From 1f88afd65f133bbd427d8b9fbacec007bb21accc Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Fri, 3 Feb 2023 15:56:54 -0500
Subject: [PATCH 01/28] Separate the select sample task as a individual wdl

---
 .dockstore.yml                                |  7 +-
 BenchmarkCNV/BenchmarkCNV.inputs.json         | 12 ++--
 BenchmarkCNV/BenchmarkCNV.wdl                 | 62 +++---------------
 .../SelectSampleFromCallSet.inputs.json       |  9 +++
 BenchmarkCNV/SelectSampleFromCallSet.wdl      | 65 +++++++++++++++++++
 5 files changed, 96 insertions(+), 59 deletions(-)
 create mode 100644 BenchmarkCNV/SelectSampleFromCallSet.inputs.json
 create mode 100644 BenchmarkCNV/SelectSampleFromCallSet.wdl

diff --git a/.dockstore.yml b/.dockstore.yml
index 059ca98..6ff83ce 100644
--- a/.dockstore.yml
+++ b/.dockstore.yml
@@ -35,8 +35,13 @@ workflows:
    primaryDescriptorPath: /wdl/CollectSamErrorMetrics.wdl
    testParameterFiles:
    - /input_json/CollectSamErrorMetrics_inputs.json
+ - name: SelectSampleFromCallSet
+   subclass: WDL
+   primaryDescriptorPath: /BenchmarkCNV/SelectSampleFromCallSet.wdl
+   testParameterFiles:
+   - /BenchmarkCNV/SelectSampleFromCallSet.inputs.json
  - name: BenchmarkCNV
    subclass: WDL
    primaryDescriptorPath: /BenchmarkCNV/BenchmarkCNV.wdl
    testParameterFiles:
-   - /BenchmarkCNV/BenchmarkCNV_test.json
\ No newline at end of file
+   - /BenchmarkCNV/BenchmarkCNV.inputs.json
diff --git a/BenchmarkCNV/BenchmarkCNV.inputs.json b/BenchmarkCNV/BenchmarkCNV.inputs.json
index 2810dbe..3c2b002 100644
--- a/BenchmarkCNV/BenchmarkCNV.inputs.json
+++ b/BenchmarkCNV/BenchmarkCNV.inputs.json
@@ -1,12 +1,16 @@
 {
+  "Benchmark_CNV_Caller.BenchmarkCNV.mem_size": "Int? (optional)",
   "Benchmark_CNV_Caller.wittyer_docker": "us.gcr.io/tag-team-160914/wittyer:v2",
-  "Benchmark_CNV_Caller.bcftools_docker": "us.gcr.io/broad-dsde-methods/liquidbiopsy:0.0.4.3",
+  "Benchmark_CNV_Caller.BenchmarkCNV.mem": "Int? (optional)",
+  "Benchmark_CNV_Caller.BenchmarkCNV.disk_size": "Int? (optional)",
+  "Benchmark_CNV_Caller.wittyer4mat_docker": "us.gcr.io/tag-team-160914/wittyer4mat:v9-funnydual-broom",
   "Benchmark_CNV_Caller.wittyer_sv_config": "gs://gptag/tag_1455_Dragen_CNV_Caller_Validation/wittyerConfigFile/sv-config.json",
-  "Benchmark_CNV_Caller.wittyer_cnv_evaluation_mode": "CrossTypeAndSimpleCounting",
-  "Benchmark_CNV_Caller.wittyer_sv_evaluation_mode": "SimpleCounting",
+  "Benchmark_CNV_Caller.wittyer_cnv_evaluation_mode": "SimpleCounting",
+  "Benchmark_CNV_Caller.BenchmarkCNV.disk_space": "Int? (optional)",
+  "Benchmark_CNV_Caller.wittyer_sv_evaluation_mode": "CrossTypeAndSimpleCounting",
   "Benchmark_CNV_Caller.wittyer_cnv_config": "gs://gptag/tag_1455_Dragen_CNV_Caller_Validation/wittyerConfigFile/cnv-config.json",
-  "Benchmark_CNV_Caller.variant_callset": "gs://gptag/tag_1455_Dragen_CNV_Caller_Validation/1KGP_3202.gatksv_svtools_novelins.freeze_V3_fixed.wAF.vcf",
   "Benchmark_CNV_Caller.truth_sample_name": "HG00513",
+  "Benchmark_CNV_Caller.truth_vcf": "gs://gptag/tag_1455_Dragen_CNV_Caller_Validation/example_truth_vcf/HG00513_filtered.vcf",
   "Benchmark_CNV_Caller.query_sample_name": "SM-GZQKA",
   "Benchmark_CNV_Caller.eval_sv_vcf": "gs://dragen_v_3_10_4_cnv_validation/hg38_ml/HG00513_HG00513_1_SM-GZQKA_v1/HG00513_HG00513_1_SM-GZQKA_v1.sv.vcf.gz",
   "Benchmark_CNV_Caller.eval_cnv_vcf": "gs://dragen_v_3_10_4_cnv_validation/hg38_ml/HG00513_HG00513_1_SM-GZQKA_v1/HG00513_HG00513_1_SM-GZQKA_v1.cnv.vcf.gz"
diff --git a/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV.wdl
index f612805..c0fa423 100644
--- a/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV.wdl
@@ -2,33 +2,24 @@ version 1.0
 
 workflow Benchmark_CNV_Caller {
     input {
-        String bcftools_docker
-        File variant_callset
         String truth_sample_name
         String query_sample_name
-        String wittyer_docker
+        File truth_vcf
         File eval_cnv_vcf
-        File wittyer_cnv_config
-        String wittyer_cnv_evaluation_mode
         File eval_sv_vcf
+        File wittyer_cnv_config
         File wittyer_sv_config
+        String wittyer_cnv_evaluation_mode
         String wittyer_sv_evaluation_mode
+        String wittyer_docker
         String wittyer4mat_docker
     }
 
-    # Select vcf for specific sample
-    call SelectSample {
-        input:
-            bcftools_docker = bcftools_docker,
-            vcf = variant_callset,
-            truth_sample_name = truth_sample_name
-    }
-
     # benchmark cnv.vcf and sv.vcf using witty.er tool
     call BenchmarkCNV {
         input:
             wittyer_docker = wittyer_docker,
-            truth_vcf = SelectSample.output_vcf,
+            truth_vcf = truth_vcf,
             truth_sample_name = truth_sample_name,
             query_sample_name = query_sample_name,
             eval_cnv_vcf = eval_cnv_vcf,
@@ -50,7 +41,6 @@ workflow Benchmark_CNV_Caller {
 
     # Outputs that will be retained when execution is complete
     output {
-        File truth_vcf = SelectSample.output_vcf
         File cnv_wittyer_stats = BenchmarkCNV.cnv_wittyer_stats
         File cnv_wittyer_annotated_vcf = BenchmarkCNV.cnv_wittyer_annotated_vcf
         File cnv_wittyer_annotated_vcf_index = BenchmarkCNV.cnv_wittyer_annotated_vcf_index
@@ -70,46 +60,10 @@ workflow Benchmark_CNV_Caller {
     }
 }
 
-    # Task 1: Select sample vcf from a large callset (e.g. 1KGP)
-    task SelectSample {
-
-        input {
-            String bcftools_docker
-            File vcf
-            String truth_sample_name
-            Int? mem
-            Int? disk_space
-            # If mem and disk size were not specified, use 4GB and 100 GB as default
-            Int mem_size = select_first([mem, 4])
-            Int disk_size = select_first([disk_space,100])
-
-        }
-        command <<<
-            set -e
-            # Select sample using bcftools
-            bcftools view -s ~{truth_sample_name} -O v -o ~{truth_sample_name}.vcf ~{vcf}
-
-            # Remove Complex SV from the sample vcf because wittyer can't process CPX variants
-            # Remove INV from the sample vcf because wittyer's exception
-            # Remove reference allele
-
-            bcftools view -e 'SVTYPE="INV" | SVTYPE="CPX" | GT="0/0"' ~{truth_sample_name}.vcf -o ~{truth_sample_name}_filtered.vcf
-
-            >>>
-        runtime {
-            docker: bcftools_docker
-            bootDiskSizeGb: 12
-            memory: mem_size + " GB"
-            disks: "local-disk " + disk_size + " HDD"
-            preemptible: 2
-        }
-        output {
-            File output_vcf = "~{truth_sample_name}_filtered.vcf"
-        }
-
-}
 
