From 064712c4ea2b42a405a98e55a4aac81c3f79d3ff Mon Sep 17 00:00:00 2001
From: SusiJo <susanne.jodoin@gmx.de>
Date: Fri, 20 May 2022 09:11:45 +0200
Subject: [PATCH 01/19] added cram_bam conversion & tumor_only check

---
 modules/cnvkit/batch/main.nf | 33 ++++++++++++++++++++++++++++-----
 1 file changed, 28 insertions(+), 5 deletions(-)

diff --git a/modules/cnvkit/batch/main.nf b/modules/cnvkit/batch/main.nf
index 7c44d9f6..1ceb7072 100644
--- a/modules/cnvkit/batch/main.nf
+++ b/modules/cnvkit/batch/main.nf
@@ -5,7 +5,7 @@ process CNVKIT_BATCH {
     conda (params.enable_conda ? 'bioconda::cnvkit=0.9.9' : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://depot.galaxyproject.org/singularity/cnvkit:0.9.9--pyhdfd78af_0' :
-        'quay.io/biocontainers/cnvkit:0.9.9--pyhdfd78af_0' }"
+        'quay.io/biocontainers/mulled-v2-780d630a9bb6a0ff2e7b6f730906fd703e40e98f:304d1c5ab610f216e77c61420ebe85f1e7c5968a-0' }"
 
     input:
     tuple val(meta), path(tumor), path(normal)
@@ -18,6 +18,8 @@ process CNVKIT_BATCH {
     tuple val(meta), path("*.cnn"), emit: cnn, optional: true
     tuple val(meta), path("*.cnr"), emit: cnr, optional: true
     tuple val(meta), path("*.cns"), emit: cns, optional: true
+    tuple val(meta), path("*.pdf"), emit: pdf, optional: true
+    tuple val(meta), path("*.png"), emit: png, optional: true
     path "versions.yml"           , emit: versions
 
     when:
@@ -25,21 +27,42 @@ process CNVKIT_BATCH {
 
     script:
     def args = task.ext.args ?: ''
-    def normal_args = normal ? "--normal $normal" : ""
-    def fasta_args = fasta ? "--fasta $fasta" : ""
+    // execute samtools only when cram files are input
+    // input pair is assumed to have same extension if both exist
+    def is_cram = tumor.Extension == "cram" ? true : false
+    def tumor_out = is_cram ? tumor.BaseName + ".bam" : "${tumor}"
+    // do not run samtools on normal samples in tumor_only
+    def normal_exists = normal ? true: false
+    // tumor_only mode does not need fasta & target
+    // instead it requires a pre-computed reference which is built from fasta & target
+    def (normal_out, normal_args, fasta_args, target_args) = ["", "", "", ""]
     def reference_args = reference ? "--reference $reference" : ""
 
-    def target_args = ""
+    if (normal_exists){
+        def normal_prefix = normal.BaseName
+        normal_out = is_cram ? "${normal_prefix}" + ".bam" : "${normal}"
+        normal_args = normal_prefix ? "--normal $normal_out" : ""
+        fasta_args = fasta ? "--fasta $fasta" : ""
+    }
+
     if (args.contains("--method wgs") || args.contains("-m wgs")) {
         target_args = targets ? "--targets $targets" : ""
     }
     else {
         target_args = "--targets $targets"
     }
+
     """
+    if $is_cram; then
+        samtools view -T $fasta $tumor -@ $task.cpus -o $tumor_out
+        if $normal_exists; then
+            samtools view -T $fasta $normal -@ $task.cpus -o $normal_out
+        fi
+    fi
+
     cnvkit.py \\
         batch \\
-        $tumor \\
+        $tumor_out \\
         $normal_args \\
         $fasta_args \\
         $reference_args \\

From 5a1297cc7d55de78cdb945977f8e963fe5ecde78 Mon Sep 17 00:00:00 2001
From: SusiJo <susanne.jodoin@gmx.de>
Date: Fri, 20 May 2022 09:12:47 +0200
Subject: [PATCH 02/19] added optional pdf/png outputs

---
 modules/cnvkit/batch/meta.yml | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/modules/cnvkit/batch/meta.yml b/modules/cnvkit/batch/meta.yml
index 474c55f2..03277e33 100644
--- a/modules/cnvkit/batch/meta.yml
+++ b/modules/cnvkit/batch/meta.yml
@@ -80,6 +80,14 @@ output:
       type: file
       description: File containing copy number segment information
       pattern: "*.{cns}"
+  - pdf:
+      type: file
+      description: File with plot of copy numbers or segments on chromosomes
+      pattern: "*.{pdf}"
+  - png:
+      type: file
+      description: File with plot of bin-level log2 coverages and segmentation calls
+      pattern: "*.{png}"
   - versions:
       type: file
       description: File containing software versions
@@ -91,3 +99,4 @@ authors:
   - "@drpatelh"
   - "@fbdtemme"
   - "@lassefolkersen"
+  - "@SusiJo"

From 3d57caa683a48a014abf986cfdaaf0b9f6ff9676 Mon Sep 17 00:00:00 2001
From: SusiJo <susanne.jodoin@gmx.de>
Date: Fri, 20 May 2022 09:13:27 +0200
Subject: [PATCH 03/19] added test & corrected cram input

