Merge pull request #26 from ghga-de/fix-annotation-file-input

final annotation fix

README.md

@@ -38,7 +38,6 @@ The pipeline has 6 main steps: Indel calling using platypus, basic annotations,
 
    Reliability and confidation annotations: It is an optional ste for mapability, hiseq, selfchain and repeat regions checks for reliability and confidence of those scores.
 
-
 3. Deep Annotation (--runIndelDeepAnnotation True):
 
    If basic annotations are applied, an extra optional step for number of extra indel annotations like enhancer, cosmic, mirBASE, encode databases can be applied too.
@@ -207,7 +206,6 @@ We thank the following people for their extensive assistance in the development
 
 - Nagarajan Paramasivam (@NagaComBio) [email protected]
 
-
 **TODO**
 
 <!-- TODO nf-core: If applicable, make list of people who have also contributed -->

modules/local/annotate_vcf.nf

@@ -9,7 +9,14 @@ process ANNOTATE_VCF {
 
     input:
     tuple val(meta), path(vcf), path(vcf_tbi)
-    tuple val(meta2),path(kgenome),path(kgenome_i),path(dbsnpindel),path(dbsnpindel_i),path(exac),path(evs),path(evs_i),path(exac_i),path(localcontrolwgs),path(localcontrolwgs_i),path(localcontrolwes),path(localcontrolwes_i),path(gnomadgenomes),path(gnomadgenomes_i),path(gnomadexomes),path(gnomadexomes_i)
+    tuple path(kgenome),path(kgenome_i)
+    tuple path(dbsnpindel),path(dbsnpindel_i)
+    tuple path(exac),path(exac_i)
+    tuple path(evs),path(evs_i)
+    tuple path(localcontrolwgs),path(localcontrolwgs_i)
+    tuple path(localcontrolwes),path(localcontrolwes_i)
+    tuple path(gnomadgenomes),path(gnomadgenomes_i)
+    tuple path(gnomadexomes),path(gnomadexomes_i)
     val (chrprefix)
 
     output:

modules/local/annotation_pipes.nf

@@ -9,7 +9,18 @@ process ANNOTATION_PIPES {
 
     input:
     tuple val(meta), path(vcf), path(vcf_tbi)
-    tuple val(meta2),path(enchangers),path(enchangers_i),path(cpgislands),path(cpgislands_i),path(tfbscons),path(tfbscons_i),path(encode_dnase),path(encode_dnase_i),path(mirnas_snornas),path(mirnas_snornas_i),path(cosmic),file(cosmic_i),path(mirbase),path(mirbase_i),path(mir_targets),path(mir_targets_i),path(cgi_mountains),path(cgi_mountains_i),path(phastconselem),path(phastconselem_i),path(encode_tfbs),path(encode_tfbs_i),path(mirnas_sncrnas),path(mirnas_sncrnas_i)
+    tuple path(enchangers),path(enchangers_i)
+    tuple path(cpgislands),path(cpgislands_i)
+    tuple path(tfbscons),path(tfbscons_i)
+    tuple path(encode_dnase),path(encode_dnase_i)
+    tuple path(mirnas_snornas),path(mirnas_snornas_i)
+    tuple path(cosmic),file(cosmic_i)
+    tuple path(mirbase),path(mirbase_i)
+    tuple path(mir_targets),path(mir_targets_i)
+    tuple path(cgi_mountains),path(cgi_mountains_i)
+    tuple path(phastconselem),path(phastconselem_i)
+    tuple path(encode_tfbs),path(encode_tfbs_i)
+    tuple path(mirnas_sncrnas),path(mirnas_sncrnas_i)
 
     output:
     tuple val(meta), path('*.deepanno.vcf.gz'), path('*.deepanno.vcf.gz.tbi') , emit: vcf

modules/local/annovar.nf

@@ -1,6 +1,5 @@
 //# Gene annotation with annovar
 // PROCESS ANNOVAR table_annovar
-// working database is annovar_Feb2016
 
 process ANNOVAR {
     tag "$meta.id"
@@ -11,8 +10,8 @@ process ANNOVAR {
     'docker://kubran/odcf_platypusindelcalling:v1' :'kubran/odcf_platypusindelcalling:v1' }"
 
     input:          
-    tuple val(meta)         , path(ch_vcf),  path(annovar_bed)
-    each file(annovar_table)
+    tuple val(meta)    , path(ch_vcf),  path(annovar_bed)
+    path(annovar_table)
     val(chrprefix)
 
     output:

