def main(argv=sys.argv[1:]):
"""
Basic command line interface to qcat.
:param argv: Command line arguments
:type argv: list
:return: None
:rtype: NoneType
"""
try:
args = parse_args(argv=argv)
qcat_config = config.get_default_config()
numeric_level = getattr(logging, args.log.upper(), None)
if not isinstance(numeric_level, int):
raise ValueError('Invalid log level: %s' % args.log.upper())
logging.basicConfig(level=numeric_level, format='%(message)s')
if args.list_kits:
kits = get_kits_info()
for kit in sorted(kits.keys()):
if kit != "auto" and kit != "DUAL":
logging.info("{:<30}{}".format(kit, kits[kit]))
return
mode = get_mode(args)
kit = args.kit
if mode == "simple":
kit = args.SIMPLE_BARCODES
start = time.time()
qcat_cli(
reads_fq=args.fastq,
# no_header=args.no_header,
kit=kit,
mode=mode,
nobatch=args.nobatch,
out=args.barcode_dir,
min_qual=args.min_qual,
tsv=args.tsv,
output=args.output,
threads=args.threads,
trim=args.TRIM,
adapter_yaml=None, #=args.adapter_yaml, #args.barcode_fa,
quiet=args.QUIET,
filter_barcodes=args.FILTER_BARCODES,
middle_adapter=args.DETECT_MIDDLE,
min_read_length=args.min_length,
qcat_config=qcat_config)
end = time.time()
if not args.QUIET:
logging.info("Demultiplexing finished in {0:.2f}s".format(end -
start))
except IOError as e:
logging.error(e)
except ValueError as e:
logging.error(e)
def test_scanner_find_best_adapter_template():
qcat_config = config.get_default_config()
best_adapter_template, best_adapter_end_position, best_adapter_score =\
find_best_adapter_template(None, None, qcat_config)
assert best_adapter_template == -1
assert best_adapter_end_position == -1
best_adapter_template, best_adapter_end_position, best_adapter_score = \
find_best_adapter_template(get_adapter_by_name("RBK001"), read_bc3_exact, qcat_config)
assert best_adapter_template == 0
assert best_adapter_end_position == 101
def test_scanner_detect_barcode_generic():
qcat_config = config.get_default_config()
# config.min_quality = 0.1
detector = BarcodeScannerEPI2ME()
seq = extract_align_sequence(read, False, qcat_config.max_align_length)
barcode_dict = detector.detect_barcode(seq, qcat_config=qcat_config)
assert barcode_dict['barcode'].name == "barcode02"
seq = extract_align_sequence(read_bc3_exact, False, qcat_config.max_align_length)
barcode_dict = detector.detect_barcode(seq, qcat_config=qcat_config)
assert barcode_dict['barcode'].name == "barcode03"
seq = extract_align_sequence(read_bc3, False,
qcat_config.max_align_length)
barcode_dict = detector.detect_barcode(seq, qcat_config=qcat_config)
assert barcode_dict['barcode'].name == "barcode03"
seq = extract_align_sequence(real_bc03_porechop, False,
qcat_config.max_align_length)
barcode_dict = detector.detect_barcode(seq)
assert barcode_dict['barcode'].name == "barcode03"
seq = extract_align_sequence(read_nobc, False,
qcat_config.max_align_length)
barcode_dict = detector.detect_barcode(seq)
assert barcode_dict['barcode'] is None
seq = extract_align_sequence("", False,
qcat_config.max_align_length)
barcode_dict = detector.detect_barcode(seq)
assert barcode_dict['barcode'] is None
seq = extract_align_sequence(simulated_bc03, False,
qcat_config.max_align_length)
barcode_dict = detector.detect_barcode(seq)
assert barcode_dict['barcode'].name == "barcode03"
seq = extract_align_sequence(real_bc03_porechop, False,
qcat_config.max_align_length)
barcode_dict = detector.detect_barcode(seq, qcat_config=qcat_config)
assert barcode_dict['barcode'].name == "barcode03"
seq = extract_align_sequence(real_bc03_porechop, False,
qcat_config.max_align_length)
barcode_dict = detector.detect_barcode(seq, qcat_config=qcat_config)
assert barcode_dict['barcode'].name == "barcode03"
def parse_args(argv):
"""
Commandline parser
:param argv: Command line arguments
:type argv: List
:param defaults: qcat config object that holds default values passed to
ArgumentParser
:type defaults: qcatConfig
:return: None
"""
defaults = config.get_default_config()
usage = "Python command-line tool for demultiplexing Oxford Nanopore reads from FASTQ files"
parser = ArgumentParser(description=usage,
formatter_class=RawDescriptionHelpFormatter)
parser.add_argument("-V",
'--version',
action='version',
version='%(prog)s ' + __version__)
parser.add_argument('-l',
"--log",
dest="log",
type=str,
default="INFO",
help="Print debug information")
parser.add_argument("--quiet",
dest="QUIET",
action='store_true',
help="Don't print summary")
general_group = parser.add_argument_group('General settings')
general_group.add_argument("-f",
"--fastq",
type=str,
dest="fastq",
help="Barcoded read file")
general_group.add_argument(
'-b',
"--barcode_dir",
dest="barcode_dir",
type=str,
default=None,
help="If specified, qcat will demultiplex reads "
"to this folder")
general_group.add_argument(
'-o',
"--output",
dest="output",
type=str,
default=None,
help="Output file trimmed reads will be written to "
"(default: stdout).")