---
 tests/modules/cnvkit/batch/main.nf  | 19 ++++++++++++++---
 tests/modules/cnvkit/batch/test.yml | 33 +++++++++++++++++++----------
 2 files changed, 38 insertions(+), 14 deletions(-)

diff --git a/tests/modules/cnvkit/batch/main.nf b/tests/modules/cnvkit/batch/main.nf
index 6b40dec6..15b5dfe6 100755
--- a/tests/modules/cnvkit/batch/main.nf
+++ b/tests/modules/cnvkit/batch/main.nf
@@ -35,8 +35,8 @@ workflow test_cnvkit_cram {
 
     input = [
         [ id:'test'], // meta map
-        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true),
-        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_cram'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true)
     ]
     fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
 
@@ -53,5 +53,18 @@ workflow test_cnvkit_tumoronly {
     fasta     = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
     reference = file(params.test_data['generic']['cnn']['reference'], checkIfExists: true)
 
-    CNVKIT_TUMORONLY ( input, [], [], reference )
+    CNVKIT_TUMORONLY ( input, fasta, [], reference )
+}
+
+workflow test_cnvkit_tumoronly_cram {
+
+    input = [
+        [ id:'test'], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_cram'], checkIfExists: true),
+        []
+    ]
+    fasta     = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    reference = file(params.test_data['generic']['cnn']['reference'], checkIfExists: true)
+
+    CNVKIT_TUMORONLY ( input, fasta, [], reference )
 }
diff --git a/tests/modules/cnvkit/batch/test.yml b/tests/modules/cnvkit/batch/test.yml
index 57af3603..9bce265a 100755
--- a/tests/modules/cnvkit/batch/test.yml
+++ b/tests/modules/cnvkit/batch/test.yml
@@ -1,15 +1,15 @@
 - name: cnvkit batch test_cnvkit_hybrid
-  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_hybrid -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
+  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_hybrid -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
   tags:
-    - cnvkit/batch
     - cnvkit
+    - cnvkit/batch
   files:
     - path: output/cnvkit/baits.antitarget.bed
       md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/cnvkit/baits.target.bed
       md5sum: 26d25ff2d6c45b6d92169b3559c6acdb
     - path: output/cnvkit/reference.cnn
-      md5sum: ac99c1ad8b917b96ae15119146c91ab9
+      md5sum: 035d031f54c5f1b43b903da96559b475
     - path: output/cnvkit/test.paired_end.sorted.antitargetcoverage.cnn
       md5sum: 203caf8cef6935bb50b4138097955cb8
     - path: output/cnvkit/test.paired_end.sorted.bintest.cns
@@ -28,10 +28,10 @@
       md5sum: aa8a018b1d4d1e688c9f9f6ae01bf4d7
 
 - name: cnvkit batch test_cnvkit_wgs
-  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_wgs -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
+  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_wgs -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
   tags:
-    - cnvkit/batch
     - cnvkit
+    - cnvkit/batch
   files:
     - path: output/cnvkit/genome.antitarget.bed
       md5sum: d41d8cd98f00b204e9800998ecf8427e
@@ -40,7 +40,7 @@
     - path: output/cnvkit/genome.target.bed
       md5sum: a13353ae9c8405e701390c069255bbd2
     - path: output/cnvkit/reference.cnn
-      md5sum: 05c6211e0179885b8a83e44fd21d5f86
+      md5sum: 1606a85410bfaa79464be6e98699aa83
     - path: output/cnvkit/test.paired_end.sorted.antitargetcoverage.cnn
       md5sum: 203caf8cef6935bb50b4138097955cb8
     - path: output/cnvkit/test.paired_end.sorted.targetcoverage.cnn
@@ -59,10 +59,10 @@
       md5sum: 6ae6b3fce7299eedca6133d911c38fe1
 
 - name: cnvkit batch test_cnvkit_cram
-  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_cram -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
+  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_cram -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
   tags:
-    - cnvkit/batch
     - cnvkit
+    - cnvkit/batch
   files:
     - path: output/cnvkit/genome.antitarget.bed
       md5sum: d41d8cd98f00b204e9800998ecf8427e
@@ -71,7 +71,7 @@
     - path: output/cnvkit/genome.target.bed
       md5sum: a13353ae9c8405e701390c069255bbd2
     - path: output/cnvkit/reference.cnn
-      md5sum: 05c6211e0179885b8a83e44fd21d5f86
+      md5sum: 1606a85410bfaa79464be6e98699aa83
     - path: output/cnvkit/test.paired_end.sorted.antitargetcoverage.cnn
       md5sum: 203caf8cef6935bb50b4138097955cb8
     - path: output/cnvkit/test.paired_end.sorted.targetcoverage.cnn
@@ -90,10 +90,21 @@
       md5sum: 6ae6b3fce7299eedca6133d911c38fe1
 
 - name: cnvkit batch test_cnvkit_tumoronly
-  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_tumoronly -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
+  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_tumoronly -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
   tags:
-    - cnvkit/batch
     - cnvkit
+    - cnvkit/batch
+  files:
+    - path: output/cnvkit/reference.antitarget-tmp.bed
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/cnvkit/reference.target-tmp.bed
+      md5sum: 26d25ff2d6c45b6d92169b3559c6acdb
+
+- name: cnvkit batch test_cnvkit_tumoronly_cram
+  command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_tumoronly_cram -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/batch/nextflow.config
+  tags:
+    - cnvkit
+    - cnvkit/batch
   files:
     - path: output/cnvkit/reference.antitarget-tmp.bed
       md5sum: d41d8cd98f00b204e9800998ecf8427e

