def test_preferred_transcripts_false(self):
"""
Check that preferred transcripts are labelled correctly.
Not in preferred transcripts - should be false.
"""
# apply preferred transcripts
self.pt = preferred_transcripts()
self.pt.load(os.path.abspath('test/PreferredTranscripts.txt'))
self.pt.apply(self.report, 'low')
# check in report
with open(self.report.report_path) as report:
reader = csv.reader(report, delimiter='\t')
for line in reader:
if line[1] == '3:41265953CT>C':
self.assertEqual(line[2], 'False')
def test_preferred_transcripts_low_strictness_true_1(self):
"""
Check that preferred transcripts are labelled correctly.
NM_001007553 should be true with high and low strictness
"""
# apply preferred transcripts
self.pt = preferred_transcripts()
self.pt.load(os.path.abspath('test/PreferredTranscripts.txt'))
self.pt.apply(self.report, 'low')
# check in report
with open(self.report.report_path) as report:
reader = csv.reader(report, delimiter='\t')
for line in reader:
if line[1] == '1:115256669G>A':
if 'NM_001007553' in line[29]:
self.assertEqual(line[3], 'True')
def test_preferred_transcripts_low_strictness_true_2(self):
"""
Check that preferred transcripts are labelled correctly.
XM_005245221 should be false with high strictness and true with
low strictness.
"""
# apply preferred transcripts
self.pt = preferred_transcripts()
self.pt.load(os.path.abspath('test/PreferredTranscripts.txt'))
self.pt.apply(self.report, 'low')
# check in report
with open(self.report.report_path) as report:
reader = csv.reader(report, delimiter='\t')
for line in reader:
if line[1] == '1:162681151T>G':
if 'XM_005245221' in line[29]:
self.assertEqual(line[3], 'True')
def main(args):
# setup logger
logger = logging.getLogger('vcf_parse')
logger.setLevel(logging.DEBUG)
handler = logging.StreamHandler()
handler.setLevel(logging.DEBUG)
formatter = logging.Formatter(
'%(levelname)s\t%(asctime)s\t%(name)s\t%(message)s')
handler.setFormatter(formatter)
logger.addHandler(handler)
logger.info('running vcf_parse.py...')
# Load arguments, make vcf report object and load data
report = vcf_report()
report.load_data(args.input, args.output)
# If -l flag called, print headers and exit
if args.config_list:
report.list_config()
exit()
# If config file provided, load config
if args.config:
report.load_config(args.config)
else:
logger.info('no config file found -- outputting all data from VCF.')
# Make variant report of whole VCF
report.make_report(args.filter_non_pass)
# If preferred transcripts provided, apply to variant report
if args.transcripts:
pt = preferred_transcripts()
pt.load(args.transcripts)
pt.apply(report, args.transcript_strictness)
else:
logger.info('no preferred transcripts file provided -- preferred ' +
'transcripts column will all be labelled as "Unknown"')
# If known variants provided, apply to variant report
if args.known_variants:
known = known_variants()
known.load_known_variants(args.known_variants)
known.apply_known_variants(report)
else:
logger.info('no known variants file provided -- Classification ' +
'column will be empty')
# If single BED file provided, make variant report with BED file
# applied
if args.bed:
bed = bed_object()
bed.apply_single(args.bed, report)
# If folder of BED file provided, make a seperate variant report
# for each BED file. Output will be saved in a folder named the
# same as the BED file folder, within the output directory.
elif args.bed_folder:
bed = bed_object()
bed.apply_multiple(args.bed_folder, report)
# If no BED files provided, pass
else:
logger.info('no BED files provided')
# Finish
logger.info('vcf_parse.py completed\n{}'.format('---' * 30))