def single_copy_wrapper(target, args):
"""
Main pipeline wrapper. Runs halSingleCopyRegionsExtract once for each region in the conserved_bed file.
"""
bed_recs = [x.split()[:3] for x in open(args.conserved_bed)]
result_dir = target.getGlobalTempDir()
result_tree = TempFileTree(result_dir)
for chunk in grouper(bed_recs, 10):
result_path = result_tree.getTempFile()
target.addChildTargetFn(find_single_copy,
args=(args, chunk, result_path))
target.setFollowOnTargetFn(cat_results,
args=(args, result_tree.listFiles()))
def extract_maf_wrapper(target, args):
"""
Main pipeline wrapper. Calls out to hal2maf once for each region in args.conserved_bed
"""
accelerated_genomes = set(args.accelerated_genomes + [args.ref_genome])
outgroup_genomes = set(args.target_genomes) - accelerated_genomes
bed_recs = [x.split() for x in open(args.conserved_bed)]
result_dir = target.getGlobalTempDir()
result_tree = TempFileTree(result_dir)
for chunk in grouper(bed_recs, 50):
result_path = result_tree.getTempFile()
target.addChildTargetFn(extract_and_calculate, args=(args, chunk, accelerated_genomes, outgroup_genomes, result_path))
target.setFollowOnTargetFn(cat_results, args=(args, result_tree.listFiles()))
def testTempFileTree(self):
for test in range(100): #self.testNo):
levels = random.choice(range(1, 4))
fileNo = random.choice(range(1, 6))
maxTempFiles = int(math.pow(fileNo, levels))
print("Got %s levels, %s fileNo and %s maxTempFiles" %
(levels, fileNo, maxTempFiles))
tempFileTreeRootDir = os.path.join(self.tempDir,
getRandomAlphaNumericString())
tempFileTree = TempFileTree(tempFileTreeRootDir, fileNo, levels)
tempFiles = []
tempDirs = []
#Check we can mac number of temp files.
for i in range(maxTempFiles):
if random.random() > 0.5:
tempFile = tempFileTree.getTempFile()
assert os.path.isfile(tempFile)
tempFiles.append(tempFile)
else:
tempFile = tempFileTree.getTempDirectory()
assert os.path.isdir(tempFile)
tempDirs.append(tempFile)
#Check assertion is created
try:
tempFileTree.getTempFile()
assert False
except RuntimeError:
logger.debug("Got expected error message")
#Now remove a few temp files
while random.random() > 0.1 and len(tempFiles) > 0:
tempFile = tempFiles.pop()
assert os.path.isfile(tempFile)
tempFileTree.destroyTempFile(tempFile)
assert not os.path.isfile(tempFile)
#Now remove a few temp dirs
while random.random() > 0.1 and len(tempDirs) > 0:
tempDir = tempDirs.pop()
assert os.path.isdir(tempDir)
tempFileTree.destroyTempDir(tempDir)
assert not os.path.isdir(tempDir)
#Check temp files is okay
set(tempFileTree.listFiles()) == set(tempFiles + tempDirs)
#Either remove all the temp files or just destroy the whole thing
if random.random() > 0.5:
#Remove all temp files and check thing is empty.
for tempFile in tempFiles:
tempFileTree.destroyTempFile(tempFile)
for tempDir in tempDirs:
tempFileTree.destroyTempDir(tempDir)
os.remove(os.path.join(tempFileTreeRootDir, "lock"))
os.rmdir(tempFileTreeRootDir)
else:
tempFileTree.destroyTempFiles()
assert not os.path.isdir(tempFileTreeRootDir)