From 129270d7bc31830ea5f4772264c6dcb5007ee817 Mon Sep 17 00:00:00 2001
From: SusiJo <susanne.jodoin@gmx.de>
Date: Fri, 20 May 2022 10:37:46 +0200
Subject: [PATCH 04/19] adjusted conda env & singularity container

---
 modules/cnvkit/batch/main.nf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/modules/cnvkit/batch/main.nf b/modules/cnvkit/batch/main.nf
index 1ceb7072..063808a1 100644
--- a/modules/cnvkit/batch/main.nf
+++ b/modules/cnvkit/batch/main.nf
@@ -2,9 +2,9 @@ process CNVKIT_BATCH {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? 'bioconda::cnvkit=0.9.9' : null)
+    conda (params.enable_conda ? 'bioconda::cnvkit=0.9.9 bioconda::samtools=1.15.1' : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/cnvkit:0.9.9--pyhdfd78af_0' :
+        'https://depot.galaxyproject.org/singularity/mulled-v2-780d630a9bb6a0ff2e7b6f730906fd703e40e98f:304d1c5ab610f216e77c61420ebe85f1e7c5968a-0' :
         'quay.io/biocontainers/mulled-v2-780d630a9bb6a0ff2e7b6f730906fd703e40e98f:304d1c5ab610f216e77c61420ebe85f1e7c5968a-0' }"
 
     input:

From f392c4bed533ccacd0e79cca736666417e877ad0 Mon Sep 17 00:00:00 2001
From: SusiJo <susanne.jodoin@gmx.de>
Date: Fri, 20 May 2022 13:05:43 +0200
Subject: [PATCH 05/19] removed params section & added description fasta

---
 modules/cnvkit/batch/meta.yml | 23 +----------------------
 1 file changed, 1 insertion(+), 22 deletions(-)

diff --git a/modules/cnvkit/batch/meta.yml b/modules/cnvkit/batch/meta.yml
index 03277e33..2cd675c7 100644
--- a/modules/cnvkit/batch/meta.yml
+++ b/modules/cnvkit/batch/meta.yml
@@ -11,27 +11,6 @@ tools:
       homepage: https://cnvkit.readthedocs.io/en/stable/index.html
       documentation: https://cnvkit.readthedocs.io/en/stable/index.html
       licence: ["Apache-2.0"]
-params:
-  - outdir:
-      type: string
-      description: |
-        The pipeline's output directory. By default, the module will
-        output files into `$params.outdir/<SOFTWARE>`
-  - publish_dir_mode:
-      type: string
-      description: |
-        Value for the Nextflow `publishDir` mode parameter.
-        Available: symlink, rellink, link, copy, copyNoFollow, move.
-  - enable_conda:
-      type: boolean
-      description: |
-        Run the module with Conda using the software specified
-        via the `conda` directive
-  - singularity_pull_docker_container:
-      type: boolean
-      description: |
-        Instead of directly downloading Singularity images for use with Singularity,
-        force the workflow to pull and convert Docker containers instead.
 input:
   - meta:
       type: map
@@ -49,7 +28,7 @@ input:
   - fasta:
       type: file
       description: |
-        Input reference genome fasta file
+        Input reference genome fasta file (only needed for cram_input and/or when normal_samples are provided)
   - targetfile:
       type: file
       description: |

From 00077c36c8f57474c7540053b7ec43d4c4378c13 Mon Sep 17 00:00:00 2001
From: SusiJo <susanne.jodoin@gmx.de>
Date: Fri, 20 May 2022 13:06:16 +0200
Subject: [PATCH 06/19] removed unnecessary fasta for tumor_only_bam

---
 tests/modules/cnvkit/batch/main.nf | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tests/modules/cnvkit/batch/main.nf b/tests/modules/cnvkit/batch/main.nf
index 15b5dfe6..988ed3ad 100755
--- a/tests/modules/cnvkit/batch/main.nf
+++ b/tests/modules/cnvkit/batch/main.nf
@@ -50,10 +50,9 @@ workflow test_cnvkit_tumoronly {
         file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true),
         []
     ]
-    fasta     = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
     reference = file(params.test_data['generic']['cnn']['reference'], checkIfExists: true)
 
-    CNVKIT_TUMORONLY ( input, fasta, [], reference )
+    CNVKIT_TUMORONLY ( input, [], [], reference )
 }
 
 workflow test_cnvkit_tumoronly_cram {

From 3b3921cfa319602ed15c7021969122d72d600e46 Mon Sep 17 00:00:00 2001
From: SusiJo <43847534+SusiJo@users.noreply.github.com>
Date: Fri, 20 May 2022 13:07:57 +0200
Subject: [PATCH 07/19] refine comment