-    # Task 2: Benchmark the large variant vcf against truth set generated in task 1
+    # Task 1: Benchmark the large variant vcf against truth set
+    # If you are extracting vcf from a large callset vcf
+    # Checkout /BenchmarkCNV/SelectSampleFromCallSet.wdl
     task BenchmarkCNV {
 
         input {
diff --git a/BenchmarkCNV/SelectSampleFromCallSet.inputs.json b/BenchmarkCNV/SelectSampleFromCallSet.inputs.json
new file mode 100644
index 0000000..a3fd317
--- /dev/null
+++ b/BenchmarkCNV/SelectSampleFromCallSet.inputs.json
@@ -0,0 +1,9 @@
+{
+  "SelectSampleFromCallSet.SelectSample.mem": "Int? (optional)",
+  "SelectSampleFromCallSet.sample_name": "HG00513",
+  "SelectSampleFromCallSet.SelectSample.disk_size": "Int? (optional)",
+  "SelectSampleFromCallSet.variant_callset": "gs://gptag/tag_1455_Dragen_CNV_Caller_Validation/1KGP_3202.gatksv_svtools_novelins.freeze_V3_fixed.wAF.vcf",
+  "SelectSampleFromCallSet.SelectSample.disk_space": "Int? (optional)",
+  "SelectSampleFromCallSet.SelectSample.mem_size": "Int? (optional)",
+  "SelectSampleFromCallSet.bcftools_docker": "us.gcr.io/broad-dsde-methods/liquidbiopsy:0.0.4.3"
+}
diff --git a/BenchmarkCNV/SelectSampleFromCallSet.wdl b/BenchmarkCNV/SelectSampleFromCallSet.wdl
new file mode 100644
index 0000000..3e5fd5a
--- /dev/null
+++ b/BenchmarkCNV/SelectSampleFromCallSet.wdl
@@ -0,0 +1,65 @@
+version 1.0
+
+workflow SelectSampleFromCallSet {
+    input {
+        String bcftools_docker
+        File variant_callset
+        String sample_name
+    }
+
+    # Select vcf for specific sample
+    call SelectSample {
+        input:
+            bcftools_docker = bcftools_docker,
+            vcf = variant_callset,
+            sample_name = sample_name
+    }
+
+
+    # Outputs that will be retained when execution is complete
+    output {
+        File selected_vcf = SelectSample.output_vcf
+    }
+    meta {
+        author: "Yueyao Gao"
+        email: "tag@broadinstitute.org"
+        description: "SelectSampleFromCallSet.wdl is design to extract specific sample from a large callset vcf"
+    }
+}
+task SelectSample {
+
+        input {
+            String bcftools_docker
+            File vcf
+            String sample_name
+            Int? mem
+            Int? disk_space
+            # If mem and disk size were not specified, use 4GB and 100 GB as default
+            Int mem_size = select_first([mem, 4])
+            Int disk_size = select_first([disk_space,100])
+
+        }
+        command <<<
+            set -e
+            # Select sample using bcftools
+            bcftools view -s ~{sample_name} -O v -o ~{sample_name}.vcf ~{vcf}
+
+            # Remove Complex SV from the sample vcf because wittyer can't process CPX variants
+            # Remove INV from the sample vcf because wittyer's exception
+            # Remove reference allele
+
+            bcftools view -e 'SVTYPE="INV" | SVTYPE="CPX" | GT="0/0"' ~{sample_name}.vcf -o ~{sample_name}_filtered.vcf
+
+            >>>
+        runtime {
+            docker: bcftools_docker
+            bootDiskSizeGb: 12
+            memory: mem_size + " GB"
+            disks: "local-disk " + disk_size + " HDD"
+            preemptible: 2
+        }
+        output {
+            File output_vcf = "~{sample_name}_filtered.vcf"
+        }
+
+}
\ No newline at end of file

From 0e757c7e1b6646a1c520507981b89accbd024cf6 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Thu, 23 Feb 2023 10:31:49 -0500
Subject: [PATCH 02/28] Added the optional bed file option

---
 BenchmarkCNV/BenchmarkCNV.wdl | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV.wdl
index c0fa423..526b5a4 100644
--- a/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV.wdl
@@ -9,6 +9,7 @@ workflow Benchmark_CNV_Caller {
         File eval_sv_vcf
         File wittyer_cnv_config
         File wittyer_sv_config
+        File? bedfile
         String wittyer_cnv_evaluation_mode
         String wittyer_sv_evaluation_mode
         String wittyer_docker
@@ -27,7 +28,8 @@ workflow Benchmark_CNV_Caller {
             cnv_evaluation_mode = wittyer_cnv_evaluation_mode,
             eval_sv_vcf = eval_sv_vcf,
             sv_config_file = wittyer_sv_config,
-            sv_evaluation_mode = wittyer_sv_evaluation_mode
+            sv_evaluation_mode = wittyer_sv_evaluation_mode,
+            bedfile = bedfile
     }
 
     # wittyer4mat to parse the wittyer json output
@@ -74,6 +76,7 @@ workflow Benchmark_CNV_Caller {
             String cnv_evaluation_mode
             File eval_sv_vcf
             File sv_config_file
+            File? bedfile
             String sv_evaluation_mode
             String truth_sample_name
             String query_sample_name
@@ -85,6 +88,24 @@ workflow Benchmark_CNV_Caller {
     }
         command <<<
             set -e
+
+            if [[ -f "~{bedfile}" ]]; then
+            # Run Benchmarking tool wittyer on dragen generated cnv.vcf with bed file
+            /opt/Wittyer/Wittyer -i ~{eval_cnv_vcf} \
+            -t ~{truth_vcf} \
+            -em ~{cnv_evaluation_mode} \
+            --configFile ~{cnv_config_file} \
+            --includeBed ~{bedfile} \
+            -o ~{truth_sample_name}_cnv_wittyer_output
+
+            # Run Benchmarking tool wittyer on dragen generated sv.vcf with bed file
+            /opt/Wittyer/Wittyer -i ~{eval_sv_vcf} \
+            -t ~{truth_vcf} \
+            -em ~{sv_evaluation_mode} \
+            --configFile ~{sv_config_file} \
+            --includeBed ~{bedfile} \
+            -o ~{truth_sample_name}_sv_wittyer_output
+            else
             # Run Benchmarking tool wittyer on dragen generated cnv.vcf
             /opt/Wittyer/Wittyer -i ~{eval_cnv_vcf} \
             -t ~{truth_vcf} \

From 8746e226b5022892b953fdc4cd3d18978a258ca5 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Thu, 23 Feb 2023 10:53:58 -0500
Subject: [PATCH 03/28] fix broken if-then-else statement

---
 BenchmarkCNV/BenchmarkCNV.wdl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV.wdl
index 526b5a4..965e749 100644
--- a/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV.wdl
@@ -119,7 +119,7 @@ workflow Benchmark_CNV_Caller {
             -em ~{sv_evaluation_mode} \
             --configFile ~{sv_config_file} \
             -o ~{truth_sample_name}_sv_wittyer_output
-
+            fi
         >>>
         runtime {
             docker: wittyer_docker

From 9e8d101a5c750ad4e45f176061ed9212e65c4c00 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Mon, 27 Feb 2023 10:00:55 -0500
Subject: [PATCH 04/28] Generalize BenchmarkCNV wdl

