def test_scvi_library_size_update(save_path):
n_latent = 5
adata1 = synthetic_iid()
model = SCVI(adata1, n_latent=n_latent, use_observed_lib_size=False)
assert (getattr(model.module, "library_log_means", None) is not None
and model.module.library_log_means.shape == (1, 2)
and model.module.library_log_means.count_nonzero().item() == 2)
assert getattr(
model.module, "library_log_vars",
None) is not None and model.module.library_log_vars.shape == (1, 2)
model.train(1, check_val_every_n_epoch=1)
dir_path = os.path.join(save_path, "saved_model/")
model.save(dir_path, overwrite=True)
# also test subset var option
adata2 = synthetic_iid(run_setup_anndata=False, n_genes=110)
adata2.obs["batch"] = adata2.obs.batch.cat.rename_categories(
["batch_2", "batch_3"])
model2 = SCVI.load_query_data(adata2,
dir_path,
inplace_subset_query_vars=True)
assert (getattr(model2.module, "library_log_means", None) is not None
and model2.module.library_log_means.shape == (1, 4)
and model2.module.library_log_means[:, :2].equal(
model.module.library_log_means)
and model2.module.library_log_means.count_nonzero().item() == 4)
assert (getattr(model2.module, "library_log_vars", None) is not None
and model2.module.library_log_vars.shape == (1, 4)
and model2.module.library_log_vars[:, :2].equal(
model.module.library_log_vars))
def test_save_best_state_callback(save_path):
n_latent = 5
adata = synthetic_iid()
SCVI.setup_anndata(adata, batch_key="batch", labels_key="labels")
model = SCVI(adata, n_latent=n_latent)
callbacks = [SaveBestState(verbose=True)]
model.train(3, check_val_every_n_epoch=1, train_size=0.5, callbacks=callbacks)
def test_save_best_state_callback(save_path):
n_latent = 5
adata = synthetic_iid()
model = SCVI(adata, n_latent=n_latent)
callbacks = [SaveBestState(verbose=True)]
model.train(3,
check_val_every_n_epoch=1,
train_size=0.5,
callbacks=callbacks)
def unsupervised_training_one_epoch(
adata: AnnData,
run_setup_anndata: bool = True,
batch_key: Optional[str] = None,
labels_key: Optional[str] = None,
):
if run_setup_anndata:
SCVI.setup_anndata(adata, batch_key=batch_key, labels_key=labels_key)
m = SCVI(adata)
m.train(1, train_size=0.4, use_gpu=use_gpu)
def test_solo(save_path):
n_latent = 5
adata = synthetic_iid(run_setup_anndata=False)
setup_anndata(adata)
model = SCVI(adata, n_latent=n_latent)
model.train(1, check_val_every_n_epoch=1, train_size=0.5)
solo = SOLO.from_scvi_model(model)
solo.train(1, check_val_every_n_epoch=1, train_size=0.9)
assert "validation_loss" in solo.history.keys()
solo.predict()
def test_solo_multiple_batch(save_path):
n_latent = 5
adata = synthetic_iid()
setup_anndata(adata, batch_key="batch")
model = SCVI(adata, n_latent=n_latent)
model.train(1, check_val_every_n_epoch=1, train_size=0.5)
solo = SOLO.from_scvi_model(model, restrict_to_batch="batch_0")
solo.train(1, check_val_every_n_epoch=1, train_size=0.9)
assert "validation_loss" in solo.history.keys()
solo.predict()
def test_early_stopping():
n_epochs = 100
adata = synthetic_iid(run_setup_anndata=False, )
SCVI.setup_anndata(
adata,
batch_key="batch",
labels_key="labels",
)
model = SCVI(adata)
model.train(n_epochs, early_stopping=True, plan_kwargs=dict(lr=0))
assert len(model.history["elbo_train"]) < n_epochs
def test_backed_anndata_scvi(save_path):
adata = scvi.data.synthetic_iid()
path = os.path.join(save_path, "test_data.h5ad")
adata.write_h5ad(path)
