def go_enrichment(self, bioent_ids, callback=None):
from src.sgd.model.perf.core import Bioentity, Bioconcept
bioent_format_names = []
num_chunks = ceil(1.0*len(bioent_ids)/500)
for i in range(num_chunks):
bioent_format_names.extend([json.loads(x.json)['format_name'] for x in DBSession.query(Bioentity).filter(Bioentity.id.in_(bioent_ids[i*500:(i+1)*500])).all()])
enrichment_results = query_batter.query_go_processes(bioent_format_names)
json_format = []
for enrichment_result in enrichment_results:
identifier = 'GO:' + str(int(enrichment_result[0][3:])).zfill(7)
goterm_id = get_obj_id(str(identifier).upper(), 'BIOCONCEPT', 'GO')
goterm = json.loads(get_obj(Bioconcept, 'json', goterm_id))
json_format.append({'go': goterm,
'match_count': enrichment_result[1],
'pvalue': enrichment_result[2]})
return json.dumps(json_format)
def make_enrichment(bioent_ids):
print len(bioent_ids)
bioent_ids = list(set(bioent_ids))
bioent_format_names = []
num_chunks = int(ceil(1.0*len(bioent_ids)/500))
for i in range(0, num_chunks):
bioent_format_names.extend([x.format_name for x in DBSession.query(Locus).filter(Locus.id.in_(bioent_ids[i*500:(i+1)*500])).all()])
enrichment_results = query_batter.query_go_processes(bioent_format_names)
json_format = []
for enrichment_result in enrichment_results:
try:
identifier = 'GO:' + str(int(enrichment_result[0][3:])).zfill(7)
goterm_id = get_obj_id(identifier, class_type='BIOCONCEPT', subclass_type='GO')
if goterm_id is not None:
goterm = DBSession.query(Go).filter_by(id=goterm_id).first().to_json()
json_format.append({'go': goterm,
'match_count': enrichment_result[1],
'pvalue': enrichment_result[2]})
else:
print 'Go term not found: ' + str(enrichment_result[0])
except:
print 'Bad GO ID' + enrichment_result[0]
return json_format