From ba3fb4f9ce75a929a6ad5b0f5ae6851bbd28d14e Mon Sep 17 00:00:00 2001
From: lindaxiang <linda.xiang@oicr.on.ca>
Date: Wed, 26 Feb 2020 16:47:36 -0500
Subject: [PATCH 01/10] first nf version of sanger wxs

---
 .../sanger-wxs-variant-caller/nextflow.config |  1 +
 .../sanger-wxs-variant-caller.nf              | 90 +++++++++++++++++++
 .../tests/checker.nf                          | 61 +++++++++++++
 .../tests/nextflow.config                     |  1 +
 .../tests/test-job.nf.json                    |  9 ++
 5 files changed, 162 insertions(+)
 create mode 100644 tools/sanger-wxs-variant-caller/nextflow.config
 create mode 100644 tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
 create mode 100644 tools/sanger-wxs-variant-caller/tests/checker.nf
 create mode 100644 tools/sanger-wxs-variant-caller/tests/nextflow.config
 create mode 100644 tools/sanger-wxs-variant-caller/tests/test-job.nf.json

diff --git a/tools/sanger-wxs-variant-caller/nextflow.config b/tools/sanger-wxs-variant-caller/nextflow.config
new file mode 100644
index 0000000..d3af3ea
--- /dev/null
+++ b/tools/sanger-wxs-variant-caller/nextflow.config
@@ -0,0 +1 @@
+docker.enabled = true
diff --git a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
new file mode 100644
index 0000000..42d73d2
--- /dev/null
+++ b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
@@ -0,0 +1,90 @@
+#!/usr/bin/env nextflow
+
+/*
+ * Copyright (c) 2020, Ontario Institute for Cancer Research (OICR).
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program. If not, see <https://www.gnu.org/licenses/>.
+ */
+
+/*
+ * author Linda Xiang <linda.xiang@oicr.on.ca>
+ */
+
+nextflow.preview.dsl=2
+version = '3.1.6-2'
+
+params.reference = ""
+params.annot = ""
+params.snv_indel = ""
+params.tumour = ""
+params.tumourIdx = ""
+params.normal = ""
+params.normalIdx = ""
+params.exclude = "chrUn%,HLA%,%_alt,%_random,chrM,chrEBV"
+params.species = "human"
+params.assembly = "GRCh38"
+params.container_version = ""
+params.cpus = 18
+params.mem = 4  // GB
+
+
+def getSangerSecondaryFiles(main_file){  //this is kind of like CWL's secondary files
+  def all_files = []
+  for (ext in ['.bas']) {
+    all_files.add(main_file + ext)
+  }
+  return all_files
+}
+
+process sangerWxsVariantCall {
+  container "quay.io/icgc-argo/sanger-wxs-variant-caller:sanger-wxs-variant-caller.${params.container_version ?: version}"
+
+  cpus params.cpus
+  memory "${params.mem} GB"
+
+  tag "${tumour.size()}"
+
+  input:
+    path reference
+    path annot
+    path snv_indel
+    path tumour
+    path tidx
+    path tumour_bas
+    path normal
+    path nidex
+    path normal_bas
+
+  output:
+    path "run.params", emit: run_params
+    path "WXS_*_vs_*.result.tar.gz", emit: result_archive
+    path "WXS_*_vs_*.timings.tar.gz", emit: timings
+
+  script:
+    arg_skipqc = params.skipqc ? "-skipqc" : ""
+    """
+    /opt/wtsi-cgp/bin/ds-cgpwxs.pl \
+      -cores ${task.cpus} \
+      -reference reference \
+      -annot annot \
+      -snv_indel snv_indel \
+      -tumour tumour \
+      -tidx tidx \
+      -normal normal \
+      -nidx nidx \
+      -exclude ${params.exclude} \
+      -species ${params.species} \
+      -assembly ${params.assembly}
+    """
+}
diff --git a/tools/sanger-wxs-variant-caller/tests/checker.nf b/tools/sanger-wxs-variant-caller/tests/checker.nf
new file mode 100644
index 0000000..bedd1b7
--- /dev/null
+++ b/tools/sanger-wxs-variant-caller/tests/checker.nf
@@ -0,0 +1,61 @@
+#!/usr/bin/env nextflow
+
+/*
+ * Copyright (c) 2020, Ontario Institute for Cancer Research (OICR).
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program. If not, see <https://www.gnu.org/licenses/>.
+ */
+
+/*
+ * author Linda Xiang <linda.xiang@oicr.on.ca>
+ */
+
+nextflow.preview.dsl=2
+
+params.reference = ""
+params.annot = ""
+params.snv_indel = ""
+params.tumour = ""
+params.tumourIdx = ""
+params.normal = ""
+params.normalIdx = ""
+
+include '../sanger-wxs-variant-caller' params(params)
+
+Channel
+  .fromPath(getSangerSecondaryFiles(params.tumour), checkIfExists: true)
+  .set { tumour_ch }
+
+Channel
+  .fromPath(getSangerSecondaryFiles(params.normal), checkIfExists: true)
+  .set { normal_ch }
+
+// will not run when import as module
+workflow {
+  main:
+    sangerWxsVariantCall(
+      file(params.reference),
+      file(params.annot),
+      file(params.snv_indel),
+      file(params.tumour),
+      file(params.tumourIdx),
+      tumour_ch.collect(),
+      file(params.normal),
+      file(params.normalIdx),
+      normal_ch.collect()
+    )
+
+  publish:
+    sangerWgsVariantCall.out to: "outdir", overwrite: true
+}
diff --git a/tools/sanger-wxs-variant-caller/tests/nextflow.config b/tools/sanger-wxs-variant-caller/tests/nextflow.config
new file mode 100644
index 0000000..a2203e8
--- /dev/null
+++ b/tools/sanger-wxs-variant-caller/tests/nextflow.config
@@ -0,0 +1 @@
+includeConfig '../nextflow.config'
\ No newline at end of file
diff --git a/tools/sanger-wxs-variant-caller/tests/test-job.nf.json b/tools/sanger-wxs-variant-caller/tests/test-job.nf.json
new file mode 100644
index 0000000..6fc5eea
--- /dev/null
+++ b/tools/sanger-wxs-variant-caller/tests/test-job.nf.json
@@ -0,0 +1,9 @@
+{
+  "reference": "",
+  "annot": "",
+  "snv_indel": "",
+  "tumour": "",
+  "tumourIdx": "",
+  "normal": "",
+  "normalIdx": ""
+}
\ No newline at end of file