adata = anndata.read_h5ad(path, backed="r+")
setup_anndata(adata, batch_key="batch")
model = SCVI(adata, n_latent=5)
model.train(1, train_size=0.5)
assert model.is_trained is True
z = model.get_latent_representation()
assert z.shape == (adata.shape[0], 5)
model.get_elbo()
def test_set_seed(save_path):
scvi.settings.seed = 1
n_latent = 5
adata = synthetic_iid()
model1 = SCVI(adata, n_latent=n_latent)
model1.train(1)
scvi.settings.seed = 1
model2 = SCVI(adata, n_latent=n_latent)
model2.train(1)
assert torch.equal(
model1.module.z_encoder.encoder.fc_layers[0][0].weight,
model2.module.z_encoder.encoder.fc_layers[0][0].weight,
)
def test_set_seed(save_path):
scvi.settings.seed = 1
n_latent = 5
adata = synthetic_iid()
SCVI.setup_anndata(adata, batch_key="batch", labels_key="labels")
model1 = SCVI(adata, n_latent=n_latent)
model1.train(1)
scvi.settings.seed = 1
model2 = SCVI(adata, n_latent=n_latent)
model2.train(1)
assert torch.equal(
model1.module.z_encoder.encoder.fc_layers[0][0].weight,
model2.module.z_encoder.encoder.fc_layers[0][0].weight,
)
def test_scvi_sparse(save_path):
n_latent = 5
adata = synthetic_iid(run_setup_anndata=False)
adata.X = csr_matrix(adata.X)
setup_anndata(adata)
model = SCVI(adata, n_latent=n_latent)
model.train(1, train_size=0.5)
assert model.is_trained is True
z = model.get_latent_representation()
assert z.shape == (adata.shape[0], n_latent)
model.get_elbo()
model.get_marginal_ll(n_mc_samples=3)
model.get_reconstruction_error()
model.get_normalized_expression()
model.differential_expression(groupby="labels", group1="label_1")
def test_differential_computation(save_path):
n_latent = 5
adata = synthetic_iid()
model = SCVI(adata, n_latent=n_latent)
model.train(1)
model_fn = partial(model.get_normalized_expression, return_numpy=True)
dc = DifferentialComputation(model_fn, adata)
cell_idx1 = np.asarray(adata.obs.labels == "undefined_1")
cell_idx2 = ~cell_idx1
dc.get_bayes_factors(cell_idx1,
cell_idx2,
mode="vanilla",
use_permutation=True)
dc.get_bayes_factors(cell_idx1,
cell_idx2,
mode="change",
use_permutation=False)
dc.get_bayes_factors(cell_idx1,
cell_idx2,
mode="change",
cred_interval_lvls=[0.75])
delta = 0.5
def change_fn_test(x, y):
return x - y
def m1_domain_fn_test(samples):
return np.abs(samples) >= delta
dc.get_bayes_factors(
cell_idx1,
cell_idx2,
mode="change",
m1_domain_fn=m1_domain_fn_test,
change_fn=change_fn_test,
)
def test_differential_computation(save_path):
n_latent = 5
adata = synthetic_iid()
model = SCVI(adata, n_latent=n_latent)
model.train(1)
model_fn = partial(model.get_normalized_expression, return_numpy=True)
dc = DifferentialComputation(model_fn, adata)
cell_idx1 = np.asarray(adata.obs.labels == "label_1")
cell_idx2 = ~cell_idx1
dc.get_bayes_factors(cell_idx1, cell_idx2, mode="vanilla", use_permutation=True)
dc.get_bayes_factors(cell_idx1, cell_idx2, mode="change", use_permutation=False)
dc.get_bayes_factors(cell_idx1, cell_idx2, mode="change", cred_interval_lvls=[0.75])
delta = 0.5
def change_fn_test(x, y):
return x - y
def m1_domain_fn_test(samples):
return np.abs(samples) >= delta
dc.get_bayes_factors(
cell_idx1,
cell_idx2,
mode="change",
m1_domain_fn=m1_domain_fn_test,
change_fn=change_fn_test,
)
# should fail if just one batch
with pytest.raises(ValueError):
model.differential_expression(adata[:20], groupby="batch")
# test view
model.differential_expression(
