From b008ea1d2a54e0cd03dac09b01c37c27e264c997 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 17 Feb 2021 10:01:45 +0100
Subject: [PATCH 01/22] Added process CheckContamination. Based on
 best-practices WDL from BroadInstitute. The process runs verifyBamID to
 retrieve estimation table and calculate contamination float.

---
 .../2.0.1--h32f71e1_0/CheckContamination.nf   | 56 +++++++++++++++++++
 1 file changed, 56 insertions(+)
 create mode 100644 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
new file mode 100644
index 00000000..98137ae5
--- /dev/null
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -0,0 +1,56 @@
+process CheckContamination {
+    tag {"VerifyBamID CheckContamination ${sample_id}.${int_tag}"}
+    label 'VERIFYBAMID_2_0_1_h32f71e1_0'
+    label 'VERIFYBAMID_2_0_1_h32f71e1_0_CheckContamination'
+    container = 'quay.io/biocontainers/verifybamid2:2.0.1--h32f71e1_0'
+    shell = ['/bin/bash', '-euo', 'pipefail']
+
+    input:
+        tuple (sample_id, path(bam), path(bai)))
+
+    output:
+        tuple(sample_id, path("${output_prefix}.selfSM"), stdout(contamination))
+
+    script:
+        output_prefix = ${sample_id}.${params.library_strategy}.contamination
+
+        """
+        # creates a ${output_prefix}.selfSM file, a TSV file with 2 rows, 19 columns.
+        # First row are the keys (e.g., SEQ_SM, RG, FREEMIX), second row are the associated values
+        VerifyBamID \
+        --Verbose \
+        --NumPC 4 \
+        --Output  ${output_prefix} \
+        --BamFile ${bam} \
+        --Reference ${params.genome_fasta} \
+        --UDPath ${params.contamination_sites_ud} \
+        --MeanPath ${params.contamination_sites_mu} \
+        --BedPath ${params.contamination_sites_bed} \
+        1>/dev/null
+
+        # used to read from the selfSM file and calculate contamination, which gets printed out
+        python3 <<CODE
+        import csv
+        import sys
+        with open('${output_prefix}.selfSM') as selfSM:
+        reader = csv.DictReader(selfSM, delimiter='\t')
+        i = 0
+        for row in reader:
+            if float(row["FREELK0"])==0 and float(row["FREELK1"])==0:
+            # a zero value for the likelihoods implies no data. This usually indicates a problem rather than a real event.
+            # if the bam isn't really empty, this is probably due to the use of a incompatible reference build between
+            # vcf and bam.
+            sys.stderr.write("Found zero likelihoods. Bam is either very-very shallow, or aligned to the wrong reference (relative to the vcf).")
+            sys.exit(1)
+            print(float(row["FREEMIX"])/${params.contamination_underestimation_factor})
+            i = i + 1
+            # there should be exactly one row, and if this isn't the case the format of the output is unexpectedly different
+            # and the results are not reliable.
+            if i != 1:
+            sys.stderr.write("Found %d rows in .selfSM file. Was expecting exactly 1. This is an error"%(i))
+            sys.exit(2)
+        CODE
+  
+        """
+
+}

From 5085b10cd804db745e101bf3e278892ad277c2f3 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 17 Feb 2021 11:13:48 +0100
Subject: [PATCH 02/22] typo

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index 98137ae5..f1cb9d8e 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -6,7 +6,7 @@ process CheckContamination {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-        tuple (sample_id, path(bam), path(bai)))
+        tuple (sample_id, path(bam), path(bai))
 
     output:
         tuple(sample_id, path("${output_prefix}.selfSM"), stdout(contamination))

From f45a16409a6cd357f00084fcd018205d33bcd607 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 17 Feb 2021 11:26:16 +0100
Subject: [PATCH 03/22] Trying out to capture stdout and provide it as part of
 output tuple.

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index f1cb9d8e..00970f0e 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -9,7 +9,7 @@ process CheckContamination {
         tuple (sample_id, path(bam), path(bai))
 
     output:
-        tuple(sample_id, path("${output_prefix}.selfSM"), stdout(contamination))
+        tuple(sample_id, path("${output_prefix}.selfSM"), stdout())
 
     script:
         output_prefix = ${sample_id}.${params.library_strategy}.contamination

From ae3bf5cfbb8792eaab9587704cd246efa98bf454 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 17 Feb 2021 11:36:19 +0100
Subject: [PATCH 04/22] stdout without brackets.

