TMB

assets/tmb/mutect2.yml

@@ -0,0 +1,9 @@
+## Describe the fields
+## For definition, provide the expected key:values
+## Note that several keys/values can be defined
+##
+###############################################
+
+freq: "AF"
+depth: "DP"
+altDepth: "AD"

assets/tmb/snpeff.yml

@@ -0,0 +1,115 @@
+## Describe the fields
+## For definition, provide the expected key:values
+## Note that several keys/values can be defined
+
+###############################################
+## SnpEff Parsing
+
+## Tags
+tag: "ANN"
+sep: "&"
+
+## Annotation flags
+
+isCoding:
+  1:
+    - chromosome_number_variation
+    - coding_sequence_variant
+    - conservative_inframe_deletion
+    - conservative_inframe_insertion
+    - disruptive_inframe_deletion
+    - disruptive_inframe_insertion
+    - exon_loss
+    - exon_loss_variant
+    - exon_variant
+    - frameshift_variant
+    - gene_variant
+    - initiator_codon_variant
+    - missense_variant
+    - rare_amino_acid_variant
+    - splice_acceptor_variant
+    - splice_donor_variant
+    - splice_region_variant
+    - start_lost
+    - start_retained
+    - stop_gained
+    - stop_lost
+    - stop_retained_variant
+    - synonymous_variant
+    - transcript_ablation
+    - transcript_amplification
+    - transcript_variant
+
+isNonCoding:
+  1:
+    - 3_prime_UTR_truncation
+    - 3_prime_UTR_variant
+    - 5_prime_UTR_premature_start_codon_gain_variant
+    - 5_prime_UTR_truncation
+    - 5_prime_UTR_variant
+    - conserved_intergenic_variant
+    - conserved_intron_variant
+    - downstream_gene_variant
+    - feature_elongation
+    - feature_truncation
+    - intergenic_region
+    - intragenic_variant
+    - intron_variant
+    - mature_miRNA_variant
+    - miRNA
+    - NMD_transcript_variant
+    - non_coding_transcript_exon_variant
+    - non_coding_transcript_variant
+    - regulatory_region_ablation
+    - regulatory_region_amplification
+    - regulatory_region_variant
+    - TF_binding_site_variant
+    - TFBS_ablation
+    - TFBS_amplification
+    - upstream_gene_variant
+
+isSplicing:
+  1:
+    - splice_donor_variant
+    - splice_acceptor_variant
+    - splice_region_variant
+
+isSynonymous:
+  1:
+    - start_retained_variant
+    - stop_retained_variant
+    - synonymous_variant
+
+isNonSynonymous:
+  1:
+    - frameshift_variant
+    - missense_variant
+    - rare_amino_acid_variant
+    - splice_acceptor_variant
+    - splice_donor_variant
+    - splice_region_variant
+    - start_lost
+    - stop_gained
+    - stop_lost
+
+## Databases
+cancerDb:
+  cosmic:
+    - cosmic_coding_ID
+    - cosmic_noncoding_ID
+
+polymDb:
+  1k:
+    - kg_AMR_AF
+    - kg_AFR_AF
+    - kg_EAS_AF
+    - kg_EUR_AF
+    - kg_SAS_AF
+    - KG_AF_GLOBAL
+
+  gnomad:
+    - gnomAD_genomes_AF
+    - AF
+
+  esp:
+    - ESP_AF_GLOBAL

assets/tmb/strelka.yml

@@ -0,0 +1,12 @@
+## Describe the fields
+## For definition, provide the expected key:values
+## Note that several keys/values can be defined
+##
+###############################################
+
+freq: "AF"
+depth: "DP" #####FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read depth for tier1 (used+filtered)">
+altDepth: "AD"
+###FORMAT=<ID=AF,Number=A,Type=Float,Description="Allele fractions of alternate alleles in the tumor">
+#####FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+###FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">

conf/modules/modules.config

@@ -119,4 +119,15 @@ process {
     withName: 'VCFTOOLS_SUMMARY' {
         ext.args         = "--FILTER-summary"
     }
+
+    if (params.tools && params.tools.split(',').contains('tmb')) {
+        withName: 'BCFTOOLS_NORM'{
+            ext.args = "-m-"
+            ext.prefix = { "${vcf.baseName.minus(".vcf")}_norm" }
+        }
+
+        withName: 'TMB' {
+            ext.args = { "--sample ${meta.patient}_{meta.sample} " } //sample here is the tumor_id
+        }
+    }
 }

