Feature/variant calling

.gitignore

@@ -334,3 +334,5 @@ fabric.properties
 .nf-test/
 .nf-test/*
 .nf-test*
+
+null/

conf/hpc.config

@@ -18,6 +18,8 @@ params {
     ref_flat                     = "${params.dx_tracks_path}/rna/${params.gencode_version_name}.ref_annot.gtf.refflat"
     rrna_intervals               = "${params.dx_tracks_path}/rna/GRCh38_rRNA_genbank.interval_list"
 
+    // dbSNP
+    dbsnp = "/hpc/diaggen/data/databases/dbSNP/dbSNP_v156.vcf.gz"
 
     // Fusion config
     starfusion_ref       = params.genome_base
@@ -66,4 +68,6 @@ params {
         ]
     ]
 
+    cache_dir = "/hpc/diaggen/data/databases/Nextflow_cache/DxNextflowRNA/"
+
 }

conf/modules.config

@@ -70,6 +70,70 @@ process {
         scratch = true
     }
 
+    withName: GATK4_BEDTOINTERVALLIST {
+        ext.args = '--DROP_MISSING_CONTIGS TRUE'
+        storeDir = params.cache_dir ? "${params.cache_dir}/gatk4/bedtointervallist" : null
+    }
+
+    withName: GATK4_CREATESEQUENCEDICTIONARY {
+        storeDir = params.cache_dir ? "${params.cache_dir}/gatk4/createsequencedictionary" : null
+    }
+
+    withName: GATK4_INTERVALLISTTOOLS {
+        ext.args    = { [
+            "--SUBDIVISION_MODE BALANCING_WITHOUT_INTERVAL_SUBDIVISION_WITH_OVERFLOW",
+            "--UNIQUE true",
+            "--SORT true",
+            "--SCATTER_COUNT ${params.scatter_size}"
+        ].join(' ').trim() }
+        storeDir = params.cache_dir ? "${params.cache_dir}/gatk4/intervallisttools" : null
+    }
+
+    withName: GATK4_HAPLOTYPECALLER {
+        cpus   = 2
+        memory = { 8.GB * task.attempt }
+        time   = { 4.h  * task.attempt }
+        array  = params.scatter_size
+
+        ext.args = { [
+            "--dont-use-soft-clipped-bases",
+            "--standard-min-confidence-threshold-for-calling ${params.min_confidence_threshold}",
+            "--emit-ref-confidence GVCF"
+        ].join(' ').trim() }
+    }
+
+    withName: GATK4_SPLITNCIGARREADS {
+        cpus   = 2
+        memory = { 16.GB * task.attempt }
+        time   = { 4.h   * task.attempt }
+        array  = params.scatter_size
+
+        ext.args    =  '--create-output-bam-index false'
+        ext.prefix  = { "${meta.id}.splitncigarreads" }
+    }
+
+    withName: GATK4_VARIANTFILTRATION {
+        cpus   = 1
+        memory = { 6.GB * task.attempt }
+        time   = { 2.h  * task.attempt }
+
+        ext.prefix  = { "${meta.id}.hc.filtered" }
+        ext.args    = { [
+            params.gatk_vf_window_size ? "--cluster-window-size ${params.gatk_vf_window_size}" : '',
+            params.gatk_vf_cluster_size ? "--cluster-size ${params.gatk_vf_cluster_size}" : '',
+            params.gatk_vf_fs_filter ? "--filter-name \"FS\" --filter-expression \"FS > ${params.gatk_vf_fs_filter}\" " : '',
+            params.gatk_vf_qd_filter ? "--filter-name \"QD\" --filter-expression \"QD < ${params.gatk_vf_qd_filter}\" " : '',
+        ].join(' ').trim() }
+        publishDir  = [
+            path: { "${params.outdir}/variant_calling/" },
+            mode: params.publish_dir_mode
+        ]
+    }
+
+    withName: BEDOPS_GTF2BED {
+        storeDir = params.cache_dir ? "${params.cache_dir}/gtf2bed" : null
+    }
+
     withName: HGNC_DOWNLOAD {
         cpus = 1
         memory = { 1.GB }
@@ -82,10 +146,10 @@ process {
         time           = { 15.m * task.attempt }
 
         ext.args       = { params.multiqc_title ? "--title \"${params.multiqc_title}\"" : "--title \"${params.analysis_id}\"" }
-        ext.prefix     = { $ { params.analysis_id } }
+        ext.prefix     = { params.analysis_id }
         publishDir     = [
             [
-                path: "${params.outdir}/QC",
+                path: { "${params.outdir}/QC" },
                 mode: params.publish_dir_mode,
             ]
         ]
@@ -311,7 +375,7 @@ process {
                 path: "${params.outdir}/QC/star_align",
                 mode: params.publish_dir_mode,
                 saveAs: { filename ->
-                        filename.endsWith('.bam') || filename.endsWith(".fastq.gz") : null ? filename
+                        filename.endsWith('.bam') || filename.endsWith(".fastq.gz") ? null : filename
                 }
             ]
         ]

