbiont-host interaction: e.g. generalist (symbiont able to establish associations with distantly related hosts) or species-specific. | | +| host cellular location | optional | The localization of the symbiotic host organism within the host from which it was sampled: e.g. intracellular if the symbiotic host organism is localized within the cells or extracellular if the symbiotic host organism is localized outside of cells. (Units: %) | | +| host of the symbiotic host infra-specific rank | optional | Taxonomic rank information about the host of the symbiotic host organism below subspecies level, such as variety, form, rank etc. (Units: °C) | | +| type of symbiosis | optional | Type of biological interaction established between the symbiotic host organism being sampled and its respective host (Units: °C) | | +| observed coinfecting organisms in host of host | optional | The taxonomic name of any coinfecting organism observed in a symbiotic relationship with the host of the sampled host organism. e.g. where a sample collected from a host trematode species (a) which was collected from a host_of_host fish (b) that was also infected with a nematode (c), the value here would be (c) the nematode {species name} or {common name}. multiple co-infecting species may be added in a comma-separated list. for listing symbiotic organisms associated with the host (a) use the term observed host symbiont. (Units: year) | | +| host of the symbiotic host infra-specific name | optional | Taxonomic name information of the host of the symbiotic host organism below subspecies level. (Units: year) | | +| host of the symbiotic host total mass | optional | Total mass of the host of the symbiotic host organism at collection, the unit depends on the host. (Units: µg) | | +| host of the symbiotic host local environmental context | optional | For a symbiotic host organism the local anatomical environment within its host may have causal influences. report the anatomical entity(s) which are in the direct environment of the symbiotic host organism being sampled and which you believe have significant causal influences on your sample or specimen. for example, if the symbiotic host organism being sampled is an intestinal worm, its local environmental context will be the term for intestine from uberon (http://uberon.github.io/). (Units: g/m3) | | +| host of the symbiotic host common name | optional | Common name of the host of the symbiotic host organism. (Units: °C) | | +| host of the symbiotic host genotype | optional | Observed genotype of the host of the symbiotic host organism. (Units: year) | | +| route of transmission | optional | Description of path taken by the symbiotic host organism being sampled in order to establish a symbiotic relationship with the host (with which it was observed at the time of sampling) via a mode of transmission (specified in mode_transmission). (Units: mm) | | +| host dry mass | optional | Measurement of dry mass (Units: mg) | | +| host body product | optional | Substance produced by the body, e.g. stool, mucus, where the sample was obtained from. for foundational model of anatomy ontology (fma) (v 3.1) terms, please see http://purl.bioontology.org/ontology/fma | | +| host number individual | optional | Number of symbiotic host individuals pooled at the time of collection. | | +| perturbation | optional | Type of perturbation, e.g. chemical administration, physical disturbance, etc., coupled with time that perturbation occurred; can include multiple perturbation types | | +| negative control type | optional | The substance or equipment used as a negative control in an investigation | | +| positive control type | optional | The substance, mixture, product, or apparatus used to verify that a process which is part of an investigation delivers a true positive. | | +| experimental factor | optional | Experimental factors are essentially the variable aspects of an experiment design which can be used to describe an experiment, or set of experiments, in an increasingly detailed manner. this field accepts ontology terms from experimental factor ontology (efo) and/or ontology for biomedical investigations (obi). for a browser of efo (v 2.95) terms, please see http://purl.bioontology.org/ontology/efo; for a browser of obi (v 2018-02-12) terms please see http://purl.bioontology.org/ontology/obi. e.g. time series design [efo:efo_0001779] | | +| encoded traits | optional | Should include key traits like antibiotic resistance or xenobiotic degradation phenotypes for plasmids, converting genes for phage | | +| subspecific genetic lineage | optional | Information about the genetic distinctness of the sequenced organism below the subspecies level, e.g., serovar, serotype, biotype, ecotype, or any relevant genetic typing schemes like group i plasmid. subspecies should not be recorded in this term, but in the ncbi taxonomy. supply both the lineage name and the lineage rank separated by a colon, e.g., biovar:abc123. | | +| taxonomic classification | optional | Method used for taxonomic classification, along with reference database used, classification rank, and thresholds used to classify new genomes. expected values are: classification method, database name, and other parameters e.g. vcontact vcontact2 (references from ncbi refseq v83, genus rank classification, default parameters) | | +| isolation and growth condition | optional | Publication reference in the form of pubmed id (pmid), digital object identifier (doi) or url for isolation and growth condition specifications of the organism/material. mandatory for migs and mimarks specimen. | | +| annotation source | optional | For cases where annotation was provided by a community jamboree or model organism database rather than by a specific submitter | | +| reference for biomaterial | optional | Primary publication if isolated before genome publication; otherwise, primary genome report. mandatory for migs of bacteria and archaea. | | +| single cell or viral particle lysis approach | optional | Method used to free dna from interior of the cell(s) or particle(s) | chemical, combination, enzymatic, physical | +| single cell or viral particle lysis kit protocol | optional | Name of the kit or standard protocol used for cell(s) or particle(s) lysis | | +| sample material processing | optional | A brief description of any processing applied to the sample during or after retrieving the sample from environment, or a link to the relevant protocol(s) performed. | | +| sample volume or weight for DNA extraction | optional | Volume (ml) or mass (g) of total collected sample processed for dna extraction. note: total sample collected should be entered under the term 'sample size'. (Units: ng) | | +| nucleic acid extraction | optional | A link to a literature reference, electronic resource or a standard operating procedure (sop), that describes the material separation to recover the nucleic acid fraction from a sample | | +| nucleic acid amplification | optional | A link to a literature reference, electronic resource or a standard operating procedure (sop), that describes the enzymatic amplification (pcr, tma, nasba) of specific nucleic acids | | +| library size | optional | Total number of clones in the library prepared for the project | | +| library reads sequenced | optional | Total number of clones sequenced from the library | | +| library vector | optional | Cloning vector type(s) used in construction of libraries | | +| library screening strategy | optional | Specific enrichment or screening methods applied before and/or after creating clone libraries in order to select a specific group of sequences | | +| pcr conditions | optional | Description of reaction conditions and components for pcr in the form of 'initial denaturation:94degc_1.5min; annealing=...' | | +| pcr primers | optional | Pcr primers that were used to amplify the sequence of the targeted gene, locus or subfragment. this field should contain all the primers used for a single pcr reaction if multiple forward or reverse primers are present in a single pcr reaction. the primer sequence should be reported in uppercase letters | | +| adapters | optional | Adapters provide priming sequences for both amplification and sequencing of the sample-library fragments. both adapters should be reported; in uppercase letters | | +| depth | optional | The vertical distance below local surface, e.g. for sediment or soil samples depth is measured from sediment or soil surface, respectively. depth can be reported as an interval for subsurface samples. (Units: mm) | | +| chemical administration | optional | List of chemical compounds administered to the host or site where sampling occurred, and when (e.g. antibiotics, n fertilizer, air filter); can include multiple compounds. for chemical entities of biological interest ontology (chebi) (v111), please see http://purl.bioontology.org/ontology/chebi | | + diff --git a/templates/ERC000057/experiment.tsv b/templates/ERC000057/experiment.tsv new file mode 100644 index 0000000..55beb83 --- /dev/null +++ b/templates/ERC000057/experiment.tsv @@ -0,0 +1 @@ +"alias" "title" "study_alias" "sample_alias" "design_description" "library_name" "library_strategy" "library_source" "library_selection" "library_layout" "insert_size" "library_construction_protocol" "platform" "instrument_model" diff --git a/templates/ERC000057/metadata_template_ERC000057.xlsx b/templates/ERC000057/metadata_template_ERC000057.xlsx new file mode 100644 index 0000000..8309ed1 Binary files /dev/null and b/templates/ERC000057/metadata_template_ERC000057.xlsx differ diff --git a/templates/ERC000057/run.tsv b/templates/ERC000057/run.tsv new file mode 100644 index 0000000..e752173 --- /dev/null +++ b/templates/ERC000057/run.tsv @@ -0,0 +1 @@ +"alias" "experiment_alias" "file_name" "file_format" diff --git a/templates/ERC000057/sample.tsv b/templates/ERC000057/sample.tsv new file mode 100644 index 0000000..d2ed94a --- /dev/null +++ b/templates/ERC000057/sample.tsv @@ -0,0 +1 @@ +"alias" "title" "taxon_id" "sample_description" "trophic level" "observed biotic relationship" "known pathogenicity" "relationship to oxygen" "propagation" "host of the symbiont role" "sample symbiont of" "sample collection method" "sample storage temperature" "sample storage location" "sample storage solution" "oxygenation status of sample" "project name" "ploidy" "number of replicons" "extrachromosomal elements" "estimated size" "target gene" "target subfragment" "multiplex identifiers" "sequence quality check" "chimera check software" "relevant electronic resources" "relevant standard operating procedures" "16s recovered" "16S recovery software" "collection date" "altitude" "geographic location (country and/or sea)" "geographic location (latitude)" "geographic location (longitude)" "geographic location (region and locality)" "broad-scale environmental context" "local environmental context" "environmental medium" "elevation" "amount or size of sample collected" "organism count" "sample storage duration" "host disease status" "host of the symbiotic host disease status" "host common name" "host subject id" "host age" "host taxid" "host body habitat" "host body site" "host life stage" "host height" "host length" "host growth conditions" "host substrate" "host total mass" "host infra-specific name" "host infra-specific rank" "host phenotype" "host color" "host shape" "host sex" "host scientific name" "host of the symbiotic host subject id" "host of the symbiotic host taxon id" "duration of association with the host" "temperature" "sample salinity" "source material identifiers" "host family relationship" "host genotype" "gravidity" "host specificity or range" "host of the symbiotic host phenotype" "mode of transmission" "symbiotic host organism life cycle type" "host specificity" "host cellular location" "host of the symbiotic host infra-specific rank" "type of symbiosis" "observed coinfecting organisms in host of host" "host of the symbiotic host infra-specific name" "host of the symbiotic host total mass" "host of the symbiotic host local environmental context" "host of the symbiotic host common name" "host of the symbiotic host genotype" "route of transmission" "host dry mass" "host body product" "host number individual" "perturbation" "negative control type" "positive control type" "experimental factor" "encoded traits" "subspecific genetic lineage" "taxonomic classification" "isolation and growth condition" "annotation source" "reference for biomaterial" "single cell or viral particle lysis approach" "single cell or viral particle lysis kit protocol" "sample material processing" "sample volume or weight for DNA extraction" "nucleic acid extraction" "nucleic acid amplification" "library size" "library reads sequenced" "library vector" "library screening strategy" "pcr conditions" "pcr primers" "adapters" "depth" "chemical administration" diff --git a/templates/ERC000057/study.tsv b/templates/ERC000057/study.tsv new file mode 100644 index 0000000..fd9fd79 --- /dev/null +++ b/templates/ERC000057/study.tsv @@ -0,0 +1 @@ +"alias" "title" "study_type" "new_study_type" "study_abstract" diff --git a/templates/ERC000058/ERC000058.json b/templates/ERC000058/ERC000058.json new file mode 100644 index 0000000..918c700 --- /dev/null +++ b/templates/ERC000058/ERC000058.json @@ -0,0 +1,2173 @@ +{ + "study": { + "description": "A Study is a container for a sequencing investigation that may comprise multiple experiments. The Study has an overall goal, but is otherwise minimally defined in the SRA. A Study is composed of a descriptor, zero or more experiments, and zero or more analyses. The submitter may decorate the Study with web links and properties.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for a study. This is used to link experiments to the study.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "title", + "cardinality": "mandatory", + "description": "Title of the study as would be used in a publication.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "study_type", + "cardinality": "mandatory", + "description": "The STUDY_TYPE presents a controlled vocabulary for expressing the overall purpose of the study.", + "units": "", + "regex": "", + "cv": [ + "Whole Genome Sequencing", + "Metagenomics", + "Transcriptome Analysis", + "Resequencing", + "Epigenetics", + "Synthetic Genomics", + "Forensic or Paleo-genomics", + "Gene Regulation Study", + "Cancer Genomics", + "Population Genomics", + "RNASeq", + "Exome Sequencing", + "Pooled Clone Sequencing", + "Transcriptome Sequencing", + "Other" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "new_study_type", + "cardinality": "optional", + "description": "Optional if 'study_type' is not 'other'. To propose a new term, select Other and enter a new study type.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "study_abstract", + "cardinality": "optional", + "description": "Briefly describes the goals, purpose, and scope of the Study. This need not be listed if it can be inherited from a referenced publication.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_AREA_FIELD" + } + ] + }, + "experiment": { + "description": "An experiment object serves as a metadata record encapsulating essential details about a sequencing experiment, including the experimental design, sequencing type, and relevant parameters. This information enhances the interpretation and contextual understanding of nucleotide sequences submitted to the archive.