general_group.add_argument(
"--min-score",
dest="min_qual",
type=check_minqual_arg,
default=None,
help="Minimum barcode score. Barcode calls with a lower "
"score will be discarded. "
"Must be between 0 and 100. (default: 60)")
general_group.add_argument("--detect-middle",
dest="DETECT_MIDDLE",
action='store_true',
help="Search for adapters in the whole read")
general_group.add_argument(
'-t',
"--threads",
dest="threads",
type=int,
default=1,
help="Number of threads. Only works with in guppy mode")
general_group.add_argument("--min-read-length",
dest="min_length",
type=int,
default=100,
help="Reads short than <min-read-length> after "
"trimming will be discarded.")
general_group.add_argument(
"--tsv",
dest="tsv",
action='store_true',
help="Prints a tsv file containing barcode information "
"each read to stdout.")
general_group.add_argument(
"--trim",
dest="TRIM",
action='store_true',
help="Remove adapter and barcode sequences from reads.")
general_group.add_argument(
"-k",
"--kit",
dest="kit",
choices=get_kits(),
type=check_kit_arg,
default="auto",
help="Sequencing kit. Specifying the correct kit "
"will improve sensitivity and specificity and "
"runtime (default: auto)")
general_group.add_argument("--list-kits",
dest="list_kits",
action='store_true',
help="List all supported kits")
# Mode
mode_group = parser.add_argument_group("Demultiplexing modes")
group = mode_group.add_mutually_exclusive_group()
group.add_argument(
"--guppy",
dest="MODE_GUPPY",
action='store_true',
help="Use Guppy's demultiplexing algorithm (default: false)")
group.add_argument(
"--epi2me",
dest="MODE_EPI2ME",
action='store_true',
help="Use EPI2ME's demultiplexing algorithm (default: true)")
group.add_argument("--dual",
dest="MODE_DUAL",
action='store_true',
help="Use dual barcoding algorithm")
group.add_argument(
"--simple",
dest="MODE_SIMPLE",
action='store_true',
help="Use simple demultiplexing algorithm. Only looks for "
"barcodes, not for adapter sequences. Use only for testing "
"purposes!")
# EPI2ME
epi2me_group = parser.add_argument_group(
'EPI2ME options (only valid with --epi2me)')
epi2me_group.add_argument(
"--no-batch",
dest="nobatch",
action='store_true',
help=
"Don't use information from multiple reads for kit detection (default: false)"
)
epi2me_group.add_argument(
"--filter-barcodes",
dest="FILTER_BARCODES",
action='store_true',
help="Filter rare barcode calls when run in batch mode")
simple_group = parser.add_argument_group(
'Simple options (only valid with --simple)')
simple_group.add_argument(
"--simple-barcodes",
dest="SIMPLE_BARCODES",
choices=['standard', 'extended'],
default="standard",
help="Use 12 (standard) or 96 (extended) barcodes for demultiplexing")
# parser.add_argument("--adapter-sequences",
# type=str,
# dest="adapter_yaml",
# default=None,
# help="YAML file or folder containing YAML files that"
# "describe the Adapter sequences.")
# parser.add_argument('--no-header',
# action='store_true',
# dest='no_header',
# help="Do not write header to output tsv file."
# "Useful if results from different runs should be"
# "combined")
args = parser.parse_args(argv)
return args
def main(argv=sys.argv[1:]):
"""
Basic command line interface to qcat.
:param argv: Command line arguments
:type argv: list
:return: None
:rtype: NoneType
"""
args = parse_args(argv=argv)
reference_file = args.GENOMES
a = mp.Aligner(reference_file, preset="map-ont") # load or build index
if not a: raise Exception("ERROR: failed to load/build index")
output_file = open(args.TSV, "w")
detector = BarcodeScanner.factory(kit="NBD10X", min_quality=0)
print("dataset", "id", "length", "qscore", "score", "barcode", "truebc",
"truebc_assignment", "middle_adapter", "non_matching_bc", "sequence",
sep='\t', file=output_file)
name = args.NAME
f = args.FASTQ
i = 0
print(name, f)
with pysam.FastxFile(f) as fh:
for entry in fh:
i += 1
info = _parse_reads_info(entry.comment)
if 'truebc' in info:
truebc = info['truebc']
truebc_assignment = "Pre_assigned"
else:
truebc, truebc_assignment = get_truebc(a, entry.sequence)
c = config.get_default_config()
result = detector.detect_barcode(entry.sequence,
qcat_config=c)
middle_adapter = detector.scan_middle(entry.sequence, "NBD10X",
c)
q_score = _compute_mean_qscore(qstring_to_phred(entry.quality))
bc = "none"
score = 0.0
if result['barcode']:
bc = result['barcode'].id
score = result['barcode_score']
no_seq = False
seq = "-"
if not no_seq:
seq = entry.sequence
print(name, entry.name, len(entry.sequence), q_score, score, bc,
truebc, truebc_assignment, middle_adapter,
result['exit_status'] == 1002, seq,
sep='\t', file=output_file)
# if i == 10000:
# break
if i % 1000 == 0:
print(".", end="")
if i % 50000 == 0:
print("")
if i == int(args.MAX):
print("Reach maximumg, stopping.")
break
print("")
output_file.close()
print("finished")