add sample option to cmo_split_reads (#42)

* add 1.96 version to picard calls

* add set -o pipefail to bwa call per jaeyoung bug ticket, update version

* remove ref seq from default args, default_args probably needs another refactor

* fix dis test

* inital commit of ppflag_fixer

* inital commit of ppflag_fixer

* add ppflag-fixer to deploy list, increment _version

* add optional sample rename during splitting

*  add some comments

Author: lordzappo

bin/cmo_split_reads

@@ -4,9 +4,13 @@ import argparse, os, sys, signal, subprocess, math, gzip, io
 import cmo
 import multiprocessing
 
-def chunk(fastq, lines_per_chunk, num_pieces):
+def chunk(fastq, sample, lines_per_chunk, num_pieces):
     logger = cmo.util.get_logger()
     output_prefix = os.path.basename(fastq).split(".", 1)[0] + "."
+    if(sample != None):
+        exploded = output_prefix.split(".")
+        exploded[0]=sample
+        output_prefix = ".".join(exploded)
     while lines_per_chunk % 4 != 0:
         lines_per_chunk +=1
     fh = io.BufferedReader(gzip.open(fastq, "rb"))
@@ -40,6 +44,7 @@ if __name__ =='__main__':
     parser = argparse.ArgumentParser(description="split files into chunks based on filesize")
     parser.add_argument('-f1', "--fastq1", action='store', help="filename to split", required=True)
     parser.add_argument('-f2', "--fastq2", action='store', help="filename2 to split")
+    parser.add_argument('-s', "--sample", action='store', help="sample ID")
     args = parser.parse_args()
     fastqs = [args.fastq1]
     if args.fastq2:
@@ -53,7 +58,7 @@ if __name__ =='__main__':
     logger.info("%s lines per chunk" % str(lines_per_chunk))
     pool=multiprocessing.Pool(processes=2)
     for fastq in fastqs:
-        result = pool.apply_async(chunk, args=(fastq, lines_per_chunk, num_pieces, ))
+        result = pool.apply_async(chunk, args=(fastq, args.sample, lines_per_chunk, num_pieces, ))
     pool.close()
     pool.join()
 

cmo/_version.py

@@ -2,4 +2,5 @@
 # This file is originally generated from Git information by running 'setup.py
 # version'. Distribution tarballs contain a pre-generated copy of this file.
 
-__version__ = '1.5.0'
+
+__version__ = '1.5.1'

cmo/picard.py

@@ -37,9 +37,11 @@ def picard_cmd(self, command, default_args_override={}, command_specific_args={}
             cmd = [self.java_cmd, self.java_args, "-jar", os.path.join(self.picard_jar, command+".jar")]
         else:
             cmd = [self.java_cmd, self.java_args, "-jar", self.picard_jar, command]
+        #overwrite default args with whatever was passed in
         for arg, value in default_args_override.items():
             if arg in self.default_args:
                 self.default_args[arg] = value        
+        #add combination of pass-ins and defaults to command 
         for arg, value in self.default_args.items():
             if arg in default_args_override:
                 value = default_args_override[arg]