From d810d243eb42736ffbb1bd2b19e39ca0d7d2b4bc Mon Sep 17 00:00:00 2001 From: Retype GitHub Action Date: Wed, 5 Jun 2024 17:12:41 +0000 Subject: [PATCH] Refreshes Retype-generated documentation. Process triggered by pdimens. --- 404.html | 8 +- commonoptions/index.html | 10 +- development/index.html | 10 +- haplotagdata/index.html | 18 +- index.html | 8 +- install/index.html | 10 +- issues/index.html | 10 +- modules/align/bwa/index.html | 65 ++-- modules/align/ema/index.html | 68 ++-- modules/align/minimap/index.html | 71 ++-- modules/demultiplex/index.html | 10 +- modules/impute/index.html | 10 +- modules/other/index.html | 10 +- modules/phase/index.html | 13 +- modules/preflight/index.html | 32 +- modules/qc/index.html | 60 +++- modules/simulate/index.html | 333 ++++++++++++++++++ .../simulate/simulate-linkedreads/index.html | 14 +- modules/simulate/simulate-variants/index.html | 10 +- modules/snp/index.html | 10 +- modules/sv/leviathan/index.html | 10 +- modules/sv/naibr/index.html | 10 +- resources/js/config.js | 2 +- resources/js/search.json | 2 +- sitemap.xml.gz | Bin 483 -> 486 bytes snakemake/index.html | 10 +- software/index.html | 8 +- 27 files changed, 585 insertions(+), 237 deletions(-) create mode 100644 modules/simulate/index.html diff --git a/404.html b/404.html index 7f3d76a0a..97f410cae 100644 --- a/404.html +++ b/404.html @@ -4,7 +4,7 @@ - + @@ -29,11 +29,11 @@ - + - + - +
diff --git a/commonoptions/index.html b/commonoptions/index.html index a41d39703..d4c31d595 100644 --- a/commonoptions/index.html +++ b/commonoptions/index.html @@ -4,7 +4,7 @@ - + @@ -32,12 +32,12 @@ - + - + - - + +
diff --git a/development/index.html b/development/index.html index e966395bf..957c2d449 100644 --- a/development/index.html +++ b/development/index.html @@ -4,7 +4,7 @@ - + @@ -34,12 +34,12 @@ - + - + - - + +
diff --git a/haplotagdata/index.html b/haplotagdata/index.html index 50b64cd8c..ada861447 100644 --- a/haplotagdata/index.html +++ b/haplotagdata/index.html @@ -4,7 +4,7 @@ - + @@ -34,11 +34,11 @@ - + - + - + @@ -402,11 +402,11 @@

.fq .fastq - -
    -
  • or uppercase variants
    • -
- + + .FQ + + .FASTQ +
  • gzipped: supported and recommended
  • not gzipped: supported
    • diff --git a/index.html b/index.html index 0b437dd31..46b1c7761 100644 --- a/index.html +++ b/index.html @@ -4,7 +4,7 @@ - + @@ -34,11 +34,11 @@ - + - + - +
    diff --git a/install/index.html b/install/index.html index e54829357..600c1b358 100644 --- a/install/index.html +++ b/install/index.html @@ -4,7 +4,7 @@ - + @@ -32,12 +32,12 @@ - + - + - - + +
    diff --git a/issues/index.html b/issues/index.html index 1d27cae6d..1cbbd7e05 100644 --- a/issues/index.html +++ b/issues/index.html @@ -4,7 +4,7 @@ - + @@ -32,12 +32,12 @@ - + - + - - + +
    diff --git a/modules/align/bwa/index.html b/modules/align/bwa/index.html index dfc389889..ab12e7347 100644 --- a/modules/align/bwa/index.html +++ b/modules/align/bwa/index.html @@ -4,7 +4,7 @@ - + @@ -34,12 +34,12 @@ - + - + - - + + @@ -438,20 +438,17 @@

    ├── Sample1.bam ├── Sample1.bam.bai ├── logs -│ └── markduplicates -│    └── Sample1.markdup.log +│ ├── sample1.bwa.log +│ ├── sample1.markdup.log +│ │── sample1.sort.log └── reports ├── bwa.stats.html - ├── BXstats - │   ├── Sample1.bxstats.html - │ └── data - │ └── Sample1.bxstats.gz - └── coverage -    ├── Sample1.gencov.html - └── data - └── Sample1.gencov.gz - - + ├── Sample1.html + └── data +    ├── bxstats + │ └── Sample1.bxstats.gz + └── coverage + └── Sample1.cov.gz

