2, (gene_dataset.n_labels + 1),
n_hidden=128,
n_latent=10,
n_layers=2,
dispersion='gene')
scanvi.load_state_dict(trainer.model.state_dict(), strict=False)
trainer_scanvi = AlternateSemiSupervisedTrainer(
scanvi,
gene_dataset,
n_epochs_classifier=10,
lr_classification=5 * 1e-3)
trainer_scanvi.labelled_set = trainer_scanvi.create_posterior(
indices=gene_dataset.batch_indices.ravel() == 0)
trainer_scanvi.unlabelled_set = trainer_scanvi.create_posterior(
indices=gene_dataset.batch_indices.ravel() == 1)
trainer_scanvi.train(n_epochs=10)
scanvi_full = trainer_scanvi.create_posterior(
trainer_scanvi.model,
gene_dataset,
indices=np.arange(len(gene_dataset)))
latent, _, _ = scanvi_full.sequential().get_latent()
acc, cell_type = KNNpurity(latent1, latent2, latent,
batch_indices.ravel(), labels, keys)
f.write('scanvi' + '\t' + rmCellTypes +
("\t%.4f" * 8 + "\t%s" * 8 + "\n") %
tuple(list(acc) + list(cell_type)))
be, cell_type2 = BEbyType(keys, latent, labels, batch_indices,
celltype1)
g.write('scanvi' + '\t' + rmCellTypes +
("\t%.4f" * 8 + "\t%s" * 8 + "\n") %
tuple(be + list(cell_type2)))
labelled = np.where(gene_dataset.batch_indices == 0)[0]
# np.random.shuffle(labelled)
unlabelled = np.where(gene_dataset.batch_indices == 1)[0]
# np.random.shuffle(unlabelled)
trainer_scanvi.labelled_set = trainer_scanvi.create_posterior(indices=labelled)
trainer_scanvi.unlabelled_set = trainer_scanvi.create_posterior(
indices=unlabelled)
# file_name = '%s/scanvi.pkl' % save_path
# if os.path.isfile(file_name):
# print("loaded model from: " + file_name)
# trainer_scanvi.model.load_state_dict(torch.load(file_name))
# trainer_scanvi.model.eval()
# else:
# train & save
trainer_scanvi.train(n_epochs=5)
# torch.save(trainer_scanvi.model.state_dict(), file_name)
scanvi_labels = trainer_scanvi.full_dataset.sequential().compute_predictions(
)[1]
predicted_labels = pd.DataFrame(
[gene_dataset.labels.ravel(), scVI_labels, scanvi_labels],
index=['labels', 'scVI', 'scANVI'])
predicted_labels.T.to_csv(save_path + 'pred_labels.nb.%i.csv' % rep)
# get latent space
full_scanvi = trainer.create_posterior(trainer_scanvi.model,
gene_dataset,
indices=np.arange(len(gene_dataset)))
latent, batch_indices, labels = full_scanvi.sequential().get_latent()
def trainSCANVI(gene_dataset,
model_type,
filename,
rep,
nlayers=2,
reconstruction_loss: str = "zinb"):
vae_posterior = trainVAE(gene_dataset,
filename,
rep,
reconstruction_loss=reconstruction_loss)
filename = '../' + filename + '/' + model_type + '.' + reconstruction_loss + '.rep' + str(
rep) + '.pkl'
scanvi = SCANVI(gene_dataset.nb_genes,
gene_dataset.n_batches,
gene_dataset.n_labels,
n_layers=nlayers,
reconstruction_loss=reconstruction_loss)
scanvi.load_state_dict(vae_posterior.model.state_dict(), strict=False)
if model_type == 'scanvi1':
trainer_scanvi = AlternateSemiSupervisedTrainer(
scanvi,
gene_dataset,
classification_ratio=0,
n_epochs_classifier=100,
lr_classification=5 * 1e-3)
labelled = np.where(gene_dataset.batch_indices.ravel() == 0)[0]
labelled = np.random.choice(labelled, len(labelled), replace=False)
trainer_scanvi.labelled_set = trainer_scanvi.create_posterior(
indices=labelled)
trainer_scanvi.unlabelled_set = trainer_scanvi.create_posterior(
indices=(gene_dataset.batch_indices.ravel() == 1))
elif model_type == 'scanvi2':
trainer_scanvi = AlternateSemiSupervisedTrainer(
scanvi,
gene_dataset,
classification_ratio=0,
n_epochs_classifier=100,
lr_classification=5 * 1e-3)
labelled = np.where(gene_dataset.batch_indices.ravel() == 1)[0]
labelled = np.random.choice(labelled, len(labelled), replace=False)
trainer_scanvi.labelled_set = trainer_scanvi.create_posterior(
indices=labelled)
trainer_scanvi.unlabelled_set = trainer_scanvi.create_posterior(
indices=(gene_dataset.batch_indices.ravel() == 0))
elif model_type == 'scanvi0':
trainer_scanvi = SemiSupervisedTrainer(scanvi,
gene_dataset,
classification_ratio=0,
n_epochs_classifier=100,
lr_classification=5 * 1e-3)
trainer_scanvi.labelled_set = trainer_scanvi.create_posterior(
indices=(gene_dataset.batch_indices.ravel() < 0))
trainer_scanvi.unlabelled_set = trainer_scanvi.create_posterior(
indices=(gene_dataset.batch_indices.ravel() >= 0))
else:
trainer_scanvi = SemiSupervisedTrainer(scanvi,
gene_dataset,
classification_ratio=10,
n_epochs_classifier=100,
lr_classification=5 * 1e-3)
if os.path.isfile(filename):
trainer_scanvi.model.load_state_dict(torch.load(filename))
trainer_scanvi.model.eval()
else:
trainer_scanvi.train(n_epochs=5)
torch.save(trainer_scanvi.model.state_dict(), filename)
return trainer_scanvi