adata[adata.obs["labels"] == "label_1"], groupby="batch"
)
def test_multiple_covariates_scvi(save_path):
adata = synthetic_iid()
adata.obs["cont1"] = np.random.normal(size=(adata.shape[0], ))
adata.obs["cont2"] = np.random.normal(size=(adata.shape[0], ))
adata.obs["cat1"] = np.random.randint(0, 5, size=(adata.shape[0], ))
adata.obs["cat2"] = np.random.randint(0, 5, size=(adata.shape[0], ))
SCVI.setup_anndata(
adata,
batch_key="batch",
labels_key="labels",
continuous_covariate_keys=["cont1", "cont2"],
categorical_covariate_keys=["cat1", "cat2"],
)
m = SCVI(adata)
m.train(1)
m = SCANVI(adata, unlabeled_category="Unknown")
m.train(1)
TOTALVI.setup_anndata(
adata,
batch_key="batch",
protein_expression_obsm_key="protein_expression",
protein_names_uns_key="protein_names",
continuous_covariate_keys=["cont1", "cont2"],
categorical_covariate_keys=["cat1", "cat2"],
)
m = TOTALVI(adata)
m.train(1)
def test_scvi(save_path):
n_latent = 5
adata = synthetic_iid()
model = SCVI(adata, n_latent=n_latent)
model.train(1, check_val_every_n_epoch=1, train_size=0.5)
model = SCVI(adata, n_latent=n_latent, var_activation=Softplus())
model.train(1, check_val_every_n_epoch=1, train_size=0.5)
# tests __repr__
print(model)
assert model.is_trained is True
z = model.get_latent_representation()
assert z.shape == (adata.shape[0], n_latent)
assert len(model.history["elbo_train"]) == 1
model.get_elbo()
model.get_marginal_ll(n_mc_samples=3)
model.get_reconstruction_error()
model.get_normalized_expression(transform_batch="batch_1")
adata2 = synthetic_iid()
model.get_elbo(adata2)
model.get_marginal_ll(adata2, n_mc_samples=3)
model.get_reconstruction_error(adata2)
latent = model.get_latent_representation(adata2, indices=[1, 2, 3])
assert latent.shape == (3, n_latent)
denoised = model.get_normalized_expression(adata2)
assert denoised.shape == adata.shape
denoised = model.get_normalized_expression(
adata2, indices=[1, 2, 3], transform_batch="batch_1"
)
denoised = model.get_normalized_expression(
adata2, indices=[1, 2, 3], transform_batch=["batch_0", "batch_1"]
)
assert denoised.shape == (3, adata2.n_vars)
sample = model.posterior_predictive_sample(adata2)
assert sample.shape == adata2.shape
sample = model.posterior_predictive_sample(
adata2, indices=[1, 2, 3], gene_list=["1", "2"]
)
assert sample.shape == (3, 2)
sample = model.posterior_predictive_sample(
adata2, indices=[1, 2, 3], gene_list=["1", "2"], n_samples=3
)
assert sample.shape == (3, 2, 3)
model.get_feature_correlation_matrix(correlation_type="pearson")
model.get_feature_correlation_matrix(
adata2,
indices=[1, 2, 3],
correlation_type="spearman",
rna_size_factor=500,
n_samples=5,
)
model.get_feature_correlation_matrix(
adata2,
indices=[1, 2, 3],
correlation_type="spearman",
rna_size_factor=500,
n_samples=5,
transform_batch=["batch_0", "batch_1"],
)
params = model.get_likelihood_parameters()
assert params["mean"].shape == adata.shape
assert (
params["mean"].shape == params["dispersions"].shape == params["dropout"].shape
)
params = model.get_likelihood_parameters(adata2, indices=[1, 2, 3])
assert params["mean"].shape == (3, adata.n_vars)
params = model.get_likelihood_parameters(
adata2, indices=[1, 2, 3], n_samples=3, give_mean=True
)
assert params["mean"].shape == (3, adata.n_vars)
model.get_latent_library_size()
model.get_latent_library_size(adata2, indices=[1, 2, 3])