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index 00970f0e..16477365 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -9,7 +9,7 @@ process CheckContamination {
         tuple (sample_id, path(bam), path(bai))
 
     output:
-        tuple(sample_id, path("${output_prefix}.selfSM"), stdout())
+        tuple(sample_id, path("${output_prefix}.selfSM"), stdout)
 
     script:
         output_prefix = ${sample_id}.${params.library_strategy}.contamination

From 4986dfa19bf654c846d78b1c30d902da38652d78 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 17 Feb 2021 14:18:58 +0100
Subject: [PATCH 05/22] Without python code to test if verifyBamID can succeed.

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index 16477365..98aa6894 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -9,7 +9,7 @@ process CheckContamination {
         tuple (sample_id, path(bam), path(bai))
 
     output:
-        tuple(sample_id, path("${output_prefix}.selfSM"), stdout)
+        tuple (sample_id, path("${output_prefix}.selfSM"))
 
     script:
         output_prefix = ${sample_id}.${params.library_strategy}.contamination
@@ -28,6 +28,8 @@ process CheckContamination {
         --BedPath ${params.contamination_sites_bed} \
         1>/dev/null
 
+        """
+        /*
         # used to read from the selfSM file and calculate contamination, which gets printed out
         python3 <<CODE
         import csv
@@ -50,7 +52,6 @@ process CheckContamination {
             sys.stderr.write("Found %d rows in .selfSM file. Was expecting exactly 1. This is an error"%(i))
             sys.exit(2)
         CODE
-  
-        """
+        */
 
 }

From c70aca1fcf6ddc305f3862299db52bba08b483a6 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 17 Feb 2021 15:06:45 +0100
Subject: [PATCH 06/22] adding emit.

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index 98aa6894..b7c24a8a 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -9,7 +9,7 @@ process CheckContamination {
         tuple (sample_id, path(bam), path(bai))
 
     output:
-        tuple (sample_id, path("${output_prefix}.selfSM"))
+        tuple (sample_id, path("${output_prefix}.selfSM"), emit:contamination)
 
     script:
         output_prefix = ${sample_id}.${params.library_strategy}.contamination

From fc4c3552140713cfec4b9e9c07e8fd8ce7d41808 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 17 Feb 2021 15:19:50 +0100
Subject: [PATCH 07/22] define script variable.

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index b7c24a8a..b50179ed 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -12,7 +12,7 @@ process CheckContamination {
         tuple (sample_id, path("${output_prefix}.selfSM"), emit:contamination)
 
     script:
-        output_prefix = ${sample_id}.${params.library_strategy}.contamination
+        def output_prefix = "${sample_id}.${params.library_strategy}.contamination"
 
         """
         # creates a ${output_prefix}.selfSM file, a TSV file with 2 rows, 19 columns.

From 84c98a4e9a1515c41ee61f69b1705bb03201bcda Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 17 Feb 2021 15:59:11 +0100
Subject: [PATCH 08/22] typo

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index b50179ed..c38b3ed5 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -17,7 +17,7 @@ process CheckContamination {
         """
         # creates a ${output_prefix}.selfSM file, a TSV file with 2 rows, 19 columns.
         # First row are the keys (e.g., SEQ_SM, RG, FREEMIX), second row are the associated values
-        VerifyBamID \
+        verifyBamID \
         --Verbose \
         --NumPC 4 \
         --Output  ${output_prefix} \

From d2c3a0ef195ce94abd6be0af837ca07521e671e8 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 17 Feb 2021 16:14:08 +0100
Subject: [PATCH 09/22] verifybamid2 with lowercase.

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index c38b3ed5..5f702718 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -17,7 +17,7 @@ process CheckContamination {
         """
         # creates a ${output_prefix}.selfSM file, a TSV file with 2 rows, 19 columns.
         # First row are the keys (e.g., SEQ_SM, RG, FREEMIX), second row are the associated values
-        verifyBamID \
+        verifybamid2 \
         --Verbose \
         --NumPC 4 \
         --Output  ${output_prefix} \

From 49bef7e59db1ba9fa2c2a0b536fe23475e7ba7ac Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 17 Feb 2021 16:24:06 +0100
Subject: [PATCH 10/22] Added contamination_path_prefix