From bdf2259d921cfe58e05066a5f37cb3db33f54be1 Mon Sep 17 00:00:00 2001
From: lindaxiang <linda.xiang@oicr.on.ca>
Date: Fri, 28 Feb 2020 15:18:36 -0500
Subject: [PATCH 02/10] add -r when using ln create symbolic links to tackle
 the issue from link of link

---
 tools/sanger-wxs-variant-caller/Dockerfile    |   2 +
 .../sanger-wxs-variant-caller/analysisWXS.sh  | 236 ++++++++++++++++++
 .../sanger-wxs-variant-caller.nf              |  18 +-
 .../tests/checker.nf                          |   4 +-
 .../tests/test-job.nf.json                    |   6 +-
 5 files changed, 252 insertions(+), 14 deletions(-)
 create mode 100644 tools/sanger-wxs-variant-caller/analysisWXS.sh

diff --git a/tools/sanger-wxs-variant-caller/Dockerfile b/tools/sanger-wxs-variant-caller/Dockerfile
index 93188c3..9a7d1b0 100644
--- a/tools/sanger-wxs-variant-caller/Dockerfile
+++ b/tools/sanger-wxs-variant-caller/Dockerfile
@@ -1,3 +1,5 @@
 FROM quay.io/wtsicgp/dockstore-cgpwxs:3.1.6
 