    @@ -471,10 +468,18 @@

    - + + + + + + + + + @@ -483,28 +488,16 @@

    - - - - - - - - - - - - - - + + - - + + - - + +
    sequence alignment indexes for each sample
    logs/markduplicateslogs/*bwa.logoutput of BWA during run
    logs/*markdup.log stats provided by samtools markdup
    logs/*sort.logoutput of samtools sort
    reports/ various counts/statistics/reports relating to sequence alignment
    report summarizing samtools flagstat and stats results across all samples from multiqc
    reports/reads.bxstats.htmlinteractive html report summarizing valid vs invalid barcodes across all samples
    reports/BXstats/*.bxstats.htmlinteractive html report summarizing inferred molecule size
    reports/coverage/*.htmlsummary plots of alignment coverage per contig
    reports/coverage/data/*.gencov.gzoutput from samtools bedcov from all alignments, used for plotsreports/Sample1.htmlinteractive html report summarizing BX tag metrics and alignment coverage
    reports/BXstats/reports summarizing molecule size and reads per moleculereports/data/coverage/*.cov.gzoutput from samtools cov, used for plots
    reports/BXstats/data/tabular data containing the information used to generate the BXstats reportsreports/data/bxstatstabular data containing the information used to generate the BX stats in reports
    diff --git a/modules/align/ema/index.html b/modules/align/ema/index.html index 7c455dfd3..430bf9a03 100644 --- a/modules/align/ema/index.html +++ b/modules/align/ema/index.html @@ -4,7 +4,7 @@ - + @@ -34,12 +34,12 @@ - + - + - - + + @@ -477,25 +477,23 @@ 

    Align/ema
 ├── Sample1.bam
 ├── Sample1.bam.bai
-├── count
-│   └── Sample1.ema-ncnt
 ├── logs
-│   ├── markduplicates
-│   │   └── Sample1.markdup.nobarcode.log
+│   ├── Sample1.bwa.align.log
+│   ├── Sample1.bwa.sort.log
+│   ├── Sample1.ema.align.log
+│   ├── Sample1.ema.sort.log
+│   ├── Sample1.markdup.log
 │   └── preproc
 │       └── Sample1.preproc.log
 └── reports
     ├── ema.stats.html
     ├── reads.bxcounts.html
-    ├── BXstats
-    │   ├── Sample1.bxstats.html
-    │   └── data
-    │       └── Sample1.bxstats.gz
-    └── coverage
-        ├── Sample1.gencov.html
-        └── data
-            ├── Sample1.all.gencov.gz
-            └── Sample1.bx.gencov.gz
+    ├── Sample1.html
+    └── data
+        ├── bxstats
+        │   └── Sample1.bxstats.gz
+        └── coverage
+            └── Sample1.cov.gz

    @@ -516,14 +514,6 @@

    sequence alignment indexes for each sample -count/ -output of ema count - - -logs/markduplicates/ -stats provided by samtools markdup for alignments with invalid/missing barcodes - - logs/preproc/*.preproc.log everything ema preproc writes to stderr during operation @@ -536,32 +526,20 @@

    report summarizing samtools flagstat and stats results across all samples from multiqc -reports/reads.bxstats.html +reports/reads.bxcounts.html interactive html report summarizing ema count across all samples -reports/coverage/*.html -summary plots of alignment coverage per contig - - -reports/coverage/data/*.all.gencov.gz -output from samtools bedcov from all alignments, used for plots - - -reports/coverage/data/*.bx.gencov.gz -output from samtools bedcov from alignments with valid BX barcodes, used for plots - - -reports/BXstats/ -reports summarizing molecule size and reads per molecule +reports/Sample1.html +interactive html report summarizing BX tag metrics and alignment coverage -reports/BXstats/*.bxstats.html -interactive html report summarizing inferred molecule size +reports/data/coverage/*.cov.gz +output from samtools cov, used for plots -reports/BXstats/data/ -tabular data containing the information used to generate the BXstats reports +reports/data/bxstats +tabular data containing the information used to generate the BX stats in reports diff --git a/modules/align/minimap/index.html b/modules/align/minimap/index.html index efa4060be..e4afaf2ea 100644 --- a/modules/align/minimap/index.html +++ b/modules/align/minimap/index.html @@ -4,7 +4,7 @@ - + @@ -34,12 +34,12 @@ - + - + - - + + @@ -438,24 +438,21 @@

    The default output directory is Align/minimap with the folder structure below. Sample1 is a generic sample name for demonstration purposes. The resulting folder also includes a workflow directory (not shown) with workflow-relevant runtime files and information.

