def load_all_results(input_settings,
alg_settings,
output_settings,
prec_rec_str="",
**kwargs):
"""
Load all of the results for the datasets and algs specified in the config file
"""
df_all = pd.DataFrame()
algs = get_algs_to_run(alg_settings, **kwargs)
for dataset in input_settings['datasets']:
if kwargs.get('most_specific_terms'):
# load the ontology
obo_file = "%s/%s" % (input_settings['input_dir'],
dataset['obo_file'])
go_dags = go_examples.parse_obo_file_and_build_dags(obo_file)
for alg in algs:
if alg not in alg_settings:
print("%s not found in config file. Skipping" % (alg))
continue
alg_params = alg_settings[alg]
curr_seed = kwargs.get('cv_seed')
if 'cv-' in kwargs['exp_type']:
for rep in range(1, kwargs.get('num_reps', 1) + 1):
if curr_seed is not None:
curr_seed += rep - 1
curr_exp_type = "%s-rep%s%s" % (
kwargs['exp_type'], rep, "-seed%s" %
(curr_seed) if curr_seed is not None else "")
df = load_alg_results(
dataset,
alg,
alg_params,
prec_rec_str=prec_rec_str,
results_dir=output_settings['output_dir'],
**kwargs, #exp_type=curr_exp_type,
#only_terms=kwargs.get('only_terms'), postfix=kwargs.get('postfix',''),
)
add_dataset_settings(dataset, df)
df['rep'] = rep
df_all = pd.concat([df_all, df])
else:
df = load_alg_results(
dataset,
alg,
alg_params,
prec_rec_str=prec_rec_str,
results_dir=output_settings['output_dir'],
**kwargs, #exp_type=kwargs['exp_type'],
#only_terms=kwargs.get('only_terms'), postfix=kwargs.get('postfix',''),
)
if kwargs.get('most_specific_terms') and len(df) > 0:
df = get_most_specific_sp_term_pairs(df, go_dags, **kwargs)
print("MAD: %s" % (mad(df['fmax'].values)))
add_dataset_settings(dataset, df)
df_all = pd.concat([df_all, df])
return df_all
def setup_obo_dag_matrix(obo_file, goterms):
"""
*goterms*: if a set of goterms are given, then limit the dag to
the sub-ontology which has the given terms. Currently just returns the DAG for the first term.
TODO allow for multiple
"""
go_dags = go_examples.parse_obo_file_and_build_dags(obo_file)
dag_matrix = None
for h, dag in go_dags.items():
t = list(goterms)[0]
if not dag.has_node(t):
continue
dag_matrix, goids = build_hierarchy_matrix(dag, goterms, h=h)
if dag_matrix is None:
print("ERROR: term %s not found in any of the sub-ontologies" % (t))
sys.exit("Quitting")
else:
return dag_matrix, goids
def setup_h_ann_matrices(prots, obo_file, pos_neg_file, goterms=None):
# parse the go_dags first as it also sets up the goid_to_category dictionary
go_dags = go_examples.parse_obo_file_and_build_dags(obo_file)
goids = []
# TODO build a matrix with the direct annotations (i.e., from the gaf file)
# for now, just use all of the propagated annotations
# and then evaluate using the scores
#for pos_neg_file in pos_neg_files:
if 'bp' in pos_neg_file:
h = 'bp'
elif 'mf' in pos_neg_file:
h = 'mf'
elif 'cc' in pos_neg_file:
h = 'cc'
dag_matrix, ann_matrix, goids = build_h_ann_matrices(
prots, go_dags, pos_neg_file=pos_neg_file, h=h, goterms=goterms)
return dag_matrix, ann_matrix, goids
def main(sparse_net_file, obo_file, pos_neg_file=None, gaf_file=None, ignore_ec=["IEA"],
alpha=.5, theta=.5, mu=.5, h="bp", out_pref=None):
W, prots = alg_utils.setup_sparse_network(sparse_net_file)
# parse the go_dags first as it also sets up the goid_to_category dictionary
go_dags = go_examples.parse_obo_file_and_build_dags(obo_file)
dag_matrix, ann_matrix, goids = build_h_ann_matrices(prots, go_dags, pos_neg_file=pos_neg_file, gaf_file=gaf_file, h='bp')
# make sure they're type float so matlab will parse them correctly
sparse_net = W.astype('float')
ann_matrix = ann_matrix.astype('float')
dag_matrix = dag_matrix.astype('float')
if out_pref is not None:
out_file = "%s%s-annotations-and-go-dag.mat" % (out_pref, h)
utils.checkDir(os.path.dirname(out_file))
print("\twriting graph, annotation, and hierarchy matrices to %s" % (out_file))
# write these to a file to run the matlab BirgRank
savemat(out_file, {"G": sparse_net, "R": ann_matrix, "H": dag_matrix}, do_compression=True)
goids_file = "%s%s-goids.txt" % (out_pref, h)
print("\twriting goids to %s" % (goids_file))
with open(goids_file, 'w') as out:
out.write(''.join("%s\n" % (goid) for goid in goids))
run_birgrank = True
if run_birgrank is True:
Xh = birgRank(sparse_net, ann_matrix.transpose(), dag_matrix, alpha=.5, theta=.5, mu=.5, eps=0.0001, max_iters=1000, verbose=True)
Xh = Xh.T
print(Xh.shape)
out_file = "%s%s-pred-scores.txt" % (out_pref, h)
print("\twriting scores to %s" % (out_file))
# write the results for a single GO term
with open(out_file, 'w') as out:
for i in range(Xh.shape[0]):
print("writing results for goterm %s" % (goids[i]))
out.write(''.join("%s\t%s\t%s\n" % (goids[i], prots[j], score) for j, score in enumerate(Xh[i].toarray().flatten())))
break
return