Mercurial > repos > mini > strelka

comparison strelka_wrapper.py @ 6:87568e5a7d4f

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Testing strelka version 0.0.1
author mini
date Fri, 26 Sep 2014 13:24:13 +0200
parents
children 3e8541ece3c7
comparison
equal deleted inserted replaced
5:07cbbd662111 6:87568e5a7d4f
1 #!/usr/bin/env python
2 #Dan Blankenberg
3
4 """
5 A wrapper script for running the GenomeAnalysisTK.jar commands.
6 """
7
8 from __future__ import print_function
9 import sys, argparse, os, tempfile, subprocess, shutil
10 from binascii import unhexlify
11 from string import Template
12 from galaxy import eggs
13 #import pkg_resources; pkg_resources.require( "bx-python" )
14
15 #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
16 #GALAXY_EXT_TO_GATK_FILE_TYPE = GALAXY_EXT_TO_GATK_EXT #for now, these are the same, but could be different if needed
17 #DEFAULT_GATK_PREFIX = "gatk_file"
18 #CHUNK_SIZE = 2**20 #1mb
19 #
20 #
21 def cleanup_before_exit( tmp_dir ):
22 if tmp_dir and os.path.exists( tmp_dir ):
23 shutil.rmtree( tmp_dir )
24
25 def _create_config(args, config_path):
26 conf_file = open(config_path, "w")
27 conf_file.write("[user]\n")
28 for option in args:
29 if not option in ["tumorBam", "normalBam", "refFile", "configFile"] and args[option]!=None:
30 conf_file.write("%s=%s\n" % (option, args[option]))
31 conf_file.close()
32
33 def my_Popen(cmd, prefix_for_stderr_name, tmp_dir, msg_error):
34 stderr_name = tempfile.NamedTemporaryFile( prefix = prefix_for_stderr_name ).name
35 proc = subprocess.Popen( args=cmd, shell=True, stderr=open( stderr_name, 'wb' ) )
36 return_code = proc.wait()
37 if return_code:
38 for line in open( stderr_name ):
39 print(line, file=sys.stderr)
40 os.unlink( stderr_name ) #clean up
41 cleanup_before_exit( tmp_dir )
42 raise Exception( msg_error )
43 else:
44 os.unlink( stderr_name )
45
46 def index_bam_files( bam_filenames, tmp_dir ):
47 for bam_filename in bam_filenames:
48 bam_index_filename = "%s.bai" % bam_filename
49 print("bam_filename is: " + bam_filename + " bam_index_filename is: " + bam_index_filename + " test is: %s" % os.path.exists(bam_index_filename))
50 if not os.path.exists( bam_index_filename ):
51 #need to index this bam file
52 command = 'samtools index %s %s' % ( bam_filename, bam_index_filename )
53 my_Popen( command, "bam_index_stderr", tmp_dir, "Error during indexation of fasta file :" + bam_filename)
54
55 def index_fasta_files( fasta_filenames, tmp_dir ):
56 for fasta_filename in fasta_filenames:
57 fasta_index_filename = "%s.fai" % fasta_filename
58 print("fasta_filename is: " + fasta_filename + " fasta_index_filename is: " + fasta_index_filename + " test is: %s" % os.path.exists(fasta_index_filename))
59 if not os.path.exists( fasta_index_filename ):
60 #need to index this bam file
61 command = 'samtools faidx %s %s' % ( fasta_filename, fasta_index_filename )
62 my_Popen( command, "fasta_index_stderr", tmp_dir, "Error during indexation of fasta file :" + fasta_filename)
63
64 def __main__():
65 #Parse Command Line OPTPARSE DEPRECIATED USE ARGPARSE INSTEAD
66 #MKTEMP DEPRECIATED USE MKDTlizations#EMP INSTEAD
67
68 root_dir= "/home/galaxyusr/data/galaxy_dist/tools/strelka2"
69 expected_dir="for_tests"
70 job_dir=os.getcwd()
71 analysis_dir=job_dir + "/StrelkaAnalysis"
72 config_script=root_dir + "/configureStrelkaWorkflow.pl"
73 tmp_dir = "tmp" #tempfile.mkdtemp( prefix='tmp-strelkaAnalysis-' )
74 config_ini = "%s/config.ini" % (tmp_dir)
75
76 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)
77
78 #manage parsing
79 parser = argparse.ArgumentParser()
80 parser.add_argument( '-t', '--tumorBam', help='path to tumor bam file', required = False )
81 parser.add_argument( '-n', '--normalBam', help='path to tumor bam file', required = False )
82 parser.add_argument( '-r', '--refFile', help='path to tumor bam file', required = False )
83 parser.add_argument( '-c', '--configFile', help='path to tumor bam file', required = False )
84 parser.add_argument( '--depthFilterMultiple', help='path to tumor bam file', required = False )
85 parser.add_argument( '--snvMaxFilteredBasecallFrac', help='path to tumor bam file', required = False )
86 parser.add_argument( '--snvMaxSpanningDeletionFrac', help='path to tumor bam file', required = False )
87 parser.add_argument( '--indelMaxRefRepeat', help='path to tumor bam file', required = False )
88 parser.add_argument( '--indelMaxWindowFilteredBasecallFrac', help='path to tumor bam file', required = False )
89 parser.add_argument( '--indelMaxIntHpolLength', help='path to tumor bam file', required = False )
90 parser.add_argument( '--ssnvPrior', help='path to tumor bam file', required = False )
91 parser.add_argument( '--sindelPrior', help='path to tumor bam file', required = False )