---
 BenchmarkCNV/BenchmarkCNV.inputs.json |  28 ++++---
 BenchmarkCNV/BenchmarkCNV.wdl         | 104 ++++++++------------------
 2 files changed, 46 insertions(+), 86 deletions(-)

diff --git a/BenchmarkCNV/BenchmarkCNV.inputs.json b/BenchmarkCNV/BenchmarkCNV.inputs.json
index 3c2b002..7f0581a 100644
--- a/BenchmarkCNV/BenchmarkCNV.inputs.json
+++ b/BenchmarkCNV/BenchmarkCNV.inputs.json
@@ -1,17 +1,15 @@
 {
-  "Benchmark_CNV_Caller.BenchmarkCNV.mem_size": "Int? (optional)",
+  "Benchmark_CNV_Caller.bedfile": "gs://gptag/tag_1455_Dragen_CNV_Caller_Validation/HighConfidenceRegion_BedFile/HG002_hg38_SVs_Tier1_v0.6.bed",
+  "Benchmark_CNV_Caller.BenchmarkCNV.mem_size": 4,
   "Benchmark_CNV_Caller.wittyer_docker": "us.gcr.io/tag-team-160914/wittyer:v2",
-  "Benchmark_CNV_Caller.BenchmarkCNV.mem": "Int? (optional)",
-  "Benchmark_CNV_Caller.BenchmarkCNV.disk_size": "Int? (optional)",
-  "Benchmark_CNV_Caller.wittyer4mat_docker": "us.gcr.io/tag-team-160914/wittyer4mat:v9-funnydual-broom",
-  "Benchmark_CNV_Caller.wittyer_sv_config": "gs://gptag/tag_1455_Dragen_CNV_Caller_Validation/wittyerConfigFile/sv-config.json",
-  "Benchmark_CNV_Caller.wittyer_cnv_evaluation_mode": "SimpleCounting",
-  "Benchmark_CNV_Caller.BenchmarkCNV.disk_space": "Int? (optional)",
-  "Benchmark_CNV_Caller.wittyer_sv_evaluation_mode": "CrossTypeAndSimpleCounting",
-  "Benchmark_CNV_Caller.wittyer_cnv_config": "gs://gptag/tag_1455_Dragen_CNV_Caller_Validation/wittyerConfigFile/cnv-config.json",
-  "Benchmark_CNV_Caller.truth_sample_name": "HG00513",
-  "Benchmark_CNV_Caller.truth_vcf": "gs://gptag/tag_1455_Dragen_CNV_Caller_Validation/example_truth_vcf/HG00513_filtered.vcf",
-  "Benchmark_CNV_Caller.query_sample_name": "SM-GZQKA",
-  "Benchmark_CNV_Caller.eval_sv_vcf": "gs://dragen_v_3_10_4_cnv_validation/hg38_ml/HG00513_HG00513_1_SM-GZQKA_v1/HG00513_HG00513_1_SM-GZQKA_v1.sv.vcf.gz",
-  "Benchmark_CNV_Caller.eval_cnv_vcf": "gs://dragen_v_3_10_4_cnv_validation/hg38_ml/HG00513_HG00513_1_SM-GZQKA_v1/HG00513_HG00513_1_SM-GZQKA_v1.cnv.vcf.gz"
-}
+  "Benchmark_CNV_Caller.BenchmarkCNV.mem": 4,
+  "Benchmark_CNV_Caller.wittyer_evaluation_mode": "SimpleCounting",
+  "Benchmark_CNV_Caller.BenchmarkCNV.disk_size": 100,
+  "Benchmark_CNV_Caller.wittyer4mat_docker": "us.gcr.io/tag-team-160914/wittyer4mat:v10-stat-broom",
+  "Benchmark_CNV_Caller.eval_vcf": "gs://dragen_v_3_10_4_cnv_validation/hg38_ml/NA24385_hg38/NA24385.cnv.vcf.gz",
+  "Benchmark_CNV_Caller.BenchmarkCNV.disk_space": 100,
+  "Benchmark_CNV_Caller.truth_sample_name": "NA24385",
+  "Benchmark_CNV_Caller.truth_vcf": "gs://fc-cd2e8270-8c64-4f10-bcfb-2f1b5f44aee4/submissions/47e84385-8207-4ad0-a412-b2c113efb470/SelectSampleFromCallSet/17210bc4-e6c8-4ce5-bb23-486fcb18ab89/call-SelectSample/NA24385_filtered.vcf",
+  "Benchmark_CNV_Caller.query_sample_name": "SM-MVWA8",
+  "Benchmark_CNV_Caller.wittyer_config": "gs://gptag/tag_1455_Dragen_CNV_Caller_Validation/wittyerConfigFile/cnv-config.json"
+}
\ No newline at end of file
diff --git a/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV.wdl
index 965e749..f7be199 100644
--- a/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV.wdl
@@ -5,13 +5,10 @@ workflow Benchmark_CNV_Caller {
         String truth_sample_name
         String query_sample_name
         File truth_vcf
-        File eval_cnv_vcf
-        File eval_sv_vcf
-        File wittyer_cnv_config
-        File wittyer_sv_config
+        File eval_vcf
+        File wittyer_config
         File? bedfile
-        String wittyer_cnv_evaluation_mode
-        String wittyer_sv_evaluation_mode
+        String wittyer_evaluation_mode
         String wittyer_docker
         String wittyer4mat_docker
     }
@@ -23,12 +20,9 @@ workflow Benchmark_CNV_Caller {
             truth_vcf = truth_vcf,
             truth_sample_name = truth_sample_name,
             query_sample_name = query_sample_name,
-            eval_cnv_vcf = eval_cnv_vcf,
-            cnv_config_file = wittyer_cnv_config,
-            cnv_evaluation_mode = wittyer_cnv_evaluation_mode,
-            eval_sv_vcf = eval_sv_vcf,
-            sv_config_file = wittyer_sv_config,
-            sv_evaluation_mode = wittyer_sv_evaluation_mode,
+            eval_vcf = eval_vcf,
+            wittyer_config = wittyer_config,
+            wittyer_evaluation_mode = wittyer_evaluation_mode,
             bedfile = bedfile
     }
 
@@ -36,24 +30,16 @@ workflow Benchmark_CNV_Caller {
     call Wittyer4Mat {
         input:
             wittyer4mat_docker = wittyer4mat_docker,
-            cnv_wittyer_stats = BenchmarkCNV.cnv_wittyer_stats,
-            sv_wittyer_stats = BenchmarkCNV.sv_wittyer_stats,
+            wittyer_stats = BenchmarkCNV.wittyer_stats,
             truth_sample_name = truth_sample_name
     }
 
     # Outputs that will be retained when execution is complete
     output {
-        File cnv_wittyer_stats = BenchmarkCNV.cnv_wittyer_stats
-        File cnv_wittyer_annotated_vcf = BenchmarkCNV.cnv_wittyer_annotated_vcf
-        File cnv_wittyer_annotated_vcf_index = BenchmarkCNV.cnv_wittyer_annotated_vcf_index
-        File sv_wittyer_stats = BenchmarkCNV.sv_wittyer_stats
-        File sv_wittyer_annotated_vcf = BenchmarkCNV.sv_wittyer_annotated_vcf
-        File sv_wittyer_annotated_vcf_index = BenchmarkCNV.sv_wittyer_annotated_vcf_index
-        File cnv_deletion_stat = Wittyer4Mat.cnv_deletion_stat
-        File cnv_duplication_stat = Wittyer4Mat.cnv_duplication_stat
-        File sv_deletion_stat = Wittyer4Mat.sv_deletion_stat
-        File sv_duplication_stat = Wittyer4Mat.sv_duplication_stat
-        File sv_insertion_stat = Wittyer4Mat.sv_insertion_stat
+        File wittyer_stats = BenchmarkCNV.wittyer_stats
+        File wittyer_annotated_vcf = BenchmarkCNV.wittyer_annotated_vcf
+        File wittyer_annotated_vcf_index = BenchmarkCNV.wittyer_annotated_vcf_index
+        Array[File] Wittyer4Mat_stat = Wittyer4Mat.formatted_stat
     }
     meta {
         author: "Yueyao Gao"
@@ -71,13 +57,10 @@ workflow Benchmark_CNV_Caller {
         input {
             String wittyer_docker
             File truth_vcf
-            File eval_cnv_vcf
-            File cnv_config_file
-            String cnv_evaluation_mode
-            File eval_sv_vcf
-            File sv_config_file
+            File eval_vcf
+            File wittyer_config
+            String wittyer_evaluation_mode
             File? bedfile
-            String sv_evaluation_mode
             String truth_sample_name
             String query_sample_name
             Int? mem
@@ -91,34 +74,21 @@ workflow Benchmark_CNV_Caller {
 
             if [[ -f "~{bedfile}" ]]; then
             # Run Benchmarking tool wittyer on dragen generated cnv.vcf with bed file
-            /opt/Wittyer/Wittyer -i ~{eval_cnv_vcf} \
+            /opt/Wittyer/Wittyer -i ~{eval_vcf} \
             -t ~{truth_vcf} \
-            -em ~{cnv_evaluation_mode} \
-            --configFile ~{cnv_config_file} \
+            -em ~{wittyer_evaluation_mode} \
+            --configFile ~{wittyer_config} \
             --includeBed ~{bedfile} \
-            -o ~{truth_sample_name}_cnv_wittyer_output
+            -o ~{truth_sample_name}_wittyer_output
 