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index 5f702718..fef3d983 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -18,14 +18,15 @@ process CheckContamination {
         # creates a ${output_prefix}.selfSM file, a TSV file with 2 rows, 19 columns.
         # First row are the keys (e.g., SEQ_SM, RG, FREEMIX), second row are the associated values
         verifybamid2 \
-        --Verbose \
-        --NumPC 4 \
-        --Output  ${output_prefix} \
-        --BamFile ${bam} \
         --Reference ${params.genome_fasta} \
+        --BamFile ${bam} \
+        --SVDPrefix ${params.contamination_path_prefix} \
         --UDPath ${params.contamination_sites_ud} \
         --MeanPath ${params.contamination_sites_mu} \
         --BedPath ${params.contamination_sites_bed} \
+        --Verbose \
+        --NumPC 4 \
+        --Output  ${output_prefix} \
         1>/dev/null
 
         """

From 6191d7594e2ea032233f0ac1ad866aa7ab33599c Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 17 Feb 2021 16:30:14 +0100
Subject: [PATCH 11/22] typo

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index fef3d983..6725cbb6 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -18,7 +18,7 @@ process CheckContamination {
         # creates a ${output_prefix}.selfSM file, a TSV file with 2 rows, 19 columns.
         # First row are the keys (e.g., SEQ_SM, RG, FREEMIX), second row are the associated values
         verifybamid2 \
-        --Reference ${params.genome_fasta} \
+        --Reference ${params.genome} \
         --BamFile ${bam} \
         --SVDPrefix ${params.contamination_path_prefix} \
         --UDPath ${params.contamination_sites_ud} \

From 1bf334b0d19e1a2c31e10bc503b8d7b6934df06b Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Thu, 18 Feb 2021 11:27:17 +0100
Subject: [PATCH 12/22] parameter should not be local to script scope (removed
 'def')

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index 6725cbb6..8d5b655d 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -12,7 +12,7 @@ process CheckContamination {
         tuple (sample_id, path("${output_prefix}.selfSM"), emit:contamination)
 
     script:
-        def output_prefix = "${sample_id}.${params.library_strategy}.contamination"
+        output_prefix = "${sample_id}.${params.library_strategy}.contamination"
 
         """
         # creates a ${output_prefix}.selfSM file, a TSV file with 2 rows, 19 columns.

From 9b12e30844e4b3880a4a4e9a022db5c8705e7076 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Fri, 19 Feb 2021 10:24:23 +0100
Subject: [PATCH 13/22] calculating inpython) contamination float

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index 8d5b655d..b5056a1a 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -9,7 +9,7 @@ process CheckContamination {
         tuple (sample_id, path(bam), path(bai))
 
     output:
-        tuple (sample_id, path("${output_prefix}.selfSM"), emit:contamination)
+        tuple (sample_id, path("${output_prefix}.selfSM"), stdout)
 
     script:
         output_prefix = "${sample_id}.${params.library_strategy}.contamination"
@@ -29,8 +29,6 @@ process CheckContamination {
         --Output  ${output_prefix} \
         1>/dev/null
 
-        """
-        /*
         # used to read from the selfSM file and calculate contamination, which gets printed out
         python3 <<CODE
         import csv
@@ -53,6 +51,5 @@ process CheckContamination {
             sys.stderr.write("Found %d rows in .selfSM file. Was expecting exactly 1. This is an error"%(i))
             sys.exit(2)
         CODE
-        */
-
+        """
 }

From 111672dc78bdb6aac78c6d5dc2a62d06b8f49b8c Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Mon, 22 Feb 2021 09:28:06 +0100
Subject: [PATCH 14/22] format python code and added activation venv

---
 .../2.0.1--h32f71e1_0/CheckContamination.nf   | 37 ++++++++++---------
 1 file changed, 20 insertions(+), 17 deletions(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index b5056a1a..0a52966a 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -29,27 +29,30 @@ process CheckContamination {
         --Output  ${output_prefix} \
         1>/dev/null
 