modules/local/indel_reliability_pipe.nf

@@ -10,7 +10,13 @@ process INDEL_RELIABILITY_PIPE {
 
     input:
     tuple val(meta),path(ch_vcf),path(ch_vcf_i)
-    tuple val(meta2),path(repeatmasker),path(repeatmasker_i),path(dacblacklist),path(dacblacklist_i),path(dukeexcluded),path(dukeexcluded_i),path(hiseqdepth),path(hiseqdepth_i),path(selfchain),path(selfchain_i),path(mapability),path(mapability_i),path(simpletandemrepeats),path(simpletandemrepeats_i)
+    tuple path(repeatmasker),path(repeatmasker_i)
+    tuple path(dacblacklist),path(dacblacklist_i)
+    tuple path(dukeexcluded),path(dukeexcluded_i)
+    tuple path(hiseqdepth),path(hiseqdepth_i)
+    tuple path(selfchain),path(selfchain_i)
+    tuple path(mapability),path(mapability_i)
+    tuple path(simpletandemrepeats),path(simpletandemrepeats_i)
 
     output:
     tuple val(meta), path('*.annotated.vcf.gz'), path('*.annotated.vcf.gz.tbi')   , emit: vcf

modules/local/sample_swap.nf

@@ -10,9 +10,12 @@ process SAMPLE_SWAP {
     input:
     tuple val(meta) , path(ch_vcf), path(ch_vcf_i),  val(tumorname), val(controlname)
     tuple path(ref) , path(ref_fai)
-    each path(chrlength_file)
-    each path(genemodel)              
-    tuple val(meta2),path(localcontroltindawgs), path(localcontroltindawgs_tbi),path(localcontroltindawes),path(localcontroltindawes_tbi),path(gnomadgenomes),path(gnomadgenomes_tbi),path(gnomadexomes),path(gnomadexomes_tbi)
+    path(chrlength_file)
+    path(genemodel)              
+    tuple path(localcontroltindawgs), path(localcontroltindawgs_tbi)
+    tuple path(localcontroltindawes),path(localcontroltindawes_tbi)
+    tuple path(gnomadgenomes),path(gnomadgenomes_tbi)
+    tuple path(gnomadexomes),path(gnomadexomes_tbi)
     val chrprefix
 
     output:

modules/local/visualize.nf

@@ -10,7 +10,7 @@ process VISUALIZE {
     input:
     tuple val(meta) ,path(vcf)
     tuple path(ref) ,path(ref_fai)
-    tuple val(meta2),path(repeatmasker) ,path(repeatmasker_tbi)
+    tuple path(repeatmasker) ,path(repeatmasker_tbi)
 
     output:
     tuple val(meta)     , path('*.indel_somatic_functional_combined.pdf')  , emit: pdf, optional: true

nextflow.config

@@ -35,6 +35,7 @@ params {
     crit_evs_maxmaf            = 0             // default value: 1.0 
     crit_1kgenomes_maxmaf      = 0             // default value: 0.01
     crit_localcontrol_maxmaf   = 0             // default value: 0.05
+    filter_non_clinic          = false         // default value: false
 
     // screenshot options
     max_var_screenshots        = 100           // default value 

nextflow_schema.json

@@ -475,6 +475,12 @@
           "default": "",
           "fa_icon": "fas fa-annotation",
           "description": "Max MAF for Local Control filtration. Only apply if annotation is done"
+        },
+        "filter_non_clinic": {
+          "type": "boolean",
+          "default": "",
+          "fa_icon": "fas fa-annotation",
+          "description": "If true, dbSNP filtration will be applied. Only apply if annotation is done"
         }
       }
     },

run_pipeline.sh

@@ -1,3 +1,3 @@
 #!/bin/bash
 module load nextflow/22.07.1-edge
-nextflow run main.nf -profile test,singularity --input testdata/samplesheet_test.csv
+nextflow run main.nf -profile dkfz_cluster_38,singularity --input testdata/samplesheet_test.csv -resume

