for ic50 in ic50_data:
float_ic50_data = float(ic50)
regression_ic50.append(dataset.map_ic50_for_regression(float_ic50_data))
binarized_ic50.append(dataset.binarize_ic50(float_ic50_data))
count = 0
for item in binarized_ic50:
if item == 0:
count += 1
#print (regression_ic50)
#print (count)
"""
mask_peptides干啥的
"""
mask_len = MHCI_MASK_LEN
with open(data, 'r') as csvfile:
reader = csv.DictReader(csvfile)
peptides = [row['peptide'] for row in reader]
masked_peptides = dataset.mask_peptides(peptides, max_len=mask_len)
#print (masked_peptides)
"""
cut_pad_peptides干啥的
"""
padded_peptides = dataset.cut_pad_peptides(peptides)
#print(padded_peptides)
"""
tensorize_keras干啥的
"""
tensorized = dataset.tensorize_keras(padded_peptides, embed_type="onehot")
print(tensorized)
def predict(class_,
peptides_path,
mhc,
model='lstm',
weights_path=None,
output=None):
'''
Prediction protocol
'''
# read peptides
peptides = [p.strip() for p in open(peptides_path)]
# set the length
if class_.upper() == 'I':
mask_len = MHCI_MASK_LEN
elif class_.upper() == 'II':
mask_len = MHCII_MASK_LEN
print('Predicting for %d peptides' % (len(peptides)))
# apply cut/pad or mask to same length
if 'lstm' in model or 'gru' in model:
normed_peptides = mask_peptides(peptides, max_len=mask_len)
else:
normed_peptides = cut_pad_peptides(peptides)
# get tensorized values for prediction
peptides_tensor = tensorize_keras(normed_peptides, embed_type='softhot')
# make model
print('Building model')
# define model
if model == 'lstm':
model = mhcnuggets_lstm(input_size=(mask_len, NUM_AAS))
if weights_path:
model.load_weights(weights_path)
else:
if class_.upper() == 'I':
predictor_mhc = closest_mhcI(mhc)
elif class_.upper() == 'II':
predictor_mhc = closest_mhcII(mhc)
print("Closest allele found", predictor_mhc)
model.load_weights(
os.path.join(MHCNUGGETS_HOME, "saves", "production",
predictor_mhc + '.h5'))
model.compile(loss='mse', optimizer=Adam(lr=0.001))
# test model
preds_continuous, preds_binary = get_predictions(peptides_tensor, model)
ic50s = [map_proba_to_ic50(p[0]) for p in preds_continuous]
# write out results
if output:
filehandle = open(output, 'w')
else:
filehandle = sys.stdout
print(','.join(('peptide', 'ic50')), file=filehandle)
for i, peptide in enumerate(peptides):
print(','.join((peptide, str(ic50s[i]))), file=filehandle)
def predict(class_,
peptides_path,
mhc,
pickle_path='data/production/examples_per_allele.pkl',
model='lstm',
model_weights_path="saves/production/",
output=None,
mass_spec=False,
ic50_threshold=500,
max_ic50=50000,
embed_peptides=False,
binary_preds=False,
ba_models=False):
'''
Prediction protocol
'''
# read peptides
peptides = [p.strip() for p in open(peptides_path)]
# set the length
if class_.upper() == 'I':
mask_len = MHCI_MASK_LEN
input_size = (MHCI_MASK_LEN, NUM_AAS)
elif class_.upper() == 'II':
mask_len = MHCII_MASK_LEN
input_size = (MHCII_MASK_LEN, NUM_AAS)
print('Predicting for %d peptides' % (len(peptides)))
# apply cut/pad or mask to same length
normed_peptides, original_peptides = mask_peptides(peptides,
max_len=mask_len)
# get tensorized values for prediction
peptides_tensor = tensorize_keras(normed_peptides, embed_type='softhot')
# make model
print('Building model')
model = mhcnuggets_lstm(input_size)
if class_.upper() == 'I':
predictor_mhc = closest_mhcI(mhc, pickle_path)
elif class_.upper() == 'II':
predictor_mhc = closest_mhcII(mhc, pickle_path)
print("Closest allele found", predictor_mhc)
if model_weights_path != "saves/production/":
print('Predicting with user-specified model: ' + model_weights_path)
model.load_weights(model_weights_path)
elif ba_models:
print('Predicting with only binding affinity trained models')
model.load_weights(
os.path.join(MHCNUGGETS_HOME, model_weights_path,
predictor_mhc + '_BA.h5'))
elif os.path.isfile(
os.path.join(MHCNUGGETS_HOME, model_weights_path,
predictor_mhc + '_BA_to_HLAp.h5')):
print('BA_to_HLAp model found, predicting with BA_to_HLAp model...')
model.load_weights(
os.path.join(MHCNUGGETS_HOME, model_weights_path,
predictor_mhc + '_BA_to_HLAp.h5'))
else:
print('No BA_to_HLAp model found, predicting with BA model...')
model.load_weights(
os.path.join(MHCNUGGETS_HOME, model_weights_path,
predictor_mhc + '_BA.h5'))
if mass_spec:
model.compile(loss='binary_crossentropy', optimizer=Adam(lr=0.001))
else:
model.compile(loss='mse', optimizer=Adam(lr=0.001))
# test model
preds_continuous, preds_binary = get_predictions(peptides_tensor, model,
binary_preds,
embed_peptides,
ic50_threshold, max_ic50)
ic50s = [map_proba_to_ic50(p[0], max_ic50) for p in preds_continuous]
# write out results
if output:
filehandle = open(output, 'w')
else:
filehandle = sys.stdout
print(','.join(('peptide', 'ic50')), file=filehandle)
for i, peptide in enumerate(original_peptides):
print(','.join((peptide, str(round(ic50s[i], 2)))), file=filehandle)