Qualimap and Deepvariant bug fixes

bin/run_sequenza.R

@@ -48,19 +48,19 @@ CP.example <- sequenza.fit(seqzdata, mc.cores = n_cores)
 
 ## Sequenza.extract seems to fail if too few mutations
 num_mutations <- unlist(lapply(seqzdata$mutations, nrow))
-chrom_list1 <- names(num_mutations)[num_mutations > 3]
+chrom_list <- names(num_mutations)[num_mutations > 3]
 ## Also fails if segments <2
-num_segments <- unlist(lapply(seqzdata$segments, nrow))
-chrom_list2 <- names(num_mutations)[num_segments > 1]
+#num_segments <- unlist(lapply(seqzdata$segments, nrow))
+#chrom_list2 <- names(num_mutations)[num_segments > 1]
+#chrom_list <- intersect(chrom_list1,chrom_list2)
 
-chrom_list <- intersect(chrom_list1,chrom_list2)
 not_included <- setdiff(names(num_mutations), chrom_list)
 print("Printing results...")
 if (length(not_included) > 0) {
     print("Excluding these chromosomes because of too few mutations and/or segments...")
     print(not_included)
 }
-sequenza.results(sequenza.extract = seqzdata,cp.table = CP.example, sample.id = sampleid, out.dir=out_dir, chromosome.list=chrom_list)
+sequenza.results(sequenza.extract = seqzdata,cp.table = CP.example, sample.id = sampleid, out.dir=out_dir)
 
 date()
 print("Done")

conf/base.config

@@ -83,7 +83,7 @@ process {
         memory = { check_max( 96.GB * task.attempt, 'memory'  ) }
         time   = { check_max( 72.h   * task.attempt, 'time'    ) }
     }
-    withName:'qualimap' {
+    withName:'qualimap_bamqc' {
         cpus   = { check_max( 8     * task.attempt, 'cpus'    ) }
         memory = { check_max( 96.GB * task.attempt, 'memory'  ) }
         time   = { check_max( 24.h   * task.attempt, 'time'    ) }

conf/biowulf.config

@@ -60,7 +60,7 @@ process {
         cpus   = { check_max( 4     * task.attempt, 'cpus'    ) }
         memory = { check_max( 24.GB * task.attempt, 'memory'  ) }
         time   = { check_max( 120.h  * task.attempt, 'time'    ) }
-        clusterOptions = ' --gres=lscratch:300 '
+        clusterOptions = ' --gres=lscratch:500 '
     }
 