Co-authored-by: FriederikeHanssen <Friederike.hanssen@qbic.uni-tuebingen.de>
---
 modules/cnvkit/batch/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/cnvkit/batch/main.nf b/modules/cnvkit/batch/main.nf
index 063808a1..63482c6c 100644
--- a/modules/cnvkit/batch/main.nf
+++ b/modules/cnvkit/batch/main.nf
@@ -27,7 +27,7 @@ process CNVKIT_BATCH {
 
     script:
     def args = task.ext.args ?: ''
-    // execute samtools only when cram files are input
+    // execute samtools only when cram files are input, cnvkit runs natively on bam but is prohibitively slow 
     // input pair is assumed to have same extension if both exist
     def is_cram = tumor.Extension == "cram" ? true : false
     def tumor_out = is_cram ? tumor.BaseName + ".bam" : "${tumor}"

From 2e5aa0dbb45632072cbe862985e0e4ff50c55867 Mon Sep 17 00:00:00 2001
From: SusiJo <43847534+SusiJo@users.noreply.github.com>
Date: Fri, 20 May 2022 13:08:26 +0200
Subject: [PATCH 08/19] refine comment

Co-authored-by: FriederikeHanssen <Friederike.hanssen@qbic.uni-tuebingen.de>
---
 modules/cnvkit/batch/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/cnvkit/batch/main.nf b/modules/cnvkit/batch/main.nf
index 63482c6c..55e3ee6b 100644
--- a/modules/cnvkit/batch/main.nf
+++ b/modules/cnvkit/batch/main.nf
@@ -31,7 +31,7 @@ process CNVKIT_BATCH {
     // input pair is assumed to have same extension if both exist
     def is_cram = tumor.Extension == "cram" ? true : false
     def tumor_out = is_cram ? tumor.BaseName + ".bam" : "${tumor}"
-    // do not run samtools on normal samples in tumor_only
+    // do not run samtools on normal samples in tumor_only mode
     def normal_exists = normal ? true: false
     // tumor_only mode does not need fasta & target
     // instead it requires a pre-computed reference which is built from fasta & target

From 153c900d0e8c2e871a984bf40fb92a06ed019ae7 Mon Sep 17 00:00:00 2001
From: SusiJo <43847534+SusiJo@users.noreply.github.com>
Date: Fri, 20 May 2022 13:08:38 +0200
Subject: [PATCH 09/19] refine comment

Co-authored-by: FriederikeHanssen <Friederike.hanssen@qbic.uni-tuebingen.de>
---
 modules/cnvkit/batch/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/cnvkit/batch/main.nf b/modules/cnvkit/batch/main.nf
index 55e3ee6b..c3a4ba32 100644
--- a/modules/cnvkit/batch/main.nf
+++ b/modules/cnvkit/batch/main.nf
@@ -34,7 +34,7 @@ process CNVKIT_BATCH {
     // do not run samtools on normal samples in tumor_only mode
     def normal_exists = normal ? true: false
     // tumor_only mode does not need fasta & target
-    // instead it requires a pre-computed reference which is built from fasta & target
+    // instead it requires a pre-computed reference.cnn which is built from fasta & target
     def (normal_out, normal_args, fasta_args, target_args) = ["", "", "", ""]
     def reference_args = reference ? "--reference $reference" : ""
 

From bdf222649d04fc2748d5247e02aa7fd7a1646a70 Mon Sep 17 00:00:00 2001
From: SusiJo <susanne.jodoin@gmx.de>
Date: Fri, 20 May 2022 13:25:57 +0200
Subject: [PATCH 10/19] remove unnecessary if statement

---
 modules/cnvkit/batch/main.nf | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/modules/cnvkit/batch/main.nf b/modules/cnvkit/batch/main.nf
index c3a4ba32..66cfe8b2 100644
--- a/modules/cnvkit/batch/main.nf
+++ b/modules/cnvkit/batch/main.nf
@@ -27,7 +27,7 @@ process CNVKIT_BATCH {
 
     script:
     def args = task.ext.args ?: ''
-    // execute samtools only when cram files are input, cnvkit runs natively on bam but is prohibitively slow 
+    // execute samtools only when cram files are input, cnvkit runs natively on bam but is prohibitively slow
     // input pair is assumed to have same extension if both exist
     def is_cram = tumor.Extension == "cram" ? true : false
     def tumor_out = is_cram ? tumor.BaseName + ".bam" : "${tumor}"
@@ -35,7 +35,8 @@ process CNVKIT_BATCH {
     def normal_exists = normal ? true: false
     // tumor_only mode does not need fasta & target
     // instead it requires a pre-computed reference.cnn which is built from fasta & target
-    def (normal_out, normal_args, fasta_args, target_args) = ["", "", "", ""]
+    def (normal_out, normal_args, fasta_args) = ["", "", ""]
+    def target_args = targets ? "--targets $targets" : ""
     def reference_args = reference ? "--reference $reference" : ""
 
     if (normal_exists){
@@ -45,13 +46,6 @@ process CNVKIT_BATCH {
         fasta_args = fasta ? "--fasta $fasta" : ""
     }
 
-    if (args.contains("--method wgs") || args.contains("-m wgs")) {
-        target_args = targets ? "--targets $targets" : ""
-    }
-    else {
-        target_args = "--targets $targets"
-    }
-
     """
     if $is_cram; then
         samtools view -T $fasta $tumor -@ $task.cpus -o $tumor_out