-            # Run Benchmarking tool wittyer on dragen generated sv.vcf with bed file
-            /opt/Wittyer/Wittyer -i ~{eval_sv_vcf} \
-            -t ~{truth_vcf} \
-            -em ~{sv_evaluation_mode} \
-            --configFile ~{sv_config_file} \
-            --includeBed ~{bedfile} \
-            -o ~{truth_sample_name}_sv_wittyer_output
             else
             # Run Benchmarking tool wittyer on dragen generated cnv.vcf
-            /opt/Wittyer/Wittyer -i ~{eval_cnv_vcf} \
+            /opt/Wittyer/Wittyer -i ~{eval_vcf} \
             -t ~{truth_vcf} \
-            -em ~{cnv_evaluation_mode} \
-            --configFile ~{cnv_config_file} \
-            -o ~{truth_sample_name}_cnv_wittyer_output
+            -em ~{wittyer_evaluation_mode} \
+            --configFile ~{wittyer_config} \
+            -o ~{truth_sample_name}_wittyer_output
 
-            # Run Benchmarking tool wittyer on dragen generated sv.vcf
-            /opt/Wittyer/Wittyer -i ~{eval_sv_vcf} \
-            -t ~{truth_vcf} \
-            -em ~{sv_evaluation_mode} \
-            --configFile ~{sv_config_file} \
-            -o ~{truth_sample_name}_sv_wittyer_output
             fi
         >>>
         runtime {
@@ -129,12 +99,9 @@ workflow Benchmark_CNV_Caller {
             preemptible: 2
         }
         output {
-            File cnv_wittyer_stats = "~{truth_sample_name}_cnv_wittyer_output/Wittyer.Stats.json"
-            File cnv_wittyer_annotated_vcf = "~{truth_sample_name}_cnv_wittyer_output/Wittyer.~{truth_sample_name}.Vs.~{query_sample_name}.vcf.gz"
-            File cnv_wittyer_annotated_vcf_index = "~{truth_sample_name}_cnv_wittyer_output/Wittyer.~{truth_sample_name}.Vs.~{query_sample_name}.vcf.gz.tbi"
-            File sv_wittyer_stats = "~{truth_sample_name}_sv_wittyer_output/Wittyer.Stats.json"
-            File sv_wittyer_annotated_vcf = "~{truth_sample_name}_sv_wittyer_output/Wittyer.~{truth_sample_name}.Vs.~{query_sample_name}.vcf.gz"
-            File sv_wittyer_annotated_vcf_index = "~{truth_sample_name}_sv_wittyer_output/Wittyer.~{truth_sample_name}.Vs.~{query_sample_name}.vcf.gz.tbi"
+            File wittyer_stats = "~{truth_sample_name}_wittyer_output/Wittyer.Stats.json"
+            File wittyer_annotated_vcf = "~{truth_sample_name}_wittyer_output/Wittyer.~{truth_sample_name}.Vs.~{query_sample_name}.vcf.gz"
+            File wittyer_annotated_vcf_index = "~{truth_sample_name}_wittyer_output/Wittyer.~{truth_sample_name}.Vs.~{query_sample_name}.vcf.gz.tbi"
         }
 }
     # Task3: Format the wittyer json output
@@ -142,8 +109,7 @@ workflow Benchmark_CNV_Caller {
 
         input{
             String wittyer4mat_docker
-            File cnv_wittyer_stats
-            File sv_wittyer_stats
+            File wittyer_stats
             String truth_sample_name
         }
         command <<<
@@ -153,27 +119,23 @@ workflow Benchmark_CNV_Caller {
             mkdir ~{truth_sample_name}_cnv_wittyer4mat
             conda run --no-capture-output \
             -n wittyer-parser \
-            python3 /wittyer4mat/wittyer_4mat.py -i ~{cnv_wittyer_stats} \
-            -t cnv \
-            -o ~{truth_sample_name}_cnv_wittyer4mat
+            python3 /wittyer4mat/wittyer_4mat.py -i ~{wittyer_stats} \
+            -t base \
+            -o ~{truth_sample_name}_base_level_wittyer4mat
 
             # Run wittyer4mat script on sv wittyer output
             mkdir ~{truth_sample_name}_sv_wittyer4mat
             conda run --no-capture-output \
             -n wittyer-parser \
-            python3 /wittyer4mat/wittyer_4mat.py -i ~{sv_wittyer_stats} \
-            -t sv \
-            -o ~{truth_sample_name}_sv_wittyer4mat
+            python3 /wittyer4mat/wittyer_4mat.py -i ~{wittyer_stats} \
+            -t event \
+            -o ~{truth_sample_name}_event_level_wittyer4mat
     >>>
         runtime {
             docker: wittyer4mat_docker
             preemptible: 2
         }
         output {
-            File cnv_deletion_stat = "~{truth_sample_name}_cnv_wittyer4mat/wittyer_cnv_Deletion_output.csv"
-            File cnv_duplication_stat = "~{truth_sample_name}_cnv_wittyer4mat/wittyer_cnv_Duplication_output.csv"
-            File sv_deletion_stat = "~{truth_sample_name}_sv_wittyer4mat/wittyer_sv_Deletion_output.csv"
-            File sv_duplication_stat = "~{truth_sample_name}_sv_wittyer4mat/wittyer_sv_Duplication_output.csv"
-            File sv_insertion_stat = "~{truth_sample_name}_sv_wittyer4mat/wittyer_sv_Insertion_output.csv"
+            Array[File] formatted_stat = glob("~{truth_sample_name}_event_level_wittyer4mat/*.csv")
         }
     }
\ No newline at end of file

From c0d96ac7d0e5269909fd2b20049b5b85bfd76bbf Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Mon, 27 Feb 2023 10:09:51 -0500
Subject: [PATCH 05/28] Fixed an input error in inputs.json

---
 BenchmarkCNV/BenchmarkCNV.inputs.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/BenchmarkCNV/BenchmarkCNV.inputs.json b/BenchmarkCNV/BenchmarkCNV.inputs.json
index 7f0581a..9dec994 100644
--- a/BenchmarkCNV/BenchmarkCNV.inputs.json
+++ b/BenchmarkCNV/BenchmarkCNV.inputs.json
@@ -3,7 +3,7 @@
   "Benchmark_CNV_Caller.BenchmarkCNV.mem_size": 4,
   "Benchmark_CNV_Caller.wittyer_docker": "us.gcr.io/tag-team-160914/wittyer:v2",
   "Benchmark_CNV_Caller.BenchmarkCNV.mem": 4,
-  "Benchmark_CNV_Caller.wittyer_evaluation_mode": "SimpleCounting",
+  "Benchmark_CNV_Caller.wittyer_evaluation_mode": "CrossTypeAndSimpleCounting",
   "Benchmark_CNV_Caller.BenchmarkCNV.disk_size": 100,
   "Benchmark_CNV_Caller.wittyer4mat_docker": "us.gcr.io/tag-team-160914/wittyer4mat:v10-stat-broom",
   "Benchmark_CNV_Caller.eval_vcf": "gs://dragen_v_3_10_4_cnv_validation/hg38_ml/NA24385_hg38/NA24385.cnv.vcf.gz",

From ed38ba4505e7f68a8a3fcc700b16fee96910390e Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Mon, 27 Feb 2023 10:23:00 -0500
Subject: [PATCH 06/28] Add both base-level and event-level to workflow output

---
 BenchmarkCNV/BenchmarkCNV.wdl | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV.wdl
index f7be199..d416673 100644
--- a/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV.wdl
@@ -39,7 +39,8 @@ workflow Benchmark_CNV_Caller {
         File wittyer_stats = BenchmarkCNV.wittyer_stats
         File wittyer_annotated_vcf = BenchmarkCNV.wittyer_annotated_vcf
         File wittyer_annotated_vcf_index = BenchmarkCNV.wittyer_annotated_vcf_index
-        Array[File] Wittyer4Mat_stat = Wittyer4Mat.formatted_stat
+        Array[File] Wittyer4Mat_event_stats = Wittyer4Mat.event_level_wittyer_stats
+        Array[File] Wittyer4Mat_base_stats = Wittyer4Mat.base_level_wittyer_stats
     }
     meta {
         author: "Yueyao Gao"
@@ -136,6 +137,7 @@ workflow Benchmark_CNV_Caller {
             preemptible: 2
         }
         output {
-            Array[File] formatted_stat = glob("~{truth_sample_name}_event_level_wittyer4mat/*.csv")
+            Array[File] event_level_wittyer_stats = glob("~{truth_sample_name}_event_level_wittyer4mat/*.csv")
+            Array[File] base_level_wittyer_stats = glob("~{truth_sample_name}_base_level_wittyer4mat/*.csv")
         }
     }
\ No newline at end of file

