Merge pull request #6 from CCBR/main

Additional changes to Tumor only calling

Docker_hubmodules

@@ -0,0 +1,19 @@
+## Compile list of Modules to 
+    module=['vcf2maf/1.6.21','VEP/102']
+    module=['fastq_screen/0.15.2','bowtie/2-2.5.1']
+    module=['kraken/2.1.2', 'kronatools/2.8']
+    module=['fastqc/0.11.9']
+    module=['qualimap/2.2.1','java/12.0.1']
+    module=['samtools/1.16.1']
+    module=['vcftools/0.1.16']
+    module=['picard/2.20.8']
+    module=['bcftools/1.9']
+    module=['GATK/4.2.0.0']
+    module=["snpEff/4.3t"]
+    module=['multiqc/1.11']
+    module=['GATK/3.8-1']
+    module=['bwa-mem2/2.2.1','samblaster/0.1.26','samtools/1.15.1']
+    module=['fastp/0.23.2']
+
+
+

docker/logan_base/build.sh

@@ -1,11 +1,24 @@
 # Build image
-docker buildx create --platform linux/amd64 --use
-docker buildx build -f Dockerfile -t dnousome/ccbr_logan_base:v0.3.0 -t dnousome/ccbr_logan_base:latest  --platform=linux/amd64 --push .
+#docker buildx create --platform linux/amd64 --use
+#docker buildx use upbeat_ganguly
+#docker buildx inspect upbeat_ganguly
+#docker buildx build --platform linux/amd64 -f Dockerfile -t dnousome/ccbr_logan_base:v0.3.0 -t dnousome/ccbr_logan_base:latest --push .
+
+docker build --platform linux/amd64 --tag ccbr_logan_base:v0.3.0 -f Dockerfile . 
+docker tag ccbr_logan_base:v0.3.0 dnousome/ccbr_logan_base:v0.3.0
+docker tag ccbr_logan_base:v0.3.0 dnousome/ccbr_logan_base
+
+docker push dnousome/ccbr_logan_base:v0.3.0
+docker push dnousome/ccbr_logan_base:latest
+
+
+
 
 # Tag image with version and reset latest
 #docker tag ccbr_wgs_base:v0.1.0 nciccbr/ccbr_wgs_base:v0.1.0
 #docker tag ccbr_wgs_base:v0.1.0 nciccbr/ccbr_wgs_base
 
 # Push image to DockerHub
 #docker push nciccbr/ccbr_wgs_base:v0.1.0
-#docker push nciccbr/ccbr_wgs_base:latest
+#docker push nciccbr/ccbr_wgs_base:latest
+

nextflow.config

@@ -15,6 +15,7 @@ params {
     get_flowcell_lanes="${projectDir}/workflow/scripts/flowcell_lane.py"
     intervals="${projectDir}/workflow/resources/hg38_v0_wgs_calling_regions.hg38.bed"
     splitbed="${projectDir}/workflow/resources/split_Bed_into_equal_regions.py"
+    split_regions = "24" //Number of regions to split by 
     snpeff_genome = "GRCh38.86"
     snpeff_config = "/data/CCBR_Pipeliner/CCBR_Pipeliner_Legacy/Exome-seek/hg38/snpEff/4.3t/snpEff.config"
     snpeff_bundle = "/data/CCBR_Pipeliner/CCBR_Pipeliner_Legacy/Exome-seek/hg38/snpEff/4.3t/"
@@ -24,6 +25,7 @@ params {
     script_combineSamples = "${projectDir}/workflow/scripts/RScripts/combineAllSampleCompareResults.R"
     script_ancestry = "${projectDir}/workflow/scripts/RScripts/sampleCompareAncestoryPlots.R"
     bwagenome= "/data/CCBR_Pipeliner/CCBR_Pipeliner_Legacy/Exome-seek/hg38/genome/Homo_sapiens_assembly38.fasta"
+    vep_cache = "/fdb/VEP/102/cache"
 
     //Biowulf
     config_profile_description = 'Biowulf nf-core config'
@@ -106,6 +108,16 @@ profiles {
             }    
     }
 
