Merge pull request #8 from bio-raum/dev

Dev

README.md

@@ -15,3 +15,9 @@ If you are really impatient, check out our [quickstart](docs/quickstart.md) guid
 5. [Software](docs/software.md)
 5. [Troubleshooting](docs/troubleshooting.md)
 6. [Developer guide](docs/developer.md)
+
+## Developer team
+
+FooDMe2 is developed and supported by the following people and organizations:
+
+[Marc Höppner](https://github.com/marchoeppner), Landeslabor Schleswig-Holstein, [LSH](https://www.schleswig-holstein.de/DE/landesregierung/ministerien-behoerden/LLABOR)

conf/modules.config

@@ -127,6 +127,14 @@ process {
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
+    withName: SAMTOOLS_MERGE {
+       publishDir = [
+            path: { "${params.outdir}/samples/${meta.sample_id}/bam" },
+            mode: params.publish_dir_mode,
+            enabled: false,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ] 
+    }
     withName: 'BWAMEM2_MEM|BWAMEM2_INDEX' {
         publishDir = [
             path: { "${params.outdir}/samples/${meta.sample_id}/bwamem" },
@@ -175,6 +183,22 @@ process {
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
+    withName: 'SNIPPY_RUN' {
+        publishDir = [
+            path: { "${params.outdir}/samples/${meta.sample_id}/variants/" },
+            mode: params.publish_dir_mode,
+            enabled: true,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+    withName: 'TABIX_TABIX|BCFTOOLS_STATS' {
+        publishDir = [
+            path: { "${params.outdir}/samples/${meta.sample_id}/variants/${meta.sample_id}" },
+            mode: params.publish_dir_mode,
+            enabled: true,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
     withName: FASTQC {
         publishDir = [
             path: { "${params.outdir}/samples/${meta.sample_id}/qc/fastqc" },
@@ -430,6 +454,7 @@ process {
         ]
     }
     withName: 'CHEWBBACA_ALLELECALL_SINGLE' {
+        ext.args = "--no-inferred"
         publishDir = [
             path: { "${params.outdir}/samples/${meta.sample_id}/chewbbaca" },
             mode: params.publish_dir_mode,
@@ -446,7 +471,7 @@ process {
 	]   
     }
     withName: 'CHEWBBACA_ALLELECALL' {
-
+        ext.args = "--no-inferred"
         publishDir = [
             path: { "${params.outdir}/cgMLST/chewbbaca/${meta.sample_id}" },
             mode: params.publish_dir_mode,

conf/multiqc_config.yaml

@@ -38,3 +38,5 @@ report_section_order:
 remove_sections:
     - mosdepth-coverage-dist-cov
     - mosdepth-coverage-per-contig-section
+    - bcftools-stats_variant_quality_plot
+    - bcftools-stats_indel_plot

main.nf

@@ -19,6 +19,19 @@ params.version = workflow.manifest.version
 
 summary = [:]
 
+summary["MaxContigs"]           = params.skip_failed ? params.max_contigs : "Not applied"
+summary["Busco"]                = params.busco_lineage
+summary["ConfindR DB"]          = params.confindr_db ? params.confindr_db : "built-in"
+summary["Max Coverage"]         = params.subsample_reads ? params.max_coverage : "Not applied"
+summary["Genome size"]          = params.subsample_reads ? params.genome_size : "Not applied"
+summary["Shovill assembler"]    = params.shovill_assembler
+summary["AMRfinder"]            = [:]
+summary["Abricate"]             = [:]
+summary["AMRfinder"]["min_cov"] = params.arg_amrfinderplus_coveragemin
+summary["AMRfinder"]["min_id"]  = params.arg_amrfinderplus_identmin
+summary["Abricate"]["min_id"]   = params.arg_abricate_minid
+summary["Abricate"]["min_cov"]  = params.arg_abricate_mincov
+
 run_name = (params.run_name == false) ? "${workflow.sessionId}" : "${params.run_name}"
 