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for each experiment. This is used to link runs to experiments.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "title", + "cardinality": "optional", + "description": "Short text that can be used to call out experiment records in searches or in displays. This element is technically optional but should be used for all new records.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "study_alias", + "cardinality": "mandatory", + "description": "Identifies the parent study. (From study metadata)", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "sample_alias", + "cardinality": "mandatory", + "description": "(From sample metadata)", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "design_description", + "cardinality": "optional", + "description": "Goal and setup of the individual library including library was constructed.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_AREA_FIELD" + }, + { + "name": "library_name", + "cardinality": "optional", + "description": "The submitter's name for this library.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "library_strategy", + "cardinality": "mandatory", + "description": "Sequencing technique intended for this library.", + "units": "", + "regex": "", + "cv": [ + "WGS", + "WGA", + "WXS", + "RNA-Seq", + "ssRNA-seq", + "snRNA-seq", + "miRNA-Seq", + "ncRNA-Seq", + "FL-cDNA", + "EST", + "Hi-C", + "ATAC-seq", + "WCS", + "RAD-Seq", + "CLONE", + "POOLCLONE", + "AMPLICON", + "CLONEEND", + "FINISHING", + "ChIP-Seq", + "MNase-Seq", + "DNase-Hypersensitivity", + "Bisulfite-Seq", + "CTS", + "MRE-Seq", + "MeDIP-Seq", + "MBD-Seq", + "Tn-Seq", + "VALIDATION", + "FAIRE-seq", + "SELEX", + "RIP-Seq", + "ChIA-PET", + "Synthetic-Long-Read", + "Targeted-Capture", + "Tethered Chromatin Conformation Capture", + "NOMe-Seq", + "ChM-Seq", + "GBS", + "Ribo-Seq", + "OTHER" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "library_source", + "cardinality": "mandatory", + "description": "The LIBRARY_SOURCE specifies the type of source material that is being sequenced.", + "units": "", + "regex": "", + "cv": [ + "GENOMIC", + "GENOMIC SINGLE CELL", + "TRANSCRIPTOMIC", + "TRANSCRIPTOMIC SINGLE CELL", + "METAGENOMIC", + "METATRANSCRIPTOMIC", + "SYNTHETIC", + "VIRAL RNA", + "OTHER" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "library_selection", + "cardinality": "mandatory", + "description": "Method used to enrich the target in the sequence library preparation", + "units": "", + "regex": "", + "cv": [ + "RANDOM", + "PCR", + "RANDOM PCR", + "RT-PCR", + "HMPR", + "MF", + "repeat fractionation", + "size fractionation", + "MSLL", + "cDNA", + "cDNA_randomPriming", + "cDNA_oligo_dT", + "PolyA", + "Oligo-dT", + "Inverse rRNA", + "Inverse rRNA selection", + "ChIP", + "ChIP-Seq", + "MNase", + "DNase", + "Hybrid Selection", + "Reduced Representation", + "Restriction Digest", + "5-methylcytidine antibody", + "MBD2 protein methyl-CpG binding domain", + "CAGE", + "RACE", + "MDA", + "padlock probes capture method", + "other", + "unspecified" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "library_layout", + "cardinality": "mandatory", + "description": "LIBRARY_LAYOUT specifies whether to expect single, paired, or other configuration of reads. In the case of paired reads, information about the relative distance and orientation is specified.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "insert_size", + "cardinality": "optional", + "description": "Insert size for paired reads", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "library_construction_protocol", + "cardinality": "optional", + "description": "Free form text describing the protocol by which the sequencing library was constructed.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "platform", + "cardinality": "mandatory", + "description": "The PLATFORM record selects which sequencing platform and platform-specific runtime parameters. This will be determined by the Center. optional if 'instrument_model' is provided.", + "units": "", + "regex": "", + "cv": [ + "LS454", + "ILLUMINA", + "HELICOS", + "ABI_SOLID", + "COMPLETE_GENOMICS", + "BGISEQ", + "OXFORD_NANOPORE", + "PACBIO_SMRT", + "ION_TORRENT", + "CAPILLARY", + "DNBSEQ", + "ELEMENT", + "ULTIMA", + "VELA_DIAGNOSTICS", + "GENAPSYS", + "GENEMIND", + "TAPESTRI" + ], + "field_type": "TEXT_CHOICE_FIELD" + }, + { + "name": "instrument_model", + "cardinality": "mandatory", + "description": "Model of the sequencing instrument.", + "units": "", + "regex": "", + "cv": [ + "454 GS", + "454 GS 20", + "454 GS FLX", + "454 GS FLX Titanium", + "454 GS FLX+", + "454 GS Junior", + "AB 310 Genetic Analyzer", + "AB 3130 Genetic Analyzer", + "AB 3130xL Genetic Analyzer", + "AB 3500 Genetic Analyzer", + "AB 3500xL Genetic Analyzer", + "AB 3730 Genetic Analyzer", + "AB 3730xL Genetic Analyzer", + "AB 5500 Genetic Analyzer", + "AB 5500xl Genetic Analyzer", + "AB 5500xl-W Genetic Analysis System", + "AB SOLiD 3 Plus System", + "AB SOLiD 4 System", + "AB SOLiD 4hq System", + "AB SOLiD PI System", + "AB SOLiD System", + "AB SOLiD System 2.0", + "AB SOLiD System 3.0", + "BGISEQ-50", + "BGISEQ-500", + "Complete Genomics", + "DNBSEQ-G400", + "DNBSEQ-G400 FAST", + "DNBSEQ-G50", + "DNBSEQ-T7", + "Element AVITI", + "FASTASeq 300", + "GENIUS", + "GS111", + "Genapsys Sequencer", + "GenoCare 1600", + "GenoLab M", + "GridION", + "Helicos HeliScope", + "HiSeq X Five", + "HiSeq X Ten", + "Illumina Genome Analyzer", + "Illumina Genome Analyzer II", + "Illumina Genome Analyzer IIx", + "Illumina HiScanSQ", + "Illumina HiSeq 1000", + "Illumina HiSeq 1500", + "Illumina HiSeq 2000", + "Illumina HiSeq 2500", + "Illumina HiSeq 3000", + "Illumina HiSeq 4000", + "Illumina HiSeq X", + "Illumina MiSeq", + "Illumina MiniSeq", + "Illumina NovaSeq 6000", + "Illumina NovaSeq X", + "Illumina iSeq 100", + "Ion GeneStudio S5", + "Ion GeneStudio S5 Plus", + "Ion GeneStudio S5 Prime", + "Ion Torrent Genexus", + "Ion Torrent PGM", + "Ion Torrent Proton", + "Ion Torrent S5", + "Ion Torrent S5 XL", + "MGISEQ-2000RS", + "MinION", + "NextSeq 1000", + "NextSeq 2000", + "NextSeq 500", + "NextSeq 550", + "Onso", + "PacBio RS", + "PacBio RS II", + "PromethION", + "Revio", + "Sentosa SQ301", + "Sequel", + "Sequel II", + "Sequel IIe", + "Tapestri", + "UG 100", + "unspecified" + ], + "field_type": "TEXT_CHOICE_FIELD" + } + ] + }, + "run": { + "description": "A run contains a group of reads generated for a particular experiment.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for each run.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "experiment_alias", + "cardinality": "mandatory", + "description": "From_experiment_metadata", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "file_name", + "cardinality": "mandatory", + "description": "The name or relative pathname of a run data file.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "file_format", + "cardinality": "mandatory", + "description": "The run data file model.", + "units": "", + "regex": "", + "cv": [ + "sra", + "srf", + "sff", + "fastq", + "fasta", + "tab", + "454_native", + "454_native_seq", + "454_native_qual", + "Helicos_native", + "Illumina_native", + "Illumina_native_seq", + "Illumina_native_prb", + "Illumina_native_int", + "Illumina_native_qseq", + "Illumina_native_scarf", + "SOLiD_native", + "SOLiD_native_csfasta", + "SOLiD_native_qual", + "PacBio_HDF5", + "bam", + "cram", + "CompleteGenomics_native", + "OxfordNanopore_native" + ], + "field_type": "TEXT_CHOICE_FIELD" + } + ] + }, + "sample": { + "description": "A Sample defines an isolate of sequenceable material upon which sequencing experiments can be based. The Sample object may be a surrogate for taxonomy accession or an anonymized individual identifier. Or, it may fully specify provenance and isolation method of the starting material.", + "fields": [ + { + "name": "alias", + "cardinality": "mandatory", + "description": "Unique identificator for each run.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "title", + "cardinality": "mandatory", + "description": "Short text that can be used to call out sample records in search results or in displays.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "taxon_id", + "cardinality": "mandatory", + "description": "NCBI Taxonomy Identifier. This is appropriate for individual organisms and some environmental samples.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_FIELD" + }, + { + "name": "sample_description", + "cardinality": "optional", + "description": "Free-form text describing the sample, its origin, and its method of isolation.", + "units": "", + "regex": "", + "cv": [], + "field_type": "TEXT_AREA_FIELD" + }, + { + "name": "sample true vertical depth subsea", + "cardinality": "optional", + "description": "Depth of the sample i.e. The vertical distance between the sea level and the sampled position in the subsurface. Depth can be reported as an interval for subsurface samples e.g. 1325.75-1362.25 m", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "trophic level", + "cardinality": "optional", + "description": "Trophic levels are the feeding position in a food chain. Microbes can be a range of producers (e.g. chemolithotroph)", + "cv": [ + "autotroph", + "carboxydotroph", + "chemoautotroph", + "chemoheterotroph", + "chemolithoautotroph", + "chemolithotroph", + "chemoorganoheterotroph", + "chemoorganotroph", + "chemosynthetic", + "chemotroph", + "copiotroph", + "diazotroph", + "facultative autotroph", + "heterotroph", + "lithoautotroph", + "lithoheterotroph", + "lithotroph", + "methanotroph", + "methylotroph", + "mixotroph", + "obligate chemoautolithotroph", + "oligotroph", + "organoheterotroph", + "organotroph", + "photoautotroph", + "photoheterotroph", + "photolithoautotroph", + "photolithotroph", + "photosynthetic", + "phototroph" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "observed biotic relationship", + "cardinality": "optional", + "description": "Description of relationship(s) between the subject organism and other organism(s) it is associated with. E.g., parasite on species X; mutualist with species Y. The target organism is the subject of the relationship, and the other organism(s) is the object.", + "cv": [ + "commensal", + "free living", + "mutualism", + "parasite", + "symbiont" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "known pathogenicity", + "cardinality": "optional", + "description": "To what is the entity pathogenic, for instance plant, fungi, bacteria", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "relationship to oxygen", + "cardinality": "optional", + "description": "Is this organism an aerobe, anaerobe? Please note that aerobic and anaerobic are valid descriptors for microbial environments", + "cv": [ + "aerobe", + "anaerobe", + "facultative", + "microaerophilic", + "microanaerobe", + "obligate aerobe", + "obligate anaerobe" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "propagation", + "cardinality": "optional", + "description": "The type of reproduction from the parent stock. Values for this field is specific to different taxa. For phage or virus: lytic/lysogenic/temperate/obligately lytic. For plasmids: incompatibility group. For eukaryotes: sexual/asexual. Mandatory for MIGs of eukayotes, plasmids and viruses.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample transport conditions", + "cardinality": "optional", + "description": "Sample transport duration (in days or hrs) and temperature the sample was exposed to (e.g. 5.5 days; 20 \u00b0C)", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample collection device", + "cardinality": "optional", + "description": "The device used to collect an environmental sample. It is recommended to use terms listed under environmental sampling device (http://purl.obolibrary.org/obo/ENVO) and/or terms listed under specimen collection device (http://purl.obolibrary.org/obo/GENEPIO_0002094).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample collection method", + "cardinality": "optional", + "description": "The method employed for collecting the sample. Can be provided in the form of a PMID, DOI, url or text.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample storage temperature", + "cardinality": "optional", + "description": "temperature at which sample was stored, e.g. -80", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "sample storage location", + "cardinality": "optional", + "description": "Location at which sample was stored, usually name of a specific freezer/room. Indicate the location name.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "source rock depositional environment", + "cardinality": "optional", + "description": "Source rock depositional environment (https://en.wikipedia.org/wiki/Source_rock). If \"other\" is specified, please propose entry in \"additional info\" field", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample measured depth", + "cardinality": "optional", + "description": "In non deviated well, measured depth is equal to the true vertical depth, TVD (TVD=TVDSS plus the reference or datum it refers to). In deviated wells, the MD is the length of trajectory of the borehole measured from the same reference or datum. Common datums used are ground level (GL), drilling rig floor (DF), rotary table (RT), kelly bushing (KB) and mean sea level (MSL). If \"other\" is specified, please propose entry in \"additional info\" field", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "corrosion rate at sample location", + "cardinality": "optional", + "description": "Metal corrosion rate is the speed of metal deterioration due to environmental conditions. As environmental conditions change corrosion rates change accordingly. Therefore, long term corrosion rates are generally more informative than short term rates and for that reason they are preferred during reporting. In the case of suspected MIC, corrosion rate measurements at the time of sampling might provide insights into the involvement of certain microbial community members in MIC as well as potential microbial interplays", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample collection point", + "cardinality": "optional", + "description": "Sampling point on the asset were sample was collected (e.g. Wellhead, storage tank, separator, etc). If \"other\" is specified, please propose entry in \"additional info\" field", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "depth (tvdss) of hydrocarbon resource temperature", + "cardinality": "optional", + "description": "True vertical depth subsea (TVDSS) of the hydrocarbon resource where the original temperature was measured (e.g. 1345 m).", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "oxygenation status of sample", + "cardinality": "optional", + "description": "oxygenation status of sample", + "cv": [ + "aerobic", + "anaerobic" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "density", + "cardinality": "optional", + "description": "density of sample", + "cv": [], + "units": "g/m3", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "sample well name", + "cardinality": "optional", + "description": "Name of the well (e.g. BXA1123) where sample was taken", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "project name", + "cardinality": "optional", + "description": "Name of the project within which the sequencing was organized", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "ploidy", + "cardinality": "optional", + "description": "The ploidy level of the genome (e.g. allopolyploid, haploid, diploid, triploid, tetraploid). It has implications for the downstream study of duplicated gene and regions of the genomes (and perhaps for difficulties in assembly). For terms, please select terms listed under class ploidy (PATO:001374) of Phenotypic Quality Ontology (PATO), and for a browser of PATO (v 2018-03-27) please refer to http://purl.bioontology.org/ontology/PATO", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "number of replicons", + "cardinality": "optional", + "description": "Reports the number of replicons in a nuclear genome of eukaryotes, in the genome of a bacterium or archaea or the number of segments in a segmented virus. Always applied to the haploid chromosome count of a eukaryote. Mandatory for MIGS of eukaryotes, bacteria, archaea and segmented virus.