modules.json

@@ -10,6 +10,17 @@
                         "git_sha": "025a6f75e1f72e4ab60abb4bd65b3f289d4ad910",
                         "installed_by": ["modules"]
                     },
+                    "bcftools/index": {
+                        "branch": "master",
+                        "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
+                        "installed_by": ["modules"]
+                    },
+                    "bedops/gtf2bed": {
+                        "branch": "master",
+                        "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/bedops/gtf2bed/bedops-gtf2bed.diff"
+                    },
                     "fastqc": {
                         "branch": "master",
                         "git_sha": "dc94b6ee04a05ddb9f7ae050712ff30a13149164",
@@ -25,6 +36,41 @@
                         "git_sha": "e753770db613ce014b3c4bc94f6cba443427b726",
                         "installed_by": ["modules"]
                     },
+                    "gatk4/bedtointervallist": {
+                        "branch": "master",
+                        "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
+                        "installed_by": ["modules"]
+                    },
+                    "gatk4/createsequencedictionary": {
+                        "branch": "master",
+                        "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
+                        "installed_by": ["modules"]
+                    },
+                    "gatk4/haplotypecaller": {
+                        "branch": "master",
+                        "git_sha": "b73338eca19d798eb0ef6ed112ef4d27a30d2871",
+                        "installed_by": ["modules"]
+                    },
+                    "gatk4/intervallisttools": {
+                        "branch": "master",
+                        "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
+                        "installed_by": ["modules"]
+                    },
+                    "gatk4/mergevcfs": {
+                        "branch": "master",
+                        "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
+                        "installed_by": ["modules"]
+                    },
+                    "gatk4/splitncigarreads": {
+                        "branch": "master",
+                        "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
+                        "installed_by": ["modules"]
+                    },
+                    "gatk4/variantfiltration": {
+                        "branch": "master",
+                        "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
+                        "installed_by": ["modules"]
+                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",

modules/nf-core/bcftools/index/environment.yml

@@ -0,0 +1,10 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  # renovate: datasource=conda depName=bioconda/htslib
+  - bioconda::htslib=1.23.1
+  # renovate: datasource=conda depName=bioconda/bcftools
+  - bioconda::bcftools=1.23.1

modules/nf-core/bcftools/index/main.nf

@@ -0,0 +1,40 @@
+process BCFTOOLS_INDEX {
+    tag "${meta.id}"
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container
+        ? 'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/0b/0b4d52ca9a56d07be3f78a12af654e5116f5112908dba277e6796fd9dfb83fe5/data'
+        : 'community.wave.seqera.io/library/bcftools_htslib:1.23.1--9f08ec665533d64a'}"
+
+    input:
+    tuple val(meta), path(vcf)
+
+    output:
+    tuple val(meta), path("*.csi"), emit: csi, optional: true
+    tuple val(meta), path("*.tbi"), emit: tbi, optional: true
+    tuple val("${task.process}"), val('bcftools'), eval("bcftools --version | sed '1!d; s/^.*bcftools //'"), topic: versions, emit: versions_bcftools
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+
+    """
+    bcftools \\
+        index \\
+        ${args} \\
+        --threads ${task.cpus} \\
+        ${vcf}
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def extension = args.contains("--tbi") || args.contains("-t")
+        ? "tbi"
+        : "csi"
+    """
+    touch ${vcf}.${extension}
+    """
+}

modules/nf-core/bcftools/index/meta.yml

@@ -0,0 +1,82 @@
+name: bcftools_index
+description: Index VCF tools
+keywords:
+  - vcf
+  - index
+  - bcftools
+  - csi
+  - tbi
+tools:
+  - bcftools:
+      description: BCFtools is a set of utilities that manipulate variant calls in the
+        Variant Call Format (VCF) and its binary counterpart BCF. All commands work
+        transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.  Most
+        commands accept VCF, bgzipped VCF and BCF with filetype detected automatically
+        even when streaming from a pipe. Indexed VCF and BCF will work in all situations.
+        Un-indexed VCF and BCF and streams will work in most, but not all situations.
+      homepage: https://samtools.github.io/bcftools/
+      documentation: https://samtools.github.io/bcftools/howtos/index.html
+      tool_dev_url: https://github.com/samtools/bcftools
+      doi: "10.1093/gigascience/giab008"
+      licence: ["MIT", "GPL-3.0-or-later"]
+      identifier: biotools:bcftools
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - vcf:
+        type: file
+        description: VCF file (optionally GZIPPED)
+        pattern: "*.{vcf,vcf.gz}"
+        ontologies: []
+output:
+  csi:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.csi":
+          type: file
+          description: Default VCF file index file
+          pattern: "*.csi"
+          ontologies: []
+  tbi:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.tbi":
+          type: file
+          description: Alternative VCF file index file for larger files (activated with
+            -t parameter)
+          pattern: "*.tbi"
+          ontologies: []
+  versions_bcftools:
+    - - ${task.process}:
+          type: string
+          description: The process the versions were collected from
+      - bcftools:
+          type: string
+          description: The tool name
+      - "bcftools --version | sed '1!d; s/^.*bcftools //'":
+          type: string
+          description: The command used to generate the version of the tool
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The process the versions were collected from
+      - bcftools:
+          type: string
+          description: The tool name
+      - "bcftools --version | sed '1!d; s/^.*bcftools //'":
+          type: string
+          description: The command used to generate the version of the tool
+authors:
+  - "@jfy133"
+maintainers:
+  - "@jfy133"