From 9096be5464d800156761b7c73c574f5a5bad2f72 Mon Sep 17 00:00:00 2001
From: SusiJo <susanne.jodoin@gmx.de>
Date: Fri, 20 May 2022 13:29:49 +0200
Subject: [PATCH 11/19] improve readability

---
 modules/cnvkit/batch/main.nf | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/modules/cnvkit/batch/main.nf b/modules/cnvkit/batch/main.nf
index 66cfe8b2..c1f9ef87 100644
--- a/modules/cnvkit/batch/main.nf
+++ b/modules/cnvkit/batch/main.nf
@@ -27,17 +27,17 @@ process CNVKIT_BATCH {
 
     script:
     def args = task.ext.args ?: ''
+
     // execute samtools only when cram files are input, cnvkit runs natively on bam but is prohibitively slow
     // input pair is assumed to have same extension if both exist
     def is_cram = tumor.Extension == "cram" ? true : false
     def tumor_out = is_cram ? tumor.BaseName + ".bam" : "${tumor}"
+
     // do not run samtools on normal samples in tumor_only mode
     def normal_exists = normal ? true: false
     // tumor_only mode does not need fasta & target
     // instead it requires a pre-computed reference.cnn which is built from fasta & target
     def (normal_out, normal_args, fasta_args) = ["", "", ""]
-    def target_args = targets ? "--targets $targets" : ""
-    def reference_args = reference ? "--reference $reference" : ""
 
     if (normal_exists){
         def normal_prefix = normal.BaseName
@@ -46,6 +46,9 @@ process CNVKIT_BATCH {
         fasta_args = fasta ? "--fasta $fasta" : ""
     }
 
+    def target_args = targets ? "--targets $targets" : ""
+    def reference_args = reference ? "--reference $reference" : ""
+
     """
     if $is_cram; then
         samtools view -T $fasta $tumor -@ $task.cpus -o $tumor_out

From 4f9d672e55bc42d24fcc9e197e1ea7d86c1d2dd0 Mon Sep 17 00:00:00 2001
From: SusiJo <susanne.jodoin@gmx.de>
Date: Mon, 23 May 2022 16:52:06 +0200
Subject: [PATCH 12/19] added new module cnvkit/antitarget

---
 modules/cnvkit/antitarget/main.nf             | 40 +++++++++++++++++
 modules/cnvkit/antitarget/meta.yml            | 44 +++++++++++++++++++
 tests/config/pytest_modules.yml               |  4 ++
 tests/modules/cnvkit/antitarget/main.nf       | 16 +++++++
 .../modules/cnvkit/antitarget/nextflow.config |  5 +++
 tests/modules/cnvkit/antitarget/test.yml      |  8 ++++
 6 files changed, 117 insertions(+)
 create mode 100644 modules/cnvkit/antitarget/main.nf
 create mode 100644 modules/cnvkit/antitarget/meta.yml
 create mode 100644 tests/modules/cnvkit/antitarget/main.nf
 create mode 100644 tests/modules/cnvkit/antitarget/nextflow.config
 create mode 100644 tests/modules/cnvkit/antitarget/test.yml

diff --git a/modules/cnvkit/antitarget/main.nf b/modules/cnvkit/antitarget/main.nf
new file mode 100644
index 00000000..af2d7558
--- /dev/null
+++ b/modules/cnvkit/antitarget/main.nf
@@ -0,0 +1,40 @@
+
+process CNVKIT_ANTITARGET {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::cnvkit=0.9.9" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/cnvkit:0.9.9--pyhdfd78af_0':
+        'quay.io/biocontainers/cnvkit:0.9.9--pyhdfd78af_0' }"
+
+    input:
+
+    tuple val(meta), path(targets)
+
+    output:
+
+    tuple val(meta), path("*.bed"), emit: bed
+
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    cnvkit.py \\
+        antitarget \\
+        $targets \\
+        --output ${prefix}.antitarget.bed \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+    END_VERSIONS
+    """
+}
diff --git a/modules/cnvkit/antitarget/meta.yml b/modules/cnvkit/antitarget/meta.yml
new file mode 100644
index 00000000..28a2bfa4
--- /dev/null
+++ b/modules/cnvkit/antitarget/meta.yml
@@ -0,0 +1,44 @@
+name: cnvkit_antitarget
+description:
+keywords:
+  - cvnkit
+  - antitarget
+tools:
+  - cnvkit:
+      description: |
+        CNVkit is a Python library and command-line software toolkit to infer and visualize copy number from high-throughput DNA sequencing data.
+        It is designed for use with hybrid capture, including both whole-exome and custom target panels, and short-read sequencing platforms such as Illumina and Ion Torrent.
+      homepage: https://cnvkit.readthedocs.io/en/stable/index.html
+      documentation: https://cnvkit.readthedocs.io/en/stable/index.html
+      tool_dev_url: "https://github.com/etal/cnvkit"
+      doi: 10.1371/journal.pcbi.1004873
+      licence: ["Apache-2.0"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - targets:
+      type: file
+      description: File containing genomic regions
+      pattern: "*.{bed}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bed:
+      type: file
+      description: File containing off-target regions
+      pattern: "*.{bed}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@SusiJo"
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index c1aeb0c6..7aa4b64d 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -447,6 +447,10 @@ cmseq/polymut:
   - modules/cmseq/polymut/**
   - tests/modules/cmseq/polymut/**
 