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "extrachromosomal elements", + "cardinality": "optional", + "description": "Do plasmids exist of significant phenotypic consequence (e.g. ones that determine virulence or antibiotic resistance). Megaplasmids? Other plasmids (borrelia has 15+ plasmids).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "estimated size", + "cardinality": "optional", + "description": "The estimated size of the genome (in bp) prior to sequencing. Of particular importance in the sequencing of (eukaryotic) genome which could remain in draft form for a long or unspecified period. Mandatory for MIGS of eukaryotes.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "target gene", + "cardinality": "optional", + "description": "Targeted gene or locus name for marker gene studies", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "target subfragment", + "cardinality": "optional", + "description": "Name of subfragment of a gene or locus. Important to e.g. identify special regions on marker genes like V6 on 16S rRNA", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "multiplex identifiers", + "cardinality": "optional", + "description": "Molecular barcodes, called Multiplex Identifiers (MIDs), that are used to specifically tag unique samples in a sequencing run. Sequence should be reported in uppercase letters", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sequence quality check", + "cardinality": "optional", + "description": "Indicate if the sequence has been called by automatic systems (none) or undergone a manual editing procedure (e.g. by inspecting the raw data or chromatograms). Applied only for sequences that are not submitted to SRA or DRA", + "cv": [ + "manual", + "none", + "software" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "chimera check software", + "cardinality": "optional", + "description": "Tool(s) used for chimera checking, including version number and parameters, to discover and remove chimeric sequences. A chimeric sequence is comprised of two or more phylogenetically distinct parent sequences.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "relevant electronic resources", + "cardinality": "optional", + "description": "A related resource that is referenced, cited, or otherwise associated to the sequence in the format of a PMID, DOI or URL", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "relevant standard operating procedures", + "cardinality": "optional", + "description": "Standard operating procedures used in assembly and/or annotation of genomes, metagenomes or environmental sequences in the format of a PMID, DOI or URL", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "16s recovered", + "cardinality": "optional", + "description": "Can a 16S gene be recovered from the submitted bin, SAG or MAG?", + "cv": [ + "No", + "Yes" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "well identification number", + "cardinality": "optional", + "description": "A unique identifier of a well or wellbore. This is part of the Global Framework for Well Identification initiative which is compiled by the Professional Petroleum Data Management Association (PPDM) in an effort to improve well identification systems. (Supporting information: https://ppdm.org/ and http://dl.ppdm.org/dl/690)", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "water cut", + "cardinality": "optional", + "description": "Current amount of water (%) in a produced fluid stream; or the average of the combined streams", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "production rate", + "cardinality": "optional", + "description": "Oil and/or gas production rates per well (e.g. 524 m3 / day)", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "field name", + "cardinality": "optional", + "description": "Name of the hydrocarbon field (e.g. Albacora)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "collection date", + "cardinality": "optional", + "description": "The date the sample was collected with the intention of sequencing, either as an instance (single point in time) or interval. In case no exact time is available, the date/time can be right truncated i.e. all of these are valid ISO8601 compliant times: 2008-01-23T19:23:10+00:00; 2008-01-23T19:23:10; 2008-01-23; 2008-01; 2008.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "(^[12][0-9]{3}(-(0[1-9]|1[0-2])(-(0[1-9]|[12][0-9]|3[01])(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?(/[0-9]{4}(-[0-9]{2}(-[0-9]{2}(T[0-9]{2}:[0-9]{2}(:[0-9]{2})?Z?([+-][0-9]{1,2})?)?)?)?)?$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)" + }, + { + "name": "altitude", + "cardinality": "optional", + "description": "The altitude of the sample is the vertical distance between Earth's surface above Sea Level and the sampled position in the air.", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "((0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "geographic location (country and/or sea)", + "cardinality": "optional", + "description": "The geographical origin of where the sample was collected from, with the intention of sequencing, as defined by the country or sea name. Country or sea names should be chosen from the INSDC country list (http://insdc.org/country.html).", + "cv": [ + "Afghanistan", + "Albania", + "Algeria", + "American Samoa", + "Andorra", + "Angola", + "Anguilla", + "Antarctica", + "Antigua and Barbuda", + "Arctic Ocean", + "Argentina", + "Armenia", + "Aruba", + "Ashmore and Cartier Islands", + "Atlantic Ocean", + "Australia", + "Austria", + "Azerbaijan", + "Bahamas", + "Bahrain", + "Baker Island", + "Baltic Sea", + "Bangladesh", + "Barbados", + "Bassas da India", + "Belarus", + "Belgium", + "Belize", + "Benin", + "Bermuda", + "Bhutan", + "Bolivia", + "Borneo", + "Bosnia and Herzegovina", + "Botswana", + "Bouvet Island", + "Brazil", + "British Virgin Islands", + "Brunei", + "Bulgaria", + "Burkina Faso", + "Burundi", + "Cambodia", + "Cameroon", + "Canada", + "Cape Verde", + "Cayman Islands", + "Central African Republic", + "Chad", + "Chile", + "China", + "Christmas Island", + "Clipperton Island", + "Cocos Islands", + "Colombia", + "Comoros", + "Cook Islands", + "Coral Sea Islands", + "Costa Rica", + "Cote d'Ivoire", + "Croatia", + "Cuba", + "Curacao", + "Cyprus", + "Czechia", + "Czech Republic", + "Democratic Republic of the Congo", + "Denmark", + "Djibouti", + "Dominica", + "Dominican Republic", + "East Timor", + "Ecuador", + "Egypt", + "El Salvador", + "Equatorial Guinea", + "Eritrea", + "Estonia", + "Ethiopia", + "Europa Island", + "Falkland Islands (Islas Malvinas)", + "Faroe Islands", + "Fiji", + "Finland", + "France", + "French Guiana", + "French Polynesia", + "French Southern and Antarctic Lands", + "Gabon", + "Gambia", + "Gaza Strip", + "Georgia", + "Germany", + "Ghana", + "Gibraltar", + "Glorioso Islands", + "Greece", + "Greenland", + "Grenada", + "Guadeloupe", + "Guam", + "Guatemala", + "Guernsey", + "Guinea", + "Guinea-Bissau", + "Guyana", + "Haiti", + "Heard Island and McDonald Islands", + "Honduras", + "Hong Kong", + "Howland Island", + "Hungary", + "Iceland", + "India", + "Indian Ocean", + "Indonesia", + "Iran", + "Iraq", + "Ireland", + "Isle of Man", + "Israel", + "Italy", + "Jamaica", + "Jan Mayen", + "Japan", + "Jarvis Island", + "Jersey", + "Johnston Atoll", + "Jordan", + "Juan de Nova Island", + "Kazakhstan", + "Kenya", + "Kerguelen Archipelago", + "Kingman Reef", + "Kiribati", + "Kosovo", + "Kuwait", + "Kyrgyzstan", + "Laos", + "Latvia", + "Lebanon", + "Lesotho", + "Liberia", + "Libya", + "Liechtenstein", + "Lithuania", + "Luxembourg", + "Macau", + "Macedonia", + "Madagascar", + "Malawi", + "Malaysia", + "Maldives", + "Mali", + "Malta", + "Marshall Islands", + "Martinique", + "Mauritania", + "Mauritius", + "Mayotte", + "Mediterranean Sea", + "Mexico", + "Micronesia", + "Midway Islands", + "Moldova", + "Monaco", + "Mongolia", + "Montenegro", + "Montserrat", + "Morocco", + "Mozambique", + "Myanmar", + "Namibia", + "Nauru", + "Navassa Island", + "Nepal", + "Netherlands", + "New Caledonia", + "New Zealand", + "Nicaragua", + "Niger", + "Nigeria", + "Niue", + "Norfolk Island", + "North Korea", + "North Sea", + "Northern Mariana Islands", + "Norway", + "Oman", + "Pacific Ocean", + "Pakistan", + "Palau", + "Palmyra Atoll", + "Panama", + "Papua New Guinea", + "Paracel Islands", + "Paraguay", + "Peru", + "Philippines", + "Pitcairn Islands", + "Poland", + "Portugal", + "Puerto Rico", + "Qatar", + "Republic of the Congo", + "Reunion", + "Romania", + "Ross Sea", + "Russia", + "Rwanda", + "Saint Helena", + "Saint Kitts and Nevis", + "Saint Lucia", + "Saint Pierre and Miquelon", + "Saint Vincent and the Grenadines", + "Samoa", + "San Marino", + "Sao Tome and Principe", + "Saudi Arabia", + "Senegal", + "Serbia", + "Seychelles", + "Sierra Leone", + "Singapore", + "Sint Maarten", + "Slovakia", + "Slovenia", + "Solomon Islands", + "Somalia", + "South Africa", + "South Georgia and the South Sandwich Islands", + "South Korea", + "Southern Ocean", + "Spain", + "Spratly Islands", + "Sri Lanka", + "Sudan", + "Suriname", + "Svalbard", + "Swaziland", + "Sweden", + "Switzerland", + "Syria", + "Taiwan", + "Tajikistan", + "Tanzania", + "Tasman Sea", + "Thailand", + "Togo", + "Tokelau", + "Tonga", + "Trinidad and Tobago", + "Tromelin Island", + "Tunisia", + "Turkey", + "Turkmenistan", + "Turks and Caicos Islands", + "Tuvalu", + "USA", + "Uganda", + "Ukraine", + "United Arab Emirates", + "United Kingdom", + "Uruguay", + "Uzbekistan", + "Vanuatu", + "Venezuela", + "Viet Nam", + "Virgin Islands", + "Wake Island", + "Wallis and Futuna", + "West Bank", + "Western Sahara", + "Yemen", + "Zambia", + "Zimbabwe", + "missing: control sample", + "missing: data agreement established pre-2023", + "missing: endangered species", + "missing: human-identifiable", + "missing: lab stock", + "missing: sample group", + "missing: synthetic construct", + "missing: third party data", + "not applicable", + "not collected", + "not provided", + "restricted access" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "geographic location (latitude)", + "cardinality": "optional", + "description": "The geographical origin of the sample as defined by latitude. The values should be reported in decimal degrees and in WGS84 system", + "cv": [], + "units": "DD", + "field_type": "TEXT_FIELD", + "regex": "(^[+-]?[0-9]+.?[0-9]{0,8}$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)" + }, + { + "name": "geographic location (longitude)", + "cardinality": "optional", + "description": "The geographical origin of the sample as defined by longitude. The values should be reported in decimal degrees and in WGS84 system", + "cv": [], + "units": "DD", + "field_type": "TEXT_FIELD", + "regex": "(^[+-]?[0-9]+.?[0-9]{0,8}$)|(^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$)" + }, + { + "name": "geographic location (region and locality)", + "cardinality": "optional", + "description": "The geographical origin of the sample as defined by the specific region name followed by the locality name.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "broad-scale environmental context", + "cardinality": "optional", + "description": "Report the major environmental system the sample or specimen came from. The system(s) identified should have a coarse spatial grain, to provide the general environmental context of where the sampling was done (e.g. in the desert or a rainforest). We recommend using subclasses of EnvO\u2019s biome class: http://purl.obolibrary.org/obo/ENVO_00000428. EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "local environmental context", + "cardinality": "optional", + "description": "Report the entity or entities which are in the sample or specimen\u2019s local vicinity and which you believe have significant causal influences on your sample or specimen. We recommend using EnvO terms which are of smaller spatial grain than your entry for \"broad-scale environmental context\". Terms, such as anatomical sites, from other OBO Library ontologies which interoperate with EnvO (e.g. UBERON) are accepted in this field. EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "environmental medium", + "cardinality": "optional", + "description": "Report the environmental material(s) immediately surrounding the sample or specimen at the time of sampling. We recommend using subclasses of 'environmental material' (http://purl.obolibrary.org/obo/ENVO_00010483). EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS . Terms from other OBO ontologies are permissible as long as they reference mass/volume nouns (e.g. air, water, blood) and not discrete, countable entities (e.g. a tree, a leaf, a table top).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "elevation", + "cardinality": "optional", + "description": "The elevation of the sampling site as measured by the vertical distance from mean sea level.", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "([+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "secondary and tertiary recovery methods and start date", + "cardinality": "optional", + "description": "Additional (i.e. Secondary, tertiary, etc.) recovery methods deployed for increase of hydrocarbon recovery from resource and start date for each one of them. If \"other\" is specified, please propose entry in \"additional info\" field.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "amount or size of sample collected", + "cardinality": "optional", + "description": "The total amount or size (volume (ml), mass (g) or area (m2) ) of sample collected.", + "cv": [], + "units": "m3", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "organism count", + "cardinality": "optional", + "description": "Total cell count of any organism (or group of organisms) per gram, volume or area of sample, should include name of organism followed by count. The method that was used for the enumeration (e.g. qPCR, atp, mpn, etc.) Should also be provided. (example: total prokaryotes; 3.5e7 cells per ml; qpcr)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "organism count qpcr information", + "cardinality": "optional", + "description": "If qpcr was used for the cell count, the target gene name, the primer sequence and the cycling conditions should also be provided. (Example: 16S rrna; FWD:ACGTAGCTATGACGT REV:GTGCTAGTCGAGTAC; initial denaturation:90C_5min; denaturation:90C_2min; annealing:52C_30 sec; elongation:72C_30 sec; 90 C for 1 min; final elongation:72C_5min; 30 cycles)", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "hydrocarbon type produced", + "cardinality": "optional", + "description": "Main hydrocarbon type produced from resource (i.e. Oil, gas, condensate, etc). If \"other\" is specified, please propose entry in \"additional info\" field", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "api gravity", + "cardinality": "optional", + "description": "API gravity is a measure of how heavy or light a petroleum liquid is compared to water (source: https://en.wikipedia.org/wiki/API_gravity) (e.g. 31.1API)", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample storage duration", + "cardinality": "optional", + "description": "Duration for which the sample was stored. Indicate the duration for which the sample was stored written in ISO 8601 format.