unique_accessions.add(p1)
unique_accessions.add(p2)
for (p1, p2), _ in test.iteritems():
unique_accessions.add(p1)
unique_accessions.add(p2)
fp = open(UNIQUE_ACCESSION_FILE, 'w+')
for p in unique_accessions:
fp.write("{}\n".format(p))
fp.close()
# Construct uniprot handler to get data:
if update or (not os.path.isfile(ACCESSION_FEATURES_FILE)):
print("Building accession to feature map...")
uniprot = UniProt(sprot_cache=SPROT_FILE, trembl_cache=TREMBL_FILE, organism='h**o sapien')
uniprot_features = uniprot.get_batch_accession_data(
unique_accessions, [UniProt.GO, UniProt.IPR, UniProt.PFAM, UniProt.GO_EVD]
)
# Write features to file
fp = open(ACCESSION_FEATURES_FILE, 'w')
fp.write('uniprot\tgo\tipr\tpfam\tgoe\n')
for p, data in uniprot_features.iteritems():
fp.write('{0}\t{1}\t{2}\t{3}\n'.format(
p,
','.join(data[UniProt.GO]),
','.join(data[UniProt.IPR]),
','.join(data[UniProt.PFAM]),
','.join(data[UniProt.GO_EVD])
)
df=dataframe,
vectorizer=vectorizer,
selector=selector,
feature_col=x,
label_col=y,
continuous_cols=None
)
return estimator.predict_proba(x_numpy)
if __name__ == "__main__":
method = sys.argv[1]
outfile = sys.argv[2]
columns = ['go_cc', 'go_mf', 'go_bp']
labels = get_labels_from_file('data/labels.tsv')
uniprot = UniProt(sprot_cache=SPROT_FILE, trembl_cache=TREMBL_FILE)
dag = load_go_dag('data/gene_ontology.1_2.obo')
# Load the training data.
train, test, interactome_df = prep_data_frames(selection=columns, load_interactome=True)
training_df = pd.concat([train, test], ignore_index=True)
training_corpus_pf = compute_corpus(training_df, ['pfam'])
training_corpus_ipr = compute_corpus(training_df, ['ipr'])
training_corpus_bp = compute_corpus(training_df, ['induced_go_bp'])
training_corpus_cc = compute_corpus(training_df, ['induced_go_cc'])
training_corpus_mf = compute_corpus(training_df, ['induced_go_mf'])
pina_corpus_pf = compute_corpus(interactome_df, ['pfam'])
pina_corpus_ipr = compute_corpus(interactome_df, ['ipr'])
pina_corpus_bp = compute_corpus(interactome_df, ['induced_go_bp'])