    -
    Align/bwa
+
    Align/minimap
 ├── Sample1.bam
 ├── Sample1.bam.bai
 ├── logs
-│   └── markduplicates
-│       └── Sample1.markdup.log
+│   ├── sample1.minimap.log
+│   ├── sample1.markdup.log
+│   │── sample1.sort.log
 └── reports
     ├── minimap.stats.html
-    ├── BXstats
-    │   ├── Sample1.bxstats.html
-    │   └── data
-    │       └── Sample1.bxstats.gz
-    └── coverage
-        ├── Sample1.gencov.html
-        └── data
-            └── Sample1.gencov.gz
-
-
    
+    ├── Sample1.html
+    └── data
+        ├── bxstats
+        │   └── Sample1.bxstats.gz
+        └── coverage
+            └── Sample1.cov.gz
    @@ -475,10 +472,18 @@

    - + + + + + + + + + @@ -487,28 +492,16 @@

    - - - - - - - - - - - - - - + + - - + + - - + +
    sequence alignment indexes for each sample
    logs/markduplicateslogs/*bwa.logoutput of minimap2 during run
    logs/*markdup.log stats provided by samtools markdup
    logs/*sort.logoutput of samtools sort
    reports/ various counts/statistics/reports relating to sequence alignment
    report summarizing samtools flagstat and stats results across all samples from multiqc
    reports/reads.bxstats.htmlinteractive html report summarizing valid vs invalid barcodes across all samples
    reports/BXstats/*.bxstats.htmlinteractive html report summarizing inferred molecule size
    reports/coverage/*.htmlsummary plots of alignment coverage per contig
    reports/coverage/data/*.gencov.gzoutput from samtools bedcov from all alignments, used for plotsreports/Sample1.htmlinteractive html report summarizing BX tag metrics and alignment coverage
    reports/BXstats/reports summarizing molecule size and reads per moleculereports/data/coverage/*.cov.gzoutput from samtools cov, used for plots
    reports/BXstats/data/tabular data containing the information used to generate the BXstats reportsreports/data/bxstatstabular data containing the information used to generate the BX stats in reports
    @@ -623,10 +616,10 @@

    - + Next - Linked Reads + Simulate diff --git a/modules/demultiplex/index.html b/modules/demultiplex/index.html index 0c949ff92..63f939754 100644 --- a/modules/demultiplex/index.html +++ b/modules/demultiplex/index.html @@ -4,7 +4,7 @@ - + @@ -34,12 +34,12 @@ - + - + - - + + diff --git a/modules/impute/index.html b/modules/impute/index.html index ae581406b..869639779 100644 --- a/modules/impute/index.html +++ b/modules/impute/index.html @@ -4,7 +4,7 @@ - + @@ -34,12 +34,12 @@ - + - + - - + + diff --git a/modules/other/index.html b/modules/other/index.html index 20275a473..a802e4dcf 100644 --- a/modules/other/index.html +++ b/modules/other/index.html @@ -4,7 +4,7 @@ - + @@ -32,12 +32,12 @@ - + - + - - + +
    diff --git a/modules/phase/index.html b/modules/phase/index.html index ab3bd381d..3b59e1f3d 100644 --- a/modules/phase/index.html +++ b/modules/phase/index.html @@ -4,7 +4,7 @@ - + @@ -34,12 +34,12 @@ - + - + - - + + @@ -461,9 +461,6 @@

    ├── annotations │   ├── Sample1.annot.gz │   └── Sample1.annot.gz.tbi -├── annotations_merge -│   ├── Sample1.phased.annot.bcf -│   └── Sample1.phased.annot.bcf.csi ├── extractHairs │   ├── Sample1.unlinked.frags │   └── logs diff --git a/modules/preflight/index.html b/modules/preflight/index.html index 6d0bd8707..0e7984807 100644 --- a/modules/preflight/index.html +++ b/modules/preflight/index.html @@ -4,7 +4,7 @@ - + @@ -34,12 +34,12 @@ - + - + - - + +
    @@ -236,10 +236,14 @@

    • at least 2 cores/threads available
      • -
    • bam: SAM/BAM alignment files +
    • + preflight bam +: SAM/BAM alignment files BAM recommended
      • -
    • fastq: paired-end reads from an Illumina sequencer in FASTQ format +
    • + preflight fastq +: paired-end reads from an Illumina sequencer in FASTQ format gzip recommended
    @@ -254,14 +258,18 @@

    preflight bam submodules and the result of each is a report detailing file format quality checks.

