Update pipeline to accept threads argument

Dockerfile.with_refs

@@ -16,7 +16,7 @@ RUN mkdir /build && cd /build &&\
     tar -xvjf samtools-1.11.tar.bz2 && cd samtools-1.11/ && ./configure --prefix=/varpipe_wgs/tools/a/samtools && make && make install &&\
     cp /varpipe_wgs/tools/a/samtools/bin/samtools /varpipe_wgs/tools/ && cd / && rm -rf /build
 
-RUN ln -s /usr/bin/python2.7 /usr/bin/python &&\
+RUN ln -s /usr/bin/python2.7 /usr/bin/python && ln -s /usr/bin/python2.7 /usr/bin/python2 &&\
     wget -O- https://bootstrap.pypa.io/pip/2.7/get-pip.py >get-pip.py && python get-pip.py &&\
     pip2 install pyyaml fpdf
 

Dockerfile.without_refs

@@ -16,7 +16,7 @@ RUN mkdir /build && cd /build &&\
     tar -xvjf samtools-1.11.tar.bz2 && cd samtools-1.11/ && ./configure --prefix=/varpipe_wgs/tools/a/samtools && make && make install &&\
     cp /varpipe_wgs/tools/a/samtools/bin/samtools /varpipe_wgs/tools/ && cd / && rm -rf /build
 
-RUN ln -s /usr/bin/python2.7 /usr/bin/python &&\
+RUN ln -s /usr/bin/python2.7 /usr/bin/python && ln -s /usr/bin/python2.7 /usr/bin/python2 &&\
     wget -O- https://bootstrap.pypa.io/pip/2.7/get-pip.py >get-pip.py && python get-pip.py &&\
     pip2 install pyyaml fpdf
 

README.md

@@ -36,11 +36,11 @@ docker run -it -v <path to data>:/varpipe_wgs/data -v <path to references>:/varp
 
 Those commands will download the most recent version of the pipeline and then start the container and connect to it.
 
-When connected to the container you will be in the directory /varpipe_wgs/data. From there simply start the pipeline with the command
+When connected to the container you will be in the directory /varpipe_wgs/data. From there simply start the pipeline with the command, where \<threads\> is the number of threads you would like to run (Default: 4)
 
 ```console
 cd /varpipe_wgs/data
-./runVarpipeline.sh
+./runVarpipeline.sh <threads>
 ```
 
 That will identify all gzipped fastq files in the directory and run the pipeline over them, creating a results folder named "Output_\<MM\>_\<DD\>_\<YYYY\>"
@@ -99,7 +99,7 @@ When connected to the container you will be in your home directory. You must cd
 
 ```console
 cd /varpipe_wgs/data
-./runVarpipeline.sh
+./runVarpipeline.sh <threads>
 ```
 
 That will identify all gzipped fastq files in the directory and run the pipeline over them, creating a results folder named "Output_\<MM\>_\<DD\>_\<YYYY\>"
@@ -113,6 +113,7 @@ When the pipeline is finished you can disconnect from and close the container by
 To run the pipeline locally, you will need to have the following programs installed:
 
  - Python 2.7
+ - Python 3
  - Java 1.8
  - Singularity >=3.5
 
@@ -136,11 +137,11 @@ Latly, update the script tools/clockwork-0.11.3/clockwork script to correctly po
 
 ### Run the Pipeline ###
 
-After the data has been added to the data/ directory, cd into data/ and run the pipeline with the commands
+After the data has been added to the data/ directory, cd into data/ and run the pipeline with the command, where \<threads\> is the number of threads you would like to run (Default: 4)
 
 ```console
 cd data/
-./runVarpipeline.sh
+./runVarpipeline.sh <threads>
 ```
 
 That will identify all gzipped fastq files in the directory and run the pipeline over them, creating a results folder named "Output_\<MM\>_\<DD\>_\<YYYY\>"

data/runVarpipeline.sh

@@ -1,5 +1,11 @@
 #!/usr/bin/bash
 
+if [ -z "$1" ]; then
+    THREADS=4
+else
+    THREADS="$1"
+fi
+
 if [ -n '*_L001_R2_001*' ]
 then
 
@@ -35,8 +41,9 @@ then
 
 fi
 
-ls *_R1_001.fastq.gz | sed 's/_R1_001.fastq.gz//g' | awk '{print "../tools/Varpipeline -q "$0"_R1_001.fastq.gz -r ../tools/ref2.fa -n "$0" -q2 "$0"_R2_001.fastq.gz -a -v"}' > run_3.sh
+ls *_R1_001.fastq.gz | sed 's/_R1_001.fastq.gz//g' | awk '{print "../tools/Varpipeline -q "$0"_R1_001.fastq.gz -r ../tools/ref2.fa -n "$0" -q2 "$0"_R2_001.fastq.gz -a -v -t '${THREADS}' "}' > run_3.sh
 
+cat run_3.sh
 
 sh run_3.sh
 rm *.fastq.gz

tools/Varpipeline

@@ -1,4 +1,4 @@
-#! /usr/bin/env python
+#! /usr/bin/env python2
 
 if __name__ == '__main__':
     import sys
@@ -16,6 +16,7 @@ if __name__ == '__main__':
     group1.add_argument('-r', '--reference', required=True, metavar="STRING", help='Reference genome in FASTA format.')
     group1.add_argument('-n', '--name', required=True, metavar="STRING", help='Sample name to be used as a prefix.')
     group1.add_argument('-q2', '--fastq2', default='', metavar="STRING", help='Second paired-end FASTQ file.')
+    group1.add_argument('-t', '--threads', action='store', metavar="INT", help='Specify how many threads to use')
     group2 = parser.add_argument_group('Output', '')
     group2.add_argument('-o', '--outdir', help='Output directory', metavar="STRING")
     group2.add_argument('--keepfiles', action='store_true', help='Keep intermediate files.')
@@ -94,7 +95,7 @@ if __name__ == '__main__':
 
     # All is well let's get started!
     s = Varpipeline.snp(args.fastq, args.outdir, args.reference, args.name, paired, args.fastq2, 
-                        args.verbose, ' '.join(sys.argv))
+                        args.verbose, args.threads, ' '.join(sys.argv))
     # run Clockwork decontamination
     s.runClockwork()
 

tools/Varpipeline.py

@@ -14,7 +14,7 @@
 
 class snp():
 
-    def __init__(self, input, outdir, reference, name, paired,input2, verbose, argString):
+    def __init__(self, input, outdir, reference, name, paired,input2, verbose, threads, argString):
         i                       = datetime.now()
         self.name               = name
         self.flog               = "Output_" + i.strftime('%m_%d_%Y')
@@ -39,6 +39,7 @@ def __init__(self, input, outdir, reference, name, paired,input2, verbose, argSt
         self.__mixed            = ''
         self._low		= ''
         self.__exception        = ''
+        self.__threads          = threads
 
 
         # Create the output directory, and start the log file.

tools/clockwork-0.11.3/clockwork

@@ -1,3 +1,3 @@
 #!/bin/bash
 
-singularity exec tools/clockwork-0.11.3/clockwork_v0.11.3.img clockwork "$@"
+singularity exec ../tools/clockwork-0.11.3/clockwork_v01.11.3.img clockwork "$@"

tools/config.yml

@@ -32,4 +32,4 @@ scripts:
     create_report: /create_report.py
     print_report: /pdf_print.py
 other:
-    threads: '12'
+    threads: '4'