-        # used to read from the selfSM file and calculate contamination, which gets printed out
+        source ${params.exoncov_path}/venv/bin/activate
+        # read the selfSM file and calculate contamination, which gets printed out
         python3 <<CODE
         import csv
         import sys
         with open('${output_prefix}.selfSM') as selfSM:
-        reader = csv.DictReader(selfSM, delimiter='\t')
-        i = 0
-        for row in reader:
-            if float(row["FREELK0"])==0 and float(row["FREELK1"])==0:
-            # a zero value for the likelihoods implies no data. This usually indicates a problem rather than a real event.
-            # if the bam isn't really empty, this is probably due to the use of a incompatible reference build between
-            # vcf and bam.
-            sys.stderr.write("Found zero likelihoods. Bam is either very-very shallow, or aligned to the wrong reference (relative to the vcf).")
-            sys.exit(1)
-            print(float(row["FREEMIX"])/${params.contamination_underestimation_factor})
-            i = i + 1
-            # there should be exactly one row, and if this isn't the case the format of the output is unexpectedly different
-            # and the results are not reliable.
-            if i != 1:
-            sys.stderr.write("Found %d rows in .selfSM file. Was expecting exactly 1. This is an error"%(i))
-            sys.exit(2)
+            reader = csv.DictReader(selfSM, delimiter='\t')
+            i = 0
+            for row in reader:
+                if float(row["FREELK0"])==0 and float(row["FREELK1"])==0:
+                    sys.stderr.write("Found zero likelihoods. Bam is either very-very shallow, or aligned to the wrong reference (relative to the vcf).")
+                    sys.exit(1)
+                    # a zero value for the likelihoods implies no data. This usually indicates a problem rather than a real event.
+                    # if the bam isn't really empty, this is probably due to the use of a incompatible reference build between
+                    # vcf and bam.
+                
+                print(float(row["FREEMIX"])/${contamination_underestimation_factor})
+                i = i + 1
+                
+                # there should be exactly one row, and if this isn't the case the format of the output is unexpectedly different
+                # and the results are not reliable.
+                if i != 1:
+                    sys.stderr.write("Found %d rows in .selfSM file. Was expecting exactly 1. This is an error"%(i))
+                    sys.exit(2)
         CODE
         """
 }

From 11eab39022e00cd5bdb71e229faeacfcea2da831 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Mon, 22 Feb 2021 10:23:34 +0100
Subject: [PATCH 15/22] typo + split lines

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index 0a52966a..69e42e8e 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -6,10 +6,16 @@ process CheckContamination {
     shell = ['/bin/bash', '-euo', 'pipefail']
 
     input:
-        tuple (sample_id, path(bam), path(bai))
+        tuple (
+            sample_id, 
+            path(bam), 
+            path(bai))
 
     output:
-        tuple (sample_id, path("${output_prefix}.selfSM"), stdout)
+        tuple (
+            sample_id, 
+            path("${output_prefix}.selfSM"), 
+            stdout)
 
     script:
         output_prefix = "${sample_id}.${params.library_strategy}.contamination"
@@ -29,7 +35,7 @@ process CheckContamination {
         --Output  ${output_prefix} \
         1>/dev/null
 
-        source ${params.exoncov_path}/venv/bin/activate
+        source ${params.python_venv_path}/venv/bin/activate
         # read the selfSM file and calculate contamination, which gets printed out
         python3 <<CODE
         import csv

From 876728a56b64de291ce2153f76e3b5b3e80d6294 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Mon, 22 Feb 2021 12:55:42 +0100
Subject: [PATCH 16/22] missed 'params'

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index 69e42e8e..9b0e227f 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -51,7 +51,7 @@ process CheckContamination {
                     # if the bam isn't really empty, this is probably due to the use of a incompatible reference build between
                     # vcf and bam.
                 
-                print(float(row["FREEMIX"])/${contamination_underestimation_factor})
+                print(float(row["FREEMIX"])/${params.contamination_underestimation_factor})
                 i = i + 1
                 
                 # there should be exactly one row, and if this isn't the case the format of the output is unexpectedly different

From 104c4e183f3c25d26d1420fb36f76d9f1fea0059 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Mon, 22 Feb 2021 14:06:10 +0100
Subject: [PATCH 17/22] removed -u, to avoid unbound variable errors.

---
 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
index 9b0e227f..45194373 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
@@ -3,7 +3,7 @@ process CheckContamination {
     label 'VERIFYBAMID_2_0_1_h32f71e1_0'
     label 'VERIFYBAMID_2_0_1_h32f71e1_0_CheckContamination'
     container = 'quay.io/biocontainers/verifybamid2:2.0.1--h32f71e1_0'
-    shell = ['/bin/bash', '-euo', 'pipefail']
+    shell = ['/bin/bash', '-eo', 'pipefail']
 
     input:
         tuple (

From 7c1c9af06a0a712578fdedfbfe4af77230a8fada Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 24 Feb 2021 12:55:28 +0100
Subject: [PATCH 18/22] Pull-request review required changes

