def run_bax_to_bam(input_file_name, output_file_name):
with HdfSubreadSet(input_file_name) as ds_in:
movies = set()
for rr in ds_in.resourceReaders():
movies.add(rr.movieName)
if len(movies) > 1:
out_dir = os.path.dirname(output_file_name)
ds_out_files = []
for bax_file in ds_in.toExternalFiles():
output_file_name_tmp = os.path.join(out_dir, ".".join(
os.path.basename(bax_file).split(".")[:-2]) +
".hdfsubreadset.xml")
rc = _run_bax_to_bam(bax_file, output_file_name_tmp)
if rc != 0:
log.error("bax2bam failed")
return rc
ds_out_files.append(output_file_name_tmp)
ds = SubreadSet(*ds_out_files)
ds.name = ds_in.name
if 'Description' in ds_in.objMetadata:
ds.objMetadata['Description'] = ds_in.objMetadata['Description']
ds.metadata.merge(ds_in.metadata)
ds.write(output_file_name)
else:
return _run_bax_to_bam(input_file_name, output_file_name)
return 0
def main(parser):
args = parser.parse_args()
filt = Filters()
dset = SubreadSet(args.inXml)
names = nameGen(args.inFile, fileType='list' if args.list else 'fasta')
if args.subreads:
if args.inverted:
for name in names:
filt.addRequirement(QNAME=[('!=', name)])
else:
filt.addRequirement(QNAME=[('=', name) for name in names])
else:
assert len(
dset.movieIds
) == 1, 'This method only works for single-movie subreadsets. use --subreads option for multi-movie subreadsets'
uniqHn = set(map(getZmw, names))
if args.inverted:
for hn in uniqHn:
filt.addRequirement(zm=[('!=', hn)])
else:
filt.addRequirement(zm=[('=', hn) for hn in uniqHn])
dset.addFilters(filt)
if args.newUuid:
dset.newUuid()
if args.name:
dset.name = args.name
dset.write(args.outXml)
def run_bax_to_bam(input_file_name, output_file_name):
with HdfSubreadSet(input_file_name) as ds_in:
movies = set()
for rr in ds_in.resourceReaders():
movies.add(rr.movieName)
if len(movies) > 1:
out_dir = os.path.dirname(output_file_name)
ds_out_files = []
for bax_file in ds_in.toExternalFiles():
output_file_name_tmp = os.path.join(
out_dir,
".".join(os.path.basename(bax_file).split(".")[:-2]) +
".hdfsubreadset.xml")
rc = _run_bax_to_bam(bax_file, output_file_name_tmp)
if rc != 0:
log.error("bax2bam failed")
return rc
ds_out_files.append(output_file_name_tmp)
ds = SubreadSet(*ds_out_files)
ds.name = ds_in.name
if 'Description' in ds_in.objMetadata:
ds.objMetadata['Description'] = ds_in.objMetadata[
'Description']
ds.metadata.merge(ds_in.metadata)
ds.write(output_file_name)
else:
return _run_bax_to_bam(input_file_name, output_file_name)
return 0
def _generateSubreadSet(output_bam_file):
sset = SubreadSet(output_bam_file, generateIndices=True)
sset_output_name = output_bam_file[:-12] + 'subreadset.xml'
sset.name = sset_output_name.split('.')[0]
sset.write(sset_output_name)
return sset_output_name
def run_bam_to_bam(subread_set_file,
barcode_set_file,
output_file_name,
nproc=1,
score_mode="symmetric"):
if not score_mode in ["asymmetric", "symmetric"]:
raise ValueError("Unrecognized score mode '{m}'".format(m=score_mode))
bc = BarcodeSet(barcode_set_file)
if len(bc.resourceReaders()) > 1:
raise NotImplementedError(
"Multi-FASTA BarcodeSet input is not supported.")
barcode_fasta = bc.toExternalFiles()[0]
with SubreadSet(subread_set_file) as ds:
ds_new = SubreadSet(strict=True)
for ext_res in ds.externalResources:
subreads_bam = ext_res.bam
scraps_bam = ext_res.scraps
assert subreads_bam is not None
if scraps_bam is None:
raise TypeError("The input SubreadSet must include scraps.")
new_prefix = op.join(
op.dirname(output_file_name),
re.sub(".subreads.bam", "_barcoded",
op.basename(subreads_bam)))
if not op.isabs(subreads_bam):
subreads_bam = op.join(op.dirname(subread_set_file),
subreads_bam)
if not op.isabs(scraps_bam):
scraps_bam = op.join(op.dirname(subread_set_file), scraps_bam)
args = [
"bam2bam", "-j",
str(nproc), "-b",
str(nproc), "-o", new_prefix, "--barcodes", barcode_fasta,
"--scoreMode", score_mode, subreads_bam, scraps_bam
]
log.info(" ".join(args))
result = run_cmd(" ".join(args),
stdout_fh=sys.stdout,
stderr_fh=sys.stderr)
if result.exit_code != 0:
return result.exit_code
subreads_bam = new_prefix + ".subreads.bam"
scraps_bam = new_prefix + ".scraps.bam"
assert op.isfile(subreads_bam), "Missing {f}".format(
f=subreads_bam)
add_subread_resources(ds_new,
subreads=subreads_bam,
scraps=scraps_bam,
barcodes=barcode_set_file)
ds._filters.clearCallbacks()
ds_new._filters = ds._filters
ds_new._populateMetaTypes()
ds_new.metadata = ds.metadata
ds_new.name = ds.name + " (barcoded)"
ds_new.updateCounts()
ds_new.newUuid()
ds_new.write(output_file_name)
return 0
def run_bam_to_bam(subread_set_file, barcode_set_file, output_file_name,
nproc=1, score_mode="symmetric"):
if not score_mode in ["asymmetric", "symmetric"]:
raise ValueError("Unrecognized score mode '{m}'".format(m=score_mode))
bc = BarcodeSet(barcode_set_file)
if len(bc.resourceReaders()) > 1:
raise NotImplementedError("Multi-FASTA BarcodeSet input is not supported.")