92 parser.add_argument( '--ssnvNoise', help='path to tumor bam file', required = False )
93 parser.add_argument( '--sindelNoise', help='path to tumor bam file', required = False )
94 parser.add_argument( '--ssnvNoiseStrandBiasFrac', help='path to tumor bam file', required = False )
95 parser.add_argument( '--minTier1Mapq', help='path to tumor bam file', required = False )
96 parser.add_argument( '--minTier2Mapq', help='path to tumor bam file', required = False )
97 parser.add_argument( '--ssnvQuality_LowerBound', help='path to tumor bam file', required = False )
98 parser.add_argument( '--sindelQuality_LowerBound', help='path to tumor bam file', required = False )
99 parser.add_argument( '--isWriteRealignedBam', help='path to tumor bam file', required = False )
100 parser.add_argument( '--binSize', help='path to tumor bam file', required = False )
101 parser.add_argument( '--extraStrelkaArguments', help='path to tumor bam file', required = False )
102 parser.add_argument( '--isSkipDepthFilters', help='path to tumor bam file', required = False )
103 parser.add_argument( '--maxInputDepth', help='path to tumor bam file', required = False )
104 args = parser.parse_args()
105
106 #verifying eveything's ok
107 if not os.path.isfile(config_script):
108 sys.exit("ERROR: The strelka workflow must be built prior to running. See installation instructions in '$root_dir/README'")
109 print("configuring...", file=sys.stdout)
110 if os.path.exists(analysis_dir):
111 sys.exit("'" + analysis_dir + "' already exist, if you are executing this tool from galaxy it should not happen")
112
113
114 # creating index if needed
115 os.environ['PATH']= root_dir + "/opt/samtools:" + os.environ['PATH']
116 bam_filenames = [ args.tumorBam, args.normalBam ]
117 index_bam_files( bam_filenames, tmp_dir )
118 fasta_files = [ args.refFile ]
119 index_fasta_files( fasta_files, tmp_dir )
120
121 #creating config file if needed
122 if args.configFile == "Custom":
123 _create_config(vars(args), config_ini)
124 elif args.configFile == "Default":
125 cmdbash="cp %s %s" % (root_dir + "/strelka_config.sample", config_ini)
126 my_Popen(cmdbash, "copy_default_file_err", tmp_dir, "Error during the copy of default config file, maybe it was removed")
127 else:
128 if not os.path.exists(args.configFile):
129 print( "The path to your configuration File seems to be wrong, use another one or custom option", file=sys.stderr)
130 cmdbash="cp %s %s" % (args.configFile, config_ini)
131 my_Popen(cmdbash, "copy_default_file_err", tmp_dir, "Error during the copy of default config file, maybe it was removed")
132
133
134
135
136 #configuration of workflow
137 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)
138 print( "**** Starting configuration.")
139 print( "**** Configuration cmd: '" + cmd + "'")
140 my_Popen( cmd, "cinfugation_stderr", tmp_dir, "Error during configuration !")
141 print("completed configuration")
142
143 #run the workflow !
144 cmd="make -C " + analysis_dir
145 print("**** starting workflow.")
146 print("**** workflow cmd: '" + cmd + "'")
147 my_Popen( cmd, "workflow_stderr", tmp_dir, "Error during workflow execution !")
148 print("**** completed workflow execution")
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163 #bam_filenames = []
164 # if options.datasets:
165 # for ( dataset_arg, filename, galaxy_ext, prefix ) in options.datasets:
166 # 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
167 # if dataset_arg:
168 # cmd = '%s %s "%s"' % ( cmd, gatk_filetype_argument_substitution( dataset_arg, galaxy_ext ), gatk_filename )
169 # if galaxy_ext == "bam":
170 # bam_filenames.append( gatk_filename )
171 # #set up stdout and stderr output options
172 # stdout = open_file_from_option( options.stdout, mode = 'wb' )
173 # stderr = open_file_from_option( options.stderr, mode = 'wb' )
174 # #if no stderr file is specified, we'll use our own
175 # if stderr is None:
176 # stderr = tempfile.NamedTemporaryFile( prefix="strelka-stderr-", dir=tmp_dir )
177 #
178 # proc = subprocess.Popen( args=cmd, stdout=stdout, stderr=stderr, shell=True, cwd=tmp_dir )
179 # return_code = proc.wait()
180 #
181 # if return_code:
182 # stderr_target = sys.stderr
183 # else:
184 # stderr_target = sys.stdout
185 # stderr.flush()
186 # stderr.seek(0)
187 # while True:
188 # chunk = stderr.read( CHUNK_SIZE )
189 # if chunk:
190 # stderr_target.write( chunk )
191 # else:
192 # break
193 # stderr.close()
194 # #generate html reports
195 # if options.html_report_from_directory:
196 # for ( html_filename, html_dir ) in options.html_report_from_directory:
197 # html_report_from_directory( open( html_filename, 'wb' ), html_dir )
198 #
199 # cleanup_before_exit( tmp_dir )
200
201 if __name__=="__main__": __main__()