def run_from_args(args):
vcf = Vcf()
vcf_out=sys.stdout
in_header = True
header_lines = list()
with su.InputStream(args.manta_vcf) as input_stream:
for line in input_stream:
if in_header:
header_lines.append(line)
if line[0:6] == '#CHROM':
in_header=False
vcf.add_header(header_lines)
vcf.add_info('PRPOS', '1', 'String', 'Breakpoint probability dist')
vcf.add_info('PREND', '1', 'String', 'Breakpoint probability dist')
vcf.add_info('STRANDS', '.', 'String', 'Strand orientation of the adjacency in BEDPE format (DEL:+-, DUP:-+, INV:++/--')
vcf.add_info('SU', '.', 'Integer', 'Number of pieces of evidence supporting the variant across all samples')
vcf.add_info('PE', '.', 'Integer', 'Number of paired-end reads supporting the variant across all samples')
vcf.add_info('SR', '.', 'Integer', 'Number of split reads supporting the variant across all samples')
vcf.add_info('INSLEN_ORIG', '.', 'Integer', 'Original insertion length')
vcf.add_info('CIPOS95', '2', 'Integer', 'Confidence interval (95%) around POS for imprecise variants')
vcf.add_info('CIEND95', '2', 'Integer', 'Confidence interval (95%) around END for imprecise variants')
vcf.add_info('SECONDARY', '0', 'Flag', 'Secondary breakend in a multi-line variant')
vcf_out.write(vcf.get_header()+'\n')
else:
v = Variant(line.rstrip().split('\t'), vcf)
convert_variant(v, args.max_ins)
vcf_out.write(v.get_var_string()+"\n")
def run_from_args(args):
deletion_size_map, max_size = load_deletion_sizes(args.threshold_file)
with su.InputStream(args.input) as stream:
variant_stream = VCFReader(stream)
args.output.write(variant_stream.vcf_obj.get_header())
args.output.write('\n')
return set_missing(variant_stream, deletion_size_map, args.output, max_size, args.sr_cutoff)
def run_from_args(args):
# sys.stderr.write(args.vcf_in)
if args.tSet is None:
if args.method!="large_sample":
sys.stderr.write("Training data required for naive Bayes or hybrid classifiers\n")
parser.print_help()
sys.exit(1)
with su.InputStream(args.input) as stream:
chrom_names = args.sex_chrom.strip().split(',')
sex_chrom_names = set(chrom_names)
for chrom in chrom_names:
sex_chrom_names.add(chromosome_prefix(chrom))
sys.stderr.write('sex chromosome names are: {0}\n'.format(str(sex_chrom_names)))
run_reclassifier(
stream,
args.vcf_out,
args.gender,
sex_chrom_names,
args.ae_path,
args.f_overlap,
args.exclude,
args.slope_threshold,
args.rsquared_threshold,
args.tSet,
args.method,
args.diag_outfile
)
def run_from_args(args):
# sys.stderr.write(args.vcf_in)
if args.tSet is None:
if args.method!="large_sample":
sys.stderr.write("Training data required for naive Bayes or hybrid classifiers\n")
parser.print_help()
sys.exit(1)
with su.InputStream(args.input) as stream:
run_reclassifier(stream, args.vcf_out, args.gender, args.ae_path, args.f_overlap, args.exclude, args.slope_threshold, args.rsquared_threshold, args.tSet, args.method, args.diag_outfile)
def test_plain_iteration(self):
test_directory = os.path.dirname(os.path.abspath(__file__))
test_data_dir = os.path.join(test_directory, 'test_data', 'utils')
test_input = os.path.join(test_data_dir, 'file.txt')
stream = su.InputStream(test_input)
for line in stream:
sys.stdout.write(line)
stream.close()
self.assertTrue(stream.handle.closed)
def test_context_manager(self):
test_directory = os.path.dirname(os.path.abspath(__file__))
test_data_dir = os.path.join(test_directory, 'test_data', 'utils')
test_input = os.path.join(test_data_dir, 'file.txt.gz')
temporary_obj = None
with su.InputStream(test_input) as stream:
temporary_obj = stream
for line in stream:
sys.stdout.write(line)
self.assertTrue(temporary_obj.closed)
def run_from_args(args):
with su.InputStream(args.input, args.tempdir) as stream:
bedpeToVcf(stream, args.output)
def test_init_hyphen(self):
new_handle = su.InputStream('-')
self.assertIs(new_handle.handle, sys.stdin)
def run_from_args(args):
with su.InputStream(args.input) as stream:
pruner = Pruner(args.max_distance, args.eval_param)
pruner.cluster_bedpe(stream, args.output, args.is_sorted)
def run_from_args(args):
with su.InputStream(args.vcf_in) as stream:
run_gt_refine(stream, args.vcf_out, args.diag_outfile, args.gender)
def run_from_args(args):
with su.InputStream(args.input) as stream:
return vcfToBedpe(stream, args.output)
def run_from_args(args):
with su.InputStream(args.bedpe) as stream:
processBEDPE(stream, args.name, args.dist)
def run_from_args(args):
with su.InputStream(args.input) as stream:
return sname_filter(stream, args.filter_file, args.output,
args.complement)
def run_from_args(args):
with su.InputStream(args.bedpe) as stream:
bedpeToVcf(stream, args.output)
def run_from_args(args):
with su.InputStream(args.input_vcf) as stream:
sv_readdepth(stream, args.sample, args.root, args.window,
args.output_vcf, args.cnvnator, args.coordinates)
def run_from_args(args):
with su.InputStream(args.input) as stream:
processBEDPE(stream, args.name, args.dist, args.output)
def run_from_args(args):
with su.InputStream(args.input_vcf, args.tempdir) as input_stream:
updater = UpdateInfo(input_stream)
updater.execute()
def run_from_args(args):
with su.InputStream(args.input) as stream:
run_pairwise_ld(stream, args.exclude, args.ld_outfile, args.winsz)