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host disease status", + "cardinality": "optional", + "description": "list of diseases with which the host has been diagnosed; can include multiple diagnoses. The value of the field depends on host; for humans the terms should be chosen from DO (Disease Ontology) at http://www.disease-ontology.org, other hosts are free text", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host scientific name", + "cardinality": "optional", + "description": "Scientific name of the natural (as opposed to laboratory) host to the organism from which sample was obtained.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pressure", + "cardinality": "optional", + "description": "pressure to which the sample is subject, in atmospheres", + "cv": [], + "units": "bar", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "temperature", + "cardinality": "optional", + "description": "temperature of the sample at time of sampling", + "cv": [], + "units": "\u00baC", + "field_type": "TEXT_FIELD", + "regex": "[+-]?(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "pH", + "cardinality": "optional", + "description": "pH measurement", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "viscosity", + "cardinality": "optional", + "description": "A measure of oil's resistance to gradual deformation by shear stress or tensile stress (e.g. 3.5 cp; 100 C)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "permeability", + "cardinality": "optional", + "description": "Measure of the ability of a hydrocarbon resource to allow fluids to pass through it. (Additional information: https://en.wikipedia.org/wiki/Permeability_(earth_sciences))", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "oil water contact depth", + "cardinality": "optional", + "description": "Depth of the original oil water contact (OWC) zone (average) (m TVDSS)", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*)))" + }, + { + "name": "hydrocarbon resource original pressure", + "cardinality": "optional", + "description": "Original pressure of the hydrocarbon resource", + "cv": [], + "units": "Pa", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*)))" + }, + { + "name": "source rock geological age", + "cardinality": "optional", + "description": "Geological age of source rock (Additional info: https://en.wikipedia.org/wiki/Period_(geology)). If \"other\" is specified, please propose entry in \"additional info\" field", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "ammonium", + "cardinality": "optional", + "description": "concentration of ammonium", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "sample salinity", + "cardinality": "optional", + "description": "Salinity is the total concentration of all dissolved salts in a liquid or solid (in the form of an extract obtained by centrifugation) sample. While salinity can be measured by a complete chemical analysis, this method is difficult and time consuming. More often, it is instead derived from the conductivity measurement. This is known as practical salinity. These derivations compare the specific conductance of the sample to a salinity standard such as seawater", + "cv": [], + "units": "psu", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "calcium", + "cardinality": "optional", + "description": "concentration of calcium", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "chloride", + "cardinality": "optional", + "description": "concentration of chloride", + "cv": [], + "units": "mg/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "suspended solids", + "cardinality": "optional", + "description": "concentration of substances including a wide variety of material, such as silt, decaying plant and animal matter, etc,; can include multiple substances", + "cv": [], + "units": "parts/million", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "dissolved carbon dioxide", + "cardinality": "optional", + "description": "concentration of dissolved carbon dioxide", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "dissolved inorganic carbon", + "cardinality": "optional", + "description": "dissolved inorganic carbon concentration", + "cv": [], + "units": "\u00b5g/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "dissolved inorganic phosphorus", + "cardinality": "optional", + "description": "concentration of dissolved inorganic phosphorus", + "cv": [], + "units": "\u00b5g/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "dissolved organic carbon", + "cardinality": "optional", + "description": "concentration of dissolved organic carbon", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "magnesium", + "cardinality": "optional", + "description": "concentration of magnesium", + "cv": [], + "units": "parts/million", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "nitrate", + "cardinality": "optional", + "description": "concentration of nitrate", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "nitrite", + "cardinality": "optional", + "description": "concentration of nitrite", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "total nitrogen concentration", + "cardinality": "optional", + "description": "Concentration of nitrogen (total). Total nitrogen concentration of water samples, calculated by: total nitrogen = total dissolved nitrogen + particulate nitrogen. Can also be measured without filtering, reported as nitrogen", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "potassium", + "cardinality": "optional", + "description": "concentration of potassium", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "salinity", + "cardinality": "optional", + "description": "The total concentration of all dissolved salts in a liquid or solid sample. While salinity can be measured by a complete chemical analysis, this method is difficult and time consuming. More often, it is instead derived from the conductivity measurement. This is known as practical salinity. These derivations compare the specific conductance of the sample to a salinity standard such as seawater.", + "cv": [], + "units": "psu", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "sodium", + "cardinality": "optional", + "description": "sodium concentration", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "sulfate", + "cardinality": "optional", + "description": "concentration of sulfate", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "sulfide", + "cardinality": "optional", + "description": "concentration of sulfide", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "total phosphorus", + "cardinality": "optional", + "description": "total phosphorus concentration, calculated by: total phosphorus = total dissolved phosphorus + particulate phosphorus. Can also be measured without filtering, reported as phosphorus", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "total iron", + "cardinality": "optional", + "description": "Concentration of total iron in the sample", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "volatile fatty acids", + "cardinality": "optional", + "description": "Concentration of Volatile Fatty Acids in the sample", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "dissolved iron", + "cardinality": "optional", + "description": "Concentration of dissolved iron in the sample", + "cv": [], + "units": "\u00b5l/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "resins wt%", + "cardinality": "optional", + "description": "Saturate, Aromatic, Resin and Asphaltene(SARA) is an analysis method that divides crude oil components according to their polarizability and polarity. There are three main methods to obtain SARA results. The most popular one is known as the Iatroscan TLC-FID and is referred to as IP-143 (source: https://en.wikipedia.org/wiki/Saturate,_aromatic,_resin_and_asphaltene)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "dissolved oxygen in fluids", + "cardinality": "optional", + "description": "Concentration of dissolved oxygen in the oil field produced fluids as it contributes to oxgyen-corrosion and microbial activity (e.g. Mic).", + "cv": [], + "units": "\u00b5mol/kg", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "total sulfur", + "cardinality": "optional", + "description": "Concentration of total sulfur in the sample", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "injection water fraction", + "cardinality": "optional", + "description": "Proportion of the produced fluids derived from injected water at the time of sampling. (e.g. 87%)", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "ethylbenzene", + "cardinality": "optional", + "description": "Concentration of ethylbenzene in the sample", + "cv": [], + "units": "\u00b5mol/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "vfa in formation water", + "cardinality": "optional", + "description": "Original volatile fatty acid concentration in the hydrocarbon resource", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "total acid number", + "cardinality": "optional", + "description": "Total Acid Number(TAN) is a measurement of acidity that is determined by the amount of potassium hydroxide in milligrams that is needed to neutralize the acids in one gram of oil. It is an important quality measurement of crude oil. (source: https://en.wikipedia.org/wiki/Total_acid_number)", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "sulfate in formation water", + "cardinality": "optional", + "description": "Original sulfate concentration in the hydrocarbon resource", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "toluene", + "cardinality": "optional", + "description": "Concentration of toluene in the sample", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "asphaltenes wt%", + "cardinality": "optional", + "description": "Saturate, Aromatic, Resin and Asphaltene(SARA) is an analysis method that divides crude oil components according to their polarizability and polarity. There are three main methods to obtain SARA results. The most popular one is known as the Iatroscan TLC-FID and is referred to as IP-143 (source: https://en.wikipedia.org/wiki/Saturate,_aromatic,_resin_and_asphaltene)", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "xylene", + "cardinality": "optional", + "description": "Concentration of xylene in the sample", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "alkalinity method", + "cardinality": "optional", + "description": "Method used for alkalinity measurement", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "benzene", + "cardinality": "optional", + "description": "Concentration of benzene in the sample", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "alkalinity", + "cardinality": "optional", + "description": "alkalinity, the ability of a solution to neutralize acids to the equivalence point of carbonate or bicarbonate", + "cv": [], + "units": "mEq/L", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "source material identifiers", + "cardinality": "optional", + "description": "A unique identifier assigned to a material sample (as defined by http://rs.tdwg.org/dwc/terms/materialSampleID, and as opposed to a particular digital record of a material sample) used for extracting nucleic acids, and subsequent sequencing. The identifier can refer either to the original material collected or to any derived sub-samples. The INSDC qualifiers /specimen_voucher, /bio_material, or /culture_collection may or may not share the same value as the source_mat_id field. For instance, the /specimen_voucher qualifier and source_mat_id may both contain 'UAM:Herps:14' , referring to both the specimen voucher and sampled tissue with the same identifier. However, the /culture_collection qualifier may refer to a value from an initial culture (e.g. ATCC:11775) while source_mat_id would refer to an identifier from some derived culture from which the nucleic acids were extracted (e.g. xatc123 or ark:/2154/R2).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "source rock lithology", + "cardinality": "optional", + "description": "Lithology of source rock (https://en.wikipedia.org/wiki/Source_rock). If \"other\" is specified, please propose entry in \"additional info\" field", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample material type", + "cardinality": "optional", + "description": "The type of material from which the sample was obtained. For the Hydrocarbon package, samples include types like core, rock trimmings, drill cuttings, piping section, coupon, pigging debris, solid deposit, produced fluid, produced water, injected water, swabs, etc. For the Food Package, samples are usually categorized as food, body products or tissues, or environmental material. This field accepts terms listed under environmental specimen (http://purl.obolibrary.org/obo/GENEPIO_0001246).", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "host of the symbiotic host phenotype", + "cardinality": "optional", + "description": "Phenotype of the host of the symbiotic host organism. For phenotypic quality ontology (PATO) terms, see http://purl.bioontology.org/ontology/pato.", + "cv": [], + "units": "", + "field_type": "ONTOLOGY_FIELD", + "regex": "" + }, + { + "name": "biocide administration method", + "cardinality": "optional", + "description": "Method of biocide administration (dose, frequency, duration, time elapsed between last biociding and sampling) (e.g. 150 mg/l; weekly; 4 hr; 3 days)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "chemical treatment", + "cardinality": "optional", + "description": "List of chemical compounds administered upstream the sampling location where sampling occurred (e.g. Glycols, H2S scavenger, corrosion and scale inhibitors, demulsifiers, and other production chemicals etc.). The commercial name of the product and name of the supplier should be provided. The date of administration should also be included", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "biocide administration", + "cardinality": "optional", + "description": "List of biocides (commercial name of product and supplier) and date of administration", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "chemical treatment method", + "cardinality": "optional", + "description": "Method of chemical administration(dose, frequency, duration, time elapsed between administration and sampling) (e.g. 50 mg/l; twice a week; 1 hr; 0 days)", + "cv": [], + "units": "J/K", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "negative control type", + "cardinality": "optional", + "description": "The substance or equipment used as a negative control in an investigation", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "positive control type", + "cardinality": "optional", + "description": "The substance, mixture, product, or apparatus used to verify that a process which is part of an investigation delivers a true positive.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "experimental factor", + "cardinality": "optional", + "description": "Experimental factors are essentially the variable aspects of an experiment design which can be used to describe an experiment, or set of experiments, in an increasingly detailed manner. This field accepts ontology terms from Experimental Factor Ontology (EFO) and/or Ontology for Biomedical Investigations (OBI). For a browser of EFO (v 2.95) terms, please see http://purl.bioontology.org/ontology/EFO; for a browser of OBI (v 2018-02-12) terms please see http://purl.bioontology.org/ontology/OBI. E.g. time series design [EFO:EFO_0001779]", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "encoded traits", + "cardinality": "optional", + "description": "Should include key traits like antibiotic resistance or xenobiotic degradation phenotypes for plasmids, converting genes for phage", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "subspecific genetic lineage", + "cardinality": "optional", + "description": "Information about the genetic distinctness of the sequenced organism below the subspecies level, e.g., serovar, serotype, biotype, ecotype, or any relevant genetic typing schemes like Group I plasmid. Subspecies should not be recorded in this term, but in the NCBI taxonomy. Supply both the lineage name and the lineage rank separated by a colon, e.g., biovar:abc123.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "taxonomic classification", + "cardinality": "optional", + "description": "Method used for taxonomic classification, along with reference database used, classification rank, and thresholds used to classify new genomes. Expected values are: classification method, database name, and other parameters e.g. vConTACT vContact2 (references from NCBI RefSeq v83, genus rank classification, default parameters)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "isolation and growth condition", + "cardinality": "optional", + "description": "Publication reference in the form of pubmed ID (pmid), digital object identifier (doi) or url for isolation and growth condition specifications of the organism/material. Mandatory for MIGS and MIMARKS Specimen.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "annotation source", + "cardinality": "optional", + "description": "For cases where annotation was provided by a community jamboree or model organism database rather than by a specific submitter", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "reference for biomaterial", + "cardinality": "optional", + "description": "Primary publication if isolated before genome publication; otherwise, primary genome report. Mandatory for MIGS of bacteria and archaea.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample subtype", + "cardinality": "optional", + "description": "Name of sample sub-type. For example if \"sample type\" is \"Produced Water\" then subtype could be \"Oil Phase\" or \"Water Phase\". If \"other\" is specified, please propose entry in \"additional info\" field", + "cv": [], + "units": "m2", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "preservative added to sample", + "cardinality": "optional", + "description": "Preservative added to the sample (e.g. Rnalater, alcohol, formaldehyde, etc.). Where appropriate include volume added (e.g. Rnalater; 2 ml)", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "single cell or viral particle lysis approach", + "cardinality": "optional", + "description": "Method used to free DNA from interior of the cell(s) or particle(s)", + "cv": [ + "chemical", + "combination", + "enzymatic", + "physical" + ], + "units": "", + "field_type": "TEXT_CHOICE_FIELD", + "regex": "" + }, + { + "name": "single cell or viral particle lysis kit protocol", + "cardinality": "optional", + "description": "Name of the kit or standard protocol used for cell(s) or particle(s) lysis", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample material processing", + "cardinality": "optional", + "description": "A brief description of any processing applied to the sample during or after retrieving the sample from environment, or a link to the relevant protocol(s) performed.", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "sample volume or weight for DNA extraction", + "cardinality": "optional", + "description": "Volume (ml) or mass (g) of total collected sample processed for DNA extraction. Note: total sample collected should be entered under the term 'sample size'.", + "cv": [], + "units": "ng", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "nucleic acid extraction", + "cardinality": "optional", + "description": "A link to a literature reference, electronic resource or a standard operating procedure (SOP), that describes the material separation to recover the nucleic acid fraction from a sample", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "nucleic acid amplification", + "cardinality": "optional", + "description": "A link to a literature reference, electronic resource or a standard operating procedure (SOP), that describes the enzymatic amplification (PCR, TMA, NASBA) of specific nucleic acids", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "library size", + "cardinality": "optional", + "description": "Total number of clones in the library prepared for the project", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "library reads sequenced", + "cardinality": "optional", + "description": "Total number of clones sequenced from the library", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[+-]?[0-9]+" + }, + { + "name": "library vector", + "cardinality": "optional", + "description": "Cloning vector type(s) used in construction of libraries", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "library screening strategy", + "cardinality": "optional", + "description": "Specific enrichment or screening methods applied before and/or after creating clone libraries in order to select a specific group of sequences", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pcr conditions", + "cardinality": "optional", + "description": "Description of reaction conditions and components for PCR in the form of 'initial denaturation:94degC_1.5min; annealing=...'", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pcr primers", + "cardinality": "optional", + "description": "PCR primers that were used to amplify the sequence of the targeted gene, locus or subfragment. This field should contain all the primers used for a single PCR reaction if multiple forward or reverse primers are present in a single PCR reaction. The primer sequence should be reported in uppercase letters", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "adapters", + "cardinality": "optional", + "description": "Adapters provide priming sequences for both amplification and sequencing of the sample-library fragments. Both adapters should be reported; in uppercase letters", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "production start date", + "cardinality": "optional", + "description": "Date of field's first production", + "cv": [], + "units": "m", + "field_type": "DATE_FIELD", + "regex": "" + }, + { + "name": "aromatics wt%", + "cardinality": "optional", + "description": "Saturate, Aromatic, Resin and Asphaltene(SARA) is an analysis method that divides crude oil components according to their polarizability and polarity. There are three main methods to obtain SARA results. The most popular one is known as the Iatroscan TLC-FID and is referred to as IP-143 (source: https://en.wikipedia.org/wiki/Saturate,_aromatic,_resin_and_asphaltene)", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "saturates wt%", + "cardinality": "optional", + "description": "Saturate, Aromatic, Resin and Asphaltene\u00ac\u2020(SARA) is an analysis method that divides\u00ac\u2020crude oil\u00ac\u2020components according to their polarizability and polarity. There are three main methods to obtain SARA results. The most popular one is known as the Iatroscan TLC-FID and is referred to as IP-143 (source: https://en.wikipedia.org/wiki/Saturate,_aromatic,_resin_and_asphaltene)", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "porosity", + "cardinality": "optional", + "description": "Porosity of deposited sediment is volume of voids divided by the total volume of sample", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "[0-9]+" + }, + { + "name": "formation water salinity", + "cardinality": "optional", + "description": "Original formation water salinity (prior to secondary recovery e.g. Waterflooding) expressed as TDS", + "cv": [], + "units": "ppm", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "basin name", + "cardinality": "optional", + "description": "Name of the basin (e.g. Campos)", + "cv": [], + "units": "g/m3", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "pour point", + "cardinality": "optional", + "description": "Temperature at which a liquid becomes semi solid and loses its flow characteristics. In crude oil a high pour point is generally associated with a high paraffin content, typically found in crude deriving from a larger proportion of plant material. (source: https://en.wikipedia.org/wiki/pour_point)", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "reservoir name", + "cardinality": "optional", + "description": "Name of the reservoir (e.g. Carapebus)", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "hydrocarbon resource geological age", + "cardinality": "optional", + "description": "Geological age of hydrocarbon resource (Additional info: https://en.wikipedia.org/wiki/Period_(geology)). If \"other\" is specified, please propose entry in \"additional info\" field", + "cv": [], + "units": "", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "depositional environment", + "cardinality": "optional", + "description": "Main depositional environment (https://en.wikipedia.org/wiki/Depositional_environment). If \"other\" is specified, please propose entry in \"additional info\" field", + "cv": [], + "units": "m", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "source rock kerogen type", + "cardinality": "optional", + "description": "Origin of kerogen. Type I: Algal (aquatic), Type II: planktonic and soft plant material (aquatic or terrestrial), Type III: terrestrial woody/ fibrous plant material (terrestrial), Type IV: oxidized recycled woody debris (terrestrial) (additional information: https://en.wikipedia.org/wiki/Kerogen). If \"other\" is specified, please propose entry in \"additional info\" field", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "hydrocarbon resource type", + "cardinality": "optional", + "description": "Main Hydrocarbon Resource type. The term \"Hydrocarbon Resource\" HCR defined as a natural environmental feature containing large amounts of hydrocarbons at high concentrations potentially suitable for commercial exploitation. This term should not be confused with the Hydrocarbon Occurrence term which also includes hydrocarbon-rich environments with currently limited commercial interest such as seeps, outcrops, gas hydrates etc. If \"other\" is specified, please propose entry in \"additional info\" field", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "water production rate", + "cardinality": "optional", + "description": "Water production rates per well (e.g. 987 m3 / day)", + "cv": [], + "units": "m3/day", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?" + }, + { + "name": "lithology", + "cardinality": "optional", + "description": "Hydrocarbon resource main lithology (Additional information: http://petrowiki.org/Lithology_and_rock_type_determination). If \"other\" is specified, please propose entry in \"additional info\" field", + "cv": [], + "units": "year", + "field_type": "TEXT_FIELD", + "regex": "" + }, + { + "name": "hydrocarbon resource original temperature", + "cardinality": "optional", + "description": "Original temperature of the hydrocarbon resource", + "cv": [], + "units": "\u00b0C", + "field_type": "TEXT_FIELD", + "regex": "(0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)" + }, + { + "name": "depth", + "cardinality": "optional", + "description": "The vertical distance below local surface, e.g. for sediment or soil samples depth is measured from sediment or soil surface, respectively. Depth can be reported as an interval for subsurface samples.", + "cv": [], + "units": "mm", + "field_type": "TEXT_FIELD", + "regex": "((0|((0\\.)|([1-9][0-9]*\\.?))[0-9]*)([Ee][+-]?[0-9]+)?)|((^not collected$)|(^not provided$)|(^restricted access$)|(^missing: control sample$)|(^missing: sample group$)|(^missing: synthetic construct$)|(^missing: lab stock$)|(^missing: third party data$)|(^missing: data agreement established pre-2023$)|(^missing: endangered species$)|(^missing: human-identifiable$))" + }, + { + "name": "injection water breakthrough date of specific well", + "cardinality": "optional", + "description": "Injection water breakthrough date per well following a secondary and/or tertiary recovery", + "cv": [], + "units": "%", + "field_type": "TEXT_FIELD", + "regex": "" + } + ] + } +} \ No newline at end of file diff --git a/templates/ERC000058/README.md b/templates/ERC000058/README.md new file mode 100644 index 0000000..8f1dbed --- /dev/null +++ b/templates/ERC000058/README.md @@ -0,0 +1,207 @@ +# ERC000058: GSC MIxS Hydrocarbon + +Genomic Standards Consortium package extension for reporting of measurements and observations obtained from the environment where the sample was obtained. By choosing the environmental package, a selection of fields can be made from a relevant subsets of the GSC terms. + +## Study + +A Study is a container for a sequencing investigation that may comprise multiple experiments. The Study has an overall goal, but is otherwise minimally defined in the SRA. A Study is composed of a descriptor, zero or more experiments, and zero or more analyses. The submitter may decorate the Study with web links and properties. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:---------------|:--------------|:---------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for a study. this is used to link experiments to the study. | | +| title | mandatory | Title of the study as would be used in a publication. | | +| study_type | mandatory | The study_type presents a controlled vocabulary for expressing the overall purpose of the study. | Whole Genome Sequencing, Metagenomics, Transcriptome Analysis, Resequencing, Epigenetics, Synthetic Genomics, Forensic or Paleo-genomics, Gene Regulation Study, Cancer Genomics, Population Genomics, RNASeq, Exome Sequencing, Pooled Clone Sequencing, Transcriptome Sequencing, Other | +| new_study_type | optional | Optional if 'study_type' is not 'other'. to propose a new term, select other and enter a new study type. | | +| study_abstract | optional | Briefly describes the goals, purpose, and scope of the study. this need not be listed if it can be inherited from a referenced publication. | | + +## Experiment + +An experiment object serves as a metadata record encapsulating essential details about a sequencing experiment, including the experimental design, sequencing type, and relevant parameters. This information enhances the interpretation and contextual understanding of nucleotide sequences submitted to the archive. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:------------------------------|:--------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for each experiment. this is used to link runs to experiments. | | +| title | optional | Short text that can be used to call out experiment records in searches or in displays. this element is technically optional but should be used for all new records. | | +| study_alias | mandatory | Identifies the parent study. (from study metadata) | | +| sample_alias | mandatory | (from sample metadata) | | +| design_description | optional | Goal and setup of the individual library including library was constructed. | | +| library_name | optional | The submitter's name for this library. | | +| library_strategy | mandatory | Sequencing technique intended for this library. | WGS, WGA, WXS, RNA-Seq, ssRNA-seq, snRNA-seq, miRNA-Seq, ncRNA-Seq, FL-cDNA, EST, Hi-C, ATAC-seq, WCS, RAD-Seq, CLONE, POOLCLONE, AMPLICON, CLONEEND, FINISHING, ChIP-Seq, MNase-Seq, DNase-Hypersensitivity, Bisulfite-Seq, CTS, MRE-Seq, MeDIP-Seq, MBD-Seq, Tn-Seq, VALIDATION, FAIRE-seq, SELEX, RIP-Seq, ChIA-PET, Synthetic-Long-Read, Targeted-Capture, Tethered Chromatin Conformation Capture, NOMe-Seq, ChM-Seq, GBS, Ribo-Seq, OTHER | +| library_source | mandatory | The library_source specifies the type of source material that is being sequenced. | GENOMIC, GENOMIC SINGLE CELL, TRANSCRIPTOMIC, TRANSCRIPTOMIC SINGLE CELL, METAGENOMIC, METATRANSCRIPTOMIC, SYNTHETIC, VIRAL RNA, OTHER | +| library_selection | mandatory | Method used to enrich the target in the sequence library preparation | RANDOM, PCR, RANDOM PCR, RT-PCR, HMPR, MF, repeat fractionation, size fractionation, MSLL, cDNA, cDNA_randomPriming, cDNA_oligo_dT, PolyA, Oligo-dT, Inverse rRNA, Inverse rRNA selection, ChIP, ChIP-Seq, MNase, DNase, Hybrid Selection, Reduced Representation, Restriction Digest, 5-methylcytidine antibody, MBD2 protein methyl-CpG binding domain, CAGE, RACE, MDA, padlock probes capture method, other, unspecified | +| library_layout | mandatory | Library_layout specifies whether to expect single, paired, or other configuration of reads. in the case of paired reads, information about the relative distance and orientation is specified. | | +| insert_size | optional | Insert size for paired reads | | +| library_construction_protocol | optional | Free form text describing the protocol by which the sequencing library was constructed. | | +| platform | mandatory | The platform record selects which sequencing platform and platform-specific runtime parameters. this will be determined by the center. optional if 'instrument_model' is provided. | LS454, ILLUMINA, HELICOS, ABI_SOLID, COMPLETE_GENOMICS, BGISEQ, OXFORD_NANOPORE, PACBIO_SMRT, ION_TORRENT, CAPILLARY, DNBSEQ, ELEMENT, ULTIMA, VELA_DIAGNOSTICS, GENAPSYS, GENEMIND, TAPESTRI | +| instrument_model | mandatory | Model of the sequencing instrument. | 454 GS, 454 GS 20, 454 GS FLX, 454 GS FLX Titanium, 454 GS FLX+, 454 GS Junior, AB 310 Genetic Analyzer, AB 3130 Genetic Analyzer, AB 3130xL Genetic Analyzer, AB 3500 Genetic Analyzer, AB 3500xL Genetic Analyzer, AB 3730 Genetic Analyzer, AB 3730xL Genetic Analyzer, AB 5500 Genetic Analyzer, AB 5500xl Genetic Analyzer, AB 5500xl-W Genetic Analysis System, AB SOLiD 3 Plus System, AB SOLiD 4 System, AB SOLiD 4hq System, AB SOLiD PI System, AB SOLiD System, AB SOLiD System 2.0, AB SOLiD System 3.0, BGISEQ-50, BGISEQ-500, Complete Genomics, DNBSEQ-G400, DNBSEQ-G400 FAST, DNBSEQ-G50, DNBSEQ-T7, Element AVITI, FASTASeq 300, GENIUS, GS111, Genapsys Sequencer, GenoCare 1600, GenoLab M, GridION, Helicos HeliScope, HiSeq X Five, HiSeq X Ten, Illumina Genome Analyzer, Illumina Genome Analyzer II, Illumina Genome Analyzer IIx, Illumina HiScanSQ, Illumina HiSeq 1000, Illumina HiSeq 1500, Illumina HiSeq 2000, Illumina HiSeq 2500, Illumina HiSeq 3000, Illumina HiSeq 4000, Illumina HiSeq X, Illumina MiSeq, Illumina MiniSeq, Illumina NovaSeq 6000, Illumina NovaSeq X, Illumina iSeq 100, Ion GeneStudio S5, Ion GeneStudio S5 Plus, Ion GeneStudio S5 Prime, Ion Torrent Genexus, Ion Torrent PGM, Ion Torrent Proton, Ion Torrent S5, Ion Torrent S5 XL, MGISEQ-2000RS, MinION, NextSeq 1000, NextSeq 2000, NextSeq 500, NextSeq 550, Onso, PacBio RS, PacBio RS II, PromethION, Revio, Sentosa SQ301, Sequel, Sequel II, Sequel IIe, Tapestri, UG 100, unspecified | + +## Run + +A run contains a group of reads generated for a particular experiment. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:-----------------|:--------------|:--------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for each run. | | +| experiment_alias | mandatory | From_experiment_metadata | | +| file_name | mandatory | The name or relative pathname of a run data file. | | +| file_format | mandatory | The run data file model. | sra, srf, sff, fastq, fasta, tab, 454_native, 454_native_seq, 454_native_qual, Helicos_native, Illumina_native, Illumina_native_seq, Illumina_native_prb, Illumina_native_int, Illumina_native_qseq, Illumina_native_scarf, SOLiD_native, SOLiD_native_csfasta, SOLiD_native_qual, PacBio_HDF5, bam, cram, CompleteGenomics_native, OxfordNanopore_native | + +## Sample + +A Sample defines an isolate of sequenceable material upon which sequencing experiments can be based. The Sample object may be a surrogate for taxonomy accession or an anonymized individual identifier. Or, it may fully specify provenance and isolation method of the starting material. + +| Field name | Cardinality | Description | Controlled vocabulary | +|:-------------------------------------------------------|:--------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| alias | mandatory | Unique identificator for each run. | | +| title | mandatory | Short text that can be used to call out sample records in search results or in displays. | | +| taxon_id | mandatory | Ncbi taxonomy identifier. this is appropriate for individual organisms and some environmental samples. | | +| sample_description | optional | Free-form text describing the sample, its origin, and its method of isolation. | | +| sample true vertical depth subsea | optional | Depth of the sample i.e. the vertical distance between the sea level and the sampled position in the subsurface. depth can be reported as an interval for subsurface samples e.g. 1325.75-1362.25 m | | +| trophic level | optional | Trophic levels are the feeding position in a food chain. microbes can be a range of producers (e.g. chemolithotroph) | autotroph, carboxydotroph, chemoautotroph, chemoheterotroph, chemolithoautotroph, chemolithotroph, chemoorganoheterotroph, chemoorganotroph, chemosynthetic, chemotroph, copiotroph, diazotroph, facultative autotroph, heterotroph, lithoautotroph, lithoheterotroph, lithotroph, methanotroph, methylotroph, mixotroph, obligate chemoautolithotroph, oligotroph, organoheterotroph, organotroph, photoautotroph, photoheterotroph, photolithoautotroph, photolithotroph, photosynthetic, phototroph | +| observed biotic relationship | optional | Description of relationship(s) between the subject organism and other organism(s) it is associated with. e.g., parasite on species x; mutualist with species y. the target organism is the subject of the relationship, and the other organism(s) is the object. | commensal, free living, mutualism, parasite, symbiont | +| known pathogenicity | optional | To what is the entity pathogenic, for instance plant, fungi, bacteria | | +| relationship to oxygen | optional | Is this organism an aerobe, anaerobe? please note that aerobic and anaerobic are valid descriptors for microbial environments | aerobe, anaerobe, facultative, microaerophilic, microanaerobe, obligate aerobe, obligate anaerobe | +| propagation | optional | The type of reproduction from the parent stock. values for this field is specific to different taxa. for phage or virus: lytic/lysogenic/temperate/obligately lytic. for plasmids: incompatibility group. for eukaryotes: sexual/asexual. mandatory for migs of eukayotes, plasmids and viruses. | | +| sample transport conditions | optional | Sample transport duration (in days or hrs) and temperature the sample was exposed to (e.g. 5.5 days; 20 °c) (Units: m2) | | +| sample collection device | optional | The device used to collect an environmental sample. it is recommended to use terms listed under environmental sampling device (http://purl.obolibrary.org/obo/envo) and/or terms listed under specimen collection device (http://purl.obolibrary.org/obo/genepio_0002094). | | +| sample collection method | optional | The method employed for collecting the sample. can be provided in the form of a pmid, doi, url or text. | | +| sample storage temperature | optional | Temperature at which sample was stored, e.g. -80 (Units: °C) | | +| sample storage location | optional | Location at which sample was stored, usually name of a specific freezer/room. indicate the location name. | | +| source rock depositional environment | optional | Source rock depositional environment (https://en.wikipedia.org/wiki/source_rock). if "other" is specified, please propose entry in "additional info" field | | +| sample measured depth | optional | In non deviated well, measured depth is equal to the true vertical depth, tvd (tvd=tvdss plus the reference or datum it refers to). in deviated wells, the md is the length of trajectory of the borehole measured from the same reference or datum. common datums used are ground level (gl), drilling rig floor (df), rotary table (rt), kelly bushing (kb) and mean sea level (msl). if "other" is specified, please propose entry in "additional info" field (Units: mm) | | +| corrosion rate at sample location | optional | Metal corrosion rate is the speed of metal deterioration due to environmental conditions. as environmental conditions change corrosion rates change accordingly. therefore, long term corrosion rates are generally more informative than short term rates and for that reason they are preferred during reporting. in the case of suspected mic, corrosion rate measurements at the time of sampling might provide insights into the involvement of certain microbial community members in mic as well as potential microbial interplays | | +| sample collection point | optional | Sampling point on the asset were sample was collected (e.g. wellhead, storage tank, separator, etc). if "other" is specified, please propose entry in "additional info" field | | +| depth (tvdss) of hydrocarbon resource temperature | optional | True vertical depth subsea (tvdss) of the hydrocarbon resource where the original temperature was measured (e.g. 1345 m). (Units: m) | | +| oxygenation status of sample | optional | Oxygenation status of sample | aerobic, anaerobic | +| density | optional | Density of sample (Units: g/m3) | | +| sample well name | optional | Name of the well (e.g. bxa1123) where sample was taken | | +| project name | optional | Name of the project within which the sequencing was organized | | +| ploidy | optional | The ploidy level of the genome (e.g. allopolyploid, haploid, diploid, triploid, tetraploid). it has implications for the downstream study of duplicated gene and regions of the genomes (and perhaps for difficulties in assembly). for terms, please select terms listed under class ploidy (pato:001374) of phenotypic quality ontology (pato), and for a browser of pato (v 2018-03-27) please refer to http://purl.bioontology.org/ontology/pato | | +| number of replicons | optional | Reports the number of replicons in a nuclear genome of eukaryotes, in the genome of a bacterium or archaea or the number of segments in a segmented virus. always applied to the haploid chromosome count of a eukaryote. mandatory for migs of eukaryotes, bacteria, archaea and segmented virus. | | +| extrachromosomal elements | optional | Do plasmids exist of significant phenotypic consequence (e.g. ones that determine virulence or antibiotic resistance). megaplasmids? other plasmids (borrelia has 15+ plasmids). | | +| estimated size | optional | The estimated size of the genome (in bp) prior to sequencing. of particular importance in the sequencing of (eukaryotic) genome which could remain in draft form for a long or unspecified period. mandatory for migs of eukaryotes. | | +| target gene | optional | Targeted gene or locus name for marker gene studies | | +| target subfragment | optional | Name of subfragment of a gene or locus. important to e.g. identify special regions on marker genes like v6 on 16s rrna | | +| multiplex identifiers | optional | Molecular barcodes, called multiplex identifiers (mids), that are used to specifically tag unique samples in a sequencing run. sequence should be reported in uppercase letters | | +| sequence quality check | optional | Indicate if the sequence has been called by automatic systems (none) or undergone a manual editing procedure (e.g. by inspecting the raw data or chromatograms). applied only for sequences that are not submitted to sra or dra | manual, none, software | +| chimera check software | optional | Tool(s) used for chimera checking, including version number and parameters, to discover and remove chimeric sequences. a chimeric sequence is comprised of two or more phylogenetically distinct parent sequences. | | +| relevant electronic resources | optional | A related resource that is referenced, cited, or otherwise associated to the sequence in the format of a pmid, doi or url | | +| relevant standard operating procedures | optional | Standard operating procedures used in assembly and/or annotation of genomes, metagenomes or environmental sequences in the format of a pmid, doi or url | | +| 16s recovered | optional | Can a 16s gene be recovered from the submitted bin, sag or mag? | No, Yes | +| well identification number | optional | A unique identifier of a well or wellbore. this is part of the global framework for well identification initiative which is compiled by the professional petroleum data management association (ppdm) in an effort to improve well identification systems. (supporting information: https://ppdm.org/ and http://dl.ppdm.org/dl/690) (Units: year) | | +| water cut | optional | Current amount of water (%) in a produced fluid stream; or the average of the combined streams (Units: year) | | +| production rate | optional | Oil and/or gas production rates per well (e.g. 524 m3 / day) (Units: °C) | | +| field name | optional | Name of the hydrocarbon field (e.g. albacora) | | +| collection date | optional | The date the sample was collected with the intention of sequencing, either as an instance (single point in time) or interval. in case no exact time is available, the date/time can be right truncated i.e. all of these are valid iso8601 compliant times: 2008-01-23t19:23:10+00:00; 2008-01-23t19:23:10; 2008-01-23; 2008-01; 2008. | | +| altitude | optional | The altitude of the sample is the vertical distance between earth's surface above sea level and the sampled position in the air. (Units: m) | | +| geographic location (country and/or sea) | optional | The geographical origin of where the sample was collected from, with the intention of sequencing, as defined by the country or sea name. country or sea names should be chosen from the insdc country list (http://insdc.org/country.html). | Afghanistan, Albania, Algeria, American Samoa, Andorra, Angola, Anguilla, Antarctica, Antigua and Barbuda, Arctic Ocean, Argentina, Armenia, Aruba, Ashmore and Cartier Islands, Atlantic Ocean, Australia, Austria, Azerbaijan, Bahamas, Bahrain, Baker Island, Baltic Sea, Bangladesh, Barbados, Bassas da India, Belarus, Belgium, Belize, Benin, Bermuda, Bhutan, Bolivia, Borneo, Bosnia and Herzegovina, Botswana, Bouvet Island, Brazil, British Virgin Islands, Brunei, Bulgaria, Burkina Faso, Burundi, Cambodia, Cameroon, Canada, Cape Verde, Cayman Islands, Central African Republic, Chad, Chile, China, Christmas