+    localstub {
+         process {
+            executor = 'local'
+
+          singularity {
+                enabled = false
+          }
+         }
+    }
+
     biowulf {
         process {
             executor = 'slurm'
@@ -140,15 +152,23 @@ profiles {
                 time=24.h
                 cpus=8
             }
+            withName:fastp {
+                container= 'docker://dnousome/ccbr_logan_base:v0.3.0'
+                memory=24.GB
+                time=24.h
+                cpus=4
+            }
             withName:fc_lane {
                 container= 'docker://dnousome/ccbr_logan_base:v0.3.0'
             }
             withName:bwamem2 {
+                container= 'docker://dnousome/ccbr_logan_base:v0.3.0'
                 memory=200.GB
                 time=48.h
                 cpus=17
             }
             withName:indelrealign{
+                container= 'docker://dnousome/ccbr_logan_base:v0.3.0'
                 memory=48.GB
                 time=72.h
                 cpus=16
@@ -180,6 +200,12 @@ profiles {
                 cpus= 4
                 time= 72.h
             }
+            withName: 'vardict_tn|vardict_tonly|varscan_tn|varscan_tonly|combineVariants|combineVariants_strelka' {
+                container= 'docker://dnousome/ccbr_logan_base:v0.3.0'
+                memory= 32.GB
+                cpus= 2
+                time= 72.h
+            }
             withName: 'strelka_tn' {
                 container= 'docker://dnousome/ccbr_logan_base:v0.3.0'
                 memory= 48.GB
@@ -202,21 +228,18 @@ profiles {
                 memory= 48.GB
                 time= 24.h
                 }
-
             withName:'mergemut2stats|mergemut2stats_tonly' {
                 container= 'docker://dnousome/ccbr_logan_base:v0.3.0'
                 memory= 16.GB
                 time= 24.h
                 }
-
             withName:'pileup_paired_t|pileup_paired_n|pileup_paired_tonly' {
                 container= 'docker://dnousome/ccbr_logan_base:v0.3.0'
                 memory= 16.GB
                 time= 12.h
                 }
-
             withName:'annotvep_tn|annotvep_tonly'{
-                //container= 'docker://dnousome/ccbr_vcf2maf:v102.0.0'
+                container= 'docker://dnousome/ccbr_vcf2maf:v102.0.0'
                 memory= 32.GB
                 time= 24.h
                 cpus=16
@@ -286,9 +309,6 @@ profiles {
             }
     }
 
-    localstub {
-
-    }
 
 }
 

wgs-seek

@@ -45,13 +45,14 @@ def parse_args():
     parser.add_argument('--bam',help="Files input")
     parser.add_argument('--mode',help='Mode?')
     parser.add_argument('--paired',help='Paired',action="store_true")
+    parser.add_argument('--splitregions',default=24,help="How splits per regions")
     parser.add_argument('--sv',help="Add Structural VC calling",action="store_true")
     parser.add_argument('--output',help="Output Directory")
     parser.add_argument('--sample_sheet',help="Sample sheet")
     parser.add_argument('--profile',help="Biowulf or Local Run")
     parser.add_argument('--resume',action="store_true",default="True",help="Resume previous run?")
-    parser.add_argument('--submit',action="store_true",help="Submit to SLURM?",default="False")
-    parser.add_argument('--stub',action="store_true",help="Stub dry run",default="False")
+    parser.add_argument('--submit',action="store_true",help="Submit to SLURM?")
+    parser.add_argument('--stub',action="store_true",help="Stub run")
     args = parser.parse_args()
     return(args)
 
