def analyze(filename, plot=False):
# Load the file
results = load_file(filename)
# Put together a list of all statements
all_stmts = [stmt for paper_stmts in results.values()
for stmt in paper_stmts]
# Map grounding
logger.info('Mapping grounding...')
gmap = gm.GroundingMapper(gm.default_grounding_map)
map_stmts = gmap.map_agents(all_stmts)
map_stmts = gmap.rename_agents(map_stmts)
# Combine duplicates
logger.info('Removing duplicates...')
pa = Preassembler(hierarchies, map_stmts)
pa.combine_duplicates()
# Map GO IDs to genes and associated statements
logger.info('Building map from GO IDs to stmts')
go_gene_map = {}
go_name_map = {}
for stmt in pa.unique_stmts:
(bp_name, go, gene) = go_gene_pair(stmt)
if bp_name is None and go is None and gene is None:
continue
go_gene_list = go_gene_map.get(go, [])
go_gene_list.append((gene, stmt))
go_gene_map[go] = go_gene_list
go_name_set = go_name_map.get(go, set([]))
go_name_set.add(bp_name)
go_name_map[go] = go_name_set
# Iterate over all of the GO IDs and compare the annotated genes in GO
# to the ones from the given statements
go_stmt_map = {}
for ix, go_id in enumerate(go_gene_map.keys()):
logger.info('Getting genes for %s (%s) from GO (%d of %d)' %
(go_id, ','.join(list(go_name_map[go_id])),
ix+1, len(go_gene_map.keys())))
genes_from_go = get_genes_for_go_id(go_id)
gene_stmt_list = go_gene_map[go_id]
in_go = []
not_in_go = []
for (gene, stmt) in gene_stmt_list:
if gene in genes_from_go:
in_go.append(stmt)
else:
not_in_go.append(stmt)
go_stmt_map[go_id] = {'names': list(go_name_map[go_id]),
'in_go': in_go, 'not_in_go': not_in_go}
with open('go_stmt_map.pkl', 'wb') as f:
pickle.dump(go_stmt_map, f, protocol=2)
if plot:
plot_stmt_counts(go_stmt_map, 'go_stmts.pdf')
def assemble_model(requester_name):
global stmts
# Performing grounding mapping on the statements
gmapper = gm.GroundingMapper(gm.default_grounding_map)
stmts = gmapper.map_agents(stmts)
pa = Preassembler(hierarchies, stmts)
pa.combine_related()
stmts = pa.related_stmts
ml = MechLinker(stmts)
linked_stmts = ml.link_statements()
if linked_stmts:
for linked_stmt in linked_stmts:
if linked_stmt.inferred_stmt:
question = mechlinker_queries.print_linked_stmt(linked_stmt)
say(question)
stmts.append(linked_stmt.inferred_stmt)
say("%s: Done, updating layout." % requester_name)
update_layout()
def remove_mechanism(text, user_name):
global stmts
import ipdb
ipdb.set_trace()
tp = trips.process_text(text)
gmapper = gm.GroundingMapper(gm.default_grounding_map)
tp_stmts = gmapper.map_agents(tp.statements)
print "Statements to remove:", tp.statements
stmts_to_keep = []
for model_stmt in stmts:
remove_stmt = False
for stmt_to_remove in tp_stmts:
if model_stmt.refinement_of(stmt_to_remove, hierarchies):
remove_stmt = True
break
if not remove_stmt:
stmts_to_keep.append(model_stmt)
if stmts_to_keep == stmts:
say("Sorry, I couldn't find any matching mechanisms to remove.")
else:
say("OK, I removed it.")