+cnvkit/antitarget:
+  - modules/cnvkit/antitarget/**
+  - tests/modules/cnvkit/antitarget/**
+
 cnvkit/batch:
   - modules/cnvkit/batch/**
   - tests/modules/cnvkit/batch/**
diff --git a/tests/modules/cnvkit/antitarget/main.nf b/tests/modules/cnvkit/antitarget/main.nf
new file mode 100644
index 00000000..44e49eb2
--- /dev/null
+++ b/tests/modules/cnvkit/antitarget/main.nf
@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CNVKIT_ANTITARGET } from '../../../../modules/cnvkit/antitarget/main.nf'
+
+workflow test_cnvkit_antitarget {
+
+    input = [
+        [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
+    ]
+
+    CNVKIT_ANTITARGET ( input )
+}
+
diff --git a/tests/modules/cnvkit/antitarget/nextflow.config b/tests/modules/cnvkit/antitarget/nextflow.config
new file mode 100644
index 00000000..50f50a7a
--- /dev/null
+++ b/tests/modules/cnvkit/antitarget/nextflow.config
@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}
\ No newline at end of file
diff --git a/tests/modules/cnvkit/antitarget/test.yml b/tests/modules/cnvkit/antitarget/test.yml
new file mode 100644
index 00000000..e1c3d0c8
--- /dev/null
+++ b/tests/modules/cnvkit/antitarget/test.yml
@@ -0,0 +1,8 @@
+- name: cnvkit antitarget test_cnvkit_antitarget
+  command: nextflow run ./tests/modules/cnvkit/antitarget -entry test_cnvkit_antitarget -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/antitarget/nextflow.config
+  tags:
+    - cnvkit
+    - cnvkit/antitarget
+  files:
+    - path: output/cnvkit/test.antitarget.bed
+      md5sum: 3d4d20f9f23b39970865d29ef239d20b

From bbee9e3c3bea54e8cedc0d8ec68619b1d05dae2e Mon Sep 17 00:00:00 2001
From: SusiJo <susanne.jodoin@gmx.de>
Date: Mon, 23 May 2022 18:35:50 +0200
Subject: [PATCH 13/19] add new module cnvkit/reference

---
 modules/cnvkit/reference/main.nf              | 39 +++++++++++++++
 modules/cnvkit/reference/meta.yml             | 47 +++++++++++++++++++
 tests/config/pytest_modules.yml               |  4 ++
 tests/modules/cnvkit/reference/main.nf        | 14 ++++++
 .../modules/cnvkit/reference/nextflow.config  |  5 ++
 tests/modules/cnvkit/reference/test.yml       |  8 ++++
 6 files changed, 117 insertions(+)
 create mode 100644 modules/cnvkit/reference/main.nf
 create mode 100644 modules/cnvkit/reference/meta.yml
 create mode 100644 tests/modules/cnvkit/reference/main.nf
 create mode 100644 tests/modules/cnvkit/reference/nextflow.config
 create mode 100644 tests/modules/cnvkit/reference/test.yml

diff --git a/modules/cnvkit/reference/main.nf b/modules/cnvkit/reference/main.nf
new file mode 100644
index 00000000..1f0b20d8
--- /dev/null
+++ b/modules/cnvkit/reference/main.nf
@@ -0,0 +1,39 @@
+process CNVKIT_REFERENCE {
+    tag "$reference"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::cnvkit=0.9.9" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/cnvkit:0.9.9--pyhdfd78af_0':
+        'quay.io/biocontainers/cnvkit:0.9.9--pyhdfd78af_0' }"
+
+    input:
+    path    fasta
+    path    targets
+    path    antitargets
+
+    output:
+    path("*.cnn")                 , emit: cnn
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+
+    """
+    cnvkit.py \\
+        reference \\
+        --fasta $fasta \\
+        --targets $targets \\
+        --antitargets $antitargets \\
+        --output reference.cnn \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+    END_VERSIONS
+    """
+}
diff --git a/modules/cnvkit/reference/meta.yml b/modules/cnvkit/reference/meta.yml
new file mode 100644
index 00000000..2e0fef1a
--- /dev/null
+++ b/modules/cnvkit/reference/meta.yml
@@ -0,0 +1,47 @@
+name: cnvkit_reference
+description:
+keywords:
+  - cnvkit
+  - reference
+tools:
+  - cnvkit:
+      description: |
+        CNVkit is a Python library and command-line software toolkit to infer and visualize copy number from high-throughput DNA sequencing data.
+        It is designed for use with hybrid capture, including both whole-exome and custom target panels, and short-read sequencing platforms such as Illumina and Ion Torrent.
+      homepage: https://cnvkit.readthedocs.io/en/stable/index.html
+      documentation: https://cnvkit.readthedocs.io/en/stable/index.html
+      tool_dev_url: https://github.com/etal/cnvkit
+      doi: 10.1371/journal.pcbi.1004873
+      licence: ["Apache-2.0"]
+
+input:
+  - fasta:
+      type: file
+      description: File containing reference genome
+      pattern: "*.{fasta}"
+  - targets:
+      type: file
+      description: File containing genomic regions
+      pattern: "*.{bed}"
+  - antitargets:
+      type: file
+      description: File containing off-target genomic regions
+      pattern: "*.{bed}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reference:
+      type: file
+      description: File containing a copy-number reference (required for CNV calling in tumor_only mode)
+      pattern: "*.{cnn}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@SusiJo"
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index 78e85487..0e5a1815 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -451,6 +451,10 @@ cnvkit/batch:
   - modules/cnvkit/batch/**
   - tests/modules/cnvkit/batch/**
 