subworkflows/local/indel_annotation.nf

@@ -16,9 +16,33 @@ include { ENSEMBLVEP_DOWNLOAD    } from '../../modules/nf-core/modules/ensemblve
 workflow INDEL_ANNOTATION {
     take:
     vcf_ch           // channel: [val(meta), vcf.gz, vcf.gz.tbi ,val(tumorname), val(controlname) ]
-    annotate_vcf_ref // channel: [val(meta2),file(kgenome),file(kgenome_i),file(dbsnpindel),file(dbsnpindel_i),file(exac),file(exac_i),file(evs),file(evs_i),file(localcontrolwgs),file(localcontrolwgs_i),file(localcontrolwes),file(localcontrolwes_i),file(gnomadgenomes),file(gnomadgenomes_i),file(gnomadexomes),file(gnomadexomes_i)]
-    realibility_ref  // channel: [val(meta2),file(repeatmasker),file(repeatmasker_i),file(dacblacklist),file(dacblacklist_i),file(dukeexcluded),file(dukeexcluded_i),file(hiseqdepth),file(hiseqdepth_i),file(selfchain),file(selfchain_i),file(mapability),file(mapability_i),file(simpletandemrepeats),file(simpletandemrepeats_i)]
-    deepanno_ref     // channel: [val(meta2),file(enchangers),file(enchangers_i),file(cpgislands),file(cpgislands_i),file(tfbscons),file(tfbscons_i),tuple file(encode_dnase),file(encode_dnase_i),file(mirnas_snornas),file(mirnas_snornas_i),file(cosmic),file(cosmic_i),file(mirbase),file(mirbase_i),file(mir_targets),file(mir_targets_i),file(cgi_mountains),file(cgi_mountains_i),file(phastconselem),file(phastconselem_i),file(encode_tfbs),file(encode_tfbs_i),file(mirnas_sncrnas),file(mirnas_sncrnas_i)] 
+    kgenome          // channel: [file,index]
+    dbsnpindel       // channel: [file,index]
+    exac             // channel: [file,index]
+    evs              // channel: [file,index]
+    localcontrolwgs  // channel: [file,index] 
+    localcontrolwes  // channel: [file,index]
+    gnomadgenomes    // channel: [file,index]
+    gnomadexomes     // channel: [file,index]
+    repeatmasker     // channel: [file,index]
+    dacblacklist     // channel: [file,index]
+    dukeexcluded     // channel: [file,index]
+    hiseqdepth       // channel: [file,index]
+    selfchain        // channel: [file,index]
+    mapability       // channel: [file,index]
+    simpletandemrepeats  // channel: [file,index]
+    enchangers       // channel: [file,index]
+    cpgislands       // channel: [file,index]
+    tfbscons         // channel: [file,index]
+    encode_dnase     // channel: [file,index] 
+    mirnas_snornas   // channel: [file,index]
+    cosmic           // channel: [file,index]
+    mirbase          // channel: [file,index]
+    mir_targets      // channel: [file,index]
+    cgi_mountains    // channel: [file,index]
+    phastconselem    // channel: [file,index]
+    encode_tfbs      // channel: [file,index]
+    mirnas_sncrnas   // channel: [file,index]
     chr_prefix       // val channel: [prefix]
     ref              // channel [fasta,fai] 
     annodb           // channel: [table_annovar_dir]
@@ -35,7 +59,7 @@ workflow INDEL_ANNOTATION {
     input_ch = vcf_ch.map{ it -> tuple( it[0], it[1], it[2])}
     ANNOTATE_VCF (
         input_ch, 
-        annotate_vcf_ref, 
+        kgenome,dbsnpindel,exac,evs,localcontrolwgs,localcontrolwes,gnomadgenomes,gnomadexomes, 
         chr_prefix
     )
     versions  = versions.mix(ANNOTATE_VCF.out.versions)
@@ -84,7 +108,7 @@ workflow INDEL_ANNOTATION {
     // RUN annotate_vcf.pl : BED files are used to annotate variants
     INDEL_RELIABILITY_PIPE(
         annotated_vcf, 
-        realibility_ref
+        repeatmasker,dacblacklist,dukeexcluded,hiseqdepth,selfchain,mapability,simpletandemrepeats
     )
     versions = versions.mix(INDEL_RELIABILITY_PIPE.out.versions)
 
@@ -101,7 +125,8 @@ workflow INDEL_ANNOTATION {
     input_ch = vcf_ch.join(INDEL_RELIABILITY_PIPE.out.vcf)
     input_ch = input_ch.map{ it -> tuple( it[0], it[3], it[4], it[5], it[6])}
     CONFIDENCE_ANNOTATION(
-        input_ch, ref_type
+        input_ch, 
+        ref_type
     )
     ann_vcf_ch  = CONFIDENCE_ANNOTATION.out.vcf_ann
     versions    = versions.mix(CONFIDENCE_ANNOTATION.out.versions)
@@ -114,7 +139,7 @@ workflow INDEL_ANNOTATION {
         //
         ANNOTATION_PIPES (
             ann_vcf_ch, 
-            deepanno_ref
+            enchangers, cpgislands,tfbscons,encode_dnase,mirnas_snornas,cosmic,mirbase,mir_targets,cgi_mountains,phastconselem,encode_tfbs,mirnas_sncrnas
         )
         ann_vcf_ch  = ANNOTATION_PIPES.out.vcf 
         versions    = versions.mix(ANNOTATION_PIPES.out.versions)

testdata/samplesheet_test.csv

@@ -1,2 +1,4 @@
 sample,tumor,tumor_index,control,control_index
-test_withcontrol,testdata/WES_LL_T_1_test.bam,testdata/WES_LL_T_1_test.bam.bai,testdata/WES_LL_N_1_test.bam,testdata/WES_LL_N_1_test.bam.bai
+test,testdata/WES_LL_T_1_test.bam,testdata/WES_LL_T_1_test.bam.bai,testdata/WES_LL_N_1_test.bam,testdata/WES_LL_N_1_test.bam.bai
+test_2,testdata/WES_LL_T_1_test.bam,testdata/WES_LL_T_1_test.bam.bai,testdata/WES_LL_N_1_test.bam,testdata/WES_LL_N_1_test.bam.bai
+test_3,testdata/WES_LL_T_1_test.bam,testdata/WES_LL_T_1_test.bam.bai,testdata/WES_LL_N_1_test.bam,testdata/WES_LL_N_1_test.bam.bai