def do_realign(dataHub, sample):
processes = dataHub.args.processes
if processes is None or processes == 0:
# we don't really gain from using virtual cores, so try to figure out how many physical
# cores we have
processes = misc.cpu_count_physical()
variant = dataHub.variant
reads = sample.reads
name = "{}:{{}}".format(sample.name[:15])
t0 = time.time()
refalignments = do1remap(variant.chromParts("ref"), reads, processes, jobName=name.format("ref"))
altalignments = do1remap(variant.chromParts("alt"), reads, processes, jobName=name.format("alt"))
t1 = time.time()
logging.debug(" Time to realign: {:.1f}s".format(t1-t0))
assert refalignments.keys() == altalignments.keys()
alnCollections = []
for key in refalignments:
alnCollection = AlignmentSetCollection(key)
alnCollection.addSet(refalignments[key], "ref")
alnCollection.addSet(altalignments[key], "alt")
alnCollections.append(alnCollection)
return alnCollections
def do_realign(dataHub, sample):
processes = dataHub.args.processes
if processes is None or processes == 0:
# we don't really gain from using virtual cores, so try to figure out how many physical
# cores we have
processes = misc.cpu_count_physical()
variant = dataHub.variant
reads = sample.reads
name = "{}:{{}}".format(sample.name[:15])
t0 = time.time()
refalignments = do1remap(variant.chromParts("ref"),
reads,
processes,
jobName=name.format("ref"))
altalignments = do1remap(variant.chromParts("alt"),
reads,
processes,
jobName=name.format("alt"))
t1 = time.time()
logging.debug(" Time to realign: {:.1f}s".format(t1 - t0))
assert refalignments.keys() == altalignments.keys()
alnCollections = []
for key in refalignments:
alnCollection = AlignmentSetCollection(key)
alnCollection.addSet(refalignments[key], "ref")
alnCollection.addSet(altalignments[key], "alt")
alnCollections.append(alnCollection)
return alnCollections
def do_realign(dataHub, sample):
processes = dataHub.args.processes
if processes is None or processes == 0:
# we don't really gain from using virtual cores, so try to figure out how many physical
# cores we have
processes = misc.cpu_count_physical()
variant = dataHub.variant
reads = sample.reads
name = "{}:{{}}".format(sample.name[:15])
t0 = time.time()
refalignments, badReadsRef = do1remap(variant.chromParts("ref"),
reads,
processes,
jobName=name.format("ref"),
tryExact=dataHub.args.fast)
altalignments, badReadsAlt = do1remap(variant.chromParts("alt"),
reads,
processes,
jobName=name.format("alt"),
tryExact=dataHub.args.fast)
t1 = time.time()
logging.debug(" Time to realign: {:.1f}s".format(t1 - t0))
badReads = badReadsRef.union(badReadsAlt)
if len(badReads) > 0:
logging.warn(
" Alignment failed with {} reads (this is a known issue)".format(
badReads))
for badRead in badReads:
refalignments.pop(badRead, None)
altalignments.pop(badRead, None)
assert set(refalignments.keys()) == set(altalignments.keys()), \
set(refalignments.keys()) ^ set(altalignments.keys())
alnCollections = []
for key in refalignments:
alnCollection = AlignmentSetCollection(key)
alnCollection.addSet(refalignments[key], "ref")
alnCollection.addSet(altalignments[key], "alt")
alnCollections.append(alnCollection)
return alnCollections
def do_realign(dataHub, sample):
processes = dataHub.args.processes
if processes is None or processes == 0:
# we don't really gain from using virtual cores, so try to figure out how many physical
# cores we have
processes = misc.cpu_count_physical()
variant = dataHub.variant
reads = sample.reads
name = "{}:{{}}".format(sample.name[:15])
t0 = time.time()
refalignments, badReadsRef = do1remap(variant.chromParts("ref"), reads, processes,
jobName=name.format("ref"), tryExact=dataHub.args.fast)
altalignments, badReadsAlt = do1remap(variant.chromParts("alt"), reads, processes,
jobName=name.format("alt"), tryExact=dataHub.args.fast)
t1 = time.time()
logging.debug(" Time to realign: {:.1f}s".format(t1-t0))
badReads = badReadsRef.union(badReadsAlt)
if len(badReads) > 0:
logging.warn(" Alignment failed with {} reads (this is a known issue)".format(badReads))
for badRead in badReads:
refalignments.pop(badRead, None)
altalignments.pop(badRead, None)
assert set(refalignments.keys()) == set(altalignments.keys()), \
set(refalignments.keys()) ^ set(altalignments.keys())
alnCollections = []
for key in refalignments:
alnCollection = AlignmentSetCollection(key)
alnCollection.addSet(refalignments[key], "ref")
alnCollection.addSet(altalignments[key], "alt")
alnCollections.append(alnCollection)
return alnCollections
def do_realign(variant, reads, processes=None):
if processes is None or processes == 0:
# we don't really gain from using virtual cores, so try to figure out how many physical
# cores we have
processes = misc.cpu_count_physical()
t0 = time.time()
refalignments = do1remap(variant.chromParts("ref"), reads, processes)
altalignments = do1remap(variant.chromParts("alt"), reads, processes)
t1 = time.time()
logging.debug(" time for realigning:{}".format(t1 - t0))
assert refalignments.keys() == altalignments.keys()
alnCollections = []
for key in refalignments:
alnCollection = AlignmentSetCollection(key)
alnCollection.addSet(refalignments[key], "ref")
alnCollection.addSet(altalignments[key], "alt")
alnCollections.append(alnCollection)
return alnCollections
