def main(args):
# Word to index dictionary
amino_acids = [letter for letter in 'ARNDCEQGHILKMFPSTWYV']
if args.model_type == 'lstm':
amino_to_ix = {
amino: index
for index, amino in enumerate(['PAD'] + amino_acids)
}
if args.model_type == 'ae':
pep_atox = {
amino: index
for index, amino in enumerate(['PAD'] + amino_acids)
}
tcr_atox = {
amino: index
for index, amino in enumerate(amino_acids + ['X'])
}
# hyper-params
arg = {}
arg['train_auc_file'] = args.train_auc_file if args.train_auc_file else 'ignore'
arg['test_auc_file'] = args.test_auc_file if args.test_auc_file else 'ignore'
if args.test_auc_file == 'auto':
dir = 'memory_and_protein'
p_key = 'protein' if args.protein else ''
arg['test_auc_file'] = dir + '/' + '_'.join(
[args.model_type, args.dataset, args.sampling, p_key])
arg['ae_file'] = args.ae_file
if args.ae_file == 'auto':
args.ae_file = 'TCR_Autoencoder/tcr_autoencoder.pt'
arg['ae_file'] = 'TCR_Autoencoder/tcr_autoencoder.pt'
pass
arg['siamese'] = False
params = {}
params['lr'] = 1e-3
params['wd'] = 1e-5
params['epochs'] = 200
params['batch_size'] = 50
params['lstm_dim'] = 30
params['emb_dim'] = 10
params['dropout'] = 0.1
params['option'] = 0
params['enc_dim'] = 30
params['train_ae'] = True
# Load autoencoder params
if args.model_type == 'ae':
checkpoint = torch.load(args.ae_file)
params['max_len'] = checkpoint['max_len']
params['batch_size'] = checkpoint['batch_size']
# Load data
if args.dataset == 'mcpas':
datafile = 'data/McPAS-TCR.csv'
if args.dataset == 'vdjdb':
datafile = 'data/VDJDB_complete.tsv'
train, test = ergo_data_loader.load_data(datafile,
args.dataset,
args.sampling,
_protein=args.protein,
_hla=args.hla)
# Save test
if args.test_data_file == 'auto':
dir = 'memory_and_protein'
p_key = 'protein' if args.protein else ''
args.test_data_file = dir + '/' + '_'.join(
[args.model_type, args.dataset, args.sampling, p_key, 'test'])
if args.test_data_file:
with open(args.test_data_file + '.pickle', 'wb') as handle:
pickle.dump(test, handle)
if args.model_type == 'ae':
# train
train_tcrs, train_peps, train_signs = ae_get_lists_from_pairs(
train, params['max_len'])
train_batches = ae.get_batches(train_tcrs, train_peps, train_signs,
tcr_atox, pep_atox,
params['batch_size'], params['max_len'])
# test
test_tcrs, test_peps, test_signs = ae_get_lists_from_pairs(
test, params['max_len'])
test_batches = ae.get_batches(test_tcrs, test_peps, test_signs,
tcr_atox, pep_atox, params['batch_size'],
params['max_len'])
# Train the model
model, best_auc, best_roc = ae.train_model(train_batches, test_batches,
args.device, arg, params)
pass
if args.model_type == 'lstm':
# train
train_tcrs, train_peps, train_signs = lstm_get_lists_from_pairs(train)
lstm.convert_data(train_tcrs, train_peps, amino_to_ix)
train_batches = lstm.get_batches(train_tcrs, train_peps, train_signs,
params['batch_size'])
# test
test_tcrs, test_peps, test_signs = lstm_get_lists_from_pairs(test)
lstm.convert_data(test_tcrs, test_peps, amino_to_ix)
test_batches = lstm.get_batches(test_tcrs, test_peps, test_signs,
params['batch_size'])
# Train the model
model, best_auc, best_roc = lstm.train_model(train_batches,
test_batches, args.device,
arg, params)
pass
# Save trained model
if args.model_file == 'auto':
dir = 'memory_and_protein'
p_key = 'protein' if args.protein else ''
args.model_file = dir + '/' + '_'.join(
[args.model_type, args.dataset, args.sampling, p_key, 'model.pt'])
if args.model_file:
torch.save({
'model_state_dict': model.state_dict(),
}, args.model_file)
if args.roc_file:
# Save best ROC curve and AUC
np.savez(args.roc_file,
fpr=best_roc[0],
tpr=best_roc[1],
auc=np.array(best_auc))
pass
def main(args):
# Word to index dictionary
amino_acids = [letter for letter in 'ARNDCEQGHILKMFPSTWYV']
if args.model_type == 'lstm':
amino_to_ix = {amino: index for index, amino in enumerate(['PAD'] + amino_acids)}
if args.model_type == 'ae':
pep_atox = {amino: index for index, amino in enumerate(['PAD'] + amino_acids)}
tcr_atox = {amino: index for index, amino in enumerate(amino_acids + ['X'])}