+cnvkit/reference:
+  - modules/cnvkit/reference/**
+  - tests/modules/cnvkit/reference/**
+
 controlfreec/assesssignificance:
   - modules/controlfreec/assesssignificance/**
   - tests/modules/controlfreec/assesssignificance/**
diff --git a/tests/modules/cnvkit/reference/main.nf b/tests/modules/cnvkit/reference/main.nf
new file mode 100644
index 00000000..bd7009c0
--- /dev/null
+++ b/tests/modules/cnvkit/reference/main.nf
@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CNVKIT_REFERENCE } from '../../../../modules/cnvkit/reference/main.nf'
+
+workflow test_cnvkit_reference {
+
+    fasta       = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
+    targets     = file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
+    antitargets = file("/Users/susanne/Documents/repos/forks/modules/test_antitarget/output/cnvkit/test.antitarget.bed", checkIfExists: true)
+
+    CNVKIT_REFERENCE ( fasta, targets, antitargets )
+}
diff --git a/tests/modules/cnvkit/reference/nextflow.config b/tests/modules/cnvkit/reference/nextflow.config
new file mode 100644
index 00000000..50f50a7a
--- /dev/null
+++ b/tests/modules/cnvkit/reference/nextflow.config
@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}
\ No newline at end of file
diff --git a/tests/modules/cnvkit/reference/test.yml b/tests/modules/cnvkit/reference/test.yml
new file mode 100644
index 00000000..b1b8c896
--- /dev/null
+++ b/tests/modules/cnvkit/reference/test.yml
@@ -0,0 +1,8 @@
+- name: cnvkit reference test_cnvkit_reference
+  command: nextflow run ./tests/modules/cnvkit/reference -entry test_cnvkit_reference -c ./tests/config/nextflow.config  -c ./tests/modules/cnvkit/reference/nextflow.config
+  tags:
+    - cnvkit/reference
+    - cnvkit
+  files:
+    - path: output/cnvkit/reference.cnn
+      md5sum: 7c4a7902f5ab101b1f9d6038d331b3d9

From ddb964a4bf33b4026a31a25778a7ee26df0da1d6 Mon Sep 17 00:00:00 2001
From: SusiJo <43847534+SusiJo@users.noreply.github.com>
Date: Mon, 23 May 2022 18:48:04 +0200
Subject: [PATCH 14/19] rm line

Co-authored-by: FriederikeHanssen <Friederike.hanssen@qbic.uni-tuebingen.de>
---
 modules/cnvkit/antitarget/main.nf | 1 -
 1 file changed, 1 deletion(-)

diff --git a/modules/cnvkit/antitarget/main.nf b/modules/cnvkit/antitarget/main.nf
index af2d7558..f0516eeb 100644
--- a/modules/cnvkit/antitarget/main.nf
+++ b/modules/cnvkit/antitarget/main.nf
@@ -1,4 +1,3 @@
-
 process CNVKIT_ANTITARGET {
     tag "$meta.id"
     label 'process_low'

From 24905e26e2dcf8cacadee54c7b280d8bda511da4 Mon Sep 17 00:00:00 2001
From: SusiJo <43847534+SusiJo@users.noreply.github.com>
Date: Mon, 23 May 2022 18:48:13 +0200
Subject: [PATCH 15/19] rm line

Co-authored-by: FriederikeHanssen <Friederike.hanssen@qbic.uni-tuebingen.de>
---
 modules/cnvkit/antitarget/main.nf | 1 -
 1 file changed, 1 deletion(-)

diff --git a/modules/cnvkit/antitarget/main.nf b/modules/cnvkit/antitarget/main.nf
index f0516eeb..6c092a31 100644
--- a/modules/cnvkit/antitarget/main.nf
+++ b/modules/cnvkit/antitarget/main.nf
@@ -8,7 +8,6 @@ process CNVKIT_ANTITARGET {
         'quay.io/biocontainers/cnvkit:0.9.9--pyhdfd78af_0' }"
 
     input:
-
     tuple val(meta), path(targets)
 
     output:

From 86b5951c14eaf5a11376f2fd8abd6a912bdfb214 Mon Sep 17 00:00:00 2001
From: SusiJo <43847534+SusiJo@users.noreply.github.com>
Date: Mon, 23 May 2022 18:48:30 +0200
Subject: [PATCH 16/19] rm line

