def micro_rna(value,ns):
""" Create bel transcribedTo statement for microRNA,
given namespace keyword string and value. """
source = bel_term(value, ns, 'g')
target = bel_term(value, ns, 'm')
s = Template('${source} transcribedTo ${target}').substitute(source=source, target=target)
return s
def translated_to(value,ns):
""" Create bel translatedTo statement, given
namespace keyword string and value. """
source = bel_term(value, ns, 'r')
target = bel_term(value, ns, 'p')
s = Template('${source} translatedTo ${target}').substitute(source=source, target=target)
return s
def micro_rna(value, ns):
""" Create bel transcribedTo statement for microRNA,
given namespace keyword string and value. """
source = bel_term(value, ns, 'g')
target = bel_term(value, ns, 'm')
s = Template('${source} transcribedTo ${target}').substitute(source=source,
target=target)
return s
def translated_to(value, ns):
""" Create bel translatedTo statement, given
namespace keyword string and value. """
source = bel_term(value, ns, 'r')
target = bel_term(value, ns, 'p')
s = Template('${source} translatedTo ${target}').substitute(source=source,
target=target)
return s
data_list = ['rgd', 'hgnc', 'rgd_ortho', 'mgi']
data_dict = {}
for files in os.listdir("."):
if files.endswith("parsed_data.pickle"):
with open(files,'rb') as f:
d = pickle.load(f)
if str(d) in data_list:
data_dict[str(d)] = d
for data in data_list:
if data not in data_dict.keys():
print('missing required dependency {0}!'.format(data))
hgnc_ortho_statements = set()
for term_id in data_dict.get('hgnc').get_values():
term_label = data_dict.get('hgnc').get_label(term_id)
hgnc_term = bel_functions.bel_term(term_label, 'HGNC', 'g')
orthos = data_dict.get('hgnc').get_orthologs(term_id)
if orthos is not None:
for o in orthos:
if len(o.split(':')) == 2:
prefix, value = o.split(':')
if prefix == 'RGD':
o_label = data_dict.get('rgd').get_label(value)
if prefix == 'MGI':
o_label = data_dict.get('mgi').get_label(value)
if o_label is None:
print('WARNING - missing label for {0}, {1}'.format(prefix, value))
continue
ortho_term = bel_functions.bel_term(o_label, prefix, 'g')
hgnc_ortho_statements.add('{0} orthologous {1}'.format(hgnc_term, ortho_term))
if row[0].startswith('!'):
if 'Submission Date:' in row:
date = row[0].split(':')[1].strip()
(month, day, year) = date.split('/')
date = Template('${year}-${month}-${day}').substitute(
year=year, day=day, month=month)
else:
continue
# find records with CC GO terms, that do not have a qualifier
else:
goid = row[4].replace('GO:', '')
qualifier = row[3]
symbol = row[2]
if qualifier == '' and goid in complexes:
# convert complex into BEL term
term = bel_term(row[4].replace('GO:', ''), complex_ns,
'complex')
# convert symbol into BEL term, exclude non-protein symbols
if encoding_dict.get(symbol) == 'GRP':
gene = bel_term(symbol, ns, 'p')
gomap[term].add(gene)
# sort genes annotated to each complex in gomap
gomap = {k: sorted(list(v)) for k, v in gomap.items()}
print('\tGenerating {0} BEL hasComponents statements.\n'.format(
len(gomap)))
# create statements and associated annotations; append to output file
with open(output_file, 'a') as bel:
bel.write('SET Species = {0}\n'.format(species))
bel.write(
'SET Citation = {3}"Online Resource", "GO Annotation File - {0}", "{1}", "{2}", "", ""{4}\n\n'
.format(species, url, date, '{', '}'))
if files.endswith("parsed_data.pickle"):
with open(files, 'rb') as f:
d = pickle.load(f)
if str(d) in data_list:
data_dict[str(d)] = d
for data in data_list:
if data not in data_dict.keys():
print('missing required dependency {0}!'.format(data))
# Get ortho statements from HGNC data object
# MGI and RGD namespaceDataSet objects are required for translation of MGI
# and RGD Ids to labels
hgnc_ortho_statements = set()
for term_id in data_dict.get('hgnc').get_values():
term_label = data_dict.get('hgnc').get_label(term_id)
hgnc_term = bel_functions.bel_term(term_label, 'HGNC', 'g')
orthos = data_dict.get('hgnc').get_orthologs(term_id)
if orthos is not None:
for o in orthos:
if len(o.split(':')) == 2:
prefix, value = o.split(':')
if prefix == 'RGD':
o_label = data_dict.get('rgd').get_label(value)
if prefix == 'MGI':
o_label = data_dict.get('mgi').get_label(value)
if o_label is None:
print(
'WARNING - missing label for {0}, {1}'.format(prefix, value))
continue
ortho_term = bel_functions.bel_term(o_label, prefix, 'g')
hgnc_ortho_statements.add(
for row in reader:
if row[0].startswith('!'):
if 'Submission Date:' in row:
date = row[0].split(':')[1].strip()
(month, day, year) = date.split('/')
date = Template('${year}-${month}-${day}').substitute(year=year, day=day, month=month)
else:
continue
# find records with CC GO terms, that do not have a qualifier
else:
goid = row[4].replace('GO:','')
qualifier = row[3]
symbol = row[2]
if qualifier == '' and goid in complexes:
# convert complex into BEL term
term = bel_term(row[4].replace('GO:',''),complex_ns,'complex')
# convert symbol into BEL term, exclude non-protein symbols
if encoding_dict.get(symbol) == 'GRP':
gene = bel_term(symbol,ns,'p')
gomap[term].add(gene)
# sort genes annotated to each complex in gomap
gomap = {k:sorted(list(v)) for k, v in gomap.items()}
print('\tGenerating {0} BEL hasComponents statements.\n'.format(len(gomap)))
# create statements and associated annotations; append to output file
with open(output_file, 'a') as bel:
bel.write('SET Species = {0}\n'.format(species))
bel.write('SET Citation = {3}"Online Resource", "GO Annotation File - {0}", "{1}", "{2}", "", ""{4}\n\n'.format(species, url, date, '{', '}'))
for k, v in gomap.items():
bel.write('{0} hasComponents list({1})\n'.format(k, ','.join(v)))
#bel.write(k + ' hasComponents list(' + ",".join(v) + ')')
if files.endswith("parsed_data.pickle"):
with open(files, 'rb') as f:
d = pickle.load(f)
if str(d) in data_list:
data_dict[str(d)] = d
for data in data_list:
if data not in data_dict.keys():
print('missing required dependency {0}!'.format(data))
# Get ortho statements from HGNC data object
# MGI and RGD namespaceDataSet objects are required for translation of MGI
# and RGD Ids to labels
hgnc_ortho_statements = set()
for term_id in data_dict.get('hgnc').get_values():
term_label = data_dict.get('hgnc').get_label(term_id)
hgnc_term = bel_functions.bel_term(term_label, 'HGNC', 'g')
orthos = data_dict.get('hgnc').get_orthologs(term_id)
if orthos is not None:
for o in orthos:
if len(o.split(':')) == 2:
prefix, value = o.split(':')
if prefix == 'RGD':
o_label = data_dict.get('rgd').get_label(value)
if prefix == 'MGI':
o_label = data_dict.get('mgi').get_label(value)
if o_label is None:
print('WARNING - missing label for {0}, {1}'.format(
prefix, value))
continue
ortho_term = bel_functions.bel_term(o_label, prefix, 'g')
hgnc_ortho_statements.add('{0} orthologous {1}'.format(