# hyper-params
arg = {}
arg['train_auc_file'] = args.train_auc_file if args.train_auc_file else 'ignore'
arg['test_auc_file'] = args.test_auc_file if args.test_auc_file else 'ignore'
if args.test_auc_file == 'auto':
dir = 'save_results'
p_key = 'protein' if args.protein else ''
arg['test_auc_file'] = dir + '/' + '_'.join([args.model_type, args.dataset, args.sampling, p_key])
arg['ae_file'] = args.ae_file
if args.ae_file == 'auto':
args.ae_file = 'TCR_Autoencoder/tcr_ae_dim_30.pt'
arg['ae_file'] = 'TCR_Autoencoder/tcr_ae_dim_30.pt'
pass
arg['siamese'] = False
params = {}
params['lr'] = 1e-4
params['wd'] = 0
params['epochs'] = 100
if args.dataset == 'tumor':
params['epochs'] = 25
params['batch_size'] = 50
params['lstm_dim'] = 500
params['emb_dim'] = 10
params['dropout'] = 0.1
params['option'] = 0
params['enc_dim'] = 100
params['train_ae'] = True
# Load autoencoder params
if args.model_type == 'ae':
args.ae_file = 'TCR_Autoencoder/tcr_ae_dim_' + str(params['enc_dim']) + '.pt'
arg['ae_file'] = args.ae_file
checkpoint = torch.load(args.ae_file, map_location=args.device)
params['max_len'] = checkpoint['max_len']
params['batch_size'] = checkpoint['batch_size']
# Load data
if args.dataset == 'mcpas':
datafile = r'data/nine_class_testdata.csv'
elif args.dataset == 'vdjdb':
datafile = r'data/VDJDB_complete.tsv'
elif args.dataset == 'united':
datafile = {'mcpas': r'data/nine_class_testdata.csv', 'vdjdb': r'data/VDJDB_complete.tsv'}
elif args.dataset == 'tumor':
datafile = r'tumor/extended_cancer_pairs'
elif args.dataset == 'nettcr':
datafile = r'NetTCR/iedb_mira_pos_uniq'
#train, test = ergo_data_loader.load_data(datafile, args.dataset, args.sampling,
#_protein=False, _hla=False)
# Save train
if args.train_data_file == 'auto':
dir = 'save_results'
p_key = 'protein' if args.protein else ''
args.train_data_file = dir + '/' + '_'.join([args.model_type, args.dataset, args.sampling, p_key, 'train'])
if args.train_data_file:
with open(args.train_data_file + '.pickle', 'rb') as handle:
train = pickle.load(handle)
# Save test
if args.test_data_file == 'auto':
dir = 'final_results'
p_key = 'protein' if args.protein else ''
args.test_data_file = dir + '/' + '_'.join([args.model_type, args.dataset, args.sampling, p_key, 'test'])
if args.test_data_file:
with open(args.test_data_file + '.pickle', 'rb') as handle2:
test = pickle.load(handle2)
if args.model_type == 'ae':
# train
train_tcrs, train_peps, train_signs = ae_get_lists_from_pairs(train, params['max_len'])
train_batches = ae.get_batches(train_tcrs, train_peps, train_signs, tcr_atox, pep_atox, params['batch_size'], params['max_len'])
# test
test_tcrs, test_peps, test_signs = ae_get_lists_from_pairs(test, params['max_len'])
test_batches = ae.get_batches(test_tcrs, test_peps, test_signs, tcr_atox, pep_atox, params['batch_size'], params['max_len'])
# Train the model
model, best_auc, best_roc = ae.train_model(train_batches, test_batches, args.device, arg, params)
pass
if args.model_type == 'lstm':
# train
train_tcrs, train_peps, train_signs = lstm_get_lists_from_pairs(train)
lstm.convert_data(train_tcrs, train_peps, amino_to_ix)
train_batches = lstm.get_batches(train_tcrs, train_peps, train_signs, params['batch_size'])
# test
test_tcrs, test_peps, test_signs = lstm_get_lists_from_pairs(test)
lstm.convert_data(test_tcrs, test_peps, amino_to_ix)
test_batches = lstm.get_batches(test_tcrs, test_peps, test_signs, params['batch_size'])
# Train the model
model, best_auc, best_roc = lstm.train_model(train_batches, test_batches, args.device, arg, params)
pass
# Save trained model
if args.model_file == 'auto':
dir = 'final_results'
p_key = 'protein' if args.protein else ''
args.model_file = dir + '/' + '_'.join([args.model_type, args.dataset, args.sampling, p_key, 'model.pt'])
if args.model_file:
torch.save({
'model_state_dict': model.state_dict(),
'params': params
}, args.model_file)
if args.roc_file:
# Save best ROC curve and AUC
np.savez(args.roc_file, fpr=best_roc[0], tpr=best_roc[1], auc=np.array(best_auc))
pass