Co-authored-by: FriederikeHanssen <Friederike.hanssen@qbic.uni-tuebingen.de>
---
 modules/cnvkit/antitarget/main.nf | 1 -
 1 file changed, 1 deletion(-)

diff --git a/modules/cnvkit/antitarget/main.nf b/modules/cnvkit/antitarget/main.nf
index 6c092a31..a3181daa 100644
--- a/modules/cnvkit/antitarget/main.nf
+++ b/modules/cnvkit/antitarget/main.nf
@@ -11,7 +11,6 @@ process CNVKIT_ANTITARGET {
     tuple val(meta), path(targets)
 
     output:
-
     tuple val(meta), path("*.bed"), emit: bed
 
     path "versions.yml"           , emit: versions

From 58c5ec2f4eb44eff1fb7cc9e02df07bd448c6aaf Mon Sep 17 00:00:00 2001
From: SusiJo <43847534+SusiJo@users.noreply.github.com>
Date: Mon, 23 May 2022 18:53:28 +0200
Subject: [PATCH 17/19] rm line

Co-authored-by: FriederikeHanssen <Friederike.hanssen@qbic.uni-tuebingen.de>
---
 modules/cnvkit/antitarget/main.nf | 1 -
 1 file changed, 1 deletion(-)

diff --git a/modules/cnvkit/antitarget/main.nf b/modules/cnvkit/antitarget/main.nf
index a3181daa..bf6461bd 100644
--- a/modules/cnvkit/antitarget/main.nf
+++ b/modules/cnvkit/antitarget/main.nf
@@ -12,7 +12,6 @@ process CNVKIT_ANTITARGET {
 
     output:
     tuple val(meta), path("*.bed"), emit: bed
-
     path "versions.yml"           , emit: versions
 
     when:

From 8fec7ae3218020fc305ba14fe19720783b8baf1c Mon Sep 17 00:00:00 2001
From: SusiJo <susanne.jodoin@gmx.de>
Date: Mon, 23 May 2022 19:01:46 +0200
Subject: [PATCH 18/19] added new testdata path

---
 tests/config/test_data.config          | 1 +
 tests/modules/cnvkit/reference/main.nf | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/tests/config/test_data.config b/tests/config/test_data.config
index cf7d45f6..39331664 100644
--- a/tests/config/test_data.config
+++ b/tests/config/test_data.config
@@ -142,6 +142,7 @@ params {
                 genome_21_sizes                                = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.sizes"
                 genome_21_interval_list                        = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.interval_list"
                 genome_21_multi_interval_bed                   = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed"
+                genome_21_multi_interval_antitarget_bed        = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.antitarget.bed"
                 genome_21_multi_interval_bed_gz                = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed.gz"
                 genome_21_multi_interval_bed_gz_tbi            = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed.gz.tbi"
                 genome_21_chromosomes_dir                      = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/chromosomes.tar.gz"
diff --git a/tests/modules/cnvkit/reference/main.nf b/tests/modules/cnvkit/reference/main.nf
index bd7009c0..a72ad566 100644
--- a/tests/modules/cnvkit/reference/main.nf
+++ b/tests/modules/cnvkit/reference/main.nf
@@ -8,7 +8,7 @@ workflow test_cnvkit_reference {
 
     fasta       = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
     targets     = file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
-    antitargets = file("/Users/susanne/Documents/repos/forks/modules/test_antitarget/output/cnvkit/test.antitarget.bed", checkIfExists: true)
+    antitargets = file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_antitarget_bed'], checkIfExists: true)
 
     CNVKIT_REFERENCE ( fasta, targets, antitargets )
 }

From 1451d62be43f62045d3b30c36a51afacfb3cf1c0 Mon Sep 17 00:00:00 2001
From: SusiJo <susanne.jodoin@gmx.de>
Date: Tue, 24 May 2022 07:38:53 +0200
Subject: [PATCH 19/19] rm md5sums for empty files

---
 tests/modules/cnvkit/batch/test.yml | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/tests/modules/cnvkit/batch/test.yml b/tests/modules/cnvkit/batch/test.yml
index 9bce265a..00d6a767 100755
--- a/tests/modules/cnvkit/batch/test.yml
+++ b/tests/modules/cnvkit/batch/test.yml
@@ -5,7 +5,6 @@
     - cnvkit/batch
   files:
     - path: output/cnvkit/baits.antitarget.bed
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/cnvkit/baits.target.bed
       md5sum: 26d25ff2d6c45b6d92169b3559c6acdb
     - path: output/cnvkit/reference.cnn
@@ -34,7 +33,6 @@
     - cnvkit/batch
   files:
     - path: output/cnvkit/genome.antitarget.bed
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/cnvkit/genome.bed
       md5sum: 87a15eb9c2ff20ccd5cd8735a28708f7
     - path: output/cnvkit/genome.target.bed
@@ -65,7 +63,6 @@
     - cnvkit/batch
   files:
     - path: output/cnvkit/genome.antitarget.bed
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/cnvkit/genome.bed
       md5sum: 87a15eb9c2ff20ccd5cd8735a28708f7
     - path: output/cnvkit/genome.target.bed
@@ -96,7 +93,6 @@
     - cnvkit/batch
   files:
     - path: output/cnvkit/reference.antitarget-tmp.bed
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/cnvkit/reference.target-tmp.bed
       md5sum: 26d25ff2d6c45b6d92169b3559c6acdb
 
@@ -107,6 +103,5 @@
     - cnvkit/batch
   files:
     - path: output/cnvkit/reference.antitarget-tmp.bed
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/cnvkit/reference.target-tmp.bed
       md5sum: 26d25ff2d6c45b6d92169b3559c6acdb