Make GATKSVPipelineSingleSample validate it in MiniWDL

wdl/DepthPreprocessing.wdl

@@ -141,7 +141,7 @@ task MergeSample {
   input {
     File gcnv
     Array[File] cnmops
-    Float max_dist = 0.25
+    Float? max_dist
     String sample_id
     String sv_pipeline_docker
     RuntimeAttr? runtime_attr_override
@@ -160,14 +160,15 @@ task MergeSample {
   output {
     File sample_bed = "~{sample_id}.merged.defrag.sorted.bed"
   }
+
   command <<<
 
     set -euo pipefail
     zcat ~{sep=" " cnmops} | awk -F "\t" -v OFS="\t" '{if ($5=="~{sample_id}") print}' > cnmops.cnv
     cat ~{gcnv} cnmops.cnv | sort -k1,1V -k2,2n > ~{sample_id}.bed
     bedtools merge -i ~{sample_id}.bed -d 0 -c 4,5,6,7 -o distinct > ~{sample_id}.merged.bed
     /opt/sv-pipeline/00_preprocessing/scripts/defragment_cnvs.py \
-      --max-dist ~{max_dist} ~{sample_id}.merged.bed ~{sample_id}.merged.defrag.bed
+      --max-dist ~{if defined(max_dist) then max_dist else "0.25"} ~{sample_id}.merged.bed ~{sample_id}.merged.defrag.bed
     sort -k1,1V -k2,2n ~{sample_id}.merged.defrag.bed > ~{sample_id}.merged.defrag.sorted.bed
 
   >>>

wdl/GATKSVPipelineSingleSample.wdl

@@ -289,7 +289,7 @@ workflow GATKSVPipelineSingleSample {
 
     RuntimeAttr? runtime_attr_filter_large_pesr
     RuntimeAttr? runtime_attr_srtest
-    RuntimeAttr? runtime_attr_split_vcf
+    RuntimeAttr? runtime_attr_split_vcf_srtest
     RuntimeAttr? runtime_attr_merge_allo
     RuntimeAttr? runtime_attr_merge_stats
     RuntimeAttr? runtime_attr_rewritesrcoords
@@ -316,13 +316,15 @@ workflow GATKSVPipelineSingleSample {
     File bin_exclude
 
     # Common
-    RuntimeAttr? runtime_attr_split_vcf
     RuntimeAttr? runtime_attr_merge_counts
     RuntimeAttr? runtime_attr_split_variants
     RuntimeAttr? runtime_attr_make_subset_vcf
     RuntimeAttr? runtime_attr_rdtest_genotype
     RuntimeAttr? runtime_attr_add_genotypes
-    RuntimeAttr? runtime_attr_concat_vcfs
+    RuntimeAttr? runtime_attr_genotype_depths_concat_vcfs
+    RuntimeAttr? runtime_attr_genotype_pesr_concat_vcfs
+    RuntimeAttr? runtime_attr_split_vcf_module04
+
 
     # Master
     RuntimeAttr? runtime_attr_add_batch
@@ -339,7 +341,6 @@ workflow GATKSVPipelineSingleSample {
 
     # Depth part 2
     RuntimeAttr? runtime_attr_integrate_depth_gq
-    RuntimeAttr? runtime_attr_concat_vcfs
 
     ############################################################
     ## Module 0506
@@ -364,7 +365,7 @@ workflow GATKSVPipelineSingleSample {
 
     RuntimeAttr? runtime_override_update_sr_list
     RuntimeAttr? runtime_override_merge_pesr_depth
-    RuntimeAttr? runtime_override_merge_pesr_depth
+    RuntimeAttr? runtime_override_breakpoint_overlap_filter
     RuntimeAttr? runtime_override_integrate_resolved_vcfs
     RuntimeAttr? runtime_override_rename_variants
 