+COPY analysisWXS.sh $OPT/bin/analysisWXS.sh
+
 CMD ["/bin/bash"]
diff --git a/tools/sanger-wxs-variant-caller/analysisWXS.sh b/tools/sanger-wxs-variant-caller/analysisWXS.sh
new file mode 100644
index 0000000..fbd876d
--- /dev/null
+++ b/tools/sanger-wxs-variant-caller/analysisWXS.sh
@@ -0,0 +1,236 @@
+#!/bin/bash
+
+# about to do some parallel work...
+declare -A do_parallel
+
+TIME_FORMAT='command:%C\\nreal:%e\\nuser:%U\\nsys:%S\\npctCpu:%P\\ntext:%Xk\\ndata:%Dk\\nmax:%Mk\\n';
+
+# declare function to run parallel processing
+run_parallel () {
+  # adapted from: http://stackoverflow.com/a/18666536/4460430
+  local max_concurrent_tasks=$1
+  local -A pids=()
+
+  for key in "${!do_parallel[@]}"; do
+    while [ $(jobs 2>&1 | grep -c Running) -ge "$max_concurrent_tasks" ]; do
+      sleep 1 # gnu sleep allows floating point here...
+    done
+
+    CMD="/usr/bin/time -f $TIME_FORMAT -o $OUTPUT_DIR/timings/${PROTOCOL}_${NAME_MT}_vs_${NAME_WT}.time.$key ${do_parallel[$key]}"
+
+    echo -e "\tStarting $key"
+    set -x
+    bash -c "$CMD" &
+    set +x
+    pids+=(["$key"]="$!")
+  done
+
+  errors=0
+  for key in "${!do_parallel[@]}"; do
+    pid=${pids[$key]}
+    local cur_ret=0
+    if [ -z "$pid" ]; then
+      echo "No Job ID known for the $key process" # should never happen
+      cur_ret=1
+    else
+      wait $pid
+      cur_ret=$?
+    fi
+    if [ "$cur_ret" -ne 0 ]; then
+      errors=$(($errors + 1))
+      echo "$key (${do_parallel[$key]}) failed."
+    fi
+  done
+
+  return $errors
+}
+
+set -e
+
+echo -e "\nStart workflow: `date`\n"
+
+if [[ $# -eq 1 ]] ; then
+  PARAM_FILE=$1
+elif [ -z ${PARAM_FILE+x} ] ; then
+  PARAM_FILE=$HOME/run.params
+fi
+
+echo "Loading user options from: $PARAM_FILE"
+if [ ! -f $PARAM_FILE ]; then
+  echo -e "\tERROR: file indicated by PARAM_FILE not found: $PARAM_FILE" 1>&2
+  exit 1
+fi
+source $PARAM_FILE
+
+if [ -z ${CPU+x} ]; then
+  CPU=`grep -c ^processor /proc/cpuinfo`
+fi
+
+# create area which allows monitoring site to be started, not actively updated until after PRE-EXEC completes
+#cp -r /opt/wtsi-cgp/site $OUTPUT_DIR/site
+
+echo -e "\tBAM_MT : $BAM_MT"
+echo -e "\tBAM_WT : $BAM_WT"
+
+set -u
+
+TMP=$OUTPUT_DIR/tmp
+mkdir -p $TMP
+mkdir -p $OUTPUT_DIR/timings
+
+## get sample names from BAM headers
+NAME_MT=`samtools view -H $BAM_MT | perl -ne 'chomp; if($_ =~ m/^\@RG/) {($sm) = $_ =~m/\tSM:([^\t]+)/; print "$sm\n";}' | uniq`
+NAME_WT=`samtools view -H $BAM_WT | perl -ne 'chomp; if($_ =~ m/^\@RG/) {($sm) = $_ =~m/\tSM:([^\t]+)/; print "$sm\n";}' | uniq`
+
+echo -e "\tNAME_MT : $NAME_MT"
+echo -e "\tNAME_WT : $NAME_WT"
+
+# capture index extension type (assuming same from both)
+ALN_EXTN='bam'
+IDX_EXTN=''
+if [[ "$IDX_MT" == *.bam.bai ]]; then
+  IDX_EXTN='bam.bai'
+elif [[ "$IDX_MT" == *.bam.csi ]]; then
+  IDX_EXTN='bam.csi'
+elif [[ "$IDX_MT" == *.cram.crai ]]; then
+  IDX_EXTN='cram.crai'
+  ALN_EXTN='cram'
+else
+  echo "Alignment is not BAM or CRAM file: $" >&2
+  exit 1
+fi
+
+BAM_MT_TMP=$TMP/$NAME_MT.$ALN_EXTN
+IDX_MT_TMP=$TMP/$NAME_MT.$IDX_EXTN
+BAM_WT_TMP=$TMP/$NAME_WT.$ALN_EXTN
+IDX_WT_TMP=$TMP/$NAME_WT.$IDX_EXTN
+
+ln -rfs $BAM_MT $BAM_MT_TMP
+ln -rfs $IDX_MT $IDX_MT_TMP
+ln -rfs $BAM_WT $BAM_WT_TMP
+ln -rfs $IDX_WT $IDX_WT_TMP
+
+echo "Setting up Parallel block 1"
+
+if [ ! -f "${BAM_MT}.bas" ]; then
+  echo -e "\t[Parallel block 1] BAS $NAME_MT added..."
+  do_parallel[bas_MT]="bam_stats -i $BAM_MT_TMP -o $BAM_MT_TMP.bas"
+else
+  ln -rfs $BAM_MT.bas $BAM_MT_TMP.bas
+fi
+
+if [ ! -f "${BAM_WT}.bas" ]; then
+  echo -e "\t[Parallel block 1] BAS $NAME_WT added..."
+  do_parallel[bas_WT]="bam_stats -i $BAM_WT_TMP -o $BAM_WT_TMP.bas"
+else
+  ln -rfs $BAM_WT.bas $BAM_WT_TMP.bas
+fi
+
+if [ "$ALN_EXTN" == "cram" ]; then
+  ## prime the cache
+  USER_CACHE=$OUTPUT_DIR/ref_cache
+  export REF_CACHE=$USER_CACHE/%2s/%2s/%s
+  export REF_PATH=$REF_CACHE
+  do_parallel[cache_POP]="seq_cache_populate.pl -root $USER_CACHE $REF_BASE/genome.fa"
+fi
+
+echo "Starting Parallel block 1: `date`"
+run_parallel $CPU do_parallel
+
+# unset and redeclare the parallel array ready for block 2
+unset do_parallel
+declare -A do_parallel
+
+echo -e "\nSetting up Parallel block 2"
+
+echo -e "\t[Parallel block 2] cgpPindel added..."
+do_parallel[cgpPindel]="pindel.pl \
+ -o $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/pindel \
+ -r $REF_BASE/genome.fa \
+ -t $BAM_MT_TMP \
+ -n $BAM_WT_TMP \
+ -s $REF_BASE/pindel/simpleRepeats.bed.gz \
+ -u $REF_BASE/pindel/pindel_np.gff3.gz \
+ -f $REF_BASE/pindel/${PROTOCOL}_Rules.lst \
+ -g $REF_BASE/vagrent/codingexon_regions.indel.bed.gz \
+ -st $PROTOCOL \
+ -as $ASSEMBLY \
+ -sp '$SPECIES' \
+ -e $CONTIG_EXCLUDE \
+ -b $REF_BASE/pindel/HiDepth.bed.gz \
+ -c $CPU \
+ -sf $REF_BASE/pindel/softRules.lst"
+
+# Need empty cn bed for blanket settings
+touch $TMP/empty.cn.bed
+# Need a germline bed even though not used
+echo '#comment' >  $TMP/empty.germline.bed
+
+echo -e "\t[Parallel block 2] CaVEMan added..."
+do_parallel[CaVEMan]="caveman.pl \
+ -r $REF_BASE/genome.fa.fai \
+ -ig $REF_BASE/caveman/HiDepth.tsv \
+ -b $REF_BASE/caveman/flagging \
+ -ab $REF_BASE/vagrent \
+ -u $REF_BASE/caveman \
+ -s '$SPECIES' \
+ -sa $ASSEMBLY \
+ -t $CPU \
+ -st $PROTOCOL \
+ -in $TMP/empty.germline.bed \
+ -tc $TMP/empty.cn.bed \
+ -nc $TMP/empty.cn.bed \
+ -td 5 -nd 2 \
+ -tb $BAM_MT_TMP \
+ -nb $BAM_WT_TMP \
+ -c $SNVFLAG \
+ -f $REF_BASE/caveman/flagging/flag.to.vcf.convert.ini \
+ -o $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/caveman \
+ -np $PROTOCOL \
+ -tp $PROTOCOL \
+ -x $CONTIG_EXCLUDE"
+
+echo "Starting Parallel block 2: `date`"
+run_parallel $CPU do_parallel
+
+# unset and redeclare the parallel array ready for block 3
+unset do_parallel
+declare -A do_parallel
+
+# annotate pindel
+rm -f $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/pindel/${NAME_MT}_vs_${NAME_WT}.annot.vcf.gz*
+echo -e "\t[Parallel block 3] Pindel_annot added..."
+do_parallel[cgpPindel_annot]="AnnotateVcf.pl -t -c $REF_BASE/vagrent/vagrent.cache.gz \
+ -i $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/pindel/${NAME_MT}_vs_${NAME_WT}.flagged.vcf.gz \
+ -o $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/pindel/${NAME_MT}_vs_${NAME_WT}.annot.vcf"
+
+# annotate caveman
+rm -f $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/caveman/${NAME_MT}_vs_${NAME_WT}.annot.muts.vcf.gz*
+echo -e "\t[Parallel block 3] CaVEMan_annot added..."
+do_parallel[CaVEMan_annot]="AnnotateVcf.pl -t -c $REF_BASE/vagrent/vagrent.cache.gz \
+ -i $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/caveman/${NAME_MT}_vs_${NAME_WT}.flagged.muts.vcf.gz \
+ -o $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/caveman/${NAME_MT}_vs_${NAME_WT}.annot.muts.vcf"
+
+echo "Starting Parallel block 3: `date`"
+run_parallel $CPU do_parallel
+
+# clean up log files
+rm -rf $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/*/logs
+
+# cleanup reference area, see ds-cgpwxs.pl
+if [ $CLEAN_REF -gt 0 ]; then
+  rm -rf $REF_BASE
+fi
+
+# cleanup ref cache
+if [ "$ALN_EXTN" == "cram" ]; then
+  rm -rf $USER_CACHE
+fi
+
+echo 'Package results'
+# timings first
+tar -C $OUTPUT_DIR -zcf $OUTPUT_DIR/${PROTOCOL}_${NAME_MT}_vs_${NAME_WT}.timings.tar.gz timings
+tar -C $OUTPUT_DIR -zcf $OUTPUT_DIR/${PROTOCOL}_${NAME_MT}_vs_${NAME_WT}.result.tar.gz ${NAME_MT}_vs_${NAME_WT}
+cp $PARAM_FILE $OUTPUT_DIR/${PROTOCOL}_${NAME_MT}_vs_${NAME_WT}.run.params
+
+echo -e "\nWorkflow end: `date`"
diff --git a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
index 42d73d2..88f3e3e 100644
--- a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
+++ b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
@@ -72,19 +72,19 @@ process sangerWxsVariantCall {
     path "WXS_*_vs_*.timings.tar.gz", emit: timings
 