lib/WorkflowSarek.groovy

@@ -100,4 +100,39 @@ class WorkflowSarek {
                         exit 1, "Unknown step $params.step"
         }
     }
+
+    public static String getTMBdatabase(String annotation) {
+
+        String dbConfig = "";
+
+        switch (annotation) {
+            case 'snpeff': dbConfig = "/assets/tmb/snpeff.yml";
+                           break
+            case 'vep': dbConfig = "/assets/tmb/vep.yml";
+                           break
+            // default:    log.warn "Please provide a valid annotation tool"
+            //             exit 1, "Unknown tool ${annotation}"
+        }
+
+       return dbConfig
+    }
+
+    public static String getTMBvariantcaller(String variantcaller) {
+
+        String varConfig = "";
+
+        switch (variantcaller) {
+            case 'freebayes': varConfig = "/assets/tmb/freebayes.yml";
+                            break
+            case 'mutect2': varConfig = "/assets/tmb/mutect2.yml";
+                            break
+            case 'strelka': varConfig = "/assets/tmb/strelka.yml";
+                            break
+            // default:    log.warn "Please provide a valid variantcalling tool"
+            //             exit 1, "Unknown tool ${variantcaller}"
+        }
+
+       return varConfig
+
+    }
 }

modules.json

@@ -9,6 +9,10 @@
                         "branch": "master",
                         "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
                     },
+                    "bcftools/norm": {
+                        "branch": "master",
+                        "git_sha": "78cf39939fbe160a1410c44a6c5946f9a4c56e7e"
+                    },
                     "bcftools/sort": {
                         "branch": "master",
                         "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"

modules/local/tmb/main.nf

@@ -0,0 +1,38 @@
+process TMB {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::tmb=1.3.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/tmb:1.3.0--pyh5e36f6f_0':
+        'quay.io/biocontainers/tmb:1.3.0--pyh5e36f6f_0' }"
+
+    input:
+    tuple val(meta), path(vcf), path (dbconfig), path (varconfig)
+    path (target_bed)
+
+    output:
+    tuple val(meta), path("*.log"), emit: log
+    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.id}"
+    def target_bed = target_bed ? "--bed ${target_bed}" : ""
+    """
+    pyTMB.py -i $vcf \
+        --dbConfig ${dbconfig} \
+        --varConfig ${varconfig} \
+        ${target_bed} \
+        $args \
+        > ${prefix}.log
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        tmb: \$(echo \$(pyTMB.py --version 2>&1) | sed 's/^.*pyTMB.py //; s/.*\$//' | sed 's|[()]||g')
+    END_VERSIONS
+    """
+}

nextflow_schema.json

@@ -24,7 +24,8 @@
                         "prepare_recalibration",
                         "recalibrate",
                         "variant_calling",
-                        "annotate"
+                        "annotate",
+                        "post-process"
                     ]
                 },
                 "input": {
@@ -89,7 +90,7 @@
                     "fa_icon": "fas fa-toolbox",
                     "description": "Tools to use for variant calling and/or for annotation.",
                     "help_text": "Multiple tools separated with commas.\n\n**Variant Calling:**\n\nGermline variant calling can currently be performed with the following variant callers:\n- SNPs/Indels: DeepVariant, FreeBayes, HaplotypeCaller, mpileup, Strelka\n- Structural Variants: Manta, TIDDIT\n- Copy-number: CNVKit\n\nTumor-only somatic variant calling can currently be performed with the following variant callers:\n- SNPs/Indels: FreeBayes, mpileup, Mutect2, Strelka\n- Structural Variants: Manta, TIDDIT\n- Copy-number: CNVKit, ControlFREEC\n\nSomatic variant calling can currently only be performed with the following variant callers:\n- SNPs/Indels: FreeBayes, Mutect2, Strelka2\n- Structural variants: Manta, TIDDIT\n- Copy-Number: ASCAT, CNVKit, Control-FREEC\n- Microsatellite Instability: MSIsensorpro\n\n> **NB** Mutect2 for somatic variant calling cannot be combined with `--no_intervals`\n\n**Annotation:**\n \n- snpEff, VEP, merge (both consecutively).\n\n> **NB** As Sarek will use bgzip and tabix to compress and index VCF files annotated, it expects VCF files to be sorted when starting from `--step annotate`.",
-                    "pattern": "^((ascat|cnvkit|controlfreec|deepvariant|freebayes|haplotypecaller|manta|merge|mpileup|msisensorpro|mutect2|snpeff|strelka|tiddit|vep)?,?)*[^,]+$"
+                    "pattern": "^((ascat|cnvkit|controlfreec|deepvariant|freebayes|haplotypecaller|manta|merge|mpileup|msisensorpro|mutect2|snpeff|strelka|tiddit|tmb|vep)?,?)*[^,]+$"
                 },
                 "skip_tools": {
                     "type": "string",

subworkflows/local/prepare_intervals/main.nf

@@ -37,7 +37,7 @@ workflow PREPARE_INTERVALS {
         ch_intervals_combined = Channel.fromPath(file("${params.outdir}/no_intervals.bed"))
                                             .map{ it -> [[id:it.simpleName], it]}
 
-    } else if (params.step != 'annotate' && params.step != 'controlfreec') {
+    } else if (params.step != 'controlfreec') {
 
         //If no interval/target file is provided, then intervals are generated from FASTA file
         if (!params.intervals) {