def calculate_performance(molecules, ensemble, sort_order, options):
"""
determine the virtual screening performance of the input ensemble, and return the results in an
ensemble storage object.
:param molecules:
:param ensemble:
:param sort_order: string. either 'asc' (for binding energy estimates) or 'dsc' (for similarity scores)
:param options: instance of s
:return:
"""
es = EnsembleStorage()
es.set_prop('ensemble', ensemble)
# calculate the appropriate score structure type
score_structure = classification.make_score_structure(molecules, ensemble)
# determine auc value
auc_structure = classification.make_auc_structure(score_structure)
auc = classification.calculate_auc(auc_structure, sort_order, 'no stats')
es.set_prop('auc', auc)
# calculate enrichment factors
for fpf in classification.make_fpfList(options, score_structure):
fpf = float(fpf)
ef_structure = classification.make_ef_structure(
score_structure, fpf, sort_order)
if ef_structure:
ef = classification.calculate_ef(ef_structure, fpf)
es.set_prop(ef[0], ef[1], 'ef')
return es
def rank_queries(molecules, ensemble, sort_order, options):
"""
rank queries by value added to existing ensemble
:param molecules:
:param score_field:
:param ensemble:
:param sort_order:
:param options:
:return:
"""
# generate query list
query_list = [
x for x in list(molecules[0].scores.keys()) if x not in ensemble
]
results = {}
for query in query_list:
es = EnsembleStorage() # an ensemble storage project
# generate test_ensemble
test_ensemble = ensemble[0:]
test_ensemble.append(query)
test_ensemble = tuple(test_ensemble)
es.set_prop('ensemble', test_ensemble)
# calculate its performance
score_structure = classification.make_score_structure(
molecules, test_ensemble)
# determine auc value
auc_structure = classification.make_auc_structure(score_structure)
auc = classification.calculate_auc(auc_structure, sort_order,
'no stats')
es.set_prop('auc', auc)
# if the enrichment factor was set to anything other than 1, then we're training to maximize the corresponding
# enrichment factor
for fpf in classification.make_fpfList(options, score_structure):
fpf = float(fpf)
ef_structure = classification.make_ef_structure(
score_structure, fpf, sort_order)
if ef_structure:
ef = classification.calculate_ef(ef_structure, fpf)
es.set_prop(ef[0], ef[1], 'ef')
# append results to metric list
results[test_ensemble] = es
# peel away the best performing ensemble
best_ensemble = screener.find_best_ensemble(results, options)
return list(best_ensemble)
def rank_queries(molecules, sort_order, options):
results = {}
for query in [query for query in list(molecules[0].scores.keys())]:
formatted_query = []
formatted_query.append(query)
formatted_query = tuple(formatted_query)
es = EnsembleStorage()
es.set_prop('ensemble', formatted_query)
score_structure = classification.make_score_structure(molecules, formatted_query)
auc_structure = classification.make_auc_structure(score_structure)
auc = classification.calculate_auc(auc_structure, sort_order, 'no stats')
es.set_prop('auc', auc)
for fpf in classification.make_fpfList(options, score_structure):
fpf = float(fpf)
ef_structure = classification.make_ef_structure(score_structure, fpf, sort_order)
if ef_structure:
ef = classification.calculate_ef(ef_structure, fpf)
es.set_prop(ef[0], ef[1], 'ef')
results[formatted_query] = es
return results