@@ -125,7 +126,7 @@ def main():
         resume=""
     c4=["nextflow run",dirname + '/wgs-seek.nf',"-c "+ dirname +"/nextflow.config",
         in1,profile,resume,sample_path,mode,
-        "--output '" +args.output+"'"]
+        "--output '" +args.output+"'"+" --split_regions " +str(args.splitregions)]
     cmd1=' '.join(c4)
     code=c1+"\n"+c2+"\n"+c3+"\n"+cmd1
     time1=time.strftime("%Y_%m_%d_%H%M%S")
@@ -135,7 +136,7 @@ def main():
         outfile.write(code+"\n")
     sbatch_mut="sbatch --cpus-per-task=2 --mem=16g --time 10-00:00:00 --partition norm --output submit_"+time1+".log --error error_"+time1+".log --mail-type=BEGIN,TIME_LIMIT_90,END "+outswarmmut 
     if args.stub:
-        cmd2=cmd1+" -stub -without-podman T -without-conda -without-docker"
+        cmd2=cmd1+" --split_regions 4 -stub -without-podman T -without-conda -without-docker"
         print(cmd2)
         os.system(cmd2)
     elif args.submit:

workflow/modules/splitbed.nf

@@ -1,3 +1,7 @@
+SPLIT_BED=file(params.splitbed)
+SPLIT_REGIONS=params.split_regions
+
+
 // Split Bed Step to create the path 
 process splitinterval {
     //Keep Process Local
@@ -12,11 +16,9 @@ process splitinterval {
     path('bedout/*.bed')
 
     script:
-
-    SPLIT_BED=file(params.splitbed)
 
     """
     mkdir -p bedout
-    python ${SPLIT_BED} -infile ${BED_IN} -num 32 -out 'bedout/bed'
+    python $SPLIT_BED -infile ${BED_IN} -num ${SPLIT_REGIONS} -out 'bedout/bed'
     """
 }

workflow/modules/variant_calling.nf

@@ -7,6 +7,7 @@ KGP=file(params.kgp) //1000G_phase1.snps.high_confidence.hg38.vcf.gz"
 DBSNP=file(params.dbsnp) //dbsnp_138.hg38.vcf.gz"
 GNOMAD=file(params.gnomad) //somatic-hg38-af-only-gnomad.hg38.vcf.gz
 PON=file(params.pon) 
+VEP_CACHEDIR=file(params.vep_cache)
 
 //Output
 outdir=file(params.output)
@@ -394,7 +395,7 @@ process combineVariants {
     mkdir ${vc}
     bcftools concat $vcfin -Oz -o ${sample}.${vc}.temp.vcf.gz
     bcftools sort ${sample}.${vc}.temp.vcf.gz -Oz -o ${sample}.${vc}.marked.vcf.gz
-    bcftools norm ${sample}.${vc}.marked.vcf.gz --threads $task.cpus --check-ref s -f $GENOME -O |\
+    bcftools norm ${sample}.${vc}.marked.vcf.gz --threads $task.cpus --check-ref s -f $GENOME -O v |\
         awk '{{gsub(/\\y[W|K|Y|R|S|M]\\y/,"N",\$4); OFS = "\\t"; print}}' |\
         sed '/^\$/d' > ${sample}.${vc}.temp.vcf
 
@@ -473,8 +474,8 @@ process annotvep_tn {
     --output-maf !{vc}/!{tumorsample}.maf \
     --tumor-id !{tumorsample} \
     --normal-id !{normalsample} \
-    --vep-path ${VEP_HOME}/bin \
-    --vep-data ${VEP_CACHEDIR} \
+    --vep-path /opt/vep/src/ensembl-vep \
+    --vep-data $VEP_CACHEDIR \
     --ncbi-build GRCh38 --species homo_sapiens --ref-fasta !{GENOME}
 
     """

workflow/modules/variant_calling_tonly.nf

@@ -7,6 +7,7 @@ KGP=file(params.kgp) //1000G_phase1.snps.high_confidence.hg38.vcf.gz"
 DBSNP=file(params.dbsnp) //dbsnp_138.hg38.vcf.gz"
 GNOMAD=file(params.gnomad) //somatic-hg38-af-only-gnomad.hg38.vcf.gz
 PON=file(params.pon) 
+VEP_CACHEDIR=file(params.vep_cache)
 