stmts = stmts_to_keep
assemble_model(user_name)
if args.date_range:
min_date_str, max_date_str = args.date_range.split(':')
if min_date_str:
min_date = datetime.strptime(min_date_str, '%Y%m%d%H%M%S')
clauses.add(db.RawStatements.create_date > min_date)
if max_date_str:
max_date = datetime.strptime(max_date_str, '%Y%m%d%H%M%S')
clauses.add(db.RawStatements.create_date < max_date)
all_stmts, results = load_stmts_from_db(clauses, db)
report_stmt_counts(results['reach'], plot_prefix='raw_reach')
report_stmt_counts(results['sparser'], plot_prefix='raw_sparser')
report_grounding(all_stmts, plot_prefix='raw')
report_stmt_types(all_stmts, plot_prefix='raw')
report_stmt_participants(all_stmts)
# Map grounding
logger.info('Mapping grounding...')
gmap = gm.GroundingMapper(gm.default_grounding_map)
map_stmts = gmap.map_agents(all_stmts)
report_grounding(map_stmts, plot_prefix='preassembled')
# Combine duplicates
logger.info('Removing duplicates...')
pa = Preassembler(hierarchies, map_stmts)
pa.combine_duplicates()
report_evidence_distribution(pa.unique_stmts, plot_prefix='preassembled')
def analyze(filename):
results = load_file(filename)
all_stmts = [stmt for paper_stmts in results.values()
for stmt in paper_stmts]
# Map grounding
logger.info('Mapping grounding...')
gmap = gm.GroundingMapper(gm.default_grounding_map)
map_stmts = gmap.map_agents(all_stmts)
map_stmts = gmap.rename_agents(map_stmts)
# Combine duplicates
logger.info('Removing duplicates...')
pa = Preassembler(hierarchies, map_stmts)
pa.combine_duplicates()
# Get complexes
complexes = [s for s in pa.unique_stmts if isinstance(s, Complex)]
# Get HGNC grounding
protein_complexes = [s for s in complexes
if all([True if 'HGNC' in ag.db_refs.keys()
else False
for ag in s.agent_list()])]
logger.info('Mapping gene IDs to gene symbols')
gene_ids = list(set([ag.db_refs['HGNC'] for stmt in protein_complexes
for ag in stmt.members]))
genes = [hgnc_client.get_hgnc_name(id) for id in gene_ids]
# Get complexes from BioGrid and combine duplicates
num_genes_per_query = 50
start_indices = range(0, len(genes), num_genes_per_query)
end_indices = [i + num_genes_per_query
if i + num_genes_per_query < len(genes) else len(genes)
for i in start_indices]
bg_complexes = []
for i in range(len(start_indices)):
logger.info("Querying biogrid for %s" %
str(genes[start_indices[i]:end_indices[i]]))
bg_complexes += (bg.get_statements(
genes[start_indices[i]:end_indices[i]]))
# Filter out Biogrid statements not involving genes in the gene list
# (this will make duplicate removal more efficient
bg_filt = []
for stmt in bg_complexes:
if stmt.members[0].name in genes and \
stmt.members[1].name in genes:
bg_filt.append(stmt)
# Might as well free up some memory
del bg_complexes
logger.info("Combining duplicates with biogrid...")
pa = Preassembler(hierarchies, bg_filt + protein_complexes)
pa.combine_duplicates()
indra_only = []
bg_only = []
indra_and_bg = []
for stmt in pa.unique_stmts:
evidence_source_list = set([])
for e in stmt.evidence:
evidence_source_list.add(e.source_api)
if 'reach' in evidence_source_list and \
'biogrid' in evidence_source_list:
indra_and_bg.append(stmt)
elif 'reach' in evidence_source_list and \
'biogrid' not in evidence_source_list:
indra_only.append(stmt)
elif 'reach' not in evidence_source_list and \
'biogrid' in evidence_source_list:
bg_only.append(stmt)
rows = []
for stmt in indra_only:
rows.append([stmt.members[0].name, stmt.members[1].name,
str(len(stmt.evidence))])
write_unicode_csv('unmatched_complexes.tsv', rows, delimiter='\t')
return {'indra_only': indra_only,
'bg_only': bg_only,
'indra_and_bg': indra_and_bg}