   script:
-    arg_skipqc = params.skipqc ? "-skipqc" : ""
     """
     /opt/wtsi-cgp/bin/ds-cgpwxs.pl \
       -cores ${task.cpus} \
-      -reference reference \
-      -annot annot \
-      -snv_indel snv_indel \
-      -tumour tumour \
-      -tidx tidx \
-      -normal normal \
-      -nidx nidx \
+      -reference ${reference} \
+      -annot ${annot} \
+      -snv_indel ${snv_indel} \
+      -tumour ${tumour} \
+      -tidx ${tidx} \
+      -normal ${normal} \
+      -nidx ${nidx} \
       -exclude ${params.exclude} \
       -species ${params.species} \
-      -assembly ${params.assembly}
+      -assembly ${params.assembly} \
+      -outdir \$PWD
     """
 }
diff --git a/tools/sanger-wxs-variant-caller/tests/checker.nf b/tools/sanger-wxs-variant-caller/tests/checker.nf
index bedd1b7..372e895 100644
--- a/tools/sanger-wxs-variant-caller/tests/checker.nf
+++ b/tools/sanger-wxs-variant-caller/tests/checker.nf
@@ -31,7 +31,7 @@ params.tumourIdx = ""
 params.normal = ""
 params.normalIdx = ""
 
-include '../sanger-wxs-variant-caller' params(params)
+include sangerWxsVariantCall from '../sanger-wxs-variant-caller' params(params)
 
 Channel
   .fromPath(getSangerSecondaryFiles(params.tumour), checkIfExists: true)
@@ -57,5 +57,5 @@ workflow {
     )
 
   publish:
-    sangerWgsVariantCall.out to: "outdir", overwrite: true
+    sangerWxsVariantCall.out to: "outdir", overwrite: true
 }
diff --git a/tools/sanger-wxs-variant-caller/tests/test-job.nf.json b/tools/sanger-wxs-variant-caller/tests/test-job.nf.json
index 6fc5eea..6eb02ac 100644
--- a/tools/sanger-wxs-variant-caller/tests/test-job.nf.json
+++ b/tools/sanger-wxs-variant-caller/tests/test-job.nf.json
@@ -1,7 +1,7 @@
 {
-  "reference": "",
-  "annot": "",
-  "snv_indel": "",
+  "reference": "https://object.cancercollaboratory.org:9080/swift/v1/genomics-public-data/sanger-variant-calling/core_ref_GRCh38_hla_decoy_ebv.tar.gz",
+  "annot": "https://object.cancercollaboratory.org:9080/swift/v1/genomics-public-data/sanger-variant-calling/VAGrENT_ref_GRCh38_hla_decoy_ebv_ensembl_91.tar.gz",
+  "snv_indel": "https://object.cancercollaboratory.org:9080/swift/v1/genomics-public-data/sanger-variant-calling/SNV_INDEL_ref_GRCh38_hla_decoy_ebv-fragment.tar.gz",
   "tumour": "",
   "tumourIdx": "",
   "normal": "",

From 25cb0263bfda5e85091c0b44bc8c3839e7ed08b5 Mon Sep 17 00:00:00 2001
From: lindaxiang <linda.xiang@oicr.on.ca>
Date: Fri, 28 Feb 2020 15:59:20 -0500
Subject: [PATCH 03/10] make unique function name

---
 .../sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf  | 2 +-
 tools/sanger-wxs-variant-caller/tests/checker.nf            | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
index 88f3e3e..ac3de02 100644
--- a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
+++ b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
@@ -39,7 +39,7 @@ params.cpus = 18
 params.mem = 4  // GB
 
 
-def getSangerSecondaryFiles(main_file){  //this is kind of like CWL's secondary files
+def getSangerWxsSecondaryFiles(main_file){  //this is kind of like CWL's secondary files
   def all_files = []
   for (ext in ['.bas']) {
     all_files.add(main_file + ext)
diff --git a/tools/sanger-wxs-variant-caller/tests/checker.nf b/tools/sanger-wxs-variant-caller/tests/checker.nf
index 372e895..6325c54 100644
--- a/tools/sanger-wxs-variant-caller/tests/checker.nf
+++ b/tools/sanger-wxs-variant-caller/tests/checker.nf
@@ -31,14 +31,14 @@ params.tumourIdx = ""
 params.normal = ""
 params.normalIdx = ""
 
-include sangerWxsVariantCall from '../sanger-wxs-variant-caller' params(params)
+include { sangerWxsVariantCall; getSangerWxsSecondaryFiles } from '../sanger-wxs-variant-caller' params(params)
 
 Channel
-  .fromPath(getSangerSecondaryFiles(params.tumour), checkIfExists: true)
+  .fromPath(getSangerWxsSecondaryFiles(params.tumour), checkIfExists: true)
   .set { tumour_ch }
 
 Channel
-  .fromPath(getSangerSecondaryFiles(params.normal), checkIfExists: true)
+  .fromPath(getSangerWxsSecondaryFiles(params.normal), checkIfExists: true)
   .set { normal_ch }
 
 // will not run when import as module

From ab39d2da3faec6a235e4bb0e1d901fb92465f01e Mon Sep 17 00:00:00 2001
From: lindaxiang <linda.xiang@oicr.on.ca>
Date: Mon, 2 Mar 2020 15:16:51 -0500
Subject: [PATCH 04/10] changes process name to follow naming pattern

---
 .../sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf  | 2 +-
 tools/sanger-wxs-variant-caller/tests/checker.nf            | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
index ac3de02..41bff41 100644
--- a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
+++ b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
@@ -47,7 +47,7 @@ def getSangerWxsSecondaryFiles(main_file){  //this is kind of like CWL's seconda
   return all_files
 }
 
-process sangerWxsVariantCall {
+process sangerWxsVariantCaller {
   container "quay.io/icgc-argo/sanger-wxs-variant-caller:sanger-wxs-variant-caller.${params.container_version ?: version}"
 
   cpus params.cpus
diff --git a/tools/sanger-wxs-variant-caller/tests/checker.nf b/tools/sanger-wxs-variant-caller/tests/checker.nf
index 6325c54..393f1f8 100644
--- a/tools/sanger-wxs-variant-caller/tests/checker.nf
+++ b/tools/sanger-wxs-variant-caller/tests/checker.nf
@@ -31,7 +31,7 @@ params.tumourIdx = ""
 params.normal = ""
 params.normalIdx = ""
 
