def find_transcripts(ensembl, mut_dict, output, args):
de_novos = load_de_novos(args.de_novos)
output.write("hgnc_symbol\ttranscript_id\tlength\tde_novos\n")
for symbol in sorted(de_novos):
print(symbol)
func_events = de_novos[symbol]["missense"] + de_novos[symbol][
"nonsense"]
# find the counts per transcript, depending on whether we want to count
# for all transcripts containing one or more de novos, or to find the
# minimum set of transcripts to contain the de novos
try:
if args.all_transcripts:
counts = count_de_novos_per_transcript(ensembl, symbol,
func_events)
elif args.minimal_transcripts:
counts = minimise_transcripts(ensembl, symbol, func_events)
except (ValueError, IndexError):
print("error occured with {0}".format(symbol))
continue
# write the transcript details to a file
for key in counts:
line = "{}\t{}\t{}\t{}\n".format(symbol, key, counts[key]["len"],
counts[key]["n"])
output.write(line)
def find_transcripts(ensembl, mut_dict, output, args):
de_novos = load_de_novos(args.de_novos)
output.write("hgnc_symbol\ttranscript_id\tlength\tde_novos\n")
for symbol in sorted(de_novos):
print(symbol)
func_events = de_novos[symbol]["missense"] + de_novos[symbol]["nonsense"]
# find the counts per transcript, depending on whether we want to count
# for all transcripts containing one or more de novos, or to find the
# minimum set of transcripts to contain the de novos
try:
if args.all_transcripts:
counts = count_de_novos_per_transcript(ensembl, symbol, func_events)
elif args.minimal_transcripts:
counts = minimise_transcripts(ensembl, symbol, func_events)
except (ValueError, IndexError):
print("error occured with {0}".format(symbol))
continue
# write the transcript details to a file
for key in counts:
line = "{}\t{}\t{}\t{}\n".format(symbol, key, counts[key]["len"],
counts[key]["n"])
output.write(line)
def test_minimise_transcripts(self):
""" test that minimise_transcripts() works correctly
"""
# run through a test case for a single gene
hgnc = "DYNLL1"
sites = [120934226, 120936012]
counts = minimise_transcripts(self.ensembl, hgnc, sites)
expected = {'ENST00000242577': {'len': 89, 'n': 2},
'ENST00000392508': {'len': 89, 'n': 2},
'ENST00000392509': {'len': 89, 'n': 2},
'ENST00000549989': {'len': 89, 'n': 2},
'ENST00000548342': {'len': 89, 'n': 2}}
self.assertEqual(counts, expected)
# check that when we don't have any de novos, we return an empty list
self.assertEqual(minimise_transcripts(self.ensembl, hgnc, []), {})
# check that when none of the de novos are in a transcript, we return
# an empty list.
self.assertEqual(minimise_transcripts(self.ensembl, hgnc, [100]), {})
def test_minimise_transcripts(self):
""" test that minimise_transcripts() works correctly
"""
# run through a test case for a single gene
hgnc = "DYNLL1"
sites = [120934226, 120936012]
counts = minimise_transcripts(self.ensembl, hgnc, sites)
expected = {'ENST00000242577': {'len': 89, 'n': 2},
'ENST00000392508': {'len': 89, 'n': 2},
'ENST00000392509': {'len': 89, 'n': 2},
'ENST00000549989': {'len': 89, 'n': 2},
'ENST00000548342': {'len': 89, 'n': 2}}
self.assertEqual(counts, expected)
# check that when we don't have any de novos, we return an empty list
self.assertEqual(minimise_transcripts(self.ensembl, hgnc, []), {})
# check that when none of the de novos are in a transcript, we return
# an empty list.
self.assertEqual(minimise_transcripts(self.ensembl, hgnc, [100]), {})
def main():
input_file, output_file, old_gene_id_file, cache_dir, genome_build, \
all_transcripts, minimal_transcripts = get_options()
# load all the data
ensembl = EnsemblRequest(cache_dir, genome_build)
old_gene_ids = {}
if old_gene_id_file is not None:
old_gene_ids = get_deprecated_gene_ids(old_gene_id_file)
known_de_novos = load_de_novos(input_file, exclude_indels=False)
output = open(output_file, "w")
output.write("hgnc_symbol\ttranscript_id\tlength\tde_novos\n")
for gene_id in sorted(known_de_novos):
de_novos = known_de_novos[gene_id]
func_events = de_novos["missense"] + de_novos["nonsense"]
# fix HGNC IDs that have been discontinued in favour of other gene IDs
if gene_id in old_gene_ids:
gene_id = old_gene_ids[gene_id]
# find the counts per transcript, depending on whether we want to count
# for all transcripts containing one or more de novos, or to find the
# minimum set of transcripts to contain the de novos
try:
if all_transcripts:
counts = count_de_novos_per_transcript(ensembl, gene_id, func_events)
elif minimal_transcripts:
counts = minimise_transcripts(ensembl, gene_id, func_events)
except (ValueError, IndexError):
print("error occured with {0}".format(gene_id))
continue
# write the transcript details to a file
for key in counts:
line = "{0}\t{1}\t{2}\t{3}\n".format(gene_id, key, counts[key]["len"], counts[key]["n"])
output.write(line)
output.close()