 //Output
 outdir=file(params.output)
@@ -317,8 +318,8 @@ process annotvep_tonly {
     --vep-forks 16 --input-vcf !{tumorvcf}.vcf \
     --output-maf !{vc}/!{tumorsample}.tonly.maf \
     --tumor-id !{tumorsample} \
-    --vep-path ${VEP_HOME}/bin \
-    --vep-data ${VEP_CACHEDIR} \
+    --vep-path /opt/vep/src/ensembl-vep \
+    --vep-data $VEP_CACHEDIR \
     --ncbi-build GRCh38 --species homo_sapiens --ref-fasta !{GENOME}
 
     """
@@ -330,9 +331,6 @@ process annotvep_tonly {
     """
 }
 
-
-
-
 process combinemafs_tonly {
     publishDir(path: "${outdir}/mafs/tumor_only", mode: 'copy')
 

workflow/modules/workflows.nf

@@ -240,28 +240,28 @@ workflow VARIANTCALL_PIPE {
     .map{tumor,markedvcf,finalvcf,normal -> tuple(tumor,normal,"strelka",finalvcf)} | annotvep_tn_strelka
 
     //Vardict
-    vardict_comb=vardict_tn(bambyinterval).map{tumor,vcf-> tuple(tumor,vcf,"vardict")} | combineVariants_vardict
+    vardict_comb=vardict_tn(bambyinterval).groupTuple().map{tumor,vcf-> tuple(tumor,vcf,"vardict")} | combineVariants_vardict
     vardict_comb.join(sample_sheet)
      .map{tumor,marked,normvcf,normal ->tuple(tumor,normal,"vardict",normvcf)} | annotvep_tn_vardict
 
      //VarDict_tonly
     vardict_tonly_comb=bambyinterval.map{tumorname,tumorbam,tumorbai,normname,normbam,normbai,bed ->
         tuple(tumorname,tumorbam,tumorbai,bed)} 
-    vardict_tonly(vardict_tonly_comb).map{tumor,vcf-> tuple(tumor,vcf,"vardict_tonly")} |combineVariants_vardict_tonly
+    vardict_tonly(vardict_tonly_comb).groupTuple().map{tumor,vcf-> tuple(tumor,vcf,"vardict_tonly")} |combineVariants_vardict_tonly
     combineVariants_vardict_tonly.out.join(sample_sheet)
     .map{tumor,marked,normvcf,normal ->tuple(tumor,"vardict_tonly",normvcf)} | annotvep_tonly_vardict
 
 
     //VarScan
     varscan_in=bambyinterval.join(contamination_paired.out)
-    varscan_comb=varscan_tn(varscan_in).map{tumor,vcf-> tuple(tumor,vcf,"varscan")} | combineVariants_varscan
+    varscan_comb=varscan_tn(varscan_in).groupTuple().map{tumor,vcf-> tuple(tumor,vcf,"varscan")} | combineVariants_varscan
     varscan_comb.join(sample_sheet)
     .map{tumor,marked,normvcf,normal ->tuple(tumor,normal,"varscan",normvcf)} | annotvep_tn_varscan
 
     //VarScan_tonly
     varscan_tonly_comb=varscan_in.map{tumor,bam,bai,normal,nbam,nbai,bed,tpile,npile,tumorc,normalc ->
     tuple(tumor,bam,bai,bed,tpile,tumorc)} | varscan_tonly 
-    varscan_tonly_comb1=varscan_tonly_comb.map{tumor,vcf-> tuple(tumor,vcf,"varscan_tonly")} | combineVariants_varscan_tonly
+    varscan_tonly_comb1=varscan_tonly_comb.groupTuple().map{tumor,vcf-> tuple(tumor,vcf,"varscan_tonly")} | combineVariants_varscan_tonly
 
     varscan_tonly_comb1.join(sample_sheet)
     .map{tumor,marked,normvcf,normal ->tuple(tumor,"varscan_tonly",normvcf)} | annotvep_tonly_varscan