-include { sangerWxsVariantCall; getSangerWxsSecondaryFiles } from '../sanger-wxs-variant-caller' params(params)
+include { sangerWxsVariantCaller; getSangerWxsSecondaryFiles } from '../sanger-wxs-variant-caller' params(params)
 
 Channel
   .fromPath(getSangerWxsSecondaryFiles(params.tumour), checkIfExists: true)
@@ -44,7 +44,7 @@ Channel
 // will not run when import as module
 workflow {
   main:
-    sangerWxsVariantCall(
+    sangerWxsVariantCaller(
       file(params.reference),
       file(params.annot),
       file(params.snv_indel),
@@ -57,5 +57,5 @@ workflow {
     )
 
   publish:
-    sangerWxsVariantCall.out to: "outdir", overwrite: true
+    sangerWxsVariantCaller.out to: "outdir", overwrite: true
 }

From a5caa3d79aabf7ed1614ffa51c570d103c9828d6 Mon Sep 17 00:00:00 2001
From: lindaxiang <linda.xiang@oicr.on.ca>
Date: Thu, 5 Mar 2020 09:06:30 -0500
Subject: [PATCH 05/10] fix a typo

---
 tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
index 41bff41..4bf1b2b 100644
--- a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
+++ b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
@@ -63,7 +63,7 @@ process sangerWxsVariantCaller {
     path tidx
     path tumour_bas
     path normal
-    path nidex
+    path nidx
     path normal_bas
 
   output:

From bd525c61088f9e54000b40072dbc87b3f6df4cf2 Mon Sep 17 00:00:00 2001
From: Junjun Zhang <junjun.ca@gmail.com>
Date: Thu, 12 Mar 2020 17:12:16 -0400
Subject: [PATCH 06/10] set analysisWXS.sh executable, add .dockerignore file

---
 tools/sanger-wxs-variant-caller/.dockerignore  | 5 +++++
 tools/sanger-wxs-variant-caller/analysisWXS.sh | 0
 2 files changed, 5 insertions(+)
 create mode 100644 tools/sanger-wxs-variant-caller/.dockerignore
 mode change 100644 => 100755 tools/sanger-wxs-variant-caller/analysisWXS.sh

diff --git a/tools/sanger-wxs-variant-caller/.dockerignore b/tools/sanger-wxs-variant-caller/.dockerignore
new file mode 100644
index 0000000..71266ec
--- /dev/null
+++ b/tools/sanger-wxs-variant-caller/.dockerignore
@@ -0,0 +1,5 @@
+.gitignore
+.nextflow*
+tests
+work
+outdir
diff --git a/tools/sanger-wxs-variant-caller/analysisWXS.sh b/tools/sanger-wxs-variant-caller/analysisWXS.sh
old mode 100644
new mode 100755

From 134cc799e5877d84b38a7be01fd3d000d1e7e537 Mon Sep 17 00:00:00 2001
From: lindaxiang <linda.xiang@oicr.on.ca>
Date: Thu, 16 Apr 2020 12:59:56 -0400
Subject: [PATCH 07/10] add option to disable annotation step

---
 .../sanger-wxs-variant-caller/analysisWXS.sh  |  28 +-
 tools/sanger-wxs-variant-caller/ds-cgpwxs.pl  | 285 ++++++++++++++++++
 .../sanger-wxs-variant-caller.cwl             |   7 +
 .../sanger-wxs-variant-caller.nf              |  11 +-
 .../tests/checker.nf                          |  12 +-
 .../tests/test-job.nf.json                    |   6 +-
 6 files changed, 326 insertions(+), 23 deletions(-)
 create mode 100755 tools/sanger-wxs-variant-caller/ds-cgpwxs.pl

diff --git a/tools/sanger-wxs-variant-caller/analysisWXS.sh b/tools/sanger-wxs-variant-caller/analysisWXS.sh
index fbd876d..e4162d8 100755
--- a/tools/sanger-wxs-variant-caller/analysisWXS.sh
+++ b/tools/sanger-wxs-variant-caller/analysisWXS.sh
@@ -198,18 +198,26 @@ unset do_parallel
 declare -A do_parallel
 
 # annotate pindel
-rm -f $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/pindel/${NAME_MT}_vs_${NAME_WT}.annot.vcf.gz*
-echo -e "\t[Parallel block 3] Pindel_annot added..."
-do_parallel[cgpPindel_annot]="AnnotateVcf.pl -t -c $REF_BASE/vagrent/vagrent.cache.gz \
- -i $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/pindel/${NAME_MT}_vs_${NAME_WT}.flagged.vcf.gz \
- -o $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/pindel/${NAME_MT}_vs_${NAME_WT}.annot.vcf"
+if [ ! -z ${SKIPANNOT+x} ]; then
+  do_parallel[cgpPindel_annot]="echo 'Pindel_annot disabled by params'"
+else
+  rm -f $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/pindel/${NAME_MT}_vs_${NAME_WT}.annot.vcf.gz*
+  echo -e "\t[Parallel block 3] Pindel_annot added..."
+  do_parallel[cgpPindel_annot]="AnnotateVcf.pl -t -c $REF_BASE/vagrent/vagrent.cache.gz \
+  -i $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/pindel/${NAME_MT}_vs_${NAME_WT}.flagged.vcf.gz \
+  -o $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/pindel/${NAME_MT}_vs_${NAME_WT}.annot.vcf"
+fi
 
