broadinstitute · VJalili · Apr 25, 2024 · Apr 25, 2024 · Apr 25, 2024
diff --git a/inputs/templates/terra_workspaces/cohort_mode/workflow_configurations/EvidenceQC.json.tmpl b/inputs/templates/terra_workspaces/cohort_mode/workflow_configurations/EvidenceQC.json.tmpl
@@ -5,11 +5,10 @@
  "EvidenceQC.sv_pipeline_qc_docker": "${workspace.sv_pipeline_qc_docker}",
  "EvidenceQC.sv_base_docker": "${workspace.sv_base_docker}",
  "EvidenceQC.wgd_scoring_mask": "${workspace.wgd_scoring_mask}",
- "EvidenceQC.genome_file": "${workspace.genome_file}",
 
  "EvidenceQC.batch": "${this.sample_set_id}",
  "EvidenceQC.melt_insert_size": "${this.samples.melt_insert_size}",
- "EvidenceQC.counts": "${this.samples.coverage_counts}",
+ "EvidenceQC.coverage_counts": "${this.samples.coverage_counts}",
  "EvidenceQC.manta_vcfs": "${this.samples.manta_vcf}",
  "EvidenceQC.melt_vcfs": "${this.samples.melt_vcf}",
  "EvidenceQC.wham_vcfs": "${this.samples.wham_vcf}",

diff --git a/...plates/terra_workspaces/cohort_mode/workflow_configurations/GatherBatchEvidence.json.tmpl b/...plates/terra_workspaces/cohort_mode/workflow_configurations/GatherBatchEvidence.json.tmpl
@@ -53,7 +53,7 @@
  "GatherBatchEvidence.PE_files": "${this.samples.pesr_disc}",
  "GatherBatchEvidence.SR_files": "${this.samples.pesr_split}",
  "GatherBatchEvidence.SD_files": "${this.samples.pesr_sd}",
- "GatherBatchEvidence.counts": "${this.samples.coverage_counts}",
+ "GatherBatchEvidence.coverage_counts": "${this.samples.coverage_counts}",
  "GatherBatchEvidence.manta_vcfs": "${this.samples.manta_vcf}",
  "GatherBatchEvidence.samples": "${this.samples.sample_id}",
  "GatherBatchEvidence.melt_vcfs": "${this.samples.melt_vcf}",

diff --git a/inputs/templates/terra_workspaces/cohort_mode/workflow_configurations/TrainGCNV.json.tmpl b/inputs/templates/terra_workspaces/cohort_mode/workflow_configurations/TrainGCNV.json.tmpl
@@ -58,7 +58,7 @@
  "TrainGCNV.ploidy_sample_psi_scale" : 0.001,
 
  "TrainGCNV.cohort": "${this.sample_set_id}",
- "TrainGCNV.count_files": "${this.samples.coverage_counts}",
+ "TrainGCNV.coverage_counts": "${this.samples.coverage_counts}",
  "TrainGCNV.samples": "${this.samples.sample_id}",
 
  "TrainGCNV.n_samples_subsample": 100,

diff --git a/inputs/templates/test/EvidenceQC/EvidenceQC.json.tmpl b/inputs/templates/test/EvidenceQC/EvidenceQC.json.tmpl
@@ -5,10 +5,9 @@
  "EvidenceQC.sv_pipeline_qc_docker": {{ dockers.sv_pipeline_qc_docker | tojson }},
  "EvidenceQC.sv_base_docker": {{ dockers.sv_base_docker | tojson }},
  "EvidenceQC.wgd_scoring_mask": {{ reference_resources.wgd_scoring_mask | tojson }},
- "EvidenceQC.genome_file": {{ reference_resources.genome_file | tojson }},
 
  "EvidenceQC.batch": {{ test_batch.name | tojson }},
- "EvidenceQC.counts": {{ test_batch.counts | tojson }},
+ "EvidenceQC.coverage_counts": {{ test_batch.counts | tojson }},
  "EvidenceQC.manta_vcfs": {{ test_batch.manta_vcfs | tojson }},
  "EvidenceQC.melt_vcfs": {{ test_batch.melt_vcfs | tojson }},
  "EvidenceQC.wham_vcfs": {{ test_batch.wham_vcfs | tojson }},

diff --git a/inputs/templates/test/GatherBatchEvidence/GatherBatchEvidence.json.tmpl b/inputs/templates/test/GatherBatchEvidence/GatherBatchEvidence.json.tmpl
@@ -52,7 +52,7 @@
  "GatherBatchEvidence.PE_files": {{ test_batch.PE_files | tojson }},
  "GatherBatchEvidence.SR_files": {{ test_batch.SR_files | tojson }},
  "GatherBatchEvidence.SD_files": {{ test_batch.SD_files | tojson }},
- "GatherBatchEvidence.counts": {{ test_batch.counts | tojson }},
+ "GatherBatchEvidence.coverage_counts": {{ test_batch.counts | tojson }},
  "GatherBatchEvidence.manta_vcfs": {{ test_batch.manta_vcfs | tojson }},
  "GatherBatchEvidence.samples": {{ test_batch.samples | tojson }},
  "GatherBatchEvidence.melt_vcfs": {{ test_batch.melt_vcfs | tojson }},

diff --git a/inputs/templates/test/TrainGCNV/TrainGCNV.json.tmpl b/inputs/templates/test/TrainGCNV/TrainGCNV.json.tmpl
@@ -58,6 +58,6 @@
  "TrainGCNV.ploidy_sample_psi_scale" : 0.001,
 