# test transfer_anndata_setup
adata2 = synthetic_iid(run_setup_anndata=False)
transfer_anndata_setup(adata, adata2)
model.get_elbo(adata2)
# test automatic transfer_anndata_setup + on a view
adata = synthetic_iid()
model = SCVI(adata)
adata2 = synthetic_iid(run_setup_anndata=False)
model.get_elbo(adata2[:10])
# test that we catch incorrect mappings
adata = synthetic_iid()
adata2 = synthetic_iid(run_setup_anndata=False)
transfer_anndata_setup(adata, adata2)
adata2.uns["_scvi"]["categorical_mappings"]["_scvi_labels"]["mapping"] = np.array(
["label_4", "label_0", "label_2"]
)
with pytest.raises(ValueError):
model.get_elbo(adata2)
# test that same mapping different order doesn't raise error
adata = synthetic_iid()
adata2 = synthetic_iid(run_setup_anndata=False)
transfer_anndata_setup(adata, adata2)
adata2.uns["_scvi"]["categorical_mappings"]["_scvi_labels"]["mapping"] = np.array(
["label_1", "label_0", "label_2"]
)
model.get_elbo(adata2) # should automatically transfer setup
# test mismatched categories raises ValueError
adata2 = synthetic_iid(run_setup_anndata=False)
adata2.obs.labels.cat.rename_categories(["a", "b", "c"], inplace=True)
with pytest.raises(ValueError):
model.get_elbo(adata2)
# test differential expression
model.differential_expression(groupby="labels", group1="label_1")
model.differential_expression(
groupby="labels", group1="label_1", group2="label_2", mode="change"
)
model.differential_expression(groupby="labels")
model.differential_expression(idx1=[0, 1, 2], idx2=[3, 4, 5])
model.differential_expression(idx1=[0, 1, 2])
# transform batch works with all different types
a = synthetic_iid(run_setup_anndata=False)
batch = np.zeros(a.n_obs)
batch[:64] += 1
a.obs["batch"] = batch
setup_anndata(a, batch_key="batch")
m = SCVI(a)
m.train(1, train_size=0.5)
m.get_normalized_expression(transform_batch=1)
m.get_normalized_expression(transform_batch=[0, 1])
# test get_likelihood_parameters() when dispersion=='gene-cell'
model = SCVI(adata, dispersion="gene-cell")
model.get_likelihood_parameters()
# test train callbacks work
a = synthetic_iid()
m = scvi.model.SCVI(a)
lr_monitor = LearningRateMonitor()
m.train(
callbacks=[lr_monitor],
max_epochs=10,
log_every_n_steps=1,
plan_kwargs={"reduce_lr_on_plateau": True},
)
assert "lr-Adam" in m.history.keys()
def test_scvi():
n_latent = 5
adata = synthetic_iid()
model = SCVI(adata, n_latent=n_latent)
model.train(1, frequency=1, train_size=0.5)
assert model.is_trained is True
z = model.get_latent_representation()
assert z.shape == (adata.shape[0], n_latent)
# len of history should be 2 since metrics is also run once at the very end after training
assert len(model.history["elbo_train_set"]) == 2
model.get_elbo()
model.get_marginal_ll()
model.get_reconstruction_error()
model.get_normalized_expression(transform_batch="batch_1")
adata2 = synthetic_iid()
model.get_elbo(adata2)
model.get_marginal_ll(adata2)
model.get_reconstruction_error(adata2)
latent = model.get_latent_representation(adata2, indices=[1, 2, 3])
assert latent.shape == (3, n_latent)
denoised = model.get_normalized_expression(adata2)
assert denoised.shape == adata.shape
denoised = model.get_normalized_expression(adata2,
indices=[1, 2, 3],
transform_batch="batch_1")
denoised = model.get_normalized_expression(
adata2, indices=[1, 2, 3], transform_batch=["batch_0", "batch_1"])
assert denoised.shape == (3, adata2.n_vars)