@@ -413,13 +414,6 @@ workflow GATKSVPipelineSingleSample {
 
   }
 
-  if (defined(insert_size)) { Array[Float]? insert_size_input = [select_first([insert_size])]}
-  if (defined(read_length)) { Array[Int]? read_length_input = [select_first([read_length])]}
-  if (defined(coverage)) { Array[Float]? coverage_input = [select_first([coverage])]}
-  if (defined(pf_reads_improper_pairs)) { Array[Int]? pf_reads_improper_pairs_input = [select_first([pf_reads_improper_pairs])]}
-  if (defined(total_reads)) { Array[Float]? total_reads_input = [select_first([total_reads])]}
-  if (defined(pct_chimeras)) { Array[Float]? pct_chimeras_input = [select_first([pct_chimeras])]}
-
   String? delly_docker_ = if (!defined(case_delly_vcf) && use_delly) then delly_docker else NONE_STRING_
   String? manta_docker_ = if (!defined(case_manta_vcf) && use_manta) then manta_docker else NONE_STRING_
   String? melt_docker_ = if (!defined(case_melt_vcf) && use_melt) then melt_docker else NONE_STRING_
@@ -451,13 +445,13 @@ workflow GATKSVPipelineSingleSample {
         manta_mem_gb_per_job=manta_mem_gb_per_job,
         melt_standard_vcf_header=melt_standard_vcf_header,
         melt_metrics_intervals=melt_metrics_intervals,
-        insert_size=insert_size_input,
-        read_length=read_length_input,
-        coverage=coverage_input,
+        insert_size=insert_size,
+        read_length=read_length,
+        coverage=coverage,
         metrics_intervals=metrics_intervals,
-        pf_reads_improper_pairs=pf_reads_improper_pairs_input,
-        pct_chimeras=pct_chimeras_input,
-        total_reads=total_reads_input,
+        pf_reads_improper_pairs=pf_reads_improper_pairs,
+        pct_chimeras=pct_chimeras,
+        total_reads=total_reads,
         wham_include_list_bed_file=wham_include_list_bed_file,
         sv_pipeline_docker=sv_pipeline_docker,
         sv_base_mini_docker=sv_base_mini_docker,
@@ -778,7 +772,7 @@ workflow GATKSVPipelineSingleSample {
       linux_docker = linux_docker,
       sv_pipeline_docker = sv_pipeline_docker,
       runtime_attr_srtest = runtime_attr_srtest,
-      runtime_attr_split_vcf = runtime_attr_split_vcf,
+      runtime_attr_split_vcf = runtime_attr_split_vcf_srtest,
       runtime_attr_merge_allo = runtime_attr_merge_allo,
       runtime_attr_merge_stats = runtime_attr_merge_stats
   }
@@ -831,13 +825,14 @@ workflow GATKSVPipelineSingleSample {
       sv_pipeline_docker=sv_pipeline_docker,
       sv_pipeline_rdtest_docker=sv_pipeline_rdtest_docker,
       linux_docker=linux_docker,
-      runtime_attr_split_vcf=runtime_attr_split_vcf,
+      runtime_attr_split_vcf=runtime_attr_split_vcf_module04,
       runtime_attr_merge_counts=runtime_attr_merge_counts,
       runtime_attr_split_variants=runtime_attr_split_variants,
       runtime_attr_make_subset_vcf=runtime_attr_make_subset_vcf,
       runtime_attr_rdtest_genotype=runtime_attr_rdtest_genotype,
       runtime_attr_add_genotypes=runtime_attr_add_genotypes,
-      runtime_attr_concat_vcfs=runtime_attr_concat_vcfs,
+      runtime_attr_genotype_depths_concat_vcfs=runtime_attr_genotype_depths_concat_vcfs,
+      runtime_attr_genotype_pesr_concat_vcfs=runtime_attr_genotype_pesr_concat_vcfs,
       runtime_attr_add_batch=runtime_attr_add_batch,
       runtime_attr_index_vcf=runtime_attr_index_vcf,
       runtime_attr_count_pe=runtime_attr_count_pe,
@@ -847,8 +842,7 @@ workflow GATKSVPipelineSingleSample {
       runtime_attr_integrate_gq=runtime_attr_integrate_gq,
       runtime_attr_integrate_pesr_gq=runtime_attr_integrate_pesr_gq,
       runtime_attr_triple_stream_cat=runtime_attr_triple_stream_cat,
-      runtime_attr_integrate_depth_gq=runtime_attr_integrate_depth_gq,
-      runtime_attr_concat_vcfs=runtime_attr_concat_vcfs
+      runtime_attr_integrate_depth_gq=runtime_attr_integrate_depth_gq
   }
 
   call SingleSampleFiltering.ConvertCNVsWithoutDepthSupportToBNDs as ConvertCNVsWithoutDepthSupportToBNDs {
@@ -911,7 +905,7 @@ workflow GATKSVPipelineSingleSample {
 