 WorkflowMain.initialise(workflow, params, log)
@@ -50,10 +63,6 @@ workflow.onComplete {
     emailFields['session'] = workflow.sessionId
     emailFields['runName'] = run_name
     emailFields['Subsampling'] = params.subsample_reads
-    if (params.subsample_reads) {
-        emailFields['Maximum coverage'] = params.max_coverage
-        emailFields['Genome size'] = params.genome_size
-    }
     emailFields['success'] = workflow.success
     emailFields['dateStarted'] = workflow.start
     emailFields['dateComplete'] = workflow.complete
@@ -103,13 +112,11 @@ workflow.onComplete {
             if (workflow.success && !params.skip_multiqc) {
                 mqcReport = multiqc_report.getVal()
                 if (mqcReport.getClass() == ArrayList) {
-                    // TODO: Update name of pipeline
                     log.warn "[bio-raum/gabi] Found multiple reports from process 'multiqc', will use only one"
                     mqcReport = mqcReport[0]
                 }
             }
         } catch (all) {
-            // TODO: Update name of pipeline
             log.warn '[bio-raum/gabi] Could not attach MultiQC report to summary email'
         }
 

modules/bcftools/stats/environment.yml

@@ -0,0 +1,8 @@
+name: bcftools_stats
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - bioconda::bcftools=1.20
+  - bioconda::htslib=1.20

modules/bcftools/stats/main.nf

@@ -0,0 +1,34 @@
+process BCFTOOLS_STATS {
+    tag "$meta.sample_id"
+    label 'short_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bcftools:1.20--h8b25389_0':
+        'quay.io/biocontainers/bcftools:1.20--h8b25389_0' }"
+
+    input:
+    tuple val(meta),  path(vcf), path(tbi)
+
+    output:
+    tuple val(meta), path("*stats.txt"), emit: stats
+    path  "versions.yml"               , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.sample_id}"
+
+    """
+    bcftools stats \\
+        $args \\
+        $vcf > ${prefix}.bcftools_stats.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/bcftools/stats/meta.yml

@@ -0,0 +1,77 @@
+name: bcftools_stats
+description: Generates stats from VCF files
+keywords:
+  - variant calling
+  - stats
+  - VCF
+tools:
+  - stats:
+      description: |
+        Parses VCF or BCF and produces text file stats which is suitable for
+        machine processing and can be plotted using plot-vcfstats.
+      homepage: http://samtools.github.io/bcftools/bcftools.html
+      documentation: http://www.htslib.org/doc/bcftools.html
+      doi: 10.1093/bioinformatics/btp352
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: VCF input file
+      pattern: "*.{vcf}"
+  - tbi:
+      type: file
+      description: |
+        The tab index for the VCF file to be inspected. Optional: only required when parameter regions is chosen.
+      pattern: "*.tbi"
+  - regions:
+      type: file
+      description: |
+        Optionally, restrict the operation to regions listed in this file. (VCF, BED or tab-delimited)
+  - targets:
+      type: file
+      description: |
+        Optionally, restrict the operation to regions listed in this file (doesn't rely upon tbi index files)
+  - samples:
+      type: file
+      description: |
+        Optional, file of sample names to be included or excluded.
+        e.g. 'file.tsv'
+  - exons:
+      type: file
+      description: |
+        Tab-delimited file with exons for indel frameshifts (chr,beg,end; 1-based, inclusive, optionally bgzip compressed).
+        e.g. 'exons.tsv.gz'
+  - fasta:
+      type: file
+      description: |
+        Faidx indexed reference sequence file to determine INDEL context.
+        e.g. 'reference.fa'
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - stats:
+      type: file
+      description: Text output file containing stats
+      pattern: "*_{stats.txt}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@joseespinosa"
+  - "@drpatelh"
+  - "@SusiJo"
+  - "@TCLamnidis"
+maintainers:
+  - "@joseespinosa"
+  - "@drpatelh"
+  - "@SusiJo"
+  - "@TCLamnidis"