from itertools import combinations
import sys
import predict.preprocess as prep
if __name__ == "__main__":
if len(sys.argv) < 5:
print("Usage: python <Input predictions file> <Output results file> <Protein/Gene list> <Probability threshold>")
sys.exit(0)
interactome_file = sys.argv[1]
out_file = sys.argv[2]
protein_list = sys.argv[3]
threshold = float(sys.argv[4])
symbol_type = sys.argv[5]
labels = sorted(prep.get_labels_from_file('data/labels.tsv'))
train, _ = prep.prep_data_frames(selection=[])
uniprots = list(train['uniprot'].values)
use_protein = True
try:
interactome_fp = open(interactome_file, 'r')
except IOError:
print("Could not open supplied file {}.".format(interactome_file))
sys.exit(0)
try:
protein_fp = open(protein_list, 'r')
proteins = set()
for line in protein_fp:
xs = line.strip().upper()
import pickle
import predict.preprocess as prep
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer
if __name__ == "__main__":
print("Loading datasets...")
df_kegg = pickle.load(open("tmp/train_df.pkl", 'r'))
df_hprd = pickle.load(open("tmp/test_df.pkl", 'r'))
df_test = pickle.load(open("tmp/interactome_df.pkl", 'r'))
selection = ['ipr', 'pfam', 'induced_go_cc', 'induced_go_mf', 'induced_go_bp']
labels = prep.get_labels_from_file("data/labels.tsv")
def get_selection(row):
terms = []
for col in selection:
terms += [row[col]]
terms = [t for t in ','.join(terms).split(',') if t.strip() != '']
return ','.join(terms)
df_test['terms'] = df_test.apply(get_selection, axis=1)
df_train, df_hprd = prep.prep_data_frames(selection)
vectorizer = CountVectorizer(stop_words=['go', '', ' '], binary=False, lowercase=True)
vectorizer.fit(df_train['terms'].values)
print("Transforming features...")
x_train, y_train, feature_names, selector = prep.select_features(
df = df_train,
vectorizer=vectorizer,
feature_col='terms',
'balanced': balanced,
'induce': induce,
'iteration': iterations,
'cv_folds': cv_folds,
'selection': selection,
'ontologies': ontologies,
'vectorizer_method': vectorizer_method,
'permuted': permute,
'scale': scale
}
pretty_print_dict(config)
# ----------------------------- LOAD DATA ----------------------------------- #
np.random.seed(42)
developement_df, testing_df = prep.prep_data_frames(selection, load_interactome=False)
labels = get_labels_from_file('data/labels.tsv')
n = len(labels)
split_train = {l:0 for l in labels}
for l in labels:
split_train[l] = sum(developement_df[l].values)
split_test = {l:0 for l in labels}
for l in labels:
split_test[l] = sum(testing_df[l].values)
n_samples_train = len(developement_df)
n_samples_test = len(testing_df)
# Create the appropriate statistics container for the whole experiment.
training_stats = Statistics()
from __future__ import division
import predict.plotting as plot
import predict.preprocess as prep
import numpy as np
import sys
if __name__ == "__main__":
fp = open(sys.argv[1], 'r')
header = fp.readline().split('\t')
labels = [elem.lower() for elem in prep.get_labels_from_file('data/labels.tsv')]
idx = [header.index(elem) for elem in header if elem.lower() in labels]
idx_start = min(idx)
idx_end = max(idx)
over_p = []
ps = np.arange(0, 1.05, 0.05)
probas = []
for line in fp:
xs = line.strip().split('\t')
nums = [float(x) for x in xs[idx_start: idx_end + 1]]
probas.append(nums)
n = len(probas)
for p in ps:
n_over_p = sum([max(ls) >= p for ls in probas])
over_p.append(n_over_p / n)
for (x, y) in zip(ps, over_p):
print('{}\t{}'.format(x, y))
plot.plot(