Adding Snippy to count SNPs in the finished assembly

bio-raum · Oct 2, 2024 · 19c89f8 · 19c89f8
1 parent 60ad4c9
commit 19c89f8
Show file tree

Hide file tree

Showing 46 changed files with 2,337 additions and 6 deletions.
diff --git a/conf/modules.config b/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 +183,14 @@ 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: FASTQC {
         publishDir = [
             path: { "${params.outdir}/samples/${meta.sample_id}/qc/fastqc" },

diff --git a/modules/bcftools/stats/environment.yml b/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
diff --git a/modules/bcftools/stats/main.nf b/modules/bcftools/stats/main.nf
@@ -0,0 +1,46 @@
+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
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    touch ${prefix}.bcftools_stats.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//')
+    END_VERSIONS
+    """
+}
diff --git a/modules/bcftools/stats/meta.yml b/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"
diff --git a/modules/bcftools/stats/tests/main.nf.test b/modules/bcftools/stats/tests/main.nf.test
@@ -0,0 +1,182 @@
+nextflow_process {
+
+    name "Test Process BCFTOOLS_STATS"
+    script "../main.nf"
+    process "BCFTOOLS_STATS"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "bcftools"
+    tag "bcftools/stats"
+
+    test("sarscov2 - vcf_gz") {
+
+        when {
+            process {
+                """
+                input[0] = [ [ id:'test' ], // meta map
+                            file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test.vcf.gz', checkIfExists: true),
+                            []]
+                input[1] = [ [], [] ]
+                input[2] = [ [], [] ]
+                input[3] = [ [], [] ]
+                input[4] = [ [], [] ]
+                input[5] = [ [], [] ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match("versions") },
+                { assert snapshot(file(process.out.stats.get(0).get(1)).readLines()[0..5]).match() },
+            )
+        }
+
+    }
+
+    test("sarscov2 - vcf_gz - regions") {
+
+        when {
+            process {
+                """
+                input[0] = [ [ id:'regions_test' ], // meta map
+                            file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test.vcf.gz', checkIfExists: true),
+                            file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test.vcf.gz.tbi', checkIfExists: true)]
+                input[1] = [ [id:'regions_test'],
+                            file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test3.vcf.gz', checkIfExists: true) ]
+                input[2] = [ [], [] ]
+                input[3] = [ [], [] ]
+                input[4] = [ [], [] ]
+                input[5] = [ [], [] ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match("regions_versions") },
+                { assert snapshot(file(process.out.stats.get(0).get(1)).readLines()[0..5]).match() },
+            )
+        }
+
+    }
+
+    test("sarscov2 - vcf_gz - targets") {
+
+        when {
+            process {
+                """
+                input[0] = [ [ id:'targets_test' ], // meta map
+                            file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test.vcf.gz', checkIfExists: true),
+                            [] ]
+                input[1] = [ [], [] ]
+                input[2] = [ [id:'targets_test'],
+                            file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test2.targets.tsv.gz', checkIfExists: true)
+                            ]
+                input[3] = [ [], [] ]
+                input[4] = [ [], [] ]
+                input[5] = [ [], [] ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match("targets_versions") },
+                { assert snapshot(file(process.out.stats.get(0).get(1)).readLines()[0..5]).match() },
+            )
+        }
+
+    }
+
+    test("sarscov2 - vcf_gz - exons") {
+
+        when {
+            process {
+                """
+                input[0] = [ [ id:'exon_test' ], // meta map
+                            file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test.vcf.gz', checkIfExists: true),
+                            [] ]
+                input[1] = [ [], [] ]
+                input[2] = [ [], [] ]
+                input[3] = [ [], [] ]
+                input[4] = [ [id: "exon_test"],
+                            file(params.modules_testdata_base_path + 'delete_me/bcftools/stats/exons.tsv.gz', checkIfExists: true) ]
+                input[5] = [ [], [] ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match("exon_versions") },
+                { assert snapshot(file(process.out.stats.get(0).get(1)).readLines()[0..5]).match() },
+            )
+        }
+
+    }
+
+    test("sarscov2 - vcf_gz - reference") {
+
+        when {
+            process {
+                """
+                input[0] = [ [ id:'ref_test' ], // meta map
+                            file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test.vcf.gz', checkIfExists: true),
+                            [] ]
+                input[1] = [ [], [] ]
+                input[2] = [ [], [] ]
+                input[3] = [ [], [] ]
+                input[4] = [ [], [] ]
+                input[5] = [ [id: 'ref_test'],
+                            file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                            ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match("ref_versions") },
+                { assert snapshot(file(process.out.stats.get(0).get(1)).readLines()[0..5]).match() },
+            )
+        }
+
+    }
+
+
+    test("sarscov2 - vcf_gz - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [ [ id:'test' ], // meta map
+                            file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/vcf/test.vcf.gz', checkIfExists: true),
+                            []]
+                input[1] = [ [], [] ]
+                input[2] = [ [], [] ]
+                input[3] = [ [], [] ]
+                input[4] = [ [], [] ]
+                input[5] = [ [], [] ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}