def get_cellular_barcodes(data):
if dd.get_cellular_barcodes(data):
return dd.get_cellular_barcodes(data)
if is_supported_transform(data):
stem = dd.get_umi_type(data)
bc1 = os.path.join(TRANSFORM_DIR, stem + "-cb1.txt")
bc2 = os.path.join(TRANSFORM_DIR, stem + "-cb2.txt")
return filter(file_exists, [bc1, bc2])
else:
return []
def get_cellular_barcodes(data):
if dd.get_cellular_barcodes(data):
return dd.get_cellular_barcodes(data)
if is_supported_transform(data):
stem = dd.get_umi_type(data)
bc1 = os.path.join(TRANSFORM_DIR, stem + "-cb1.txt")
bc2 = os.path.join(TRANSFORM_DIR, stem + "-cb2.txt")
bc3 = os.path.join(TRANSFORM_DIR, stem + "-cb3.txt")
return filter(file_exists, [bc1, bc2, bc3])
else:
return []
def umi_transform(data):
"""
transform each read by identifying the barcode and UMI for each read
and putting the information in the read name
"""
fq1, fq2 = dd.get_input_sequence_files(data)
fq2 = fq2 if fq2 else ""
umi_dir = os.path.join(dd.get_work_dir(data), "umis")
transform = dd.get_umi_type(data)
transform_data = transforms[transform]
safe_makedir(umi_dir)
transform_file = os.path.join(umi_dir, transform + ".json")
transform_file = write_transform_file(transform_data, transform_file)
out_base = dd.get_sample_name(data) + ".umitransformed.fq.gz"
out_file = os.path.join(umi_dir, out_base)
if file_exists(out_file):
data["files"] = [out_file]
return [[data]]
index_option = "--dual_index" if transform_data["dual"] else ""
if len(dd.get_cellular_barcodes(data)) == 2:
split_option = "--separate_cb"
else:
split_option = ""
umis = config_utils.get_program("umis", data, default="umis")
cmd = (
"{umis} fastqtransform {index_option} {split_option} {transform_file} "
"{fq1} {fq2} "
"| seqtk seq -L 20 - | gzip > {tx_out_file}")
message = (
"Inserting UMI and barcode information into the read name of %s" % fq1)
with file_transaction(out_file) as tx_out_file:
do.run(cmd.format(**locals()), message)
data["files"] = [out_file]
return [[data]]
def umi_transform(data):
"""
transform each read by identifying the barcode and UMI for each read
and putting the information in the read name
"""
fq1, fq2 = dd.get_input_sequence_files(data)
fq2 = fq2 if fq2 else ""
umi_dir = os.path.join(dd.get_work_dir(data), "umis")
transform = dd.get_umi_type(data)
transform_data = transforms[transform]
safe_makedir(umi_dir)
transform_file = os.path.join(umi_dir, transform + ".json")
transform_file = write_transform_file(transform_data, transform_file)
out_base = dd.get_sample_name(data) + ".umitransformed.fq.gz"
out_file = os.path.join(umi_dir, out_base)
if file_exists(out_file):
data["files"] = [out_file]
return [[data]]
index_option = "--dual_index" if transform_data["dual"] else ""
if len(dd.get_cellular_barcodes(data)) == 2:
split_option = "--separate_cb"
else:
split_option = ""
umis = config_utils.get_program("umis", data, default="umis")
cmd = ("{umis} fastqtransform {index_option} {split_option} {transform_file} "
"{fq1} {fq2} "
"| seqtk seq -L 20 - | gzip > {tx_out_file}")
message = ("Inserting UMI and barcode information into the read name of %s"
% fq1)
with file_transaction(out_file) as tx_out_file:
do.run(cmd.format(**locals()), message)
data["files"] = [out_file]
return [[data]]
def umi_transform(data):
"""
transform each read by identifying the barcode and UMI for each read
and putting the information in the read name
"""
fqfiles = data["files"]
fqfiles.extend(list(repeat("", 4 - len(fqfiles))))
fq1, fq2, fq3, fq4 = fqfiles
umi_dir = os.path.join(dd.get_work_dir(data), "umis")
safe_makedir(umi_dir)
transform = dd.get_umi_type(data)
if file_exists(transform):
transform_file = transform
else:
transform_data = transforms.get(transform, "")
if not transform_data:
logger.error(
"The UMI transform can be specified as either a file or a "
"bcbio-supported transform. Either the file %s does not exist "
"or the transform is not supported by bcbio.")
sys.exit(1)
transform_file = os.path.join(umi_dir, transform + ".json")
transform_file = write_transform_file(transform_data, transform_file)
out_base = dd.get_sample_name(data) + ".umitransformed.fq.gz"
out_file = os.path.join(umi_dir, out_base)
if file_exists(out_file):
data["files"] = [out_file]
return [[data]]
if len(dd.get_cellular_barcodes(data)) == 2:
split_option = "--separate_cb"
else:
split_option = ""
umis = config_utils.get_program("umis", data, default="umis")
cores = dd.get_num_cores(data)
# skip transformation if the file already looks transformed
with open_fastq(fq1) as in_handle:
read = in_handle.next()
if "UMI_" in read:
data["files"] = [out_file]
return [[data]]
cmd = ("{umis} fastqtransform {split_option} {transform_file} "
"--cores {cores} "
"{fq1} {fq2} {fq3} {fq4}"
"| seqtk seq -L 20 - | gzip > {tx_out_file}")
message = (
"Inserting UMI and barcode information into the read name of %s" % fq1)
with file_transaction(out_file) as tx_out_file:
do.run(cmd.format(**locals()), message)
data["files"] = [out_file]
return [[data]]
def umi_transform(data):
"""
transform each read by identifying the barcode and UMI for each read
and putting the information in the read name
"""
fqfiles = data["files"]
fqfiles.extend(list(repeat("", 4-len(fqfiles))))
fq1, fq2, fq3, fq4 = fqfiles
umi_dir = os.path.join(dd.get_work_dir(data), "umis")
safe_makedir(umi_dir)
transform = dd.get_umi_type(data)
if file_exists(transform):
transform_file = transform
else:
transform_data = transforms.get(transform, "")
if not transform_data:
logger.error(
"The UMI transform can be specified as either a file or a "
"bcbio-supported transform. Either the file %s does not exist "
"or the transform is not supported by bcbio.")
