def load_data(parent_id, go_id):
data = list()
labels = list()
positive = list()
negative = list()
with open(DATA_ROOT + parent_id + '/' + go_id + '.txt') as f:
for line in f:
line = line.strip().split(' ')
label = int(line[0])
seq = line[2][:MAXLEN]
if label == 1:
labels.append(1)
positive.append(seq)
else:
labels.append(0)
negative.append(seq)
shuffle(negative, seed=0)
n = len(positive)
negative = negative[:n]
n = len(positive)
labels = [0] * len(negative) + [1] * len(positive)
data = negative + positive
for i in range(len(data)):
data[i] = encode_seq_one_hot(data[i], maxlen=MAXLEN)
shuffle(data, labels, seed=0)
return numpy.array(labels), numpy.array(data, dtype='float32')
def load_data(go_id):
positive1 = list()
positive2 = list()
negative1 = list()
negative2 = list()
with open(DATA_ROOT + go_id + '.txt') as f:
for line in f:
line = line.strip().split(' ')
label = int(line[0])
seq = line[2][:MAXLEN]
hydro = encode_seq_hydro(seq, maxlen=MAXLEN)
seq = encode_seq_one_hot(seq, maxlen=MAXLEN)
if label == 1:
positive1.append(seq)
positive2.append(hydro)
else:
negative1.append(seq)
negative2.append(hydro)
shuffle(negative1, negative2, seed=0)
n = len(positive1)
data1 = negative1[:n] + positive1
data2 = negative2[:n] + positive2
labels = [0] * len(negative1) + [1] * len(positive1)
shuffle(data1, data2, labels, seed=0)
data = (numpy.array(data1,
dtype='float32'), numpy.array(data2, dtype='float32'))
return (numpy.array(labels, dtype='float32'), data)
def load_data(go_id):
positive1 = list()
positive2 = list()
negative1 = list()
negative2 = list()
with open(DATA_ROOT + go_id + '.txt') as f:
for line in f:
line = line.strip().split(' ')
label = int(line[0])
seq = line[2][:MAXLEN]
hydro = encode_seq_hydro(seq, maxlen=MAXLEN)
seq = encode_seq_one_hot(seq, maxlen=MAXLEN)
if label == 1:
positive1.append(seq)
positive2.append(hydro)
else:
negative1.append(seq)
negative2.append(hydro)
shuffle(negative1, negative2, seed=0)
n = len(positive1)
data1 = negative1[:n] + positive1
data2 = negative2[:n] + positive2
labels = [0] * len(negative1) + [1] * len(positive1)
shuffle(data1, data2, labels, seed=0)
data = (
numpy.array(data1, dtype='float32'),
numpy.array(data2, dtype='float32'))
return (
numpy.array(labels, dtype='float32'),
data)
def load_data(parent_id, go_id):
data = list()
labels = list()
global nb_classes
with open(DATA_ROOT + parent_id + '/' + go_id + '.txt') as f:
for line in f:
line = line.strip().split('\t')
seq = line[1][:MAXLEN]
labs = line[2].split('|')
data.append(seq)
for i in range(len(labs)):
labs[i] = int(labs[i])
nb_classes = max(nb_classes, labs[i])
labels.append(labs)
nb_classes += 1
for i in range(len(labels)):
l = [0] * nb_classes
for x in labels[i]:
l[x] = 1
labels[i] = l
for i in range(len(data)):
data[i] = encode_seq_one_hot(data[i], maxlen=MAXLEN)
shuffle(data, labels, seed=0)
return numpy.array(
labels, dtype='float32'), numpy.array(data, dtype='float32')
def load_data(parent_id, go_id):
data = list()
labels = list()
positive = list()
negative = list()
with open(DATA_ROOT + parent_id + '/' + go_id + '.txt') as f:
for line in f:
line = line.strip().split(' ')
label = int(line[0])
seq = line[2][:MAXLEN]
if label == 1:
labels.append(1)
positive.append(seq)
else:
labels.append(0)
negative.append(seq)
shuffle(negative, seed=0)
n = len(positive)
negative = negative[:n]
n = len(positive)
labels = [0] * len(negative) + [1] * len(positive)
data = negative + positive
for i in range(len(data)):
data[i] = encode_seq_one_hot(data[i], maxlen=MAXLEN)
shuffle(data, labels, seed=0)
return numpy.array(labels), numpy.array(data, dtype='float32')
def predict_functions(classifier, seq):
q = deque()
q.append(classifier)
functions = list()
data = numpy.array([encode_seq_one_hot(seq, maxlen=MAXLEN)])
while len(q) > 0:
x = q.popleft()
ok = True
for ch_id in x['children']:
if 'model' in go[ch_id] and go[ch_id]['model']:
model = go[ch_id]['model']
pred = model.predict_classes(data, batch_size=1, verbose=0)
if pred[0][0] == 1:
ok = False
q.append(go[ch_id])
if ok:
functions.append(x['id'])
return functions