From c499c6c8e5104f83ca052bf2791bd59ea647c27a Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Mon, 27 Feb 2023 10:35:20 -0500
Subject: [PATCH 07/28] Updated the directory to allow more workflows can be
 utilized

---
 .dockstore.yml                                            | 8 ++++----
 BenchmarkCNV/{ => BenchmarkCNV}/BenchmarkCNV.inputs.json  | 0
 BenchmarkCNV/{ => BenchmarkCNV}/BenchmarkCNV.wdl          | 0
 .../SelectSampleFromCallSet.inputs.json                   | 0
 .../SelectSampleFromCallSet.wdl                           | 0
 5 files changed, 4 insertions(+), 4 deletions(-)
 rename BenchmarkCNV/{ => BenchmarkCNV}/BenchmarkCNV.inputs.json (100%)
 rename BenchmarkCNV/{ => BenchmarkCNV}/BenchmarkCNV.wdl (100%)
 rename BenchmarkCNV/{ => SelectSampleFromCallSet}/SelectSampleFromCallSet.inputs.json (100%)
 rename BenchmarkCNV/{ => SelectSampleFromCallSet}/SelectSampleFromCallSet.wdl (100%)

diff --git a/.dockstore.yml b/.dockstore.yml
index 4478115..760a64f 100644
--- a/.dockstore.yml
+++ b/.dockstore.yml
@@ -22,14 +22,14 @@ workflows:
    - /input_json/CollectSamErrorMetrics_inputs.json
  - name: SelectSampleFromCallSet
    subclass: WDL
-   primaryDescriptorPath: /BenchmarkCNV/SelectSampleFromCallSet.wdl
+   primaryDescriptorPath: /BenchmarkCNV/SelectSampleFromCallSet/SelectSampleFromCallSet.wdl
    testParameterFiles:
-   - /BenchmarkCNV/SelectSampleFromCallSet.inputs.json
+   - /BenchmarkCNV/SelectSampleFromCallSet/SelectSampleFromCallSet.inputs.json
  - name: BenchmarkCNV
    subclass: WDL
-   primaryDescriptorPath: /BenchmarkCNV/BenchmarkCNV.wdl
+   primaryDescriptorPath: /BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
    testParameterFiles:
-   - /BenchmarkCNV/BenchmarkCNV.inputs.json
+   - /BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.inputs.json
  - name: GATK4_CNV
    subclass: WDL
    primaryDescriptorPath: /GATK_CNV_Mutect2/GATK4_CNV/GATK4_CNV.wdl
diff --git a/BenchmarkCNV/BenchmarkCNV.inputs.json b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.inputs.json
similarity index 100%
rename from BenchmarkCNV/BenchmarkCNV.inputs.json
rename to BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.inputs.json
diff --git a/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
similarity index 100%
rename from BenchmarkCNV/BenchmarkCNV.wdl
rename to BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
diff --git a/BenchmarkCNV/SelectSampleFromCallSet.inputs.json b/BenchmarkCNV/SelectSampleFromCallSet/SelectSampleFromCallSet.inputs.json
similarity index 100%
rename from BenchmarkCNV/SelectSampleFromCallSet.inputs.json
rename to BenchmarkCNV/SelectSampleFromCallSet/SelectSampleFromCallSet.inputs.json
diff --git a/BenchmarkCNV/SelectSampleFromCallSet.wdl b/BenchmarkCNV/SelectSampleFromCallSet/SelectSampleFromCallSet.wdl
similarity index 100%
rename from BenchmarkCNV/SelectSampleFromCallSet.wdl
rename to BenchmarkCNV/SelectSampleFromCallSet/SelectSampleFromCallSet.wdl

From 0569dc5dc0f5c95ddb101d6a9dc0aac4100a7bf5 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Mon, 27 Feb 2023 11:39:50 -0500
Subject: [PATCH 08/28] Updated the Wittyer4mat image to the lastest one

---
 BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.inputs.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.inputs.json b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.inputs.json
index 9dec994..e5bf04e 100644
--- a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.inputs.json
+++ b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.inputs.json
@@ -5,7 +5,7 @@
   "Benchmark_CNV_Caller.BenchmarkCNV.mem": 4,
   "Benchmark_CNV_Caller.wittyer_evaluation_mode": "CrossTypeAndSimpleCounting",
   "Benchmark_CNV_Caller.BenchmarkCNV.disk_size": 100,
-  "Benchmark_CNV_Caller.wittyer4mat_docker": "us.gcr.io/tag-team-160914/wittyer4mat:v10-stat-broom",
+  "Benchmark_CNV_Caller.wittyer4mat_docker": "us.gcr.io/tag-team-160914/wittyer4mat:v11-outstat-broom",
   "Benchmark_CNV_Caller.eval_vcf": "gs://dragen_v_3_10_4_cnv_validation/hg38_ml/NA24385_hg38/NA24385.cnv.vcf.gz",
   "Benchmark_CNV_Caller.BenchmarkCNV.disk_space": 100,
   "Benchmark_CNV_Caller.truth_sample_name": "NA24385",

From b73f1cc27432b3bce36804061b5c093ac78209e2 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Mon, 27 Feb 2023 13:32:01 -0500
Subject: [PATCH 09/28] Added MergeVCF.wdl

---
 BenchmarkCNV/MergeVCF/MergeVCF.inputs.json | 10 ++++
 BenchmarkCNV/MergeVCF/MergeVCF.wdl         | 68 ++++++++++++++++++++++
 2 files changed, 78 insertions(+)
 create mode 100644 BenchmarkCNV/MergeVCF/MergeVCF.inputs.json
 create mode 100644 BenchmarkCNV/MergeVCF/MergeVCF.wdl

diff --git a/BenchmarkCNV/MergeVCF/MergeVCF.inputs.json b/BenchmarkCNV/MergeVCF/MergeVCF.inputs.json
new file mode 100644
index 0000000..b0b19e4
--- /dev/null
+++ b/BenchmarkCNV/MergeVCF/MergeVCF.inputs.json
@@ -0,0 +1,10 @@
+{
+  "MergeVCF.mergeVCF.mem_size": "Int? (optional)",
+  "MergeVCF.mergeVCF.mem": "Int? (optional)",
+  "MergeVCF.mergeVCF.disk_space": "Int? (optional)",
+  "MergeVCF.vcf1": "File",
+  "MergeVCF.sample_name": "String",
+  "MergeVCF.vcf2": "File",
+  "MergeVCF.bcftools_docker": "us.gcr.io/broad-dsde-methods/liquidbiopsy:0.0.4.3",
+  "MergeVCF.mergeVCF.disk_size": "Int? (optional)"
+}
diff --git a/BenchmarkCNV/MergeVCF/MergeVCF.wdl b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
new file mode 100644
index 0000000..0507b08
--- /dev/null
+++ b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
@@ -0,0 +1,68 @@
+version 1.0
+
+workflow MergeVCF {
+    input {
+        String bcftools_docker
+        File vcf1
+        File vcf2
+        String sample_name
+    }
+
+    # Merge Two Input VCF Files
+    call mergeVCF {
+        input:
+            bcftools_docker = bcftools_docker,
+            vcf1 = vcf1,
+            vcf2 = vcf2,
+            sample_name = sample_name
+    }
+
+
+    # Outputs that will be retained when execution is complete
+    output {
+        File selected_vcf = mergeVCF.output_vcf
+    }
+    meta {
+        author: "Yueyao Gao"
+        email: "tag@broadinstitute.org"
+        description: "MergeVCF.wdl is design to merge two input vcfs"
+    }
+}
+task mergeVCF {
+
+        input {
+            String bcftools_docker
+            File vcf1
+            File vcf2
+            String sample_name
+            Int? mem
+            Int? disk_space
+            # If mem and disk size were not specified, use 4GB and 100 GB as default
+            Int mem_size = select_first([mem, 4])
+            Int disk_size = select_first([disk_space,100])
+
+        }
+        command <<<
+            set -e
+
+            echo "Input VCF files:"
+            echo "vcf1: ~{vcf1}"
+            echo "vcf2: ~{vcf2}"
+
+            bcftools concat ~{vcf1} ~{vcf2} -o ~{sample_name}_merged.vcf
+
+            # Print the output file name
+            echo "Merged VCF file: ~{sample_name}_merged.vcf"
+            >>>
+        runtime {
+            docker: bcftools_docker
+            bootDiskSizeGb: 12
+            memory: mem_size + " GB"
+            disks: "local-disk " + disk_size + " HDD"
+            preemptible: 2
+        }
+        output {
+            File output_vcf = "~{sample_name}_merged.vcf"
+        }
+
+}
\ No newline at end of file