sample = model.posterior_predictive_sample(adata2)
assert sample.shape == adata2.shape
sample = model.posterior_predictive_sample(adata2,
indices=[1, 2, 3],
gene_list=["1", "2"])
assert sample.shape == (3, 2)
sample = model.posterior_predictive_sample(adata2,
indices=[1, 2, 3],
gene_list=["1", "2"],
n_samples=3)
assert sample.shape == (3, 2, 3)
model.get_feature_correlation_matrix(correlation_type="pearson")
model.get_feature_correlation_matrix(
adata2,
indices=[1, 2, 3],
correlation_type="spearman",
rna_size_factor=500,
n_samples=5,
)
model.get_feature_correlation_matrix(
adata2,
indices=[1, 2, 3],
correlation_type="spearman",
rna_size_factor=500,
n_samples=5,
transform_batch=["batch_0", "batch_1"],
)
params = model.get_likelihood_parameters()
assert params["mean"].shape == adata.shape
assert (params["mean"].shape == params["dispersions"].shape ==
params["dropout"].shape)
params = model.get_likelihood_parameters(adata2, indices=[1, 2, 3])
assert params["mean"].shape == (3, adata.n_vars)
params = model.get_likelihood_parameters(adata2,
indices=[1, 2, 3],
n_samples=3,
give_mean=True)
assert params["mean"].shape == (3, adata.n_vars)
model.get_latent_library_size()
model.get_latent_library_size(adata2, indices=[1, 2, 3])
# test transfer_anndata_setup
adata2 = synthetic_iid(run_setup_anndata=False)
transfer_anndata_setup(adata, adata2)
model.get_elbo(adata2)
# test automatic transfer_anndata_setup + on a view
adata = synthetic_iid()
model = SCVI(adata)
adata2 = synthetic_iid(run_setup_anndata=False)
model.get_elbo(adata2[:10])
# test that we catch incorrect mappings
adata = synthetic_iid()
adata2 = synthetic_iid(run_setup_anndata=False)
transfer_anndata_setup(adata, adata2)
adata2.uns["_scvi"]["categorical_mappings"]["_scvi_labels"][
"mapping"] = np.array(["label_1", "label_0", "label_2"])
with pytest.raises(ValueError):
model.get_elbo(adata2)
# test mismatched categories raises ValueError
adata2 = synthetic_iid(run_setup_anndata=False)
adata2.obs.labels.cat.rename_categories(["a", "b", "c"], inplace=True)
with pytest.raises(ValueError):
model.get_elbo(adata2)
# test differential expression
model.differential_expression(groupby="labels", group1="label_1")
model.differential_expression(groupby="labels",
group1="label_1",
group2="label_2",
mode="change")
model.differential_expression(groupby="labels")
model.differential_expression(idx1=[0, 1, 2], idx2=[3, 4, 5])
model.differential_expression(idx1=[0, 1, 2])
# transform batch works with all different types
a = synthetic_iid(run_setup_anndata=False)
batch = np.zeros(a.n_obs)
batch[:64] += 1
a.obs["batch"] = batch
setup_anndata(a, batch_key="batch")
m = SCVI(a)
m.train(1, train_size=0.5)
m.get_normalized_expression(transform_batch=1)
m.get_normalized_expression(transform_batch=[0, 1])
def test_scvi_online_update(save_path):
n_latent = 5
adata1 = synthetic_iid()
model = SCVI(adata1, n_latent=n_latent)
model.train(1, check_val_every_n_epoch=1)
dir_path = os.path.join(save_path, "saved_model/")
model.save(dir_path, overwrite=True)
# also test subset var option
adata2 = synthetic_iid(run_setup_anndata=False, n_genes=110)
adata2.obs["batch"] = adata2.obs.batch.cat.rename_categories(["batch_2", "batch_3"])
model2 = SCVI.load_query_data(adata2, dir_path, inplace_subset_query_vars=True)
model2.train(max_epochs=1, plan_kwargs=dict(weight_decay=0.0))
model2.get_latent_representation()