 # annotate caveman
-rm -f $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/caveman/${NAME_MT}_vs_${NAME_WT}.annot.muts.vcf.gz*
-echo -e "\t[Parallel block 3] CaVEMan_annot added..."
-do_parallel[CaVEMan_annot]="AnnotateVcf.pl -t -c $REF_BASE/vagrent/vagrent.cache.gz \
- -i $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/caveman/${NAME_MT}_vs_${NAME_WT}.flagged.muts.vcf.gz \
- -o $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/caveman/${NAME_MT}_vs_${NAME_WT}.annot.muts.vcf"
+if [ ! -z ${SKIPANNOT+x} ]; then
+  do_parallel[CaVEMan_annot]="echo 'CaVEMan_annot disabled by params'"
+else
+  rm -f $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/caveman/${NAME_MT}_vs_${NAME_WT}.annot.muts.vcf.gz*
+  echo -e "\t[Parallel block 3] CaVEMan_annot added..."
+  do_parallel[CaVEMan_annot]="AnnotateVcf.pl -t -c $REF_BASE/vagrent/vagrent.cache.gz \
+  -i $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/caveman/${NAME_MT}_vs_${NAME_WT}.flagged.muts.vcf.gz \
+  -o $OUTPUT_DIR/${NAME_MT}_vs_${NAME_WT}/caveman/${NAME_MT}_vs_${NAME_WT}.annot.muts.vcf"
+fi
 
 echo "Starting Parallel block 3: `date`"
 run_parallel $CPU do_parallel
diff --git a/tools/sanger-wxs-variant-caller/ds-cgpwxs.pl b/tools/sanger-wxs-variant-caller/ds-cgpwxs.pl
new file mode 100755
index 0000000..ef7ed1f
--- /dev/null
+++ b/tools/sanger-wxs-variant-caller/ds-cgpwxs.pl
@@ -0,0 +1,285 @@
+#!/usr/bin/perl
+
+use strict;
+use Getopt::Long;
+use File::Path qw(make_path);
+use Pod::Usage qw(pod2usage);
+use Data::Dumper;
+use autodie qw(:all);
+use warnings FATAL => 'all';
+
+pod2usage(-verbose => 1, -exitval => 1) if(@ARGV == 0);
+
+# set defaults
+my %opts = ('c' => undef,
+            'o' => $ENV{HOME},
+            'sp' => undef,
+            'as' => undef,
+            );
+
+GetOptions( 'h|help' => \$opts{'h'},
+            'm|man' => \$opts{'m'},
+            'r|reference=s' => \$opts{'r'},
+            'a|annot=s' => \$opts{'a'},
+            'si|snv_indel=s' => \$opts{'si'},
+            't|tumour=s' => \$opts{'t'},
+            'tidx=s' => \$opts{'tidx'},
+            'n|normal=s' => \$opts{'n'},
+            'nidx=s' => \$opts{'nidx'},
+            'e|exclude=s' => \$opts{'e'},
+            'sp|species:s' => \$opts{'sp'},
+            'as|assembly:s' => \$opts{'as'},
+            'sa|skipannot' => \$opts{'sa'},
+            'c|cores:i' => \$opts{'c'},
+            'o|outdir:s' => \$opts{'o'},
+) or pod2usage(2);
+
+pod2usage(-verbose => 1, -exitval => 0) if(defined $opts{'h'});
+pod2usage(-verbose => 2, -exitval => 0) if(defined $opts{'m'});
+
+delete $opts{'h'};
+delete $opts{'m'};
+
+resolve_sp_as(\%opts);
+
+printf "Options loaded: \n%s\n",Dumper(\%opts);
+
+# check for bas file
+for my $base_af(($opts{'t'}, $opts{'n'})) {
+  warn "WARN: No 'bas' file found for $base_af, this is generated by the mapping flow\n".
+       "\tWill generate internally but suboptimal\n" unless(-e "$base_af.bas");
+}
+
+# figure out if ref already unpacked:
+my $ref_area = $opts{'o'}.'/reference_files';
+my $ref_unpack = 1;
+if($opts{'r'} eq $opts{'a'} && $opts{'r'} eq $opts{'si'} && -d $opts{'r'}) {
+  $ref_area = $opts{'r'};
+  $ref_unpack = 0;
+}
+else {
+  ref_unpack($ref_area, $opts{'r'});
+  ref_unpack($ref_area, $opts{'a'});
+  ref_unpack($ref_area, $opts{'si'});
+}
+
+## now complete the caveman flaging file correctly
+my $ini = add_species_flag_ini($opts{'sp'}, $ref_area.'/caveman/flag.vcf.config.WXS.ini', $opts{'o'});
+
+# make the param file
+make_path($opts{'o'}) unless(-e $opts{'o'});
+my $run_file = $opts{'o'}.'/run.params';
+open my $FH,'>',$run_file or die "Failed to write to $run_file: $!";
+print $FH "export PCAP_THREADED_REM_LOGS=1\n";
+# hard-coded
+printf $FH "PROTOCOL=WXS\n";
+# required options
+printf $FH "OUTPUT_DIR='%s'\n", $opts{'o'};
+printf $FH "REF_BASE='%s'\n", $ref_area;
+printf $FH "BAM_MT='%s'\n", $opts{'t'};
+printf $FH "IDX_MT='%s'\n", $opts{'tidx'};
+printf $FH "BAM_WT='%s'\n", $opts{'n'};
+printf $FH "IDX_WT='%s'\n", $opts{'nidx'};
+printf $FH "CONTIG_EXCLUDE='%s'\n", $opts{'e'};
+printf $FH "SPECIES='%s'\n", $opts{'sp'};
+printf $FH "ASSEMBLY='%s'\n", $opts{'as'};
+printf $FH "SNVFLAG='%s'\n", $ini;
+printf $FH "CPU=%d\n", $opts{'c'} if(defined $opts{'c'});
+printf $FH "CLEAN_REF=%d\n", $ref_unpack;
+# options to disable algorithms
+print $FH "SKIPANNOT=1\n" if(exists $opts{'sa'});
+close $FH;
+
+exec('analysisWXS.sh', $run_file); # I will never return to the perl code
+
+sub resolve_sp_as {
+  my $options = shift;
+  ## read species/assembly from bam headers
+  my ($mt_species, $mt_assembly) = species_assembly_from_xam($options->{'t'});
+  my ($wt_species, $wt_assembly) = species_assembly_from_xam($options->{'n'});
+  if($mt_species ne $wt_species) {
+    warn "WARN: Species mismatch between T/N [CR|B]AM headers\n";
+    if(!defined $options->{'sp'} || $options->{'sp'} eq q{}) {
+      die "ERROR: Please define species to handle this mismatch\n";
+    }
+  }