       runtime_override_update_sr_list=runtime_override_update_sr_list,
       runtime_override_merge_pesr_depth=runtime_override_merge_pesr_depth,
-      runtime_override_breakpoint_overlap_filter=runtime_override_merge_pesr_depth,
+      runtime_override_breakpoint_overlap_filter=runtime_override_breakpoint_overlap_filter,
       runtime_override_integrate_resolved_vcfs=runtime_override_integrate_resolved_vcfs,
       runtime_override_rename_variants=runtime_override_rename_variants,
 

wdl/MakeBincovMatrix.wdl

@@ -45,7 +45,7 @@ workflow MakeBincovMatrix {
       input:
         count_file = all_count_files[i],
         sample = all_samples[i],
-        binsize = SetBins.binsize,
+        binsize = SetBins.out_binsize,
         bin_locs = SetBins.bin_locs,
         disk_overhead_gb = disk_overhead_gb,
         sv_base_mini_docker = sv_base_mini_docker,
@@ -73,7 +73,7 @@ task SetBins {
     File count_file
     Int? binsize
     Array[String]? bincov_matrix_samples
-    Int disk_overhead_gb = 10
+    Int? disk_overhead_gb
     String sv_base_mini_docker
     RuntimeAttr? runtime_attr_override
   }
@@ -84,7 +84,7 @@ task SetBins {
   String binsize_output_file_name = "binsize.txt"
 
   Float disk_scale_factor = 10.0
-  Int disk_gb = disk_overhead_gb + ceil(disk_scale_factor * size(count_file, "GiB"))
+  Int disk_gb = select_first([disk_overhead_gb, 10]) + ceil(disk_scale_factor * size(count_file, "GiB"))
   RuntimeAttr default_attr = object {
     cpu_cores: 1,
     mem_gb: 2.0,
@@ -97,7 +97,7 @@ task SetBins {
 
   output {
     File bin_locs = bin_file_name
-    Int binsize = read_int(binsize_output_file_name)
+    Int out_binsize = read_int(binsize_output_file_name)
     File bincov_matrix_header_file = bincov_header_file_name
   }
 
@@ -166,13 +166,12 @@ task MakeBincovMatrixColumns {
     String sample
     Int binsize
     File bin_locs
-    Int disk_overhead_gb = 10
+    Int? disk_overhead_gb = 10
     String sv_base_mini_docker
     RuntimeAttr? runtime_attr_override
   }
-
   Float disk_scale_factor = 10.0
-  Int disk_gb = disk_overhead_gb + ceil(disk_scale_factor * (size(count_file, "GiB") + size(bin_locs, "GiB")))
+  Int disk_gb = select_first([disk_overhead_gb, 10])+ ceil(disk_scale_factor * (size(count_file, "GiB") + size(bin_locs, "GiB")))
   RuntimeAttr default_attr = object {
     cpu_cores: 1,
     mem_gb: 2.0,
@@ -232,15 +231,15 @@ task ZPaste {
   input {
     Array[File]+ column_files
     String matrix_file_name
-    Int disk_overhead_gb = 10
+    Int? disk_overhead_gb = 10
     Float mem_overhead_gb = 1.0
     String sv_base_docker
     RuntimeAttr? runtime_attr_override
   }
 
   # Only compressed files are stored (if localization_optional, then only output file is stored),
   # so this is a reasonably conservative estimate for disk:
-  Int disk_gb = disk_overhead_gb + ceil(3.0 * size(column_files, "GiB"))
+  Int disk_gb = select_first([disk_overhead_gb, 10]) + ceil(3.0 * size(column_files, "GiB"))
   # Some memory is used up by the named pipes. Not a lot, but allocate in case the batch is huge:
   Float mem_gb = mem_overhead_gb + 0.003 * length(column_files)
   RuntimeAttr default_attr = object {

wdl/MasterVcfQc.wdl

@@ -137,8 +137,6 @@ workflow MasterVcfQc {
       runtime_override_collect_vids_per_sample=runtime_override_collect_vids_per_sample,
       runtime_override_split_samples_list=runtime_override_split_samples_list,
       runtime_override_tar_shard_vid_lists=runtime_override_tar_shard_vid_lists,
-      sv_base_mini_docker=sv_base_mini_docker,
-      sv_pipeline_docker=sv_pipeline_docker
   }
 
