zzh
/
gatk-3.8
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

The system now requires a dictionary file for a fasta file, or it throws an error. You can't just operate without a sequence dictionary any longer. We will transition to a GenomeLoc system that assumes a dictionary is available. 

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@320 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
depristo 2009-04-07 22:21:57 +00:00
parent 00722e19bc
commit 9d35f0ca67
1 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
python/StressTestGATK.py
View File

@ -9,11 +9,12 @@ def usage():
print "Optional arguments:" print "Optional arguments:"
print " -f QUEUE Farm jobs to QUEUE on LSF" print " -f QUEUE Farm jobs to QUEUE on LSF"
print " -c cmd1,cmd2 Walkers to execute, otherwise", ' '.join(defaultCommands) print " -c cmd1,cmd2 Walkers to execute, otherwise", ' '.join(defaultCommands)
print " -e Ignore existing files", ' '.join(defaultCommands)
if __name__ == "__main__": if __name__ == "__main__":
opts = None opts = None
try: try:
opts, args = getopt.getopt(sys.argv[1:], "f:c:i", ["farm", "commands", "ignoreExistingFiles"]) opts, args = getopt.getopt(sys.argv[1:], "f:c:a:e", ["farm", "commands", "args", "ignoreExistingFiles"])
except getopt.GetoptError: except getopt.GetoptError:
print sys.argv print sys.argv
usage() usage()
@ -22,6 +23,7 @@ if __name__ == "__main__":
farm_sub = False farm_sub = False
commandsList = defaultCommands commandsList = defaultCommands
ignoreExistingFiles = False ignoreExistingFiles = False
extraArgs = ''
for opt, arg in opts: for opt, arg in opts:
if opt in ("-f", "--farm"): if opt in ("-f", "--farm"):
@ -30,10 +32,17 @@ if __name__ == "__main__":
commandsList = arg.split(',') commandsList = arg.split(',')
if opt in ("-e", "--ignoreExistingFiles"): if opt in ("-e", "--ignoreExistingFiles"):
ignoreExistingFiles = True ignoreExistingFiles = True
if opt in ("-a", "--args"):
extraArgs = arg
directory = args[1] directory = args[1]
for line in open(args[0]): for line in open(args[0]):
lane = line.strip() lineParts = line.split()
lane = lineParts[0].strip()
ref = '/seq/references/Homo_sapiens_assembly18/v0/Homo_sapiens_assembly18.fasta'
if ( len(lineParts) > 1 ):
ref = lineParts[1].strip()
if not os.path.exists(lane): if not os.path.exists(lane):
print 'Input SAM/BAM file: "', lane, '" does not exist, skipping...' print 'Input SAM/BAM file: "', lane, '" does not exist, skipping...'
@ -46,7 +55,7 @@ if __name__ == "__main__":
for analysis in commandsList: for analysis in commandsList:
output = os.path.join(directory, filebase + '.' + analysis + '.output') output = os.path.join(directory, filebase + '.' + analysis + '.output')
if ignoreExistingFiles or not os.path.exists(output): if ignoreExistingFiles or not os.path.exists(output):
cmd = "java -jar ~/dev/GenomeAnalysisTK/trunk/dist/GenomeAnalysisTK.jar T=" + analysis + " I= " + lane + " R= /seq/references/Homo_sapiens_assembly18/v0/Homo_sapiens_assembly18.fasta " cmd = "java -jar ~/dev/GenomeAnalysisTK/trunk/dist/GenomeAnalysisTK.jar -T " + analysis + " -I " + lane + " -R " + ref + " -o " + output + " -l INFO " + extraArgs
print cmd print cmd
farm_commands.cmd(cmd, farm_sub, output) farm_commands.cmd(cmd, farm_sub, output)