    -

    +

    # - when to run -

    + When to run +

      -
    • FASTQ: the preflight checks for FASTQ files are best performed after demultiplexing (or trimming/QC) and before sequence alignment
      • -
    • BAM: the preflight checks for BAM files should be run after sequence alignment and before consuming those files for other purposes +
    • + preflight fastq +: the preflight checks for FASTQ files are best performed after demultiplexing (or trimming/QC) and before sequence alignment
      • +
    • + preflight bam +: the preflight checks for BAM files should be run after sequence alignment and before consuming those files for other purposes (e.g. variant calling, phasing, imputation)
    diff --git a/modules/qc/index.html b/modules/qc/index.html index 8f045933d..35138dd37 100644 --- a/modules/qc/index.html +++ b/modules/qc/index.html @@ -4,7 +4,7 @@ - + @@ -34,12 +34,12 @@ - + - + - - + + @@ -237,9 +237,55 @@

    • at least 2 cores/threads available
      • -
    • paired-end fastq sequence files +
    • paired-end fastq sequence files gzip recommended + +
        +
      • forward: + _F + + .F + + _R1_001 + + .R1_001 + + _R1 + + .R1
        • +
      • reverse: + _R + + .R + + _R2_001 + + .R2_001 + + _R2 + + .R2 + +
          +
        • note that this does not include + .1 + or + _1 + conventions for forward/reverse
          • +
        +
        • +
      • fastq extension: + .fq + + .fastq + + .FQ + + .FASTQ +
        • +
      +

    Raw sequences are not suitable for downstream analyses. They have sequencing adapters, @@ -247,7 +293,7 @@

    analyses is to remove these adapters and trim poor quality data. You can remove adapters and quality trim sequences using the qc -` module:

    + module:

    usage
    harpy qc OPTIONS... INPUTS...
    diff --git a/modules/simulate/index.html b/modules/simulate/index.html new file mode 100644 index 000000000..f45e295b6 --- /dev/null +++ b/modules/simulate/index.html @@ -0,0 +1,333 @@ + + + + + + + + + + + + + Simulate Genomic Data | Harpy + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
    +
    + +
    +
    + + +
    + + +
    +
    + +
    + + +
    + +
    + + + + +
    + + + + + +
    + +
    + + +
    + + +
    + +
    +
    + +
    +
    + + + + +
    +
    +
    +
    + +
    + +
    + + +
    + +
    + +
    +
    +
    +
    +
    +
    +
    +
    + +
    + + Powered by + + +
    +
    + + + + + + +
    + +
    +
    +
    +
    + +
    + + +

    + # + Simulate Genomic Data +

    +     +

    You may be interested in benchmarking variant detection or maybe just trying out +haplotagging data without any financial commitment-- that's where simulations +come in handy.

    + +

    + # + Simulate Genomic Variants +

    +     +

    Harpy lets you simulate genomic variants via + simulate {snpindel,inversion,...} + for different variant +types such as single nucleotide polymorphisms (SNP), indels, inversions, copy number variants (CNV), and translocations. All you need is to provide a genome to simulate +those variants onto.

    + +

    + # + Simulate Haplotag Linked-Reads +

    +     +

    You can also simulate haplotag-style linked reads from an existing genome using + simulate linkedreads +. Harpy +incorporates LRSIM to generate linked reads +from a diploid genomic. If you only have a haploid genome, then you can create a diploid genome by simulating variants into it with + simulate {snpindel,inversion,...} +.

    + + + + +
    + +
    + +
    +
    +
    +
      +
    +
    +

    © Copyright 2024. All rights reserved.

    +
    +
    +
    + + + +
    +
    +
    +
    +
    +
    +
    + + + +
    + +
    +
    + + + +
    + + +
    + + + + diff --git a/modules/simulate/simulate-linkedreads/index.html b/modules/simulate/simulate-linkedreads/index.html index 6e9588b39..7cd65dcd3 100644 --- a/modules/simulate/simulate-linkedreads/index.html +++ b/modules/simulate/simulate-linkedreads/index.html @@ -4,7 +4,7 @@ - + @@ -34,12 +34,12 @@ - + - + - - + + @@ -542,11 +542,11 @@