diff strelka_wrapper.py @ 10:f66f23fcc83a

Modified layout

--- a/strelka_wrapper.py	Fri Sep 26 14:33:07 2014 +0200
+++ b/strelka_wrapper.py	Tue Sep 30 11:08:39 2014 +0200
@@ -1,5 +1,8 @@
 #!/usr/bin/env python
-#Dan Blankenberg
+#Gregoire Seguin-Henry (Engineer IT)
+#Amine Sbitti (Data Scientist)
+#Ludovic Marie-Sainte (Project Manager)
+#For Geviteam 2014
 
 """
 A wrapper script for running the GenomeAnalysisTK.jar commands.
@@ -10,14 +13,7 @@
 from binascii import unhexlify
 from string import Template
 from galaxy import eggs
-#import pkg_resources; pkg_resources.require( "bx-python" )
 
-#GALAXY_EXT_TO_GATK_EXT = { 'gatk_interval':'intervals', 'bam_index':'bam.bai', 'gatk_dbsnp':'dbSNP', 'picard_interval_list':'interval_list' } #items not listed here will use the galaxy extension as-is
-#GALAXY_EXT_TO_GATK_FILE_TYPE = GALAXY_EXT_TO_GATK_EXT #for now, these are the same, but could be different if needed
-#DEFAULT_GATK_PREFIX = "gatk_file"
-#CHUNK_SIZE = 2**20 #1mb
-#
-#
 def cleanup_before_exit( tmp_dir ):
     if tmp_dir and os.path.exists( tmp_dir ):
         shutil.rmtree( tmp_dir )
@@ -62,9 +58,8 @@
             my_Popen( command, "fasta_index_stderr", tmp_dir, "Error during indexation of fasta file :" + fasta_filename)
 
 def __main__():
-    #Parse Command Line  OPTPARSE DEPRECIATED USE ARGPARSE INSTEAD
-    #MKTEMP DEPRECIATED USE MKDTlizations#EMP INSTEAD
-    #manage parsing
+
+    #Manage options
     parser = argparse.ArgumentParser()                                             
     parser.add_argument( '-t', '--tumorBam', help='path to tumor bam file', required = False )
     parser.add_argument( '-n', '--normalBam', help='path to tumor bam file', required = False )   
@@ -98,10 +93,10 @@
     job_dir=os.getcwd()
     analysis_dir=job_dir + "/StrelkaAnalysis"
     config_script=root_dir + "/configureStrelkaWorkflow.pl"
-    tmp_dir = "tmp"  #tempfile.mkdtemp( prefix='tmp-strelkaAnalysis-' )
+    tmp_dir = tempfile.mkdtemp( prefix='tmp-strelkaAnalysis-' )
     config_ini = "%s/config.ini" % (tmp_dir)
 
-    print("root_dir: " + root_dir + "\njob_dir :" + job_dir + "\nanalysis_dir :" + analysis_dir + "\nconfig_script :" + config_script + "\ntmp_dir :" + tmp_dir + "\nconfig_ini :" +  config_ini)
+    #print("root_dir: " + root_dir + "\njob_dir :" + job_dir + "\nanalysis_dir :" + analysis_dir + "\nconfig_script :" + config_script + "\ntmp_dir :" + tmp_dir + "\nconfig_ini :" +  config_ini)
 
 
     #verifying eveything's ok
@@ -113,7 +108,6 @@
     
 
     # creating index if needed
-    os.environ['PATH']= root_dir + "/opt/samtools:" + os.environ['PATH']
     bam_filenames = [ args.tumorBam, args.normalBam ]
     index_bam_files( bam_filenames, tmp_dir )
     fasta_files = [ args.refFile ]
@@ -129,7 +123,7 @@
     	if not os.path.exists(args.configFile):
 	     print( "The path to your configuration File seems to be wrong, use another one or custom option", file=sys.stderr)
     	cmdbash="cp %s %s" % (args.configFile, config_ini)
-        my_Popen(cmdbash, "copy_default_file_err", tmp_dir, "Error during the copy of default config file, maybe it was removed")
+        my_Popen(cmdbash, "copy_default_file_err", tmp_dir, "Error during the copy of the selected config file")
 
 
 
@@ -148,55 +142,3 @@
     my_Popen( cmd, "workflow_stderr", tmp_dir, "Error during workflow execution !")   
     print("**** completed workflow execution")
 
-
-
-
-
-
-
-
-
-
-
-
-
-
-#bam_filenames = []
-#    if options.datasets:
-#        for ( dataset_arg, filename, galaxy_ext, prefix ) in options.datasets:
-#            gatk_filename = filename_from_galaxy( filename, galaxy_ext, target_dir = tmp_dir, prefix = prefix )#return the link to the dataset that has been created in the function
-#            if dataset_arg:
-#                cmd = '%s %s "%s"' % ( cmd, gatk_filetype_argument_substitution( dataset_arg, galaxy_ext ), gatk_filename )
-#            if galaxy_ext == "bam":
-#                bam_filenames.append( gatk_filename )
-#    #set up stdout and stderr output options
-#    stdout = open_file_from_option( options.stdout, mode = 'wb' )
-#    stderr = open_file_from_option( options.stderr, mode = 'wb' )
-#    #if no stderr file is specified, we'll use our own
-#    if stderr is None:
-#        stderr = tempfile.NamedTemporaryFile( prefix="strelka-stderr-", dir=tmp_dir )
-#    
-#    proc = subprocess.Popen( args=cmd, stdout=stdout, stderr=stderr, shell=True, cwd=tmp_dir )
-#    return_code = proc.wait()
-#    
-#    if return_code:
-#        stderr_target = sys.stderr
-#    else:
-#        stderr_target = sys.stdout
-#    stderr.flush()
-#    stderr.seek(0)
-#    while True:
-#        chunk = stderr.read( CHUNK_SIZE )
-#        if chunk:
-#            stderr_target.write( chunk )
-#        else:
-#            break
-#    stderr.close()
-#    #generate html reports
-#    if options.html_report_from_directory:
-#        for ( html_filename, html_dir ) in options.html_report_from_directory:
-#            html_report_from_directory( open( html_filename, 'wb' ), html_dir )
-#    
-#    cleanup_before_exit( tmp_dir )
-
-if __name__=="__main__": __main__()