 }

conf/genomes.config

@@ -28,8 +28,9 @@ params {
             annotsvgenome = "GRCh38"
             octopus_sforest= "--somatic-forest /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/octopus/somatic.v0.7.4.forest"
             octopus_gforest= "--forest /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/octopus/germline.v0.7.4.forest"
-            SEQUENZAGC = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/SEQUENZA/hg38_gc50Base.txt.gz"
-            chromosomes = ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']
+            SEQUENZAGC = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/SEQUENZA/hg38.gc200Base.wig.gz"
+            SEQUENZAGC_EXOME = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/SEQUENZA/hg38.gc50Base.wig.gz"
+            chromosomes = ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY']
             //HMFTOOLS
             GENOMEVER = "38"
             HMFGENOME =  "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/bwamem2/GRCh38.d1.vd1.fa"
@@ -72,7 +73,8 @@ params {
             dbsnp = "/fdb/GATK_resource_bundle/hg19-2.8/dbsnp_138.hg19.vcf.gz"
             germline_resource = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg19/GATKbundle/af-only-gnomad.raw.sites.liftover.hg19.vcf.gz"
             gnomad = '--germline-resource /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg19/GATKbundle/af-only-gnomad.raw.sites.liftover.hg19.vcf.gz'
-            pon = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg19/GATKbundle/hg19.liftGRCh37.noCOSMIC_ClinVar.pon.vcf.gz"
+            PON = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg19/GATKbundle/hg19.liftGRCh37.noCOSMIC_ClinVar.pon.vcf.gz"
+            tonly_PON = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg19/GATKbundle/hg19.liftGRCh37.noCOSMIC_ClinVar.pon.vcf.gz"
             KRAKENBACDB = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/kraken/20180907_standard_kraken2"
             snpeff_genome = "GRCh37.75"
             snpeff_config = "/usr/local/apps/snpEff/4.3t/snpEff.config"
@@ -85,8 +87,9 @@ params {
             annotsvgenome = "GRCh37"
             octopus_sforest= "" //NO hg19 somaticforest"--somatic-forest /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/octopus/somatic.v0.7.4.forest"
             octopus_gforest= "" //no hg19 gforest"--forest /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/octopus/germline.v0.7.4.forest"
-            SEQUENZAGC = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/SEQUENZA/hg38_gc50Base.txt.gz"
-            chromosomes = ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']
+            SEQUENZAGC = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg19/SEQUENZA/hg19.gc200Base.wig.gz"
+            SEQUENZAGC_EXOME = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg19/SEQUENZA/hg19.gc50Base.wig.gz"
+            chromosomes = ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY']
             //HMFTOOLS
             GENOMEVER = "37"
             HMFGENOME =  "/data/CCBR_Pipeliner/db/PipeDB/lib/hs37d5.fa"
@@ -142,14 +145,15 @@ params {
             annotsvgenome = "mm10"
             octopus_sforest = ""
             octopus_gforest = ""
-	 	    SEQUENZAGC =  '/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/mm10/SEQUENZA/mm10.gc50Base.wig.gz'
+	 	    SEQUENZAGC =  '/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/mm10/SEQUENZA/mm10.gc200Base.wig.gz'
+	 	    SEQUENZAGC_EXOME =  '/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/mm10/SEQUENZA/mm10.gc50Base.wig.gz'
             FREEC {
                 FREECLENGTHS = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/mm10/FREEC/mm10.fa.fai"
                 FREECCHROMS = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/mm10/FREEC/Chromosomes"
                 FREECPILEUP = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/mm10/FREEC/mm10_dbSNP137.ucsc.freec.bed"
                 FREECSNPS= "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/mm10/FREEC/mm10_dbSNP137.ucsc.freec.txt"
             }
-            chromosomes = ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chrX','chrY','chrM']
+            chromosomes = ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chrX','chrY']
             //CNVKIT
             REFFLAT = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/mm10/cnvkit/refFlat.txt"
             ACCESS = "/data/CCBR_Pipeliner/Pipelines/LOGAN/resources/mm10/cnvkit/access-10kb.mm10.bed"
@@ -183,8 +187,9 @@ params {
             annotsvgenome = "GRCh38"
             octopus_sforest= "--somatic-forest /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/octopus/somatic.v0.7.4.forest"
             octopus_gforest= "--forest /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/octopus/germline.v0.7.4.forest"
-            SEQUENZAGC = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/SEQUENZA/hg38_gc50Base.txt.gz"
-            chromosomes = ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']
+            SEQUENZAGC = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/SEQUENZA/hg38.gc200Base.wig.gz"
+            SEQUENZAGC_EXOME = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/SEQUENZA/hg38.gc50Base.wig.gz"
+            chromosomes = ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY']
             //HMFTOOLS
             GENOMEVER = "38"
             HMFGENOME =  "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/bwamem2/GRCh38.d1.vd1.fa"
@@ -237,8 +242,9 @@ params {
             annotsvgenome = "GRCh38"
             octopus_sforest= "--somatic-forest /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/octopus/somatic.v0.7.4.forest"
             octopus_gforest= "--forest /data/CCBR_Pipeliner/Pipelines/LOGAN/resources/hg38/octopus/germline.v0.7.4.forest"
-            SEQUENZAGC = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/SEQUENZA/hg38_gc50Base.txt.gz"
-            chromosomes = ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY','chrM']
+            SEQUENZAGC = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/SEQUENZA/hg38.gc200Base.wig.gz"
+            SEQUENZAGC_EXOME = "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/SEQUENZA/hg38.gc50Base.wig.gz"
+            chromosomes = ['chr1','chr2','chr3','chr4','chr5','chr6','chr7','chr8','chr9','chr10','chr11','chr12','chr13','chr14','chr15','chr16','chr17','chr18','chr19','chr20','chr21','chr22','chrX','chrY']
             //HMFTOOLS
             GENOMEVER = "38"
             HMFGENOME =  "/data/CCBR_Pipeliner/Pipelines/XAVIER/resources/hg38/genome_noalt/bwamem2/GCA_000001405.15_GRCh38_no_alt_analysis_set.fasta"

modules/local/bwamem/bwamem2.nf

@@ -11,7 +11,6 @@ process bwamem2 {
         else if (task.attempt == 3) return '200 GB'
     }
 
-
     input:
         tuple val(samplename),
         path("${samplename}.R1.trimmed.fastq.gz"),

modules/local/deepvariant.nf

@@ -95,6 +95,7 @@ process deepvariant_step3 {
     """
     postprocess_variants \
         --ref $GENOMEREF \
+        --sample_name ${samplename} \
         --infile outdv/${samplename}_call_variants_output.tfrecord.gz \
         --outfile ${samplename}_${bed}.vcf.gz \
         --gvcf_outfile ${samplename}_${bed}.gvcf.gz \
@@ -151,19 +152,19 @@ process glnexus {
 
