def benchmark(dataset, n_epochs=250, use_cuda=True):
vae = VAE(dataset.nb_genes, n_batch=dataset.n_batches)
infer = VariationalInference(vae, dataset, use_cuda=use_cuda)
infer.train(n_epochs=n_epochs)
infer.ll('test')
infer.marginal_ll('test')
infer.imputation('test', rate=0.1) # assert ~ 2.1
return infer
def base_benchmark(gene_dataset):
vae = VAE(gene_dataset.nb_genes, gene_dataset.n_batches,
gene_dataset.n_labels)
infer = VariationalInference(vae,
gene_dataset,
train_size=0.5,
use_cuda=use_cuda)
infer.train(n_epochs=1)
return infer
count.append(nsamples)
cells.append(sample)
correlation = (np.corrcoef(count[0], count[1])[0, 1])
print("dataset 1 has %d cells" % (np.sum(count[0])))
print("dataset 2 has %d cells" % (np.sum(count[1])))
print(
"correlation between the cell-type composition of the subsampled dataset is %.3f"
% correlation)
sub_dataset = deepcopy(gene_dataset)
sub_dataset.update_cells(np.concatenate(cells))
vae = VAE(sub_dataset.nb_genes,
n_batch=sub_dataset.n_batches,
n_labels=sub_dataset.n_labels,
n_hidden=128,
dispersion='gene')
infer = VariationalInference(vae, sub_dataset, use_cuda=use_cuda)
infer.train(n_epochs=250)
latent, batch_indices, labels = infer.get_latent('sequential')
keys = sub_dataset.cell_types
batch_entropy = entropy_batch_mixing(latent, batch_indices)
print("Entropy batch mixing :", batch_entropy)
sample = select_indices_evenly(1000, labels)
res = knn_purity_avg(latent[sample, :],
labels[sample].astype('int'),
keys=keys,
acc=True)
print('average classification accuracy per cluster')
for x in res:
print(x)
knn_acc = np.mean([x[1] for x in res])
print("average KNN accuracy:", knn_acc)
def cortex_benchmark(n_epochs=250, use_cuda=True, unit_test=False):
cortex_dataset = CortexDataset()
vae = VAE(cortex_dataset.nb_genes)
infer_cortex_vae = VariationalInference(vae, cortex_dataset, use_cuda=use_cuda)
infer_cortex_vae.train(n_epochs=n_epochs)
infer_cortex_vae.ll('test') # assert ~ 1200
infer_cortex_vae.differential_expression('test')
infer_cortex_vae.imputation('test', rate=0.1) # assert ~ 2.3
n_samples = 1000 if not unit_test else 10
infer_cortex_vae.show_t_sne('test', n_samples=n_samples)
return infer_cortex_vae
def test_cortex():
cortex_dataset = CortexDataset()
vae = VAE(cortex_dataset.nb_genes, cortex_dataset.n_batches)
infer_cortex_vae = VariationalInference(vae,
cortex_dataset,
train_size=0.1,
use_cuda=use_cuda)
infer_cortex_vae.train(n_epochs=1)
infer_cortex_vae.ll('train')
infer_cortex_vae.differential_expression_stats('train')
infer_cortex_vae.differential_expression('test')
infer_cortex_vae.imputation_errors('test', rate=0.5)
svaec = SVAEC(cortex_dataset.nb_genes, cortex_dataset.n_batches,
cortex_dataset.n_labels)
infer_cortex_svaec = JointSemiSupervisedVariationalInference(
svaec,
cortex_dataset,
n_labelled_samples_per_class=50,
use_cuda=use_cuda)
infer_cortex_svaec.train(n_epochs=1)
infer_cortex_svaec.accuracy('labelled')
infer_cortex_svaec.ll('all')
svaec = SVAEC(cortex_dataset.nb_genes,
cortex_dataset.n_batches,
cortex_dataset.n_labels,
logreg_classifier=True)
infer_cortex_svaec = AlternateSemiSupervisedVariationalInference(
svaec,
cortex_dataset,
n_labelled_samples_per_class=50,
use_cuda=use_cuda)
infer_cortex_svaec.train(n_epochs=1, lr=1e-2)
infer_cortex_svaec.accuracy('unlabelled')
infer_cortex_svaec.svc_rf(unit_test=True)
cls = Classifier(cortex_dataset.nb_genes, n_labels=cortex_dataset.n_labels)
infer_cls = ClassifierInference(cls, cortex_dataset)
infer_cls.train(n_epochs=1)
infer_cls.accuracy('train')
print('total number of cells =' + str([
np.sum(sub_dataset1.labels == i)
for i, k in enumerate(sub_dataset1.cell_types) if k == subpop
][0]))
gene_dataset = GeneExpressionDataset.concat_datasets(sub_dataset1, dataset2,
dataset3)
gene_dataset.subsample_genes(5000)
vae = VAE(gene_dataset.nb_genes,
n_batch=gene_dataset.n_batches,
n_labels=gene_dataset.n_labels,
n_hidden=128,
n_latent=10,
n_layers=1,
dispersion='gene')
infer_vae = VariationalInference(vae, gene_dataset, use_cuda=use_cuda)
infer_vae.fit(n_epochs=100)
np.save("../" + plotname + '.label.npy', gene_dataset.labels)
np.save("../" + plotname + '.batch.npy', gene_dataset.batch_indices)
mmwrite("../" + plotname + '.count.mtx', gene_dataset.X)
data_loader = DataLoader(gene_dataset,
batch_size=128,
pin_memory=use_cuda,
shuffle=False,
collate_fn=gene_dataset.collate_fn)
latent, batch_indices, labels = get_latent(infer_vae.model, data_loader)
keys = gene_dataset.cell_types
batch_indices = np.concatenate(batch_indices)