---
 .../2.0.1--h32f71e1_0/CheckContamination.nf   | 64 -------------------
 VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf | 32 ++++++++++
 2 files changed, 32 insertions(+), 64 deletions(-)
 delete mode 100644 VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
 create mode 100644 VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf b/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
deleted file mode 100644
index 45194373..00000000
--- a/VerifyBamID/2.0.1--h32f71e1_0/CheckContamination.nf
+++ /dev/null
@@ -1,64 +0,0 @@
-process CheckContamination {
-    tag {"VerifyBamID CheckContamination ${sample_id}.${int_tag}"}
-    label 'VERIFYBAMID_2_0_1_h32f71e1_0'
-    label 'VERIFYBAMID_2_0_1_h32f71e1_0_CheckContamination'
-    container = 'quay.io/biocontainers/verifybamid2:2.0.1--h32f71e1_0'
-    shell = ['/bin/bash', '-eo', 'pipefail']
-
-    input:
-        tuple (
-            sample_id, 
-            path(bam), 
-            path(bai))
-
-    output:
-        tuple (
-            sample_id, 
-            path("${output_prefix}.selfSM"), 
-            stdout)
-
-    script:
-        output_prefix = "${sample_id}.${params.library_strategy}.contamination"
-
-        """
-        # creates a ${output_prefix}.selfSM file, a TSV file with 2 rows, 19 columns.
-        # First row are the keys (e.g., SEQ_SM, RG, FREEMIX), second row are the associated values
-        verifybamid2 \
-        --Reference ${params.genome} \
-        --BamFile ${bam} \
-        --SVDPrefix ${params.contamination_path_prefix} \
-        --UDPath ${params.contamination_sites_ud} \
-        --MeanPath ${params.contamination_sites_mu} \
-        --BedPath ${params.contamination_sites_bed} \
-        --Verbose \
-        --NumPC 4 \
-        --Output  ${output_prefix} \
-        1>/dev/null
-
-        source ${params.python_venv_path}/venv/bin/activate
-        # read the selfSM file and calculate contamination, which gets printed out
-        python3 <<CODE
-        import csv
-        import sys
-        with open('${output_prefix}.selfSM') as selfSM:
-            reader = csv.DictReader(selfSM, delimiter='\t')
-            i = 0
-            for row in reader:
-                if float(row["FREELK0"])==0 and float(row["FREELK1"])==0:
-                    sys.stderr.write("Found zero likelihoods. Bam is either very-very shallow, or aligned to the wrong reference (relative to the vcf).")
-                    sys.exit(1)
-                    # a zero value for the likelihoods implies no data. This usually indicates a problem rather than a real event.
-                    # if the bam isn't really empty, this is probably due to the use of a incompatible reference build between
-                    # vcf and bam.
-                
-                print(float(row["FREEMIX"])/${params.contamination_underestimation_factor})
-                i = i + 1
-                
-                # there should be exactly one row, and if this isn't the case the format of the output is unexpectedly different
-                # and the results are not reliable.
-                if i != 1:
-                    sys.stderr.write("Found %d rows in .selfSM file. Was expecting exactly 1. This is an error"%(i))
-                    sys.exit(2)
-        CODE
-        """
-}
diff --git a/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf b/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf
new file mode 100644
index 00000000..47cc283c
--- /dev/null
+++ b/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf
@@ -0,0 +1,32 @@
+process VerifyBamID2 {
+    tag {"VerifyBamID VerifyBamID2 ${sample_id}.${int_tag}"}
+    label 'VERIFYBAMID_2_0_1_h32f71e1_0'
+    label 'VERIFYBAMID_2_0_1_h32f71e1_0_VerifyBamID2'
+    container = 'quay.io/biocontainers/verifybamid2:2.0.1--h32f71e1_0'
+    shell = ['/bin/bash', '-eo', 'pipefail']
+
+    input:
+        tuple (sample_id, path(bam), path(bai))
+
+    output:
+        tuple (sample_id, path("${output_prefix}.selfSM"), path("${output_prefix}.Ancestry"))
+
+    script:
+        output_prefix = "${sample_id}.contamination"
+
+        """
+        # creates a ${output_prefix}.selfSM file, a TSV file with 2 rows, 19 columns.
+        # First row are the keys (e.g., SEQ_SM, RG, FREEMIX), second row are the associated values
+        verifybamid2 \
+        --Reference ${params.genome} \
+        --BamFile ${bam} \
+        --SVDPrefix ${params.contamination_path_prefix} \
+        --UDPath ${params.contamination_sites_ud} \
+        --MeanPath ${params.contamination_sites_mu} \
+        --BedPath ${params.contamination_sites_bed} \
+        --Verbose \
+        --NumPC 4 \
+        --NumThread ${task.cpus} \
+        --Output  ${output_prefix}
+        """
+}

