def cortex_benchmark(n_epochs=250,
use_cuda=True,
save_path="data/",
show_plot=True):
cortex_dataset = CortexDataset(save_path=save_path)
vae = VAE(cortex_dataset.nb_genes)
trainer_cortex_vae = UnsupervisedTrainer(vae,
cortex_dataset,
use_cuda=use_cuda)
trainer_cortex_vae.train(n_epochs=n_epochs)
couple_celltypes = (4, 5) # the couple types on which to study DE
cell_idx1 = cortex_dataset.labels.ravel() == couple_celltypes[0]
cell_idx2 = cortex_dataset.labels.ravel() == couple_celltypes[1]
trainer_cortex_vae.train_set.differential_expression_score(
cell_idx1, cell_idx2, genes=["THY1", "MBP"])
trainer_cortex_vae.test_set.reconstruction_error() # assert ~ 1200
vae = VAE(cortex_dataset.nb_genes)
trainer_cortex_vae = UnsupervisedTrainer(vae,
cortex_dataset,
use_cuda=use_cuda)
trainer_cortex_vae.corrupt_posteriors()
trainer_cortex_vae.train(n_epochs=n_epochs)
trainer_cortex_vae.uncorrupt_posteriors()
trainer_cortex_vae.train_set.imputation_benchmark(save_path=save_path,
show_plot=show_plot)
n_samples = 10 if n_epochs == 1 else None # n_epochs == 1 is unit tests
trainer_cortex_vae.train_set.show_t_sne(n_samples=n_samples)
return trainer_cortex_vae
def cortex_benchmark(n_epochs=250,
use_cuda=True,
save_path='data/',
show_plot=True):
cortex_dataset = CortexDataset(save_path=save_path)
vae = VAE(cortex_dataset.nb_genes)
trainer_cortex_vae = UnsupervisedTrainer(vae,
cortex_dataset,
use_cuda=use_cuda)
trainer_cortex_vae.train(n_epochs=n_epochs)
trainer_cortex_vae.train_set.differential_expression_score(
'oligodendrocytes', 'pyramidal CA1', genes=["THY1", "MBP"])
trainer_cortex_vae.test_set.ll() # assert ~ 1200
vae = VAE(cortex_dataset.nb_genes)
trainer_cortex_vae = UnsupervisedTrainer(vae,
cortex_dataset,
use_cuda=use_cuda)
trainer_cortex_vae.corrupt_posteriors()
trainer_cortex_vae.train(n_epochs=n_epochs)
trainer_cortex_vae.uncorrupt_posteriors()
trainer_cortex_vae.train_set.imputation_benchmark(verbose=(n_epochs > 1),
save_path=save_path,
show_plot=show_plot)
n_samples = 10 if n_epochs == 1 else None # n_epochs == 1 is unit tests
trainer_cortex_vae.train_set.show_t_sne(n_samples=n_samples)
return trainer_cortex_vae
def test_cortex(save_path):
cortex_dataset = CortexDataset(save_path=save_path)
vae = VAE(cortex_dataset.nb_genes, cortex_dataset.n_batches)
trainer_cortex_vae = UnsupervisedTrainer(vae, cortex_dataset, train_size=0.5, use_cuda=use_cuda)
trainer_cortex_vae.train(n_epochs=1)
trainer_cortex_vae.train_set.ll()
trainer_cortex_vae.train_set.differential_expression_stats()
trainer_cortex_vae.corrupt_posteriors(corruption='binomial')
trainer_cortex_vae.corrupt_posteriors()
trainer_cortex_vae.train(n_epochs=1)
trainer_cortex_vae.uncorrupt_posteriors()
trainer_cortex_vae.train_set.imputation_benchmark(n_samples=1, show_plot=False,
title_plot='imputation', save_path=save_path)
svaec = SCANVI(cortex_dataset.nb_genes, cortex_dataset.n_batches, cortex_dataset.n_labels)
trainer_cortex_svaec = JointSemiSupervisedTrainer(svaec, cortex_dataset,
n_labelled_samples_per_class=3,
use_cuda=use_cuda)
trainer_cortex_svaec.train(n_epochs=1)
trainer_cortex_svaec.labelled_set.accuracy()
trainer_cortex_svaec.full_dataset.ll()
svaec = SCANVI(cortex_dataset.nb_genes, cortex_dataset.n_batches, cortex_dataset.n_labels)
trainer_cortex_svaec = AlternateSemiSupervisedTrainer(svaec, cortex_dataset,
n_labelled_samples_per_class=3,
use_cuda=use_cuda)
trainer_cortex_svaec.train(n_epochs=1, lr=1e-2)
trainer_cortex_svaec.unlabelled_set.accuracy()
data_train, labels_train = trainer_cortex_svaec.labelled_set.raw_data()
data_test, labels_test = trainer_cortex_svaec.unlabelled_set.raw_data()
compute_accuracy_svc(data_train, labels_train, data_test, labels_test,
param_grid=[{'C': [1], 'kernel': ['linear']}])
compute_accuracy_rf(data_train, labels_train, data_test, labels_test,
param_grid=[{'max_depth': [3], 'n_estimators': [10]}])
cls = Classifier(cortex_dataset.nb_genes, n_labels=cortex_dataset.n_labels)
cls_trainer = ClassifierTrainer(cls, cortex_dataset)
cls_trainer.train(n_epochs=1)
cls_trainer.train_set.accuracy()
def test_cortex(save_path):
cortex_dataset = CortexDataset(save_path=save_path)
vae = VAE(cortex_dataset.nb_genes, cortex_dataset.n_batches)
trainer_cortex_vae = UnsupervisedTrainer(
vae, cortex_dataset, train_size=0.5, use_cuda=use_cuda
)
trainer_cortex_vae.train(n_epochs=1)
trainer_cortex_vae.train_set.reconstruction_error()
trainer_cortex_vae.train_set.differential_expression_stats()