+  elsif($mt_species ne q{}) {
+    $options->{'sp'} = $mt_species;
+  }
+  if(!defined $options->{'sp'} || $options->{'sp'} eq q{}) {
+    die "ERROR: Please define species, not found in [CR|B]AM headers.\n";
+  }
+
+  if($mt_assembly ne $wt_assembly) {
+    warn "WARN: Assembly mismatch between T/N [CR|B]AM headers\n";
+    if(!defined $options->{'as'} || $options->{'as'} eq q{}) {
+      die "ERROR: Please define assembly to handle this mismatch\n";
+    }
+  }
+  elsif($mt_assembly ne q{}) {
+    $options->{'as'} = $mt_assembly;
+  }
+  if(!defined $options->{'as'} || $options->{'as'} eq q{}) {
+    die "ERROR: Please define assembly, not found in [CR|B]AM headers.\n";
+  }
+}
+
+sub add_species_flag_ini {
+  my ($species, $ini_in, $outdir) = @_;
+  $species =~ s/ /_/g;
+  $species = uc $species;
+  my $ini_out = $outdir.'/flag.vcf.config.WXS.ini';
+  open my $IN, '<', $ini_in;
+  open my $OUT,'>',$ini_out;
+  while(my $line = <$IN>) {
+    $line =~ s/^\[HUMAN_/[${species}_/;
+    print $OUT $line;
+  }
+  close $OUT;
+  close $IN;
+  return $ini_out;
+}
+
+sub species_assembly_from_xam {
+  my $xam = shift;
+  my %assembly_set;
+  my %species_set;
+  open my $SAM, '-|', "samtools view -H $xam" or die $!;
+  while(my $line = <$SAM>) {
+    next unless($line =~ m/^\@SQ/);
+    chomp $line;
+    $line .= "\t"; # simplify matching
+    if($line =~ m/\tAS:([^\t]+)\t/) {
+      $assembly_set{$1}++;
+    }
+    if($line =~ m/\SP:([^\t]+)\t/) {
+      $species_set{$1}++;
+    }
+  }
+  close $SAM;
+  my $species = q{};
+  my $max_val = 0;
+  for(keys %species_set) {
+    if($species_set{$_} > $max_val) {
+      $max_val = $species_set{$_};
+      $species = $_;
+    }
+  }
+  my $assembly = q{};
+  $max_val = 0;
+  for(keys %assembly_set) {
+    if($assembly_set{$_} > $max_val) {
+      $max_val = $assembly_set{$_};
+      $assembly = $_;
+    }
+  }
+  return ($species, $assembly);
+}
+
+sub ref_unpack {
+  my ($ref_area, $item) = @_;
+  make_path($ref_area) unless(-d $ref_area);
+  my $untar = sprintf 'tar --strip-components 1 -C %s -zxvf %s', $ref_area, $item;
+  system($untar) && die $!;
+  return 1;
+}
+
+__END__
+
+
+=head1 NAME
+
+dh-wrapper.pl - Generate the param file and execute analysisWXS.sh (for dockstore)
+
+=head1 SYNOPSIS
+
+dh-wrapper.pl [options] [file(s)...]
+
+  Required parameters:
+    -reference   -r   Path to core reference tar.gz
+    -annot       -a   Path to VAGrENT*.tar.gz
+    -snv_indel   -si  Path to SNV_INDEL*.tar.gz
+    -tumour      -t   Tumour [CR|B]AM file
+    -tidx             Tumour index file
+    -normal      -n   Normal [CR|B]AM file
+    -nidx             Normal index file
+    -exclude     -e   Exclude these contigs from analysis
+                        e.g. NC_007605,hs37d5,GL%
+
+  Optional parameters
+    -species     -sp  Species name (may require quoting)
+    -assembly    -a   Reference assembly
+    -outdir      -o   Set the output folder [$HOME]
+    -cores       -c   Set the number of cpu/cores available [default all].
+
+  Other:
+    -help        -h   Brief help message.
+    -man         -m   Full documentation.
+
+=head1 DESCRIPTION
+
+Wrapper script to map dockstore cwl inputs to PARAMS file used by underlying code.
+
+=head1 OPTION DETAILS
+
+=over 4
+
+=item B<-reference>
+
+Path to mapping tar.gz reference files
+
+=item B<-annot>
+
+Path to VAGrENT*.tar.gz
+
+=item B<-snv_indel>
+
+Path to Path to SNV_INDEL*.tar.gz
+
+=item B<-tumour>
+
+Path to tumour BAM or CRAM file with co-located index and BAS file.
+
+=item B<-tidx>
+
+Path to tumour alignment file index (bai|csi|crai), still needs to be colocated.
+
+=item B<-normal>
+
+Path to normal BAM or CRAM file with co-located index and BAS file.
+
+=item B<-nidx>
+
+Path to normal alignment file index (bai|csi|crai), still needs to be colocated.
+
+=item B<-exclude>
+
+Contigs to be excluded from analysis, csv, use '%' for wildcard.
+
+=item B<-species>
+
+Specify overriding species, by default will select the most prevelant entry in
+[CR|B]AM header (to cope with inclusion of viral/decoy sequences).
+
+=item B<-assembly>
+
+Specify overriding assembly, by default will select the most prevelant entry in
+[CR|B]AM header (to cope with inclusion of viral/decoy sequences).
+
+=item B<-skipannot>
+Disable Pindel, CAVEMan Annotation.
+
+=item B<-outdir>
+
+Set the output directory.  Defaults to $HOME.
+
+NOTE: Should B<NOT> be set when working with dockstore wrapper.
+
+=item B<-cores>
+
+Sets the number of cores to be used during processing.  Default to use all at appropriate
+points in analysis.
+
+=back
+
+=cut
diff --git a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.cwl b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.cwl
index f03496a..57ebb40 100644
--- a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.cwl
+++ b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.cwl
@@ -119,6 +119,13 @@ inputs:
       separate: true
       shellQuote: true
 