From a5155dc062a8c58a5e79b80266147b2b833e83b1 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Mon, 27 Feb 2023 13:34:08 -0500
Subject: [PATCH 10/28] Added MergeVCF to dockerstore.yml

---
 .dockstore.yml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/.dockstore.yml b/.dockstore.yml
index 760a64f..278e019 100644
--- a/.dockstore.yml
+++ b/.dockstore.yml
@@ -25,6 +25,11 @@ workflows:
    primaryDescriptorPath: /BenchmarkCNV/SelectSampleFromCallSet/SelectSampleFromCallSet.wdl
    testParameterFiles:
    - /BenchmarkCNV/SelectSampleFromCallSet/SelectSampleFromCallSet.inputs.json
+ - name: MergeVCF
+   subclass: WDL
+   primaryDescriptorPath: /BenchmarkCNV/MergeVCF/MergeVCF.wdl
+   testParameterFiles:
+   - /BenchmarkCNV/MergeVCF/MergeVCF.inputs.json
  - name: BenchmarkCNV
    subclass: WDL
    primaryDescriptorPath: /BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl

From 96485f3e84cfbee911ee22004acc8e98c3922ac7 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Mon, 27 Feb 2023 13:54:03 -0500
Subject: [PATCH 11/28] Changed the output VCF name

---
 BenchmarkCNV/MergeVCF/MergeVCF.wdl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/BenchmarkCNV/MergeVCF/MergeVCF.wdl b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
index 0507b08..51522e4 100644
--- a/BenchmarkCNV/MergeVCF/MergeVCF.wdl
+++ b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
@@ -20,7 +20,7 @@ workflow MergeVCF {
 
     # Outputs that will be retained when execution is complete
     output {
-        File selected_vcf = mergeVCF.output_vcf
+        File merged_vcf = mergeVCF.output_vcf
     }
     meta {
         author: "Yueyao Gao"

From b4fd6918d543e8fdda1adc89a60ee1c1d3d00809 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Mon, 27 Feb 2023 14:40:07 -0500
Subject: [PATCH 12/28] Continue reporting the output regardless of the warning

---
 BenchmarkCNV/MergeVCF/MergeVCF.wdl | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/BenchmarkCNV/MergeVCF/MergeVCF.wdl b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
index 51522e4..b07626e 100644
--- a/BenchmarkCNV/MergeVCF/MergeVCF.wdl
+++ b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
@@ -49,7 +49,9 @@ task mergeVCF {
             echo "vcf1: ~{vcf1}"
             echo "vcf2: ~{vcf2}"
 
-            bcftools concat ~{vcf1} ~{vcf2} -o ~{sample_name}_merged.vcf
+            # Use bcftools to concat two vcfs
+            # Ignore the warning message
+            bcftools concat ~{vcf1} ~{vcf2} -o ~{sample_name}_merged.vcf 2>/dev/null || true
 
             # Print the output file name
             echo "Merged VCF file: ~{sample_name}_merged.vcf"

From 6dc34f351e5430291a908c68f5557868ec2edbdf Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Tue, 28 Feb 2023 14:26:57 -0500
Subject: [PATCH 13/28] Added allow-overlapping option in merge

---
 BenchmarkCNV/MergeVCF/MergeVCF.wdl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/BenchmarkCNV/MergeVCF/MergeVCF.wdl b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
index b07626e..714ee1b 100644
--- a/BenchmarkCNV/MergeVCF/MergeVCF.wdl
+++ b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
@@ -51,7 +51,7 @@ task mergeVCF {
 
             # Use bcftools to concat two vcfs
             # Ignore the warning message
-            bcftools concat ~{vcf1} ~{vcf2} -o ~{sample_name}_merged.vcf 2>/dev/null || true
+            bcftools concat -a ~{vcf1} ~{vcf2} -o ~{sample_name}_merged.vcf
 
             # Print the output file name
             echo "Merged VCF file: ~{sample_name}_merged.vcf"

From 449b9012513a6e8e79a78d8b6ba6127fad3023a2 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Tue, 28 Feb 2023 15:11:17 -0500
Subject: [PATCH 14/28] Updated wdl with index step before merging

---
 BenchmarkCNV/MergeVCF/MergeVCF.wdl | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/BenchmarkCNV/MergeVCF/MergeVCF.wdl b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
index 714ee1b..746979b 100644
--- a/BenchmarkCNV/MergeVCF/MergeVCF.wdl
+++ b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
@@ -49,12 +49,15 @@ task mergeVCF {
             echo "vcf1: ~{vcf1}"
             echo "vcf2: ~{vcf2}"
 
+            echo "Index the input VCFs"
+            bcftools index -t ~{vcf1}
+            bcftools index -t ~{vcf2}
+
             # Use bcftools to concat two vcfs
-            # Ignore the warning message
-            bcftools concat -a ~{vcf1} ~{vcf2} -o ~{sample_name}_merged.vcf
+            bcftools concat -Oz -a ~{vcf1} ~{vcf2} -o ~{sample_name}_merged.vcf.gz
 
             # Print the output file name
-            echo "Merged VCF file: ~{sample_name}_merged.vcf"
+            echo "Merged VCF file: ~{sample_name}_merged.vcf.gz"
             >>>
         runtime {
             docker: bcftools_docker
@@ -64,7 +67,7 @@ task mergeVCF {
             preemptible: 2
         }
         output {
-            File output_vcf = "~{sample_name}_merged.vcf"
+            File output_vcf = "~{sample_name}_merged.vcf.gz"
         }
 
 }
\ No newline at end of file

From ce4f252e8039ae029a379cb33197423994e7306a Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Wed, 1 Mar 2023 14:03:24 -0500
Subject: [PATCH 15/28] Only collect event level stats using 4mat script

---
 BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

diff --git a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
index d416673..dbb1beb 100644
--- a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
@@ -40,7 +40,6 @@ workflow Benchmark_CNV_Caller {
         File wittyer_annotated_vcf = BenchmarkCNV.wittyer_annotated_vcf
         File wittyer_annotated_vcf_index = BenchmarkCNV.wittyer_annotated_vcf_index
         Array[File] Wittyer4Mat_event_stats = Wittyer4Mat.event_level_wittyer_stats
-        Array[File] Wittyer4Mat_base_stats = Wittyer4Mat.base_level_wittyer_stats
     }
     meta {
         author: "Yueyao Gao"
@@ -116,16 +115,7 @@ workflow Benchmark_CNV_Caller {
         command <<<
             set -e
 
-            # Run wittyer4mat script on cnv wittyer output
-            mkdir ~{truth_sample_name}_cnv_wittyer4mat
-            conda run --no-capture-output \
-            -n wittyer-parser \
-            python3 /wittyer4mat/wittyer_4mat.py -i ~{wittyer_stats} \
-            -t base \
-            -o ~{truth_sample_name}_base_level_wittyer4mat
-
-            # Run wittyer4mat script on sv wittyer output
-            mkdir ~{truth_sample_name}_sv_wittyer4mat
+            # Run wittyer4mat script on wittyer output
             conda run --no-capture-output \
             -n wittyer-parser \
             python3 /wittyer4mat/wittyer_4mat.py -i ~{wittyer_stats} \
@@ -138,6 +128,5 @@ workflow Benchmark_CNV_Caller {
         }
         output {
             Array[File] event_level_wittyer_stats = glob("~{truth_sample_name}_event_level_wittyer4mat/*.csv")
-            Array[File] base_level_wittyer_stats = glob("~{truth_sample_name}_base_level_wittyer4mat/*.csv")
         }
     }
\ No newline at end of file