# encoder linear layer equal
one = (
model.module.z_encoder.encoder.fc_layers[0][0]
.weight.detach()
.cpu()
.numpy()[:, : adata1.shape[1]]
)
two = (
model2.module.z_encoder.encoder.fc_layers[0][0]
.weight.detach()
.cpu()
.numpy()[:, : adata1.shape[1]]
)
np.testing.assert_equal(one, two)
assert (
np.sum(
model2.module.z_encoder.encoder.fc_layers[0][0]
.weight.grad.cpu()
.numpy()[:, : adata1.shape[1]]
)
== 0
)
# dispersion
assert model2.module.px_r.requires_grad is False
# library encoder linear layer
assert model2.module.l_encoder.encoder.fc_layers[0][0].weight.requires_grad is True
# 5 for n_latent, 4 for batches
assert model2.module.decoder.px_decoder.fc_layers[0][0].weight.shape[1] == 9
# test options
adata1 = synthetic_iid()
model = SCVI(
adata1,
n_latent=n_latent,
n_layers=2,
encode_covariates=True,
use_batch_norm="encoder",
use_layer_norm="none",
)
model.train(1, check_val_every_n_epoch=1)
dir_path = os.path.join(save_path, "saved_model/")
model.save(dir_path, overwrite=True)
adata2 = synthetic_iid(run_setup_anndata=False)
adata2.obs["batch"] = adata2.obs.batch.cat.rename_categories(["batch_2", "batch_3"])
model2 = SCVI.load_query_data(adata2, dir_path, freeze_expression=True)
model2.train(max_epochs=1, plan_kwargs=dict(weight_decay=0.0))
# deactivate no grad decorator
model2.get_latent_representation()
# pytorch lightning zeros the grad, so this will get a grad to inspect
single_pass_for_online_update(model2)
grad = model2.module.z_encoder.encoder.fc_layers[0][0].weight.grad.cpu().numpy()
# expression part has zero grad
assert np.sum(grad[:, :-4]) == 0
# categorical part has non-zero grad
assert np.sum(grad[:, -4:]) != 0
grad = model2.module.decoder.px_decoder.fc_layers[0][0].weight.grad.cpu().numpy()
# linear layer weight in decoder layer has non-zero grad
assert np.sum(grad[:, :-4]) == 0
# do not freeze expression
model3 = SCVI.load_query_data(
adata2,
dir_path,
freeze_expression=False,
freeze_batchnorm_encoder=True,
freeze_decoder_first_layer=False,
)
model3.train(max_epochs=1)
model3.get_latent_representation()
assert model3.module.z_encoder.encoder.fc_layers[0][1].momentum == 0
# batch norm weight in encoder layer
assert model3.module.z_encoder.encoder.fc_layers[0][1].weight.requires_grad is False
single_pass_for_online_update(model3)
grad = model3.module.z_encoder.encoder.fc_layers[0][0].weight.grad.cpu().numpy()
# linear layer weight in encoder layer has non-zero grad
assert np.sum(grad[:, :-4]) != 0
grad = model3.module.decoder.px_decoder.fc_layers[0][0].weight.grad.cpu().numpy()
# linear layer weight in decoder layer has non-zero grad
assert np.sum(grad[:, :-4]) != 0
# do not freeze batchnorm
model3 = SCVI.load_query_data(adata2, dir_path, freeze_batchnorm_encoder=False)
model3.train(max_epochs=1)
model3.get_latent_representation()
def test_differential_computation(save_path):
n_latent = 5
adata = synthetic_iid()
model = SCVI(adata, n_latent=n_latent)
model.train(1)
model_fn = partial(model.get_normalized_expression, return_numpy=True)
dc = DifferentialComputation(model_fn, adata)
cell_idx1 = np.asarray(adata.obs.labels == "label_1")
cell_idx2 = ~cell_idx1
dc.get_bayes_factors(cell_idx1, cell_idx2, mode="vanilla", use_permutation=True)
res = dc.get_bayes_factors(
cell_idx1, cell_idx2, mode="change", use_permutation=False
)
assert (res["delta"] == 0.5) and (res["pseudocounts"] == 0.0)