+  skipannot:
+    type: boolean?
+    doc: "Disable Pindel and CaVEMan annotation steps"
+    default: false
+    inputBinding:
+      prefix: -skipannot
+      separate: true
 
 outputs:
   run_params:
diff --git a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
index 4bf1b2b..e3542ae 100644
--- a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
+++ b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
@@ -24,9 +24,9 @@
 nextflow.preview.dsl=2
 version = '3.1.6-2'
 
-params.reference = ""
-params.annot = ""
-params.snv_indel = ""
+params.ref_genome_tar = ""
+params.vagrent_annot = ""
+params.ref_snv_indel_tar = ""
 params.tumour = ""
 params.tumourIdx = ""
 params.normal = ""
@@ -34,9 +34,10 @@ params.normalIdx = ""
 params.exclude = "chrUn%,HLA%,%_alt,%_random,chrM,chrEBV"
 params.species = "human"
 params.assembly = "GRCh38"
+params.skipannot = false
 params.container_version = ""
 params.cpus = 18
-params.mem = 4  // GB
+params.mem = 32  // GB
 
 
 def getSangerWxsSecondaryFiles(main_file){  //this is kind of like CWL's secondary files
@@ -72,6 +73,7 @@ process sangerWxsVariantCaller {
     path "WXS_*_vs_*.timings.tar.gz", emit: timings
 
   script:
+    arg_skipannot = params.skipannot ? "-skipannot" : ""
     """
     /opt/wtsi-cgp/bin/ds-cgpwxs.pl \
       -cores ${task.cpus} \
@@ -85,6 +87,7 @@ process sangerWxsVariantCaller {
       -exclude ${params.exclude} \
       -species ${params.species} \
       -assembly ${params.assembly} \
+      ${arg_skipannot} \
       -outdir \$PWD
     """
 }
diff --git a/tools/sanger-wxs-variant-caller/tests/checker.nf b/tools/sanger-wxs-variant-caller/tests/checker.nf
index 393f1f8..1a6cdf9 100644
--- a/tools/sanger-wxs-variant-caller/tests/checker.nf
+++ b/tools/sanger-wxs-variant-caller/tests/checker.nf
@@ -23,9 +23,9 @@
 
 nextflow.preview.dsl=2
 
-params.reference = ""
-params.annot = ""
-params.snv_indel = ""
+params.ref_genome_tar = ""
+params.vagrent_annot = ""
+params.ref_snv_indel_tar = ""
 params.tumour = ""
 params.tumourIdx = ""
 params.normal = ""
@@ -45,9 +45,9 @@ Channel
 workflow {
   main:
     sangerWxsVariantCaller(
-      file(params.reference),
-      file(params.annot),
-      file(params.snv_indel),
+      file(params.ref_genome_tar),
+      file(params.vagrent_annot),
+      file(params.ref_snv_indel_tar),
       file(params.tumour),
       file(params.tumourIdx),
       tumour_ch.collect(),
diff --git a/tools/sanger-wxs-variant-caller/tests/test-job.nf.json b/tools/sanger-wxs-variant-caller/tests/test-job.nf.json
index 6eb02ac..318c45f 100644
--- a/tools/sanger-wxs-variant-caller/tests/test-job.nf.json
+++ b/tools/sanger-wxs-variant-caller/tests/test-job.nf.json
@@ -1,7 +1,7 @@
 {
-  "reference": "https://object.cancercollaboratory.org:9080/swift/v1/genomics-public-data/sanger-variant-calling/core_ref_GRCh38_hla_decoy_ebv.tar.gz",
-  "annot": "https://object.cancercollaboratory.org:9080/swift/v1/genomics-public-data/sanger-variant-calling/VAGrENT_ref_GRCh38_hla_decoy_ebv_ensembl_91.tar.gz",
-  "snv_indel": "https://object.cancercollaboratory.org:9080/swift/v1/genomics-public-data/sanger-variant-calling/SNV_INDEL_ref_GRCh38_hla_decoy_ebv-fragment.tar.gz",
+  "ref_genome_tar": "https://object.cancercollaboratory.org:9080/swift/v1/genomics-public-data/sanger-variant-calling/core_ref_GRCh38_hla_decoy_ebv.tar.gz",
+  "vagrent_annot": "https://object.cancercollaboratory.org:9080/swift/v1/genomics-public-data/sanger-variant-calling/VAGrENT_ref_GRCh38_hla_decoy_ebv_ensembl_91.tar.gz",
+  "ref_snv_indel_tar": "https://object.cancercollaboratory.org:9080/swift/v1/genomics-public-data/sanger-variant-calling/SNV_INDEL_ref_GRCh38_hla_decoy_ebv-fragment.tar.gz",
   "tumour": "",
   "tumourIdx": "",
   "normal": "",

From f9148799254a571103c153535b4d7afc48b344b8 Mon Sep 17 00:00:00 2001
From: Junjun Zhang <junjun.ca@gmail.com>
Date: Fri, 17 Apr 2020 13:17:05 -0400
Subject: [PATCH 08/10] fix the version

---
 tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
index e3542ae..4f7f832 100644
--- a/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
+++ b/tools/sanger-wxs-variant-caller/sanger-wxs-variant-caller.nf
@@ -22,7 +22,7 @@
  */
 
 nextflow.preview.dsl=2
-version = '3.1.6-2'
+version = '3.1.6-3'
 
 params.ref_genome_tar = ""
 params.vagrent_annot = ""

From 965dad98d484bc1d80a9d0a63895ab71f3fc26c7 Mon Sep 17 00:00:00 2001
From: Junjun Zhang <junjun.ca@gmail.com>
Date: Fri, 17 Apr 2020 13:26:37 -0400
Subject: [PATCH 09/10] copy missing script into docker image

---
 tools/sanger-wxs-variant-caller/Dockerfile | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/sanger-wxs-variant-caller/Dockerfile b/tools/sanger-wxs-variant-caller/Dockerfile
index 9a7d1b0..4975921 100644
--- a/tools/sanger-wxs-variant-caller/Dockerfile
+++ b/tools/sanger-wxs-variant-caller/Dockerfile
@@ -2,4 +2,6 @@ FROM quay.io/wtsicgp/dockstore-cgpwxs:3.1.6
 
 COPY analysisWXS.sh $OPT/bin/analysisWXS.sh
 
+COPY ds-cgpwgs.pl $OPT/bin/ds-cgpwgs.pl
+
 CMD ["/bin/bash"]

From ca0f149141c610c88663a869f8dbf25028613507 Mon Sep 17 00:00:00 2001
From: Junjun Zhang <junjun.ca@gmail.com>
Date: Fri, 17 Apr 2020 13:29:26 -0400
Subject: [PATCH 10/10] correct the file name

---
 tools/sanger-wxs-variant-caller/Dockerfile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/sanger-wxs-variant-caller/Dockerfile b/tools/sanger-wxs-variant-caller/Dockerfile
index 4975921..308e971 100644
--- a/tools/sanger-wxs-variant-caller/Dockerfile
+++ b/tools/sanger-wxs-variant-caller/Dockerfile
@@ -2,6 +2,6 @@ FROM quay.io/wtsicgp/dockstore-cgpwxs:3.1.6
 
 COPY analysisWXS.sh $OPT/bin/analysisWXS.sh
 
-COPY ds-cgpwgs.pl $OPT/bin/ds-cgpwgs.pl
+COPY ds-cgpwxs.pl $OPT/bin/ds-cgpwxs.pl
 
 CMD ["/bin/bash"]