barcode_fasta = bc.toExternalFiles()[0]
with SubreadSet(subread_set_file) as ds:
ds_new = SubreadSet(strict=True)
for ext_res in ds.externalResources:
subreads_bam = ext_res.bam
scraps_bam = ext_res.scraps
assert subreads_bam is not None
if scraps_bam is None:
raise TypeError("The input SubreadSet must include scraps.")
new_prefix = op.join(op.dirname(output_file_name),
re.sub(".subreads.bam", "_barcoded", op.basename(subreads_bam)))
if not op.isabs(subreads_bam):
subreads_bam = op.join(op.dirname(subread_set_file),
subreads_bam)
if not op.isabs(scraps_bam):
scraps_bam = op.join(op.dirname(subread_set_file), scraps_bam)
args = [
"bam2bam",
"-j", str(nproc),
"-b", str(nproc),
"-o", new_prefix,
"--barcodes", barcode_fasta,
"--scoreMode", score_mode,
subreads_bam, scraps_bam
]
log.info(" ".join(args))
result = run_cmd(" ".join(args),
stdout_fh=sys.stdout,
stderr_fh=sys.stderr)
if result.exit_code != 0:
return result.exit_code
subreads_bam = new_prefix + ".subreads.bam"
scraps_bam = new_prefix + ".scraps.bam"
assert op.isfile(subreads_bam), "Missing {f}".format(f=subreads_bam)
add_subread_resources(ds_new,
subreads=subreads_bam,
scraps=scraps_bam,
barcodes=barcode_set_file)
ds._filters.clearCallbacks()
ds_new._filters = ds._filters
ds_new._populateMetaTypes()
ds_new.metadata = ds.metadata
ds_new.name = ds.name + " (barcoded)"
ds_new.updateCounts()
ds_new.newUuid()
ds_new.write(output_file_name)
return 0
def test_sanitize_dataset_tags(self):
ds = SubreadSet(pbtestdata.get_file("subreads-sequel"))
base_name = ds.name
ds.name = ds.name + " (filtered) (CCS)"
ds.tags = "subreads,hidden,testdata,filtered "
sanitize_dataset_tags(ds)
assert ds.name == base_name + " (CCS)"
assert ds.tags == "hidden,subreads,testdata"
sanitize_dataset_tags(ds, remove_hidden=True)
assert ds.name == base_name + " (CCS)"
assert ds.tags == "subreads,testdata"
ds.tags = ", hidden, ccs"
sanitize_dataset_tags(ds, remove_hidden=True)
assert ds.tags == "ccs"
def test_mock_update_barcoded_sample_metadata(self):
tmp_dir = tempfile.mkdtemp()
datastore_tmp = op.join(tmp_dir, "lima.datastore.json")
barcodeset = pbtestdata.get_file("barcodeset")
barcodes = ["lbc1--lbc1", "lbc3--lbc3"]
files = [
op.join(tmp_dir, "lima.lbc1--lbc1.subreadset.xml"),
op.join(tmp_dir, "lima.lbc3--lbc3.subreadset.xml")
]
uuids = [uuid.uuid4() for fn in files]
# XXX these are hardcoded to match the actual barcoded test input
bc_uuids = [
"dffb30e8-9243-4743-9980-468a20952167",
"eef1a8ea-c6a7-4233-982a-d426e1e7d8c9"
]
ds = SubreadSet(pbtestdata.get_file("subreads-sequel"))
def _add_barcoded_sample(sn, bn, id_):
ds.metadata.collections[0].wellSample.bioSamples.addSample(sn)
ds.metadata.collections[0].wellSample.bioSamples[
-1].DNABarcodes.addBarcode(bn)
ds.metadata.collections[0].wellSample.bioSamples[-1].DNABarcodes[
-1].uniqueId = id_
_add_barcoded_sample("Alice", "lbc1--lbc1", bc_uuids[0])
_add_barcoded_sample("Charles", "lbc3--lbc3", bc_uuids[1])
tmp_ds = op.join(tmp_dir, "input.subreadset.xml")
ds.write(tmp_ds)
for fn, bc, dsid in zip(files, barcodes, uuids):
ds = SubreadSet(tmp_ds)
ds.uuid = str(dsid)
ds.name = ds.name + " ({b})".format(b=bc)
ds.write(fn)
ds_files = [
DataStoreFile(dsid, "barcoding.tasks.lima-0",
FileTypes.DS_SUBREADS.file_type_id, fn)
for (dsid, fn) in zip(uuids, files)
]
ds = DataStore(ds_files)
ds.write_json(datastore_tmp)
base_dir = tempfile.mkdtemp()
datastore = mock_update_barcoded_sample_metadata(
base_dir, datastore_tmp, tmp_ds, barcodeset)
validate_barcoded_datastore_files(self,
tmp_ds,
datastore,
number_of_expected_filters=0)