From 70ab5cca1619dce5c2ddfeb4b5ec98f6597ad7ab Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Thu, 2 Mar 2023 13:56:51 -0500
Subject: [PATCH 16/28] Reflect the sample name in the output CSV name

---
 BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl | 1 +
 1 file changed, 1 insertion(+)

diff --git a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
index dbb1beb..6939a0f 100644
--- a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
@@ -121,6 +121,7 @@ workflow Benchmark_CNV_Caller {
             python3 /wittyer4mat/wittyer_4mat.py -i ~{wittyer_stats} \
             -t event \
             -o ~{truth_sample_name}_event_level_wittyer4mat
+            -p ~{truth_sample_name}
     >>>
         runtime {
             docker: wittyer4mat_docker

From 93e30ef8af665dad6d85349c7be76f059cc8ece8 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Thu, 2 Mar 2023 14:13:15 -0500
Subject: [PATCH 17/28] Fixed typo in 4mat command

---
 BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
index 6939a0f..a6322f9 100644
--- a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
@@ -120,7 +120,7 @@ workflow Benchmark_CNV_Caller {
             -n wittyer-parser \
             python3 /wittyer4mat/wittyer_4mat.py -i ~{wittyer_stats} \
             -t event \
-            -o ~{truth_sample_name}_event_level_wittyer4mat
+            -o ~{truth_sample_name}_event_level_wittyer4mat \
             -p ~{truth_sample_name}
     >>>
         runtime {

From 9151da77156550ff3aa96c9b5d0c4aa4cb062928 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Thu, 23 Mar 2023 17:40:16 -0400
Subject: [PATCH 18/28] Added BGZIP command

---
 BenchmarkCNV/MergeVCF/MergeVCF.wdl | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/BenchmarkCNV/MergeVCF/MergeVCF.wdl b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
index 746979b..a6c2adb 100644
--- a/BenchmarkCNV/MergeVCF/MergeVCF.wdl
+++ b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
@@ -49,12 +49,16 @@ task mergeVCF {
             echo "vcf1: ~{vcf1}"
             echo "vcf2: ~{vcf2}"
 
+            # bgzf-compress the input vcf files
+            bcftools view ~{vcf1} -Oz -o ~{vcf1}.gz
+            bcftools view ~{vcf2} -Oz -o ~{vcf2}.gz
+
             echo "Index the input VCFs"
-            bcftools index -t ~{vcf1}
-            bcftools index -t ~{vcf2}
+            bcftools index -t ~{vcf1}.gz
+            bcftools index -t ~{vcf2}.gz
 
             # Use bcftools to concat two vcfs
-            bcftools concat -Oz -a ~{vcf1} ~{vcf2} -o ~{sample_name}_merged.vcf.gz
+            bcftools concat -Oz -a ~{vcf1}.gz ~{vcf2}.gz -o ~{sample_name}_merged.vcf.gz
 
             # Print the output file name
             echo "Merged VCF file: ~{sample_name}_merged.vcf.gz"

From 7da8e7451f8f6ed1277e9ed936009baf1fbf53b4 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Thu, 23 Mar 2023 18:29:37 -0400
Subject: [PATCH 19/28] Make the wittyer output vcf be optional

---
 BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
index a6322f9..0879ab7 100644
--- a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
@@ -37,8 +37,8 @@ workflow Benchmark_CNV_Caller {
     # Outputs that will be retained when execution is complete
     output {
         File wittyer_stats = BenchmarkCNV.wittyer_stats
-        File wittyer_annotated_vcf = BenchmarkCNV.wittyer_annotated_vcf
-        File wittyer_annotated_vcf_index = BenchmarkCNV.wittyer_annotated_vcf_index
+        File? wittyer_annotated_vcf = BenchmarkCNV.wittyer_annotated_vcf
+        File? wittyer_annotated_vcf_index = BenchmarkCNV.wittyer_annotated_vcf_index
         Array[File] Wittyer4Mat_event_stats = Wittyer4Mat.event_level_wittyer_stats
     }
     meta {

From 86d39671c3e47247f1f5c394056a51da900f5e03 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Thu, 23 Mar 2023 18:58:03 -0400
Subject: [PATCH 20/28] make the vcf output required

---
 BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
index 0879ab7..a6322f9 100644
--- a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
@@ -37,8 +37,8 @@ workflow Benchmark_CNV_Caller {
     # Outputs that will be retained when execution is complete
     output {
         File wittyer_stats = BenchmarkCNV.wittyer_stats
-        File? wittyer_annotated_vcf = BenchmarkCNV.wittyer_annotated_vcf
-        File? wittyer_annotated_vcf_index = BenchmarkCNV.wittyer_annotated_vcf_index
+        File wittyer_annotated_vcf = BenchmarkCNV.wittyer_annotated_vcf
+        File wittyer_annotated_vcf_index = BenchmarkCNV.wittyer_annotated_vcf_index
         Array[File] Wittyer4Mat_event_stats = Wittyer4Mat.event_level_wittyer_stats
     }
     meta {

From 86d35a0bd040dc9219d299a9662075332ff7c696 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Thu, 23 Mar 2023 20:00:33 -0400
Subject: [PATCH 21/28] make 4mat task optional

---
 BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
index a6322f9..fa6f27f 100644
--- a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
@@ -11,6 +11,7 @@ workflow Benchmark_CNV_Caller {
         String wittyer_evaluation_mode
         String wittyer_docker
         String wittyer4mat_docker
+        Boolean? run_wittyer4mat
     }
 
     # benchmark cnv.vcf and sv.vcf using witty.er tool
@@ -27,11 +28,13 @@ workflow Benchmark_CNV_Caller {
     }
 
     # wittyer4mat to parse the wittyer json output
-    call Wittyer4Mat {
-        input:
-            wittyer4mat_docker = wittyer4mat_docker,
-            wittyer_stats = BenchmarkCNV.wittyer_stats,
-            truth_sample_name = truth_sample_name
+    if (run_wittyer4mat) {
+        call Wittyer4Mat {
+            input:
+                wittyer4mat_docker = wittyer4mat_docker,
+                wittyer_stats = BenchmarkCNV.wittyer_stats,
+                truth_sample_name = truth_sample_name
+        }
     }
 
     # Outputs that will be retained when execution is complete
@@ -39,7 +42,7 @@ workflow Benchmark_CNV_Caller {
         File wittyer_stats = BenchmarkCNV.wittyer_stats
         File wittyer_annotated_vcf = BenchmarkCNV.wittyer_annotated_vcf
         File wittyer_annotated_vcf_index = BenchmarkCNV.wittyer_annotated_vcf_index
-        Array[File] Wittyer4Mat_event_stats = Wittyer4Mat.event_level_wittyer_stats
+        Array[File]? Wittyer4Mat_event_stats = Wittyer4Mat.event_level_wittyer_stats
     }
     meta {
         author: "Yueyao Gao"

From d9f5411a0fa727a559edc28e623d27d1095cd6dd Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Thu, 23 Mar 2023 20:04:00 -0400
Subject: [PATCH 22/28] fixed the input typo

---
 BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
index fa6f27f..abdd707 100644
--- a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
@@ -11,7 +11,7 @@ workflow Benchmark_CNV_Caller {
         String wittyer_evaluation_mode
         String wittyer_docker
         String wittyer4mat_docker
-        Boolean? run_wittyer4mat
+        Boolean run_wittyer4mat
     }
 
     # benchmark cnv.vcf and sv.vcf using witty.er tool

From 369efec3caeb12fbeb890016b9a500f632e3fd76 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Fri, 14 Apr 2023 14:01:11 -0400
Subject: [PATCH 23/28] Replace bash if statement with WDL trick

---
 BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)

diff --git a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
index abdd707..e1f3178 100644
--- a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
@@ -75,24 +75,14 @@ workflow Benchmark_CNV_Caller {
         command <<<
             set -e
 
-            if [[ -f "~{bedfile}" ]]; then
-            # Run Benchmarking tool wittyer on dragen generated cnv.vcf with bed file
+            # Run Benchmarking tool wittyer on dragen generated cnv.vcf and truth set
             /opt/Wittyer/Wittyer -i ~{eval_vcf} \
             -t ~{truth_vcf} \
             -em ~{wittyer_evaluation_mode} \
             --configFile ~{wittyer_config} \
-            --includeBed ~{bedfile} \
+            ~{'--includeBed '+ bedfile} \
             -o ~{truth_sample_name}_wittyer_output
 