   # Plot per-sample stats

wdl/Module00a.wdl

@@ -61,13 +61,13 @@ workflow Module00a {
     # Melt inputs
     File? melt_standard_vcf_header # required if run_melt True
     File? melt_metrics_intervals
-    Array[Float]? insert_size
-    Array[Int]? read_length
-    Array[Float]? coverage
+    Float? insert_size
+    Int? read_length
+    Float? coverage
     File? metrics_intervals
-    Array[Float]? pct_chimeras
-    Array[Float]? total_reads
-    Array[Int]? pf_reads_improper_pairs
+    Float? pct_chimeras
+    Float? total_reads
+    Int? pf_reads_improper_pairs
 
     # Wham inputs
     File wham_include_list_bed_file
@@ -196,12 +196,6 @@ workflow Module00a {
   }
 
   if (run_melt) {
-    Float? insert_size_i = if defined(insert_size) then select_first([insert_size]) else NONE_FLOAT_
-    Int? read_length_i = if defined(read_length) then select_first([read_length]) else NONE_INT_
-    Float? coverage_i = if defined(coverage) then select_first([coverage]) else NONE_FLOAT_
-    Float? pct_chimeras_i = if defined(pct_chimeras) then select_first([pct_chimeras]) else NONE_FLOAT_
-    Float? total_reads_i = if defined(total_reads) then select_first([total_reads]) else NONE_INT_
-    Int? pf_reads_improper_pairs_i = if defined(pf_reads_improper_pairs) then select_first([pf_reads_improper_pairs]) else NONE_INT_
     call melt.MELT {
       input:
         bam_or_cram_file = bam_file_,
@@ -212,13 +206,13 @@ workflow Module00a {
         reference_index = reference_index,
         reference_version = reference_version,
         melt_standard_vcf_header = select_first([melt_standard_vcf_header]),
-        insert_size = insert_size_i,
-        read_length = read_length_i,
-        coverage = coverage_i,
+        insert_size = insert_size,
+        read_length = read_length,
+        coverage = coverage,
         wgs_metrics_intervals = melt_metrics_intervals,
-        pct_chimeras = pct_chimeras_i,
-        total_reads = total_reads_i,
-        pf_reads_improper_pairs = pf_reads_improper_pairs_i,
+        pct_chimeras = pct_chimeras,
+        total_reads = total_reads,
+        pf_reads_improper_pairs = pf_reads_improper_pairs,
         runtime_attr_coverage = runtime_attr_melt_coverage,
         runtime_attr_metrics = runtime_attr_melt_metrics,
         samtools_cloud_docker = samtools_cloud_docker,

wdl/Module00aBatch.wdl

@@ -84,6 +84,8 @@ workflow Module00aBatch {
 
     File? NONE_FILE_
     String? NONE_STRING_
+    Float? NONE_FLOAT_
+    Int? NONE_INT_
   }
 
   scatter (i in range(length(bam_or_cram_files))) {
@@ -112,13 +114,13 @@ workflow Module00aBatch {
         manta_mem_gb_per_job = manta_mem_gb_per_job,
         melt_standard_vcf_header = melt_standard_vcf_header,
         melt_metrics_intervals = melt_metrics_intervals,
-        insert_size = insert_size,
-        read_length = read_length,
-        coverage = coverage,
+        insert_size = if defined(insert_size) then select_first([insert_size])[i] else NONE_FLOAT_,
+        read_length = if defined(read_length) then select_first([read_length])[i] else NONE_INT_,
+        coverage = if defined(coverage) then select_first([coverage])[i] else NONE_FLOAT_,
         metrics_intervals = metrics_intervals,
-        pct_chimeras = pct_chimeras,
-        total_reads = total_reads,
-        pf_reads_improper_pairs = pf_reads_improper_pairs,
+        pct_chimeras = if defined(pct_chimeras) then select_first([pct_chimeras])[i] else NONE_FLOAT_,
+        total_reads = if defined(total_reads) then select_first([total_reads])[i] else NONE_FLOAT_,
+        pf_reads_improper_pairs = if defined(pf_reads_improper_pairs) then select_first([pf_reads_improper_pairs])[i] else NONE_INT_,
         wham_include_list_bed_file = wham_include_list_bed_file,
         sv_pipeline_docker = sv_pipeline_docker,
         sv_base_mini_docker = sv_base_mini_docker,
@@ -168,4 +170,4 @@ workflow Module00aBatch {
     Array[File?] wham_vcf = Module00a.wham_vcf
     Array[File?] wham_index = Module00a.wham_index
   }
-}
+}