From d3135537b82e4049645f8d4f40e23aa1474f7643 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 24 Feb 2021 13:00:37 +0100
Subject: [PATCH 19/22] typo

---
 VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf b/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf
index 47cc283c..4a2caa14 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf
@@ -1,5 +1,5 @@
 process VerifyBamID2 {
-    tag {"VerifyBamID VerifyBamID2 ${sample_id}.${int_tag}"}
+    tag {"VerifyBamID VerifyBamID2 ${sample_id}"}
     label 'VERIFYBAMID_2_0_1_h32f71e1_0'
     label 'VERIFYBAMID_2_0_1_h32f71e1_0_VerifyBamID2'
     container = 'quay.io/biocontainers/verifybamid2:2.0.1--h32f71e1_0'

From afbf1f96387ecd570f035c1cb5d494f2d1e9c75b Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 24 Feb 2021 13:02:48 +0100
Subject: [PATCH 20/22] removed duplicate value in tag

---
 VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf b/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf
index 4a2caa14..7fc8bf4a 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf
@@ -1,5 +1,5 @@
 process VerifyBamID2 {
-    tag {"VerifyBamID VerifyBamID2 ${sample_id}"}
+    tag {"VerifyBamID2 ${sample_id}"}
     label 'VERIFYBAMID_2_0_1_h32f71e1_0'
     label 'VERIFYBAMID_2_0_1_h32f71e1_0_VerifyBamID2'
     container = 'quay.io/biocontainers/verifybamid2:2.0.1--h32f71e1_0'

From 48fd0c4a783c2b4f874648556427a71331bf0cc0 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Mon, 29 Mar 2021 10:06:10 +0200
Subject: [PATCH 21/22] Removed ancestry from files.

---
 VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf b/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf
index 7fc8bf4a..6474d414 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf
@@ -9,7 +9,7 @@ process VerifyBamID2 {
         tuple (sample_id, path(bam), path(bai))
 
     output:
-        tuple (sample_id, path("${output_prefix}.selfSM"), path("${output_prefix}.Ancestry"))
+        tuple (sample_id, path("${output_prefix}.selfSM"))
 
     script:
         output_prefix = "${sample_id}.contamination"

From e307a1a659951d5948af2423c6d8086067456329 Mon Sep 17 00:00:00 2001
From: ellendejong <de.jong.ellen@hotmail.com>
Date: Wed, 31 Mar 2021 14:52:15 +0200
Subject: [PATCH 22/22] Switched container, includes exome resources.

---
 .../VerifyBamID2.nf                                         | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
 rename VerifyBamID/{2.0.1--h32f71e1_0 => 2.0.1--h32f71e1_2}/VerifyBamID2.nf (90%)

diff --git a/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf b/VerifyBamID/2.0.1--h32f71e1_2/VerifyBamID2.nf
similarity index 90%
rename from VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf
rename to VerifyBamID/2.0.1--h32f71e1_2/VerifyBamID2.nf
index 6474d414..b185d3c3 100644
--- a/VerifyBamID/2.0.1--h32f71e1_0/VerifyBamID2.nf
+++ b/VerifyBamID/2.0.1--h32f71e1_2/VerifyBamID2.nf
@@ -1,8 +1,8 @@
 process VerifyBamID2 {
     tag {"VerifyBamID2 ${sample_id}"}
-    label 'VERIFYBAMID_2_0_1_h32f71e1_0'
-    label 'VERIFYBAMID_2_0_1_h32f71e1_0_VerifyBamID2'
-    container = 'quay.io/biocontainers/verifybamid2:2.0.1--h32f71e1_0'
+    label 'VERIFYBAMID_2_0_1_h32f71e1_2'
+    label 'VERIFYBAMID_2_0_1_h32f71e1_2_VerifyBamID2'
+    container = 'quay.io/biocontainers/verifybamid2:2.0.1--h32f71e1_2'
     shell = ['/bin/bash', '-eo', 'pipefail']
 
     input: