Merge pull request #43 from EBI-Metagenomics/dev

Dev -> main for release v1.3

.nf-core.yml

@@ -2,14 +2,14 @@ repository_type: pipeline
 lint:
   files_exist:
     - CODE_OF_CONDUCT.md
+    - CHANGELOG.md
     - assets/nf-core-mettannotator_logo_light.png
     - docs/images/nf-core-mettannotator_logo_light.png
     - docs/images/nf-core-mettannotator_logo_dark.png
     - .github/ISSUE_TEMPLATE/config.yml
     - conf/test_full.config
     - docs/output.md
     - docs/README.md
-    - docs/README.md
     - docs/usage.md
     - conf/igenomes.config
     - .github/workflows/awstest.yml

CITATIONS.md

@@ -1,5 +1,9 @@
 # ebi-metagenomics/mettannotator: Citations
 
+## [mettannotator: a comprehensive and scalable Nextflow annotation pipeline for prokaryotic assemblies (pre-print)](https://doi.org/10.1101/2024.07.11.603040)
+
+> Gurbich TA, Beracochea M, De Silva NH, Finn RD. mettannotator: a comprehensive and scalable Nextflow annotation pipeline for prokaryotic assemblies. doi: https://doi.org/10.1101/2024.07.11.603040
+
 ## [MGnify Genomes](https://pubmed.ncbi.nlm.nih.gov/36806692/)
 
 > Gurbich TA, Almeida A, Beracochea M, Burdett T, Burgin J, Cochrane G, Raj S, Richardson L, Rogers AB, Sakharova E, Salazar GA and Finn RD. MGnify Genomes: A Resource for Biome-specific Microbial Genome Catalogues. J Mol Biol. 2023 Jul; 435(14). doi: https://doi.org/10.1016/j.jmb.2023.168016. PubMed PMID:

README.md

@@ -200,7 +200,9 @@ Input/output options
   --multiqc_title                    [string]  MultiQC report title. Printed as page header, used for filename if not otherwise specified.
 
 Reference databases
-  --dbs                              [string]  Folder for the tools' reference databases used by the pipeline for downloading.
+  --dbs                              [string]  Folder for the tools' reference databases used by the pipeline for downloading. It's important to note that
+                                               mixing the --dbs flag with individual database paths and versions is not allowed; they are mutually
+                                               exclusive.
   --interproscan_db                  [string]  The InterProScan reference database, ftp://ftp.ebi.ac.uk/pub/software/unix/iprscan/
   --interproscan_db_version          [string]  The InterProScan reference database version. [default: 5.62-94.0]
   --interpro_entry_list              [string]  TSV file listing basic InterPro entry information - the accessions, types and names,
@@ -262,6 +264,18 @@ nextflow run ebi-metagenomics/mettannotator \
 > provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_;
 > see [docs](https://nf-co.re/usage/configuration#custom-configuration-files).
 
+#### Local execution
+
+The pipeline can be run on a desktop or laptop, with the caveat that it will take a few hours to complete depending on the resources. There is a local profile in the Nextflow config that limits the total resources the pipeline can use to 8 cores and 12 GB of RAM. In order to run it (Docker or Singularity are still required):
+
+```bash
+nextflow run ebi-metagenomics/mettannotator \
+   -profile local,<docker or singulairty> \
+   --input assemblies_sheet.csv \
+   --outdir <OUTDIR> \
+   --dbs <PATH/TO/WHERE/DBS/WILL/BE/SAVED>
+```
+
 ### Gene caller choice
 
 By default, `mettannotator` uses Prokka to identify protein-coding genes. Users can choose to use Bakta instead by

assets/methods_description_template.yml

@@ -12,6 +12,7 @@ data: |
   <p>${tool_citations}</p>
   <h4>References</h4>
   <ul>
+    <li>Gurbich, T. A., Beracochea, M., De Silva, N. H., & Finn, R. D. (2024). mettannotator: a comprehensive and scalable Nextflow annotation pipeline for prokaryotic assemblies. doi: <a href="https://doi.org/10.1101/2024.07.11.603040">10.1101/2024.07.11.603040</a></li>
     <li>Di Tommaso, P., Chatzou, M., Floden, E. W., Barja, P. P., Palumbo, E., & Notredame, C. (2017). Nextflow enables reproducible computational workflows. Nature Biotechnology, 35(4), 316-319. doi: <a href="https://doi.org/10.1038/nbt.3820">10.1038/nbt.3820</a></li>
     <li>Ewels, P. A., Peltzer, A., Fillinger, S., Patel, H., Alneberg, J., Wilm, A., Garcia, M. U., Di Tommaso, P., & Nahnsen, S. (2020). The nf-core framework for community-curated bioinformatics pipelines. Nature Biotechnology, 38(3), 276-278. doi: <a href="https://doi.org/10.1038/s41587-020-0439-x">10.1038/s41587-020-0439-x</a></li>
     <li>Grüning, B., Dale, R., Sjödin, A., Chapman, B. A., Rowe, J., Tomkins-Tinch, C. H., Valieris, R., Köster, J., & Bioconda Team. (2018). Bioconda: sustainable and comprehensive software distribution for the life sciences. Nature Methods, 15(7), 475–476. doi: <a href="https://doi.org/10.1038/s41592-018-0046-7">10.1038/s41592-018-0046-7</a></li>

assets/multiqc_config.yml

@@ -1,5 +1,5 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/ebi-metagenomics/mettannotator/1.0dev" target="_blank">ebi-metagenomics/mettannotator</a>
+  This report has been generated by the <a href="https://github.com/ebi-metagenomics/mettannotator" target="_blank">ebi-metagenomics/mettannotator</a>
   analysis pipeline.
 report_section_order:
   "ebi-metagenomics-mettannotator-methods-description":

modules/local/eggnog.nf

@@ -17,17 +17,25 @@ process EGGNOG_MAPPER {
     path "versions.yml", emit: versions
 
     script:
+    def db_mem_flag = ""
+    /*
+    The required memory of the executor needs to be greater than 44GB
+    to be able to load the eggnog SQLite database into memory.
+    Docs: https://github.com/eggnogdb/eggnog-mapper/wiki/eggNOG-mapper-v2.1.5-to-v2.1.12#a-few-recipes
+    */
+    if ( task.memory >= 44.GB ) {
+        db_mem_flag = "--dbmem"
+    }
     if ( mode == "mapper" )
         """
         emapper.py -i ${fasta} \
         --database ${eggnog_db_dir}/eggnog.db \
         --dmnd_db ${eggnog_db_dir}/eggnog_proteins.dmnd \
         --data_dir ${eggnog_db_dir} \
-        --dbmem \
         -m diamond \
         --no_file_comments \
         --cpu ${task.cpus} \
-        --no_annot \
+        --no_annot ${db_mem_flag} \
         -o ${meta.prefix}
 
         cat <<-END_VERSIONS > versions.yml
@@ -43,8 +51,7 @@ process EGGNOG_MAPPER {
         --no_file_comments \
         --cpu ${task.cpus} \
         --tax_scope 'prokaryota_broad' \
-        --dbmem \
-        --annotate_hits_table ${annotation_hit_table} \
+        --annotate_hits_table ${annotation_hit_table} ${db_mem_flag} \
         -o ${meta.prefix}
 
         cat <<-END_VERSIONS > versions.yml

modules/local/interproscan.nf

@@ -11,7 +11,7 @@ process INTERPROSCAN {
         if (workflow.containerEngine == 'singularity') {
             return "--bind ${interproscan_db}/data:/opt/interproscan-5.62-94.0/data"
         } else {
-            return "-v ${interproscan_db}/data:/opt/interproscan-5.62-94.0/data"
+            return "-v ./${interproscan_db}/data:/opt/interproscan-5.62-94.0/data"
         }
     }
 

modules/local/unifire.nf

@@ -5,11 +5,12 @@ process UNIFIRE {
     label 'error_retry'
 
     container "dockerhub.ebi.ac.uk/uniprot-public/unifire:2023.4"
+
     containerOptions {
         if (workflow.containerEngine == 'singularity') {
             return "--bind unifire:/volume"
         } else {
-            return "-v unifire:/volume"
+            return "-v ./unifire:/volume"
         }
     }
 

nextflow.config

@@ -175,6 +175,14 @@ profiles {
     }
     test      { includeConfig 'conf/test.config'      }
 
+    local {
+        params {
+            // Any modern laptop / desktop should have at least...
+            max_memory = "12GB"
+            max_cpus   = 8
+        }
+    }
+
     ebi {
         params.workdir = "/hps/nobackup/rdf/metagenomics/service-team/nextflow-workdir/mett-pipeline"
         params.singularity_cachedir = "/hps/nobackup/rdf/metagenomics/service-team/singularity-cache/"
@@ -274,8 +282,8 @@ manifest {
     description     = """ME TT assembly annotation pipeline"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=23.04.0'
-    version         = '1.2'
-    doi             = ''
+    version         = '1.3'
+    doi             = 'https://doi.org/10.1101/2024.07.11.603040'
 }
 
 // Load modules.config for DSL2 module specific options

nextflow_schema.json

@@ -62,7 +62,7 @@
         "dbs": {
           "type": "string",
           "format": "directory-path",
-          "description": "Folder for the tools' reference databases used by the pipeline for downloading.",
+          "description": "Folder for the tools' reference databases used by the pipeline for downloading. It's important to note that mixing the --dbs flag with individual database paths and versions is not allowed; they are mutually exclusive.",
           "help_text": "Set this parameter to trigger the reference database download; otherwise, specify the databases individually."
         },
         "interproscan_db": {