  "TrainGCNV.cohort": {{ test_batch.name | tojson }},
- "TrainGCNV.count_files": {{ test_batch.counts | tojson }},
+ "TrainGCNV.coverage_counts": {{ test_batch.counts | tojson }},
  "TrainGCNV.samples": {{ test_batch.samples | tojson }}
 }
diff --git a/wdl/CollectCoverage.wdl b/wdl/CollectCoverage.wdl
@@ -78,7 +78,7 @@ task CollectCounts {
 
 task CondenseReadCounts {
  input {
- File counts
+ File coverage_counts
  String sample
  Int? max_interval_size
  Int? min_interval_size
@@ -103,8 +103,8 @@ task CondenseReadCounts {
  set -euo pipefail
  export GATK_LOCAL_JAR=~{default="/root/gatk.jar" gatk4_jar_override}
 
- zcat ~{counts} | grep '^@' | grep -v '@RG' > ref.dict
- zcat ~{counts} | grep -v '^@' | sed -e 1d | \
+ zcat ~{coverage_counts} | grep '^@' | grep -v '@RG' > ref.dict
+ zcat ~{coverage_counts} | grep -v '^@' | sed -e 1d | \
  awk 'BEGIN{FS=OFS="\t";print "#Chr\tStart\tEnd\tNA21133"}{print $1,$2-1,$3,$4}' | bgzip > in.rd.txt.gz 
  tabix -0 -s1 -b2 -e3 in.rd.txt.gz 
  gatk --java-options -Xmx2g CondenseDepthEvidence -F in.rd.txt.gz -O out.rd.txt.gz --sequence-dictionary ref.dict \

diff --git a/wdl/EvidenceQC.wdl b/wdl/EvidenceQC.wdl
@@ -21,11 +21,8 @@ workflow EvidenceQC {
  # Optional QC tasks
  Boolean run_vcf_qc
 
- # Global files
- File genome_file
-
  # Coverage files
- Array[File] counts
+ Array[File] coverage_counts
 
  # SV tool calls
  Array[File]? manta_vcfs # Manta VCF
@@ -65,7 +62,7 @@ workflow EvidenceQC {
  call mbm.MakeBincovMatrix as MakeBincovMatrix {
  input:
  samples = samples,
- count_files = counts,
+ coverage_counts = coverage_counts,
  batch = batch,
  disk_overhead_gb = disk_overhead_bincov_gb,
  sv_base_mini_docker = sv_base_mini_docker,

diff --git a/wdl/GatherBatchEvidence.wdl b/wdl/GatherBatchEvidence.wdl
@@ -40,7 +40,7 @@ workflow GatherBatchEvidence {
  # PE/SR/BAF/bincov files
  # If neither SD_files nor ref_panel_SD_files is present, BAF_files must be supplied
  # If BAF_files is absent, SD_files and/or ref_panel_SD_files and sd_locs_vcf must be supplied
- Array[File] counts
+ Array[File] coverage_counts
  File? ref_panel_bincov_matrix
  File? bincov_matrix
  File? bincov_matrix_index
@@ -189,7 +189,7 @@ workflow GatherBatchEvidence {
  call mbm.MakeBincovMatrix as MakeBincovMatrix {
  input:
  samples = samples,
- count_files = counts,
+ coverage_counts = coverage_counts,
  bincov_matrix = ref_panel_bincov_matrix,
  bincov_matrix_samples = ref_panel_samples,
  batch = batch,
@@ -311,7 +311,7 @@ workflow GatherBatchEvidence {
  scatter (i in range(length(samples))) {
  call cov.CondenseReadCounts as CondenseReadCounts {
  input:
- counts = counts[i],
+ coverage_counts = coverage_counts[i],
  sample = samples[i],
  min_interval_size = min_interval_size,
  max_interval_size = max_interval_size,

diff --git a/wdl/MakeBincovMatrix.wdl b/wdl/MakeBincovMatrix.wdl
@@ -5,7 +5,7 @@ import "Structs.wdl"
 workflow MakeBincovMatrix {
  input {
  Array[String] samples
- Array[File] count_files
+ Array[File] coverage_counts
  Array[String]? bincov_matrix_samples
  File? bincov_matrix
  String batch
@@ -30,7 +30,7 @@ workflow MakeBincovMatrix {
  }
 
  Array[String]+ all_samples = flatten([samples, select_all([bincov_matrix_header])])
- Array[File]+ all_count_files = flatten([count_files, select_all([bincov_matrix])])
+ Array[File]+ all_count_files = flatten([coverage_counts, select_all([bincov_matrix])])
 
  scatter(i in range(length(all_count_files))) {
  call MakeBincovMatrixColumns {

diff --git a/wdl/TrainGCNV.wdl b/wdl/TrainGCNV.wdl
@@ -9,7 +9,7 @@ import "Utils.wdl" as util
 workflow TrainGCNV {
  input {
  Array[String] samples
- Array[File] count_files
+ Array[File] coverage_counts
 
  # Common parameters
  String cohort
@@ -129,7 +129,7 @@ workflow TrainGCNV {
  String sample_ids_ = samples[i]
  call cov.CondenseReadCounts as CondenseReadCounts {
  input:
- counts = count_files[i],
+ counts = coverage_counts[i],
  sample = samples[i],
  min_interval_size = min_interval_size,
  max_interval_size = max_interval_size,