sys.exit(1)
transform_file = os.path.join(umi_dir, transform + ".json")
transform_file = write_transform_file(transform_data, transform_file)
out_base = dd.get_sample_name(data) + ".umitransformed.fq.gz"
out_file = os.path.join(umi_dir, out_base)
if file_exists(out_file):
data["files"] = [out_file]
return [[data]]
if len(dd.get_cellular_barcodes(data)) == 2:
split_option = "--separate_cb"
else:
split_option = ""
umis = config_utils.get_program("umis", data, default="umis")
cores = dd.get_num_cores(data)
# skip transformation if the file already looks transformed
with open_fastq(fq1) as in_handle:
read = in_handle.next()
if "UMI_" in read:
data["files"] = [out_file]
return [[data]]
cmd = ("{umis} fastqtransform {split_option} {transform_file} "
"--cores {cores} "
"{fq1} {fq2} {fq3} {fq4}"
"| seqtk seq -L 20 - | gzip > {tx_out_file}")
message = ("Inserting UMI and barcode information into the read name of %s"
% fq1)
with file_transaction(out_file) as tx_out_file:
do.run(cmd.format(**locals()), message)
data["files"] = [out_file]
return [[data]]
def filter_barcodes(data):
fq1 = dd.get_input_sequence_files(data)[0]
umi_dir = os.path.join(dd.get_work_dir(data), "umis")
correction = dd.get_cellular_barcode_correction(data)
bc = dd.get_cellular_barcodes(data)
if not bc:
return [[data]]
bc1 = None
bc2 = None
umi_dir = os.path.join(dd.get_work_dir(data), "umis")
if isinstance(bc, basestring):
bc1 = bc
if len(bc) == 1:
bc1 = bc[0]
if len(bc) == 2:
bc1 = bc[0]
bc2 = bc[1]
out_base = dd.get_sample_name(data) + ".filtered.fq.gz"
out_file = os.path.join(umi_dir, out_base)
if file_exists(out_file):
data["files"] = [out_file]
return [[data]]
ncores = dd.get_num_cores(data)
cmd = "{umis} cb_filter --cores {ncores} "
if bc1:
cmd += "--bc1 {bc1} "
if correction:
cmd += "--nedit {correction} "
if bc2:
cmd += "--bc2 {bc2} "
fq1_cmd = "{fq1} " if not is_gzipped(fq1) else "<(gzip -cd {fq1}) "
fq1_cmd = fq1_cmd.format(fq1=fq1)
cmd += "{fq1_cmd} | gzip > {tx_out_file}"
sample_dir = os.path.join(umi_dir, dd.get_sample_name(data))
safe_makedir(sample_dir)
umis = config_utils.get_program("umis", data, default="umis")
with file_transaction(out_file) as tx_out_file:
message = "Filtering by cellular barcode."
do.run(cmd.format(**locals()), message)
data["files"] = [out_file]
return [[data]]
def filter_barcodes(data):
fq1 = dd.get_input_sequence_files(data)[0]
umi_dir = os.path.join(dd.get_work_dir(data), "umis")
correction = dd.get_cellular_barcode_correction(data)
bc = dd.get_cellular_barcodes(data)
if not bc:
return [[data]]
bc1 = None
bc2 = None
umi_dir = os.path.join(dd.get_work_dir(data), "umis")
if isinstance(bc, basestring):
bc1 = bc
if len(bc) == 1:
bc1 = bc[0]
if len(bc) == 2:
bc1 = bc[0]
bc2 = bc[1]
out_base = dd.get_sample_name(data) + ".filtered.fq.gz"
out_file = os.path.join(umi_dir, out_base)
if file_exists(out_file):
data["files"] = [out_file]
return [[data]]
ncores = dd.get_num_cores(data)
cmd = "{umis} cb_filter --cores {ncores} "
if bc1:
cmd += "--bc1 {bc1} "
if correction:
cmd += "--nedit {correction} "
if bc2:
cmd += "--bc2 {bc2} "
fq1_cmd = "{fq1} " if not is_gzipped(fq1) else "<(gzip -cd {fq1}) "
fq1_cmd = fq1_cmd.format(fq1=fq1)
cmd += "{fq1_cmd} | gzip > {tx_out_file}"
sample_dir = os.path.join(umi_dir, dd.get_sample_name(data))
safe_makedir(sample_dir)
umis = config_utils.get_program("umis", data, default="umis")
with file_transaction(out_file) as tx_out_file:
message = "Filtering by cellular barcode."
do.run(cmd.format(**locals()), message)
data["files"] = [out_file]
return [[data]]
