def main(argv):
if len(argv) > 1:
raise app.UsageError('Too many command-line arguments.')
# Set random seed
np.random.seed(FLAGS.seed)
torch.manual_seed(FLAGS.seed)
if torch.cuda.is_available(): # cuda device
device = 'cuda'
torch.cuda.set_device(FLAGS.gpu)
else:
device = 'cpu'
adata, trainloader, testloader = load_dataset(
FLAGS.input_path,
batch_name='batch',
min_genes=FLAGS.min_peaks,
min_cells=FLAGS.min_cells,
batch_size=FLAGS.batch_size,
n_top_genes=FLAGS.n_feature,
log=None,
)
input_dim = adata.shape[1]
tf.io.gfile.makedirs(FLAGS.output_path)
dims = [input_dim, FLAGS.latent, FLAGS.encode_dim, FLAGS.decode_dim]
model = SCALE(dims, n_centroids=FLAGS.n_centroids)
print(model)
print('\n## Training Model ##')
model.init_gmm_params(testloader)
model.fit(trainloader,
lr=FLAGS.lr,
weight_decay=FLAGS.weight_decay,
verbose=FLAGS.verbose,
device=device,
max_iter=FLAGS.max_iter,
outdir=FLAGS.output_path)
adata.obsm['latent'] = model.encodeBatch(testloader,
device=device,
out='z')
dr = pd.DataFrame(adata.obsm['latent'], index=adata.obs_names)
with tf.io.gfile.GFile(os.path.join(FLAGS.output_path, 'SCALE.csv'),
'w') as f:
dr.to_csv(f)
print(
'Cell number: {}\nInput_dim: {}\nn_centroids: {}\nEpoch: {}\nSeed: {}\nDevice: {}'
.format(cell_num, input_dim, k, epochs, args.seed, args.device))
print("============================")
dims = [input_dim, config.latent, config.encode_dim, config.decode_dim]
model = SCALE(dims, n_centroids=k, device=device)
model.to(device)
data = data.to(device)
if not args.pretrain:
print('\n## Training Model ##')
t0 = time.time()
model.init_gmm_params(data)
model.fit(dataloader,
lr=lr,
weight_decay=config.weight_decay,
epochs=epochs,
verbose=args.verbose,
print_interval=config.print_interval)
print('\nRunning Time: {:.2f} s'.format(time.time() - t0))
else:
print('\n## Loading Model {} ##\n'.format(args.pretrain))
model.load_model(args.pretrain)
# Clustering Report
if args.reference:
ref, classes = read_labels(args.reference)
pred = model.predict(data)
cluster_report(ref, pred, classes)
outdir = args.outdir
if not args.no_results:
.format(cell_num, input_dim, k, args.max_iter, batch_size,
args.min_peaks, args.min_cells))
print("============================")
dims = [input_dim, args.latent, args.encode_dim, args.decode_dim]
model = SCALE(dims, n_centroids=k)
print(model)
if not args.pretrain:
print('\n## Training Model ##')
model.init_gmm_params(testloader)
model.fit(
trainloader,
lr=lr,
weight_decay=args.weight_decay,
verbose=args.verbose,
device=device,
max_iter=args.max_iter,
# name=name,
outdir=outdir)
torch.save(model.state_dict(), os.path.join(outdir,
'model.pt')) # save model
else:
print('\n## Loading Model: {}\n'.format(args.pretrain))
model.load_model(args.pretrain)
model.to(device)
### output ###
print('outdir: {}'.format(outdir))
# 1. latent feature
adata.obsm['latent'] = model.encodeBatch(testloader,