trainer_cortex_vae.train_set.generate_feature_correlation_matrix(
n_samples=2, correlation_type="pearson"
)
trainer_cortex_vae.train_set.generate_feature_correlation_matrix(
n_samples=2, correlation_type="spearman"
)
trainer_cortex_vae.train_set.imputation(n_samples=1)
trainer_cortex_vae.test_set.imputation(n_samples=5)
trainer_cortex_vae.corrupt_posteriors(corruption="binomial")
trainer_cortex_vae.corrupt_posteriors()
trainer_cortex_vae.train(n_epochs=1)
trainer_cortex_vae.uncorrupt_posteriors()
trainer_cortex_vae.train_set.imputation_benchmark(
n_samples=1, show_plot=False, title_plot="imputation", save_path=save_path
)
trainer_cortex_vae.train_set.generate_parameters()
n_cells, n_genes = (
len(trainer_cortex_vae.train_set.indices),
cortex_dataset.nb_genes,
)
n_samples = 3
(dropout, means, dispersions,) = trainer_cortex_vae.train_set.generate_parameters()
assert dropout.shape == (n_cells, n_genes) and means.shape == (n_cells, n_genes)
assert dispersions.shape == (n_cells, n_genes)
(dropout, means, dispersions,) = trainer_cortex_vae.train_set.generate_parameters(
n_samples=n_samples
)
assert dropout.shape == (n_samples, n_cells, n_genes)
assert means.shape == (n_samples, n_cells, n_genes,)
(dropout, means, dispersions,) = trainer_cortex_vae.train_set.generate_parameters(
n_samples=n_samples, give_mean=True
)
assert dropout.shape == (n_cells, n_genes) and means.shape == (n_cells, n_genes)
full = trainer_cortex_vae.create_posterior(
vae, cortex_dataset, indices=np.arange(len(cortex_dataset))
)
x_new, x_old = full.generate(n_samples=10)
assert x_new.shape == (cortex_dataset.nb_cells, cortex_dataset.nb_genes, 10)
assert x_old.shape == (cortex_dataset.nb_cells, cortex_dataset.nb_genes)
trainer_cortex_vae.train_set.imputation_benchmark(
n_samples=1, show_plot=False, title_plot="imputation", save_path=save_path
)
svaec = SCANVI(
cortex_dataset.nb_genes, cortex_dataset.n_batches, cortex_dataset.n_labels
)
trainer_cortex_svaec = JointSemiSupervisedTrainer(
svaec, cortex_dataset, n_labelled_samples_per_class=3, use_cuda=use_cuda
)
trainer_cortex_svaec.train(n_epochs=1)
trainer_cortex_svaec.labelled_set.accuracy()
trainer_cortex_svaec.full_dataset.reconstruction_error()
svaec = SCANVI(
cortex_dataset.nb_genes, cortex_dataset.n_batches, cortex_dataset.n_labels
)
trainer_cortex_svaec = AlternateSemiSupervisedTrainer(
svaec, cortex_dataset, n_labelled_samples_per_class=3, use_cuda=use_cuda
)
trainer_cortex_svaec.train(n_epochs=1, lr=1e-2)
trainer_cortex_svaec.unlabelled_set.accuracy()
data_train, labels_train = trainer_cortex_svaec.labelled_set.raw_data()
data_test, labels_test = trainer_cortex_svaec.unlabelled_set.raw_data()
compute_accuracy_svc(
data_train,
labels_train,
data_test,
labels_test,
param_grid=[{"C": [1], "kernel": ["linear"]}],
)
compute_accuracy_rf(
data_train,
labels_train,
data_test,
labels_test,
param_grid=[{"max_depth": [3], "n_estimators": [10]}],
)
cls = Classifier(cortex_dataset.nb_genes, n_labels=cortex_dataset.n_labels)
cls_trainer = ClassifierTrainer(cls, cortex_dataset)
cls_trainer.train(n_epochs=1)
cls_trainer.train_set.accuracy()
print(input_gene_bc_mat.shape)
row_attrs = {"Gene": gene_name[gene_filter]}
col_attrs = {"CellID": cell_id}
input_loom_name = FLAGS["loom"].rsplit("/", 1)[1]
output_loom_name = input_loom_name.replace(
".loom",
"_mc_{}_mce_{}.loom".format(min_expressed_cell,
min_expressed_cell_average_expression))
filt_gene_loom_path = "{}/{}".format(output_dir, output_loom_name)
loompy.create(filt_gene_loom_path, input_gene_bc_mat, row_attrs, col_attrs)
loom_dataset = LoomDataset(filt_gene_loom_path, save_path="")
vae = VAE(loom_dataset.nb_genes, n_batch=loom_dataset.n_batches)
trainer = UnsupervisedTrainer(vae, loom_dataset)
trainer.corrupt_posteriors()
trainer.train(n_epochs=250, lr=0.001)
trainer.uncorrupt_posteriors()
full = trainer.create_posterior(trainer.model,
loom_dataset,
indices=np.arange(len(loom_dataset)))
imputed_values = full.sequential().imputation()
output_h5 = input_loom_name.replace(
".loom",
"_scVI_mc_{}_mce_{}.hdf5".format(min_expressed_cell,
min_expressed_cell_average_expression))
with h5py.File("{}/{}".format(output_dir, output_h5), "w") as f:
f["cell_id"] = cell_id.astype(h5py.special_dtype(vlen=str))
f["gene_name"] = gene_name[gene_filter].astype(
h5py.special_dtype(vlen=str))
if_dset_imputation = f.create_dataset("imputation",
shape=(cell_id.size,
gene_filter.sum()),