Island, Clipperton Island, Cocos Islands, Colombia, Comoros, Cook Islands, Coral Sea Islands, Costa Rica, Cote d'Ivoire, Croatia, Cuba, Curacao, Cyprus, Czechia, Czech Republic, Democratic Republic of the Congo, Denmark, Djibouti, Dominica, Dominican Republic, East Timor, Ecuador, Egypt, El Salvador, Equatorial Guinea, Eritrea, Estonia, Ethiopia, Europa Island, Falkland Islands (Islas Malvinas), Faroe Islands, Fiji, Finland, France, French Guiana, French Polynesia, French Southern and Antarctic Lands, Gabon, Gambia, Gaza Strip, Georgia, Germany, Ghana, Gibraltar, Glorioso Islands, Greece, Greenland, Grenada, Guadeloupe, Guam, Guatemala, Guernsey, Guinea, Guinea-Bissau, Guyana, Haiti, Heard Island and McDonald Islands, Honduras, Hong Kong, Howland Island, Hungary, Iceland, India, Indian Ocean, Indonesia, Iran, Iraq, Ireland, Isle of Man, Israel, Italy, Jamaica, Jan Mayen, Japan, Jarvis Island, Jersey, Johnston Atoll, Jordan, Juan de Nova Island, Kazakhstan, Kenya, Kerguelen Archipelago, Kingman Reef, Kiribati, Kosovo, Kuwait, Kyrgyzstan, Laos, Latvia, Lebanon, Lesotho, Liberia, Libya, Liechtenstein, Lithuania, Luxembourg, Macau, Macedonia, Madagascar, Malawi, Malaysia, Maldives, Mali, Malta, Marshall Islands, Martinique, Mauritania, Mauritius, Mayotte, Mediterranean Sea, Mexico, Micronesia, Midway Islands, Moldova, Monaco, Mongolia, Montenegro, Montserrat, Morocco, Mozambique, Myanmar, Namibia, Nauru, Navassa Island, Nepal, Netherlands, New Caledonia, New Zealand, Nicaragua, Niger, Nigeria, Niue, Norfolk Island, North Korea, North Sea, Northern Mariana Islands, Norway, Oman, Pacific Ocean, Pakistan, Palau, Palmyra Atoll, Panama, Papua New Guinea, Paracel Islands, Paraguay, Peru, Philippines, Pitcairn Islands, Poland, Portugal, Puerto Rico, Qatar, Republic of the Congo, Reunion, Romania, Ross Sea, Russia, Rwanda, Saint Helena, Saint Kitts and Nevis, Saint Lucia, Saint Pierre and Miquelon, Saint Vincent and the Grenadines, Samoa, San Marino, Sao Tome and Principe, Saudi Arabia, Senegal, Serbia, Seychelles, Sierra Leone, Singapore, Sint Maarten, Slovakia, Slovenia, Solomon Islands, Somalia, South Africa, South Georgia and the South Sandwich Islands, South Korea, Southern Ocean, Spain, Spratly Islands, Sri Lanka, Sudan, Suriname, Svalbard, Swaziland, Sweden, Switzerland, Syria, Taiwan, Tajikistan, Tanzania, Tasman Sea, Thailand, Togo, Tokelau, Tonga, Trinidad and Tobago, Tromelin Island, Tunisia, Turkey, Turkmenistan, Turks and Caicos Islands, Tuvalu, USA, Uganda, Ukraine, United Arab Emirates, United Kingdom, Uruguay, Uzbekistan, Vanuatu, Venezuela, Viet Nam, Virgin Islands, Wake Island, Wallis and Futuna, West Bank, Western Sahara, Yemen, Zambia, Zimbabwe, missing: control sample, missing: data agreement established pre-2023, missing: endangered species, missing: human-identifiable, missing: lab stock, missing: sample group, missing: synthetic construct, missing: third party data, not applicable, not collected, not provided, restricted access | +| geographic location (latitude) | optional | The geographical origin of the sample as defined by latitude. the values should be reported in decimal degrees and in wgs84 system (Units: DD) | | +| geographic location (longitude) | optional | The geographical origin of the sample as defined by longitude. the values should be reported in decimal degrees and in wgs84 system (Units: DD) | | +| geographic location (region and locality) | optional | The geographical origin of the sample as defined by the specific region name followed by the locality name. | | +| broad-scale environmental context | optional | Report the major environmental system the sample or specimen came from. the system(s) identified should have a coarse spatial grain, to provide the general environmental context of where the sampling was done (e.g. in the desert or a rainforest). we recommend using subclasses of envo’s biome class: http://purl.obolibrary.org/obo/envo_00000428. envo documentation about how to use the field: https://github.com/environmentontology/envo/wiki/using-envo-with-mixs. | | +| local environmental context | optional | Report the entity or entities which are in the sample or specimen’s local vicinity and which you believe have significant causal influences on your sample or specimen. we recommend using envo terms which are of smaller spatial grain than your entry for "broad-scale environmental context". terms, such as anatomical sites, from other obo library ontologies which interoperate with envo (e.g. uberon) are accepted in this field. envo documentation about how to use the field: https://github.com/environmentontology/envo/wiki/using-envo-with-mixs. | | +| environmental medium | optional | Report the environmental material(s) immediately surrounding the sample or specimen at the time of sampling. we recommend using subclasses of 'environmental material' (http://purl.obolibrary.org/obo/envo_00010483). envo documentation about how to use the field: https://github.com/environmentontology/envo/wiki/using-envo-with-mixs . terms from other obo ontologies are permissible as long as they reference mass/volume nouns (e.g. air, water, blood) and not discrete, countable entities (e.g. a tree, a leaf, a table top). | | +| elevation | optional | The elevation of the sampling site as measured by the vertical distance from mean sea level. (Units: m) | | +| secondary and tertiary recovery methods and start date | optional | Additional (i.e. secondary, tertiary, etc.) recovery methods deployed for increase of hydrocarbon recovery from resource and start date for each one of them. if "other" is specified, please propose entry in "additional info" field. | | +| amount or size of sample collected | optional | The total amount or size (volume (ml), mass (g) or area (m2) ) of sample collected. (Units: m3) | | +| organism count | optional | Total cell count of any organism (or group of organisms) per gram, volume or area of sample, should include name of organism followed by count. the method that was used for the enumeration (e.g. qpcr, atp, mpn, etc.) should also be provided. (example: total prokaryotes; 3.5e7 cells per ml; qpcr) | | +| organism count qpcr information | optional | If qpcr was used for the cell count, the target gene name, the primer sequence and the cycling conditions should also be provided. (example: 16s rrna; fwd:acgtagctatgacgt rev:gtgctagtcgagtac; initial denaturation:90c_5min; denaturation:90c_2min; annealing:52c_30 sec; elongation:72c_30 sec; 90 c for 1 min; final elongation:72c_5min; 30 cycles) (Units: year) | | +| hydrocarbon type produced | optional | Main hydrocarbon type produced from resource (i.e. oil, gas, condensate, etc). if "other" is specified, please propose entry in "additional info" field (Units: year) | | +| api gravity | optional | Api gravity is a measure of how heavy or light a petroleum liquid is compared to water (source: https://en.wikipedia.org/wiki/api_gravity) (e.g. 31.1api) (Units: °C) | | +| sample storage duration | optional | Duration for which the sample was stored. indicate the duration for which the sample was stored written in iso 8601 format. | | +| host disease status | optional | List of diseases with which the host has been diagnosed; can include multiple diagnoses. the value of the field depends on host; for humans the terms should be chosen from do (disease ontology) at http://www.disease-ontology.org, other hosts are free text | | +| host scientific name | optional | Scientific name of the natural (as opposed to laboratory) host to the organism from which sample was obtained. | | +| pressure | optional | Pressure to which the sample is subject, in atmospheres (Units: bar) | | +| temperature | optional | Temperature of the sample at time of sampling (Units: ºC) | | +| pH | optional | Ph measurement | | +| viscosity | optional | A measure of oil's resistance to gradual deformation by shear stress or tensile stress (e.g. 3.5 cp; 100 c) | | +| permeability | optional | Measure of the ability of a hydrocarbon resource to allow fluids to pass through it. (additional information: https://en.wikipedia.org/wiki/permeability_(earth_sciences)) (Units: mm) | | +| oil water contact depth | optional | Depth of the original oil water contact (owc) zone (average) (m tvdss) (Units: m) | | +| hydrocarbon resource original pressure | optional | Original pressure of the hydrocarbon resource (Units: Pa) | | +| source rock geological age | optional | Geological age of source rock (additional info: https://en.wikipedia.org/wiki/period_(geology)). if "other" is specified, please propose entry in "additional info" field (Units: °C) | | +| ammonium | optional | Concentration of ammonium (Units: µmol/L) | | +| sample salinity | optional | Salinity is the total concentration of all dissolved salts in a liquid or solid (in the form of an extract obtained by centrifugation) sample. while salinity can be measured by a complete chemical analysis, this method is difficult and time consuming. more often, it is instead derived from the conductivity measurement. this is known as practical salinity. these derivations compare the specific conductance of the sample to a salinity standard such as seawater (Units: psu) | | +| calcium | optional | Concentration of calcium (Units: µmol/L) | | +| chloride | optional | Concentration of chloride (Units: mg/L) | | +| suspended solids | optional | Concentration of substances including a wide variety of material, such as silt, decaying plant and animal matter, etc,; can include multiple substances (Units: parts/million) | | +| dissolved carbon dioxide | optional | Concentration of dissolved carbon dioxide (Units: µmol/L) | | +| dissolved inorganic carbon | optional | Dissolved inorganic carbon concentration (Units: µg/L) | | +| dissolved inorganic phosphorus | optional | Concentration of dissolved inorganic phosphorus (Units: µg/L) | | +| dissolved organic carbon | optional | Concentration of dissolved organic carbon (Units: µmol/L) | | +| magnesium | optional | Concentration of magnesium (Units: parts/million) | | +| nitrate | optional | Concentration of nitrate (Units: µmol/L) | | +| nitrite | optional | Concentration of nitrite (Units: µmol/L) | | +| total nitrogen concentration | optional | Concentration of nitrogen (total). total nitrogen concentration of water samples, calculated by: total nitrogen = total dissolved nitrogen + particulate nitrogen. can also be measured without filtering, reported as nitrogen (Units: µmol/L) | | +| potassium | optional | Concentration of potassium (Units: µmol/L) | | +| salinity | optional | The total concentration of all dissolved salts in a liquid or solid sample. while salinity can be measured by a complete chemical analysis, this method is difficult and time consuming. more often, it is instead derived from the conductivity measurement. this is known as practical salinity. these derivations compare the specific conductance of the sample to a salinity standard such as seawater. (Units: psu) | | +| sodium | optional | Sodium concentration (Units: µmol/L) | | +| sulfate | optional | Concentration of sulfate (Units: µmol/L) | | +| sulfide | optional | Concentration of sulfide (Units: µmol/L) | | +| total phosphorus | optional | Total phosphorus concentration, calculated by: total phosphorus = total dissolved phosphorus + particulate phosphorus. can also be measured without filtering, reported as phosphorus (Units: µmol/L) | | +| total iron | optional | Concentration of total iron in the sample | | +| volatile fatty acids | optional | Concentration of volatile fatty acids in the sample | | +| dissolved iron | optional | Concentration of dissolved iron in the sample (Units: µl/L) | | +| resins wt% | optional | Saturate, aromatic, resin and asphaltene(sara) is an analysis method that divides crude oil components according to their polarizability and polarity. there are three main methods to obtain sara results. the most popular one is known as the iatroscan tlc-fid and is referred to as ip-143 (source: https://en.wikipedia.org/wiki/saturate,_aromatic,_resin_and_asphaltene) | | +| dissolved oxygen in fluids | optional | Concentration of dissolved oxygen in the oil field produced fluids as it contributes to oxgyen-corrosion and microbial activity (e.g. mic). (Units: µmol/kg) | | +| total sulfur | optional | Concentration of total sulfur in the sample (Units: µmol/L) | | +| injection water fraction | optional | Proportion of the produced fluids derived from injected water at the time of sampling. (e.g. 87%) (Units: %) | | +| ethylbenzene | optional | Concentration of ethylbenzene in the sample (Units: µmol/L) | | +| vfa in formation water | optional | Original volatile fatty acid concentration in the hydrocarbon resource | | +| total acid number | optional | Total acid number(tan) is a measurement of acidity that is determined by the amount of potassium hydroxide in milligrams that is needed to neutralize the acids in one gram of oil. it is an important quality measurement of crude oil. (source: https://en.wikipedia.org/wiki/total_acid_number) (Units: year) | | +| sulfate in formation water | optional | Original sulfate concentration in the hydrocarbon resource (Units: year) | | +| toluene | optional | Concentration of toluene in the sample (Units: year) | | +| asphaltenes wt% | optional | Saturate, aromatic, resin and asphaltene(sara) is an analysis method that divides crude oil components according to their polarizability and polarity. there are three main methods to obtain sara results. the most popular one is known as the iatroscan tlc-fid and is referred to as ip-143 (source: https://en.wikipedia.org/wiki/saturate,_aromatic,_resin_and_asphaltene) (Units: %) | | +| xylene | optional | Concentration of xylene in the sample (Units: m2) | | +| alkalinity method | optional | Method used for alkalinity measurement (Units: m2) | | +| benzene | optional | Concentration of benzene in the sample (Units: m2) | | +| alkalinity | optional | Alkalinity, the ability of a solution to neutralize acids to the equivalence point of carbonate or bicarbonate (Units: mEq/L) | | +| source material identifiers | optional | A unique identifier assigned to a material sample (as defined by http://rs.tdwg.org/dwc/terms/materialsampleid, and as opposed to a particular digital record of a material sample) used for extracting nucleic acids, and subsequent sequencing. the identifier can refer either to the original material collected or to any derived sub-samples. the insdc qualifiers /specimen_voucher, /bio_material, or /culture_collection may or may not share the same value as the source_mat_id field. for instance, the /specimen_voucher qualifier and source_mat_id may both contain 'uam:herps:14' , referring to both the specimen voucher and sampled tissue with the same identifier. however, the /culture_collection qualifier may refer to a value from an initial culture (e.g. atcc:11775) while source_mat_id would refer to an identifier from some derived culture from which the nucleic acids were extracted (e.g. xatc123 or ark:/2154/r2). | | +| source rock lithology | optional | Lithology of source rock (https://en.wikipedia.org/wiki/source_rock). if "other" is specified, please propose entry in "additional info" field (Units: year) | | +| sample material type | optional | The type of material from which the sample was obtained. for the hydrocarbon package, samples include types like core, rock trimmings, drill cuttings, piping section, coupon, pigging debris, solid deposit, produced