-            else
-            # Run Benchmarking tool wittyer on dragen generated cnv.vcf
-            /opt/Wittyer/Wittyer -i ~{eval_vcf} \
-            -t ~{truth_vcf} \
-            -em ~{wittyer_evaluation_mode} \
-            --configFile ~{wittyer_config} \
-            -o ~{truth_sample_name}_wittyer_output
-
-            fi
         >>>
         runtime {
             docker: wittyer_docker

From 6d5746f191e7fb0f891d86e4b5660e660d7efec2 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Fri, 14 Apr 2023 15:10:34 -0400
Subject: [PATCH 24/28] BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl

---
 BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
index e1f3178..0d323e3 100644
--- a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
@@ -113,8 +113,7 @@ workflow Benchmark_CNV_Caller {
             -n wittyer-parser \
             python3 /wittyer4mat/wittyer_4mat.py -i ~{wittyer_stats} \
             -t event \
-            -o ~{truth_sample_name}_event_level_wittyer4mat \
-            -p ~{truth_sample_name}
+            -o ~{truth_sample_name}_event_level_wittyer4mat
     >>>
         runtime {
             docker: wittyer4mat_docker

From 72a12a6aa27d8fbceb9141b4e113a1e53a67620e Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Fri, 14 Apr 2023 15:25:23 -0400
Subject: [PATCH 25/28] Changed the taskname based on PR comment

---
 .../SelectSampleFromCallSet.wdl               | 67 ++++++++++---------
 1 file changed, 34 insertions(+), 33 deletions(-)

diff --git a/BenchmarkCNV/SelectSampleFromCallSet/SelectSampleFromCallSet.wdl b/BenchmarkCNV/SelectSampleFromCallSet/SelectSampleFromCallSet.wdl
index 3e5fd5a..b8b4206 100644
--- a/BenchmarkCNV/SelectSampleFromCallSet/SelectSampleFromCallSet.wdl
+++ b/BenchmarkCNV/SelectSampleFromCallSet/SelectSampleFromCallSet.wdl
@@ -8,7 +8,7 @@ workflow SelectSampleFromCallSet {
     }
 
     # Select vcf for specific sample
-    call SelectSample {
+    call SelectSampleRemoveComplexSV {
         input:
             bcftools_docker = bcftools_docker,
             vcf = variant_callset,
@@ -18,7 +18,7 @@ workflow SelectSampleFromCallSet {
 
     # Outputs that will be retained when execution is complete
     output {
-        File selected_vcf = SelectSample.output_vcf
+        File selected_vcf = SelectSampleRemoveComplexSV.output_vcf
     }
     meta {
         author: "Yueyao Gao"
@@ -26,40 +26,41 @@ workflow SelectSampleFromCallSet {
         description: "SelectSampleFromCallSet.wdl is design to extract specific sample from a large callset vcf"
     }
 }
-task SelectSample {
+    # Select sample from a vcf and remove complex SVs and INV
+    task SelectSampleRemoveComplexSV {
 
-        input {
-            String bcftools_docker
-            File vcf
-            String sample_name
-            Int? mem
-            Int? disk_space
-            # If mem and disk size were not specified, use 4GB and 100 GB as default
-            Int mem_size = select_first([mem, 4])
-            Int disk_size = select_first([disk_space,100])
+            input {
+                String bcftools_docker
+                File vcf
+                String sample_name
+                Int? mem
+                Int? disk_space
+                # If mem and disk size were not specified, use 4GB and 100 GB as default
+                Int mem_size = select_first([mem, 4])
+                Int disk_size = select_first([disk_space,100])
 
-        }
-        command <<<
-            set -e
-            # Select sample using bcftools
-            bcftools view -s ~{sample_name} -O v -o ~{sample_name}.vcf ~{vcf}
+            }
+            command <<<
+                set -e
+                # Select sample using bcftools
+                bcftools view -s ~{sample_name} -O v -o ~{sample_name}.vcf ~{vcf}
 
-            # Remove Complex SV from the sample vcf because wittyer can't process CPX variants
-            # Remove INV from the sample vcf because wittyer's exception
-            # Remove reference allele
+                # Remove Complex SV from the sample vcf because wittyer can't process CPX variants
+                # Remove INV from the sample vcf because wittyer's exception
+                # Remove reference allele
 
-            bcftools view -e 'SVTYPE="INV" | SVTYPE="CPX" | GT="0/0"' ~{sample_name}.vcf -o ~{sample_name}_filtered.vcf
+                bcftools view -e 'SVTYPE="INV" | SVTYPE="CPX" | GT="0/0"' ~{sample_name}.vcf -o ~{sample_name}_filtered.vcf
 
-            >>>
-        runtime {
-            docker: bcftools_docker
-            bootDiskSizeGb: 12
-            memory: mem_size + " GB"
-            disks: "local-disk " + disk_size + " HDD"
-            preemptible: 2
-        }
-        output {
-            File output_vcf = "~{sample_name}_filtered.vcf"
-        }
+                >>>
+            runtime {
+                docker: bcftools_docker
+                bootDiskSizeGb: 12
+                memory: mem_size + " GB"
+                disks: "local-disk " + disk_size + " HDD"
+                preemptible: 2
+            }
+            output {
+                File output_vcf = "~{sample_name}_filtered.vcf"
+            }
 
-}
\ No newline at end of file
+    }
\ No newline at end of file

From 15093916555fead0fb31cc4332e256556f15d8d0 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Fri, 14 Apr 2023 15:30:23 -0400
Subject: [PATCH 26/28] Added vcf sorting task based on PR comment

---
 BenchmarkCNV/MergeVCF/MergeVCF.wdl | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/BenchmarkCNV/MergeVCF/MergeVCF.wdl b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
index a6c2adb..25894a2 100644
--- a/BenchmarkCNV/MergeVCF/MergeVCF.wdl
+++ b/BenchmarkCNV/MergeVCF/MergeVCF.wdl
@@ -60,8 +60,11 @@ task mergeVCF {
             # Use bcftools to concat two vcfs
             bcftools concat -Oz -a ~{vcf1}.gz ~{vcf2}.gz -o ~{sample_name}_merged.vcf.gz
 
+            #sort the merged vcf
+            bcftools sort -Oz -o ~{sample_name}_sorted_merged.vcf.gz ~{sample_name}_merged.vcf.gz
+
             # Print the output file name
-            echo "Merged VCF file: ~{sample_name}_merged.vcf.gz"
+            echo "Merged VCF file: ~{sample_name}_sorted_merged.vcf.gz"
             >>>
         runtime {
             docker: bcftools_docker
@@ -71,7 +74,7 @@ task mergeVCF {
             preemptible: 2
         }
         output {
-            File output_vcf = "~{sample_name}_merged.vcf.gz"
+            File output_vcf = "~{sample_name}_sorted_merged.vcf.gz"
         }
 
 }
\ No newline at end of file

From 52be6f0b897f11144dc40410669d778129bf992b Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Fri, 14 Apr 2023 15:37:45 -0400
Subject: [PATCH 27/28] Added a default docker image

---
 BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
index 0d323e3..651d6f7 100644
--- a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
@@ -9,7 +9,7 @@ workflow Benchmark_CNV_Caller {
         File wittyer_config
         File? bedfile
         String wittyer_evaluation_mode
-        String wittyer_docker
+        String wittyer_docker = "yg96/wittyer:v2"
         String wittyer4mat_docker
         Boolean run_wittyer4mat
     }

From 019a8d9f15c52c341fafc9fd1de88a4f3d4d6dc7 Mon Sep 17 00:00:00 2001
From: Yueyao Gao <gaoyueya@broadinstitute.org>
Date: Fri, 14 Apr 2023 15:54:30 -0400
Subject: [PATCH 28/28] Fixed a typo in a comment

---
 BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
index 651d6f7..fe433ae 100644
--- a/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
+++ b/BenchmarkCNV/BenchmarkCNV/BenchmarkCNV.wdl
@@ -97,7 +97,7 @@ workflow Benchmark_CNV_Caller {
             File wittyer_annotated_vcf_index = "~{truth_sample_name}_wittyer_output/Wittyer.~{truth_sample_name}.Vs.~{query_sample_name}.vcf.gz.tbi"
         }
 }
-    # Task3: Format the wittyer json output
+    # Task2: Format the wittyer json output
     task Wittyer4Mat{
 
         input{