     """
     glnexus_cli --config DeepVariant_unfiltered \
-        *.gvcf.gz --threads 8 > germline.v.bcf
+        *.gvcf.gz --threads $task.cpus > germline.v.bcf
 
     bcftools norm \
         -m - \
         -Oz \
-        --threads 8 \
+        --threads $task.cpus \
         -f $GENOMEREF \
         -o germline.norm.vcf.gz \
         germline.v.bcf
 
     bcftools index \
         -f -t \
-        --threads 8 \
+        --threads $task.cpus \
         germline.norm.vcf.gz
     """
 
@@ -198,7 +199,7 @@ process deepvariant_combined {
         --reads=${bam} \
         --output_gvcf=${samplename}.gvcf.gz \
         --output_vcf=${samplename}.vcf.gz \
-        --num_shards=16
+        --num_shards=$task.cpus
     """
 
 

modules/local/gridss.nf

@@ -82,13 +82,10 @@ process gridss_tonly {
 
     output:
         tuple val(tumorname),
-        path("${tumorname}.vcf.gz"),
-        path("${tumorname}.vcf.gz.tbi"),
+        path("${tumorname}.vcf.gz"), path("${tumorname}.vcf.gz.tbi"),
         path("${tumorname}.vcf.gz.assembly.bam"),
-        path("${tumorname}.gripss.vcf.gz"),
-        path("${tumorname}.gripss.vcf.gz.tbi"),
-        path("${tumorname}.gripss.filtered.vcf.gz"),
-        path("${tumorname}.gripss.filtered.vcf.gz.tbi")
+        path("${tumorname}.gripss.vcf.gz"), path("${tumorname}.gripss.vcf.gz.tbi"),
+        path("${tumorname}.gripss.filtered.vcf.gz"), path("${tumorname}.gripss.filtered.vcf.gz.tbi")
 
     script:
     """

modules/local/purple.nf

@@ -16,8 +16,9 @@ GERMLINEHOTSPOTS = file(params.genomes[params.genome].GERMLINEHOTSPOTS)
 
 process amber_tonly {
     container = "${params.containers.logan}"
-
     label 'process_medium'
+    errorStrategy 'ignore'
+
 
     input:
         tuple val(tumorname), path(tumor), path(tumorbai)
@@ -49,8 +50,8 @@ process amber_tonly {
 
 process amber_tn {
     container = "${params.containers.logan}"
-
     label 'process_medium'
+    errorStrategy 'ignore'
 
     input:
         tuple val(tumorname), path(tumor), path(tumorbai),
@@ -85,6 +86,7 @@ process amber_tn {
 process cobalt_tonly {
     container = "${params.containers.logan}"
     label 'process_medium'
+    errorStrategy 'ignore'
 
     input:
         tuple val(tumorname), path(tumor), path(tumorbai)
@@ -116,6 +118,7 @@ process cobalt_tonly {
 process cobalt_tn {
     container = "${params.containers.logan}"
     label 'process_medium'
+    errorStrategy 'ignore'
 
     input:
         tuple val(tumorname), path(tumor), path(tumorbai),
@@ -149,6 +152,7 @@ process cobalt_tn {
 process purple {
     container = "${params.containers.logan}"
     label 'process_medium'
+    errorStrategy 'ignore'
 
     input:
         tuple val(id), val(tumorname), val(normalname),
@@ -190,6 +194,7 @@ process purple {
 process purple_novc {
     container = "${params.containers.logan}"
     label 'process_medium'
+    errorStrategy 'ignore'
 
     input:
         tuple val(id), val(tumorname), val(normalname),
@@ -229,6 +234,7 @@ process purple_novc {
 process purple_tonly {
     container = "${params.containers.logan}"
     label 'process_medium'
+    errorStrategy 'ignore'
 
     input:
         tuple val(tumorname), 
@@ -251,7 +257,7 @@ process purple_tonly {
     $ENSEMBLCACHE \
     -somatic_vcf ${somaticvcf} \
     -driver_gene_panel $DRIVERS \
-    -somatic_hotspots $HOTSPOTS \
+    -somatic_hotspots $SOMATICHOTSPOTS \
     -threads $task.cpus \
     -output_dir ${tumorname}
     """
@@ -269,7 +275,8 @@ process purple_tonly {
 process purple_tonly_novc {
     container = "${params.containers.logan}"
     label 'process_medium'
-
+    errorStrategy 'ignore'
+
     input:
         tuple val(tumorname), val(normalname),
         path(cobaltin), path(amberin)