fluid, produced water, injected water, swabs, etc. for the food package, samples are usually categorized as food, body products or tissues, or environmental material. this field accepts terms listed under environmental specimen (http://purl.obolibrary.org/obo/genepio_0001246). | | +| host of the symbiotic host phenotype | optional | Phenotype of the host of the symbiotic host organism. for phenotypic quality ontology (pato) terms, see http://purl.bioontology.org/ontology/pato. | | +| biocide administration method | optional | Method of biocide administration (dose, frequency, duration, time elapsed between last biociding and sampling) (e.g. 150 mg/l; weekly; 4 hr; 3 days) | | +| chemical treatment | optional | List of chemical compounds administered upstream the sampling location where sampling occurred (e.g. glycols, h2s scavenger, corrosion and scale inhibitors, demulsifiers, and other production chemicals etc.). the commercial name of the product and name of the supplier should be provided. the date of administration should also be included | | +| biocide administration | optional | List of biocides (commercial name of product and supplier) and date of administration (Units: year) | | +| chemical treatment method | optional | Method of chemical administration(dose, frequency, duration, time elapsed between administration and sampling) (e.g. 50 mg/l; twice a week; 1 hr; 0 days) (Units: J/K) | | +| negative control type | optional | The substance or equipment used as a negative control in an investigation | | +| positive control type | optional | The substance, mixture, product, or apparatus used to verify that a process which is part of an investigation delivers a true positive. | | +| experimental factor | optional | Experimental factors are essentially the variable aspects of an experiment design which can be used to describe an experiment, or set of experiments, in an increasingly detailed manner. this field accepts ontology terms from experimental factor ontology (efo) and/or ontology for biomedical investigations (obi). for a browser of efo (v 2.95) terms, please see http://purl.bioontology.org/ontology/efo; for a browser of obi (v 2018-02-12) terms please see http://purl.bioontology.org/ontology/obi. e.g. time series design [efo:efo_0001779] | | +| encoded traits | optional | Should include key traits like antibiotic resistance or xenobiotic degradation phenotypes for plasmids, converting genes for phage | | +| subspecific genetic lineage | optional | Information about the genetic distinctness of the sequenced organism below the subspecies level, e.g., serovar, serotype, biotype, ecotype, or any relevant genetic typing schemes like group i plasmid. subspecies should not be recorded in this term, but in the ncbi taxonomy. supply both the lineage name and the lineage rank separated by a colon, e.g., biovar:abc123. | | +| taxonomic classification | optional | Method used for taxonomic classification, along with reference database used, classification rank, and thresholds used to classify new genomes. expected values are: classification method, database name, and other parameters e.g. vcontact vcontact2 (references from ncbi refseq v83, genus rank classification, default parameters) | | +| isolation and growth condition | optional | Publication reference in the form of pubmed id (pmid), digital object identifier (doi) or url for isolation and growth condition specifications of the organism/material. mandatory for migs and mimarks specimen. | | +| annotation source | optional | For cases where annotation was provided by a community jamboree or model organism database rather than by a specific submitter | | +| reference for biomaterial | optional | Primary publication if isolated before genome publication; otherwise, primary genome report. mandatory for migs of bacteria and archaea. | | +| sample subtype | optional | Name of sample sub-type. for example if "sample type" is "produced water" then subtype could be "oil phase" or "water phase". if "other" is specified, please propose entry in "additional info" field (Units: m2) | | +| preservative added to sample | optional | Preservative added to the sample (e.g. rnalater, alcohol, formaldehyde, etc.). where appropriate include volume added (e.g. rnalater; 2 ml) | | +| single cell or viral particle lysis approach | optional | Method used to free dna from interior of the cell(s) or particle(s) | chemical, combination, enzymatic, physical | +| single cell or viral particle lysis kit protocol | optional | Name of the kit or standard protocol used for cell(s) or particle(s) lysis | | +| sample material processing | optional | A brief description of any processing applied to the sample during or after retrieving the sample from environment, or a link to the relevant protocol(s) performed. | | +| sample volume or weight for DNA extraction | optional | Volume (ml) or mass (g) of total collected sample processed for dna extraction. note: total sample collected should be entered under the term 'sample size'. (Units: ng) | | +| nucleic acid extraction | optional | A link to a literature reference, electronic resource or a standard operating procedure (sop), that describes the material separation to recover the nucleic acid fraction from a sample | | +| nucleic acid amplification | optional | A link to a literature reference, electronic resource or a standard operating procedure (sop), that describes the enzymatic amplification (pcr, tma, nasba) of specific nucleic acids | | +| library size | optional | Total number of clones in the library prepared for the project | | +| library reads sequenced | optional | Total number of clones sequenced from the library | | +| library vector | optional | Cloning vector type(s) used in construction of libraries | | +| library screening strategy | optional | Specific enrichment or screening methods applied before and/or after creating clone libraries in order to select a specific group of sequences | | +| pcr conditions | optional | Description of reaction conditions and components for pcr in the form of 'initial denaturation:94degc_1.5min; annealing=...' | | +| pcr primers | optional | Pcr primers that were used to amplify the sequence of the targeted gene, locus or subfragment. this field should contain all the primers used for a single pcr reaction if multiple forward or reverse primers are present in a single pcr reaction. the primer sequence should be reported in uppercase letters | | +| adapters | optional | Adapters provide priming sequences for both amplification and sequencing of the sample-library fragments. both adapters should be reported; in uppercase letters | | +| production start date | optional | Date of field's first production (Units: m) | | +| aromatics wt% | optional | Saturate, aromatic, resin and asphaltene(sara) is an analysis method that divides crude oil components according to their polarizability and polarity. there are three main methods to obtain sara results. the most popular one is known as the iatroscan tlc-fid and is referred to as ip-143 (source: https://en.wikipedia.org/wiki/saturate,_aromatic,_resin_and_asphaltene) (Units: %) | | +| saturates wt% | optional | Saturate, aromatic, resin and asphaltene¬†(sara) is an analysis method that divides¬†crude oil¬†components according to their polarizability and polarity. there are three main methods to obtain sara results. the most popular one is known as the iatroscan tlc-fid and is referred to as ip-143 (source: https://en.wikipedia.org/wiki/saturate,_aromatic,_resin_and_asphaltene) (Units: %) | | +| porosity | optional | Porosity of deposited sediment is volume of voids divided by the total volume of sample | | +| formation water salinity | optional | Original formation water salinity (prior to secondary recovery e.g. waterflooding) expressed as tds (Units: ppm) | | +| basin name | optional | Name of the basin (e.g. campos) (Units: g/m3) | | +| pour point | optional | Temperature at which a liquid becomes semi solid and loses its flow characteristics. in crude oil a high pour point is generally associated with a high paraffin content, typically found in crude deriving from a larger proportion of plant material. (source: https://en.wikipedia.org/wiki/pour_point) (Units: °C) | | +| reservoir name | optional | Name of the reservoir (e.g. carapebus) (Units: °C) | | +| hydrocarbon resource geological age | optional | Geological age of hydrocarbon resource (additional info: https://en.wikipedia.org/wiki/period_(geology)). if "other" is specified, please propose entry in "additional info" field | | +| depositional environment | optional | Main depositional environment (https://en.wikipedia.org/wiki/depositional_environment). if "other" is specified, please propose entry in "additional info" field (Units: m) | | +| source rock kerogen type | optional | Origin of kerogen. type i: algal (aquatic), type ii: planktonic and soft plant material (aquatic or terrestrial), type iii: terrestrial woody/ fibrous plant material (terrestrial), type iv: oxidized recycled woody debris (terrestrial) (additional information: https://en.wikipedia.org/wiki/kerogen). if "other" is specified, please propose entry in "additional info" field (Units: year) | | +| hydrocarbon resource type | optional | Main hydrocarbon resource type. the term "hydrocarbon resource" hcr defined as a natural environmental feature containing large amounts of hydrocarbons at high concentrations potentially suitable for commercial exploitation. this term should not be confused with the hydrocarbon occurrence term which also includes hydrocarbon-rich environments with currently limited commercial interest such as seeps, outcrops, gas hydrates etc. if "other" is specified, please propose entry in "additional info" field (Units: year) | | +| water production rate | optional | Water production rates per well (e.g. 987 m3 / day) (Units: m3/day) | | +| lithology | optional | Hydrocarbon resource main lithology (additional information: http://petrowiki.org/lithology_and_rock_type_determination). if "other" is specified, please propose entry in "additional info" field (Units: year) | | +| hydrocarbon resource original temperature | optional | Original temperature of the hydrocarbon resource (Units: °C) | | +| depth | optional | The vertical distance below local surface, e.g. for sediment or soil samples depth is measured from sediment or soil surface, respectively. depth can be reported as an interval for subsurface samples. (Units: mm) | | +| injection water breakthrough date of specific well | optional | Injection water breakthrough date per well following a secondary and/or tertiary recovery (Units: %) | | + diff --git a/templates/ERC000058/experiment.tsv b/templates/ERC000058/experiment.tsv new file mode 100644 index 0000000..55beb83 --- /dev/null +++ b/templates/ERC000058/experiment.tsv @@ -0,0 +1 @@ +"alias" "title" "study_alias" "sample_alias" "design_description" "library_name" "library_strategy" "library_source" "library_selection" "library_layout" "insert_size" "library_construction_protocol" "platform" "instrument_model" diff --git a/templates/ERC000058/metadata_template_ERC000058.xlsx b/templates/ERC000058/metadata_template_ERC000058.xlsx new file mode 100644 index 0000000..415fd83 Binary files /dev/null and b/templates/ERC000058/metadata_template_ERC000058.xlsx differ diff --git a/templates/ERC000058/run.tsv b/templates/ERC000058/run.tsv new file mode 100644 index 0000000..e752173 --- /dev/null +++ b/templates/ERC000058/run.tsv @@ -0,0 +1 @@ +"alias" "experiment_alias" "file_name" "file_format" diff --git a/templates/ERC000058/sample.tsv b/templates/ERC000058/sample.tsv new file mode 100644 index 0000000..a8163e9 --- /dev/null +++ b/templates/ERC000058/sample.tsv @@ -0,0 +1 @@ +"alias" "title" "taxon_id" "sample_description" "sample true vertical depth subsea" "trophic level" "observed biotic relationship" "known pathogenicity" "relationship to oxygen" "propagation" "sample transport conditions" "sample collection device" "sample collection method" "sample storage temperature" "sample storage location" "source rock depositional environment" "sample measured depth" "corrosion rate at sample location" "sample collection point" "depth (tvdss) of hydrocarbon resource temperature" "oxygenation status of sample" "density" "sample well name" "project name" "ploidy" "number of replicons" "extrachromosomal elements" "estimated size" "target gene" "target subfragment" "multiplex identifiers" "sequence quality check" "chimera check software" "relevant electronic resources" "relevant standard operating procedures" "16s recovered" "well identification number" "water cut" "production rate" "field name" "collection date" "altitude" "geographic location (country and/or sea)" "geographic location (latitude)" "geographic location (longitude)" "geographic location (region and locality)" "broad-scale environmental context" "local environmental context" "environmental medium" "elevation" "secondary and tertiary recovery methods and start date" "amount or size of sample collected" "organism count" "organism count qpcr information" "hydrocarbon type produced" "api gravity" "sample storage duration" "host disease status" "host scientific name" "pressure" "temperature" "pH" "viscosity" "permeability" "oil water contact depth" "hydrocarbon resource original pressure" "source rock geological age" "ammonium" "sample salinity" "calcium" "chloride" "suspended solids" "dissolved carbon dioxide" "dissolved inorganic carbon" "dissolved inorganic phosphorus" "dissolved organic carbon" "magnesium" "nitrate" "nitrite" "total nitrogen concentration" "potassium" "salinity" "sodium" "sulfate" "sulfide" "total phosphorus" "total iron" "volatile fatty acids" "dissolved iron" "resins wt%" "dissolved oxygen in fluids" "total sulfur" "injection water fraction" "ethylbenzene" "vfa in formation water" "total acid number" "sulfate in formation water" "toluene" "asphaltenes wt%" "xylene" "alkalinity method" "benzene" "alkalinity" "source material identifiers" "source rock lithology" "sample material type" "host of the symbiotic host phenotype" "biocide administration method" "chemical treatment" "biocide administration" "chemical treatment method" "negative control type" "positive control type" "experimental factor" "encoded traits" "subspecific genetic lineage" "taxonomic classification" "isolation and growth condition" "annotation source" "reference for biomaterial" "sample subtype" "preservative added to sample" "single cell or viral particle lysis approach" "single cell or viral particle lysis kit protocol" "sample material processing" "sample volume or weight for DNA extraction" "nucleic acid extraction" "nucleic acid amplification" "library size" "library reads sequenced" "library vector" "library screening strategy" "pcr conditions" "pcr primers" "adapters" "production start date" "aromatics wt%" "saturates wt%" "porosity" "formation water salinity" "basin name" "pour point" "reservoir name" "hydrocarbon resource geological age" "depositional environment" "source rock kerogen type" "hydrocarbon resource type" "water production rate" "lithology" "hydrocarbon resource original temperature" "depth" "injection water breakthrough date of specific well" diff --git a/templates/ERC000058/study.tsv b/templates/ERC000058/study.tsv new file mode 100644 index 0000000..fd9fd79 --- /dev/null +++ b/templates/ERC000058/study.tsv @@ -0,0 +1 @@ +"alias" "title" "study_type" "new_study_type" "study_abstract"