workflow/modules/workflows_tonly.nf

@@ -13,18 +13,32 @@ include {fastp; bwamem2;
     bqsr; gatherbqsr; applybqsr; samtoolsindex} from './trim_align.nf'
 include {mutect2; mutect2filter; pileup_paired_t; pileup_paired_n; 
     contamination_paired; learnreadorientationmodel;mergemut2stats;
-    } from './variant_calling.nf'
+    combineVariants as combineVariants_vardict; combineVariants as combineVariants_varscan; 
+    combineVariants as combineVariants_vardict_tonly; combineVariants as combineVariants_varscan_tonly
+    annotvep_tn as annotvep_tn_mut2; annotvep_tn as annotvep_tn_strelka; annotvep_tn as annotvep_tn_varscan; annotvep_tn as annotvep_tn_vardict;
+    combinemafs_tn} from './variant_calling.nf'
 include {mutect2_t_tonly; mutect2filter_tonly; 
+    varscan_tonly; vardict_tonly; 
     contamination_tumoronly;
     learnreadorientationmodel_tonly; 
     mergemut2stats_tonly;
-    annotvep_tonly} from './variant_calling_tonly.nf'
+    annotvep_tonly as annotvep_tonly_varscan; annotvep_tonly as annotvep_tonly_vardict; annotvep_tonly as annotvep_tonly_mut2;
+    combinemafs_tonly} from './variant_calling_tonly.nf'
 include {splitinterval} from "./splitbed.nf"
 
 
 
 workflow INPUT_TONLY_PIPE {
-    fastqinput=Channel.fromFilePairs(params.fastq_input)
+    if(params.fastq_input){
+        fastqinput=Channel.fromFilePairs(params.fastq_input)
+
+    }else if(params.file_input) {
+        fastqinput=Channel.fromPath(params.file_input)
+                        .splitCsv(header: false, sep: "\t", strip:true)
+                        .map{ sample,fq1,fq2 -> 
+                        tuple(sample, tuple(file(fq1),file(fq2)))
+                                  }
+    }
 
 
   if(params.sample_sheet){
@@ -35,11 +49,14 @@ workflow INPUT_TONLY_PIPE {
                         row.Tumor
                        )
                                   }
+
     }else{
         sample_sheet=fastqinput.map{samplename,f1 -> tuple (
              samplename)}
     }
 
+
+
     emit:
         fastqinput
         sample_sheet
@@ -142,11 +159,29 @@ workflow VARIANT_TONLY_PIPE {
 
     mutect2filter_tonly(mut2tonly_filter)
 
-    //#To implement
-    //CNMOPs from the BAM BQSRs
+
     //##VCF2MAF TO
 
-    annotvep_tonly(mutect2filter_tonly.out)
+    mutect2filter_tonly.out
+    .join(sample_sheet)
+    .map{tumor,markedvcf,finalvcf,stats -> tuple(tumor,"mutect2",finalvcf)} | annotvep_tonly_mut2
+
+    //VarDict_tonly
+    vardict_tonly_comb=bambyinterval.map{tumorname,tumorbam,tumorbai,normname,normbam,normbai,bed ->
+        tuple(tumorname,tumorbam,tumorbai,bed)} 
+    vardict_tonly(vardict_tonly_comb).groupTuple().map{tumor,vcf-> tuple(tumor,vcf,"vardict_tonly")} |combineVariants_vardict_tonly
+    combineVariants_vardict_tonly.out.join(sample_sheet)
+    .map{tumor,marked,normvcf ->tuple(tumor,"vardict_tonly",normvcf)} | annotvep_tonly_vardict
+
+    //VarScan_tonly
+    varscan_tonly_comb=varscan_in.map{tumor,bam,bai,normal,nbam,nbai,bed,tpile,npile,tumorc,normalc ->
+    tuple(tumor,bam,bai,bed,tpile,tumorc)} | varscan_tonly 
+    varscan_tonly_comb1=varscan_tonly_comb.groupTuple().map{tumor,vcf-> tuple(tumor,vcf,"varscan_tonly")} | combineVariants_varscan_tonly
+
+    varscan_tonly_comb1.join(sample_sheet)
+    .map{tumor,marked,normvcf,normal ->tuple(tumor,"varscan_tonly",normvcf)} | annotvep_tonly_varscan
+
+    annotvep_tonly_mut2.out.concat(annotvep_tonly_vardict.out).concat(annotvep_tonly_varscan.out) | combinemafs_tonly
 
 }