wdl/Module00c.wdl

@@ -174,7 +174,6 @@ workflow Module00c {
 
     RuntimeAttr? runtime_attr_merge_vcfs
     RuntimeAttr? runtime_attr_baf_gen
-    RuntimeAttr? runtime_attr_merge_baf
     RuntimeAttr? ploidy_score_runtime_attr
     RuntimeAttr? ploidy_build_runtime_attr
     RuntimeAttr? runtime_attr_subset_ped

wdl/Module04.wdl

@@ -59,7 +59,8 @@ workflow Module04 {
     RuntimeAttr? runtime_attr_make_subset_vcf
     RuntimeAttr? runtime_attr_rdtest_genotype
     RuntimeAttr? runtime_attr_add_genotypes
-    RuntimeAttr? runtime_attr_concat_vcfs
+    RuntimeAttr? runtime_attr_genotype_depths_concat_vcfs
+    RuntimeAttr? runtime_attr_genotype_pesr_concat_vcfs
 
     # Master
     RuntimeAttr? runtime_attr_add_batch
@@ -81,21 +82,17 @@ workflow Module04 {
     RuntimeAttr? runtime_attr_genotype_train
     RuntimeAttr? runtime_attr_generate_cutoff
     RuntimeAttr? runtime_attr_update_cutoff
-    RuntimeAttr? runtime_attr_split_variants
     RuntimeAttr? runtime_attr_merge_genotypes
 
     # PESR part 2
-    RuntimeAttr? runtime_attr_count_pe
     RuntimeAttr? runtime_attr_genotype_pe
-    RuntimeAttr? runtime_attr_count_sr
     RuntimeAttr? runtime_attr_genotype_sr
     RuntimeAttr? runtime_attr_integrate_gq
     RuntimeAttr? runtime_attr_integrate_pesr_gq
     RuntimeAttr? runtime_attr_triple_stream_cat
 
     # Depth part 2
     RuntimeAttr? runtime_attr_integrate_depth_gq
-    RuntimeAttr? runtime_attr_concat_vcfs
     RuntimeAttr? runtime_attr_merge_regeno_cov_med
 
   }
@@ -215,7 +212,7 @@ workflow Module04 {
       runtime_attr_integrate_pesr_gq = runtime_attr_integrate_pesr_gq,
       runtime_attr_add_genotypes = runtime_attr_add_genotypes,
       runtime_attr_triple_stream_cat = runtime_attr_triple_stream_cat,
-      runtime_attr_concat_vcfs = runtime_attr_concat_vcfs
+      runtime_attr_concat_vcfs = runtime_attr_genotype_pesr_concat_vcfs
   }
 
   if (!single_sample_mode) {
@@ -270,7 +267,7 @@ workflow Module04 {
       runtime_attr_make_subset_vcf = runtime_attr_make_subset_vcf,
       runtime_attr_integrate_depth_gq = runtime_attr_integrate_depth_gq,
       runtime_attr_add_genotypes = runtime_attr_add_genotypes,
-      runtime_attr_concat_vcfs = runtime_attr_concat_vcfs,
+      runtime_attr_concat_vcfs = runtime_attr_genotype_depths_concat_vcfs,
       runtime_attr_merge_regeno_cov_med = runtime_attr_merge_regeno_cov_med
   }
   output {

wdl/RDTest.wdl

@@ -96,7 +96,7 @@ workflow RDTest {
 
   call tasks02.MergeStats as MergeStats {
     input:
-      stats = flatten([RDTestAutosome.stats, RDTestAllosome.stats]),
+      stats = flatten([RDTestAutosome.out_stats, RDTestAllosome.out_stats]),
       prefix = "${batch}.${algorithm}",
       linux_docker = linux_docker,
       runtime_attr_override = runtime_attr_merge_stats

wdl/RDTestChromosome.wdl

@@ -124,7 +124,7 @@ workflow RDTestChromosome {
   }
 
   output {
-    File stats = MergeStats.merged_stats
+    File out_stats = MergeStats.merged_stats
   }
 }