def predict_functions(classifier, seq):
q = deque()
q.append(classifier)
functions = list()
data = numpy.array([encode_seq_one_hot(seq, maxlen=MAXLEN)])
while len(q) > 0:
x = q.popleft()
ok = True
for ch_id in x['children']:
if 'model' in go[ch_id] and go[ch_id]['model']:
model = go[ch_id]['model']
pred = model.predict_classes(
data,
batch_size=1,
verbose=0)
if pred[0][0] == 1:
ok = False
q.append(go[ch_id])
if ok:
functions.append(x['id'])
return functions
def load_data(parent_id, go_id):
data1 = list()
data2 = list()
labels = list()
positive1 = list()
negative1 = list()
positive2 = list()
negative2 = list()
with open(DATA_ROOT + parent_id + '/' + go_id + '.txt') as f:
for line in f:
line = line.strip().split(' ')
label = int(line[0])
seq = line[2][:MAXLEN]
sq1 = encode_seq_one_hot(seq, maxlen=MAXLEN)
sq2 = encode_seq(OGAK980101, seq, maxlen=MAXLEN)
sq3 = encode_seq(MEHP950102, seq, maxlen=MAXLEN)
sq4 = encode_seq(CROG050101, seq, maxlen=MAXLEN)
sq5 = encode_seq(TOBD000101, seq, maxlen=MAXLEN)
sq6 = encode_seq(ALTS910101, seq, maxlen=MAXLEN)
if label == 1:
positive1.append([sq1])
positive2.append(sq1)
else:
negative1.append([sq1])
negative2.append(sq1)
shuffle(negative1, negative2, seed=0)
n = min(len(positive1), len(negative1))
data1 = negative1[:n] + positive1[:n]
data2 = negative2[:n] + positive2[:n]
labels = [0.0] * n + [1.0] * n
# Previous was 30
shuffle(data1, data2, labels, seed=0)
data = (
numpy.array(data1, dtype='float32'),
numpy.array(data2, dtype='float32'))
return (numpy.array(labels), data)
def load_data(parent_id, go_id):
data1 = list()
data2 = list()
labels = list()
positive1 = list()
negative1 = list()
positive2 = list()
negative2 = list()
with open(DATA_ROOT + parent_id + '/' + go_id + '.txt') as f:
for line in f:
line = line.strip().split(' ')
label = int(line[0])
seq = line[2][:MAXLEN]
sq1 = encode_seq_one_hot(seq, maxlen=MAXLEN)
sq2 = encode_seq(OGAK980101, seq, maxlen=MAXLEN)
sq3 = encode_seq(MEHP950102, seq, maxlen=MAXLEN)
sq4 = encode_seq(CROG050101, seq, maxlen=MAXLEN)
sq5 = encode_seq(TOBD000101, seq, maxlen=MAXLEN)
sq6 = encode_seq(ALTS910101, seq, maxlen=MAXLEN)
if label == 1:
positive1.append([sq1])
positive2.append(sq1)
else:
negative1.append([sq1])
negative2.append(sq1)
shuffle(negative1, negative2, seed=0)
n = min(len(positive1), len(negative1))
data1 = negative1[:n] + positive1[:n]
data2 = negative2[:n] + positive2[:n]
labels = [0.0] * n + [1.0] * n
# Previous was 30
shuffle(data1, data2, labels, seed=0)
data = (numpy.array(data1,
dtype='float32'), numpy.array(data2, dtype='float32'))
return (numpy.array(labels), data)
def load_data(go_id):
data1 = list()
data2 = list()
labels = list()
positive1 = list()
negative1 = list()
positive2 = list()
negative2 = list()
with open(DATA_ROOT + '/' + go_id + '.txt') as f:
for line in f:
line = line.strip().split(' ')
label = int(line[0])
seq = line[2][:MAXLEN]
sq1 = encode_seq_one_hot(seq, maxlen=MAXLEN)
sq2 = list()
for l in seq:
sq2.append(MEHP950102[AAINDEX[l]])
while len(sq2) < MAXLEN:
sq2.append([0.0] * 20)
if label == 1:
positive1.append(sq1)
positive2.append(sq2)
else:
negative1.append(sq1)
negative2.append(sq2)
shuffle(negative1, negative2)
n = min(len(positive1), len(negative1))
data1 = negative1[:n] + positive1[:n]
data2 = negative2[:n] + positive2[:n]
labels = [0.0] * n + [1.0] * n
# Previous was 30
shuffle(data1, data2, labels)
return (numpy.array(labels), numpy.array(data1, dtype='float32'),
numpy.array(data2,
dtype='float32'), numpy.array(data1, dtype='float32'))
def load_data(go_id):
data = list()
labels = list()
pos = 1
positive = list()
negative = list()
with open(DATA_ROOT + go_id + '.txt') as f:
for line in f:
line = line.strip().split(' ')
label = int(line[0])
seq = []
seq = encode_seq_one_hot(line[2][:500], maxlen=MAXLEN)
if label == pos:
positive.append(seq)
else:
negative.append(seq)
shuffle(negative, seed=0)
n = len(positive)
data = negative[:n] + positive
labels = [0.0] * n + [1.0] * n
# Previous was 30
shuffle(data, labels, seed=0)
return numpy.array(labels), numpy.array(data, dtype="float32")
