def build_prior(gene_names):
"""Build a corpus of prior Statements from PC and BEL."""
gn = GeneNetwork(gene_names, basen)
# Read BEL Statements
bel_stmts = gn.get_bel_stmts(filter=False)
ac.dump_statements(bel_stmts, prefixed_pkl('bel'))
# Read Pathway Commons Statements
database_filter = ['reactome', 'kegg', 'pid']
biopax_stmts = gn.get_biopax_stmts(database_filter=database_filter)
# Eliminate blacklisted interactions
tmp_stmts = []
for stmt in biopax_stmts:
source_ids = [ev.source_id for ev in stmt.evidence]
if set(source_ids) & set(biopax_blacklist):
continue
tmp_stmts.append(stmt)
biopax_stmts = tmp_stmts
ac.dump_statements(biopax_stmts, prefixed_pkl('biopax'))
# Read Phosphosite Statements
phosphosite_stmts = read_phosphosite_owl(phosphosite_owl_file)
ac.dump_statements(phosphosite_stmts, prefixed_pkl('phosphosite'))
path_str = ''
for ix, (node, sign) in enumerate(path):
if ix == 0:
path_str += node
else:
if sign == last_sign:
path_str += ' -> %s' % node
else:
path_str += ' -| %s' % node
last_sign = sign
print('%s : score %s' % (path_str, score))
if __name__ == '__main__':
# Run run_task1.py before running this one
with open(prefixed_pkl('pysb_stmts'), 'rb') as f:
stmts = pickle.load(f)
with open('scored_paths.pkl', 'rb') as f:
(scored_paths, model) = pickle.load(f)
all_groups = set()
all_path_details = {}
for cell_line, drug_dict in scored_paths.items():
for drug, paths in drug_dict.items():
groups, path_details = group_scored_paths(paths, model, stmts)
for pg, path_list in path_details.items():
if pg in all_path_details:
all_path_details[pg] |= path_list
else:
all_path_details[pg] = path_list
all_groups |= groups
def assemble_pysb(stmts, data_genes, contextualize=False):
# Filter the INDRA Statements to be put into the model
stmts = ac.filter_by_type(stmts, Complex, invert=True)
stmts = ac.filter_direct(stmts)
stmts = ac.filter_belief(stmts, 0.95)
stmts = ac.filter_top_level(stmts)
# Strip the extraneous supports/supported by here
strip_supports(stmts)
stmts = ac.filter_gene_list(stmts, data_genes, 'all')
stmts = ac.filter_enzyme_kinase(stmts)
stmts = ac.filter_mod_nokinase(stmts)
stmts = ac.filter_transcription_factor(stmts)
# Simplify activity types
ml = MechLinker(stmts)
ml.gather_explicit_activities()
ml.reduce_activities()
ml.gather_modifications()
ml.reduce_modifications()
stmts = normalize_active_forms(ml.statements)
# Replace activations when possible
ml = MechLinker(stmts)
ml.gather_explicit_activities()
ml.replace_activations()
# Require active forms
ml.require_active_forms()
num_stmts = len(ml.statements)
while True:
# Remove inconsequential PTMs
ml.statements = ac.filter_inconsequential_mods(ml.statements,
get_mod_whitelist())
ml.statements = ac.filter_inconsequential_acts(ml.statements,
get_mod_whitelist())
if num_stmts <= len(ml.statements):
break
num_stmts = len(ml.statements)
stmts = ml.statements
# Save the Statements here
ac.dump_statements(stmts, prefixed_pkl('pysb_stmts'))
# Add drug target Statements
drug_target_stmts = get_drug_target_statements()
stmts += drug_target_stmts
# Just generate the generic model
pa = PysbAssembler()
pa.add_statements(stmts)
model = pa.make_model()
with open(prefixed_pkl('pysb_model'), 'wb') as f:
pickle.dump(model, f)
# Run this extra part only if contextualize is set to True
if not contextualize:
return
cell_lines_no_data = ['COLO858', 'K2', 'MMACSF', 'MZ7MEL', 'WM1552C']
for cell_line in cell_lines:
if cell_line not in cell_lines_no_data:
stmtsc = contextualize_stmts(stmts, cell_line, data_genes)
else:
stmtsc = stmts
pa = PysbAssembler()
pa.add_statements(stmtsc)
model = pa.make_model()
if cell_line not in cell_lines_no_data:
contextualize_model(model, cell_line, data_genes)
ac.dump_statements(stmtsc, prefixed_pkl('pysb_stmts_%s' % cell_line))
with open(prefixed_pkl('pysb_model_%s' % cell_line), 'wb') as f:
pickle.dump(model, f)
stmts_by_ag[stmt.agent.name].append(stmt)
except KeyError:
stmts_by_ag[stmt.agent.name] = [stmt]
unique_by_ag = {}
for k, v in stmts_by_ag.items():
for st in v:
found = False
try:
uniques = unique_by_ag[k]
except KeyError:
unique_by_ag[k] = []
uniques = []
for stmt in uniques:
if stmt.equals(st):
found = True
break
if not found:
unique_by_ag[k].append(st)
new_stmts = []
for k, v in unique_by_ag.items():
new_stmts += v
return new_stmts
if __name__ == '__main__':
stmts = []
for aff in active_forms_files:
stmts = read_stmts(aff)
with open(prefixed_pkl('r3'), 'wb') as fh:
pickle.dump(stmts, fh)
fnames = glob.glob(os.path.join(base_dir, '*.ekb'))
return fnames
def get_file_stmts(fname):
with open(fname, 'rt') as fh:
xml_str = fh.read()
tp = trips.process_xml(xml_str)
if tp is None:
return []
return tp.statements
def read_stmts(folder):
fnames = get_file_names(folder)
all_stmts = []
for i, fname in enumerate(fnames):
print('%d/%d' % (i, len(fnames)))
print(fname)
print('=' * len(fname))
st = get_file_stmts(fname)
all_stmts += st
return all_stmts
if __name__ == '__main__':
stmts = read_stmts(base_folder)
print('Collected %d Statements from TRIPS' % len(stmts))
with open(prefixed_pkl('trips'), 'wb') as fh:
pickle.dump(stmts, fh)