view strelka_wrapper.py @ 6:87568e5a7d4f

Testing strelka version 0.0.1
author mini
date Fri, 26 Sep 2014 13:24:13 +0200
parents
children 3e8541ece3c7
line wrap: on
line source

#!/usr/bin/env python
#Dan Blankenberg

"""
A wrapper script for running the GenomeAnalysisTK.jar commands.
"""

from __future__ import print_function
import sys, argparse, os, tempfile, subprocess, shutil
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 )

def _create_config(args, config_path):
    conf_file = open(config_path, "w")
    conf_file.write("[user]\n")
    for option in args:
        if not option in ["tumorBam", "normalBam", "refFile", "configFile"] and args[option]!=None:
    	    conf_file.write("%s=%s\n" % (option, args[option]))
    conf_file.close()

def my_Popen(cmd, prefix_for_stderr_name, tmp_dir, msg_error):
    stderr_name = tempfile.NamedTemporaryFile( prefix = prefix_for_stderr_name ).name
    proc = subprocess.Popen( args=cmd, shell=True, stderr=open( stderr_name, 'wb' ) )
    return_code = proc.wait()                          
    if return_code:
	for line in open( stderr_name ):
           print(line, file=sys.stderr)
	os.unlink( stderr_name ) #clean up
 	cleanup_before_exit( tmp_dir )
 	raise Exception( msg_error )
    else:
        os.unlink( stderr_name )

def index_bam_files( bam_filenames, tmp_dir ):
    for bam_filename in bam_filenames:
        bam_index_filename = "%s.bai" % bam_filename
        print("bam_filename is: " + bam_filename + " bam_index_filename is: " + bam_index_filename + " test is: %s" % os.path.exists(bam_index_filename))
        if not os.path.exists( bam_index_filename ):
            #need to index this bam file
            command = 'samtools index %s %s' % ( bam_filename, bam_index_filename )
            my_Popen( command, "bam_index_stderr", tmp_dir, "Error during indexation of fasta file :" + bam_filename)

def index_fasta_files( fasta_filenames, tmp_dir ):
    for fasta_filename in fasta_filenames:
        fasta_index_filename = "%s.fai" % fasta_filename
        print("fasta_filename is: " + fasta_filename + " fasta_index_filename is: " + fasta_index_filename + " test is: %s" % os.path.exists(fasta_index_filename))
        if not os.path.exists( fasta_index_filename ):
            #need to index this bam file
            command = 'samtools faidx %s %s' % ( fasta_filename, fasta_index_filename )
            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
        
    root_dir= "/home/galaxyusr/data/galaxy_dist/tools/strelka2"
    expected_dir="for_tests"
    job_dir=os.getcwd()
    analysis_dir=job_dir + "/StrelkaAnalysis"
    config_script=root_dir + "/configureStrelkaWorkflow.pl"
    tmp_dir = "tmp"  #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)
   
    #manage parsing
    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 )   
    parser.add_argument( '-r', '--refFile', help='path to tumor bam file', required = False )
    parser.add_argument( '-c', '--configFile', help='path to tumor bam file', required = False )
    parser.add_argument( '--depthFilterMultiple', help='path to tumor bam file', required = False )
    parser.add_argument( '--snvMaxFilteredBasecallFrac', help='path to tumor bam file', required = False )
    parser.add_argument( '--snvMaxSpanningDeletionFrac', help='path to tumor bam file', required = False )
    parser.add_argument( '--indelMaxRefRepeat', help='path to tumor bam file', required = False )
    parser.add_argument( '--indelMaxWindowFilteredBasecallFrac', help='path to tumor bam file', required = False )
    parser.add_argument( '--indelMaxIntHpolLength', help='path to tumor bam file', required = False )
    parser.add_argument( '--ssnvPrior', help='path to tumor bam file', required = False )
    parser.add_argument( '--sindelPrior', help='path to tumor bam file', required = False )
    parser.add_argument( '--ssnvNoise', help='path to tumor bam file', required = False )
    parser.add_argument( '--sindelNoise', help='path to tumor bam file', required = False )
    parser.add_argument( '--ssnvNoiseStrandBiasFrac', help='path to tumor bam file', required = False )
    parser.add_argument( '--minTier1Mapq', help='path to tumor bam file', required = False )
    parser.add_argument( '--minTier2Mapq', help='path to tumor bam file', required = False )
    parser.add_argument( '--ssnvQuality_LowerBound', help='path to tumor bam file', required = False )
    parser.add_argument( '--sindelQuality_LowerBound', help='path to tumor bam file', required = False )
    parser.add_argument( '--isWriteRealignedBam', help='path to tumor bam file', required = False )
    parser.add_argument( '--binSize', help='path to tumor bam file', required = False )
    parser.add_argument( '--extraStrelkaArguments', help='path to tumor bam file', required = False )
    parser.add_argument( '--isSkipDepthFilters', help='path to tumor bam file', required = False )
    parser.add_argument( '--maxInputDepth', help='path to tumor bam file', required = False )
    args = parser.parse_args()

    #verifying eveything's ok
    if not os.path.isfile(config_script):
    	sys.exit("ERROR: The strelka workflow must be built prior to running. See installation instructions in '$root_dir/README'")
    print("configuring...", file=sys.stdout)
    if os.path.exists(analysis_dir):
	sys.exit("'" + analysis_dir + "' already exist, if you are executing this tool from galaxy it should not happen")
    

    # 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 ]
    index_fasta_files( fasta_files, tmp_dir )
    
    #creating config file if needed
    if args.configFile == "Custom":
    	_create_config(vars(args), config_ini)
    elif args.configFile == "Default":
        cmdbash="cp %s %s" % (root_dir + "/strelka_config.sample", config_ini)
        my_Popen(cmdbash, "copy_default_file_err", tmp_dir, "Error during the copy of default config file, maybe it was removed")
    else:
    	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")




    #configuration of workflow
    cmd="%s --tumor=%s --normal=%s --ref=%s --config=%s --output-dir=%s" % (config_script, args.tumorBam, args.normalBam, args.refFile, config_ini, analysis_dir)
    print( "**** Starting configuration.")
    print( "**** Configuration cmd: '" + cmd + "'")
    my_Popen( cmd, "cinfugation_stderr", tmp_dir, "Error during configuration !")
    print("completed configuration")
    
    #run the workflow !
    cmd="make -C " + analysis_dir
    print("**** starting workflow.")
    print("**** workflow cmd: '" + cmd + "'")
    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__()