res = dc.get_bayes_factors(
cell_idx1, cell_idx2, mode="change", use_permutation=False, delta=None
)
dc.get_bayes_factors(
cell_idx1,
cell_idx2,
mode="change",
use_permutation=False,
delta=None,
pseudocounts=None,
)
dc.get_bayes_factors(cell_idx1, cell_idx2, mode="change", cred_interval_lvls=[0.75])
delta = 0.5
def change_fn_test(x, y):
return x - y
def m1_domain_fn_test(samples):
return np.abs(samples) >= delta
dc.get_bayes_factors(
cell_idx1,
cell_idx2,
mode="change",
m1_domain_fn=m1_domain_fn_test,
change_fn=change_fn_test,
)
# should fail if just one batch
with pytest.raises(ValueError):
model.differential_expression(adata[:20], groupby="batch")
# test view
model.differential_expression(
adata[adata.obs["labels"] == "label_1"], groupby="batch"
)
# Test query features
obs_col, group1, _, = _prepare_obs(
idx1="(labels == 'label_1') & (batch == 'batch_1')", idx2=None, adata=adata
)
assert (obs_col == group1).sum() == adata.obs.loc[
lambda x: (x.labels == "label_1") & (x.batch == "batch_1")
].shape[0]
model.differential_expression(
idx1="labels == 'label_1'",
)
model.differential_expression(
idx1="labels == 'label_1'", idx2="(labels == 'label_2') & (batch == 'batch_1')"
)
# test that ints as group work
a = synthetic_iid()
a.obs["test"] = [0] * 200 + [1] * 200
model = SCVI(a)
model.differential_expression(groupby="test", group1=0)
# test that string but not as categorical work
a = synthetic_iid()
a.obs["test"] = ["0"] * 200 + ["1"] * 200
model = SCVI(a)
model.differential_expression(groupby="test", group1="0")
def test_scvi():
n_latent = 5
adata = synthetic_iid()
model = SCVI(adata, n_latent=n_latent)
model.train(1)
assert model.is_trained is True
z = model.get_latent_representation()
assert z.shape == (adata.shape[0], n_latent)
model.get_elbo()
model.get_marginal_ll()
model.get_reconstruction_error()
model.get_normalized_expression()
adata2 = synthetic_iid()
model.get_elbo(adata2)
model.get_marginal_ll(adata2)
model.get_reconstruction_error(adata2)
latent = model.get_latent_representation(adata2, indices=[1, 2, 3])
assert latent.shape == (3, n_latent)
denoised = model.get_normalized_expression(adata2)
assert denoised.shape == adata.shape
denoised = model.get_normalized_expression(adata2,
indices=[1, 2, 3],
transform_batch=1)
assert denoised.shape == (3, adata2.n_vars)
sample = model.posterior_predictive_sample(adata2)
assert sample.shape == adata2.shape
sample = model.posterior_predictive_sample(adata2,
indices=[1, 2, 3],
gene_list=["1", "2"])
assert sample.shape == (3, 2)
sample = model.posterior_predictive_sample(adata2,
indices=[1, 2, 3],
gene_list=["1", "2"],
n_samples=3)
assert sample.shape == (3, 2, 3)
model.get_feature_correlation_matrix(correlation_type="pearson")
model.get_feature_correlation_matrix(
adata2,
indices=[1, 2, 3],
correlation_type="spearman",
rna_size_factor=500,
n_samples=5,
)
params = model.get_likelihood_parameters()
assert params["mean"].shape == adata.shape
assert (params["mean"].shape == params["dispersions"].shape ==
params["dropout"].shape)
params = model.get_likelihood_parameters(adata2, indices=[1, 2, 3])
assert params["mean"].shape == (3, adata.n_vars)
params = model.get_likelihood_parameters(adata2,
indices=[1, 2, 3],
n_samples=3,
give_mean=True)
assert params["mean"].shape == (3, adata.n_vars)
model.get_latent_library_size()
model.get_latent_library_size(adata2, indices=[1, 2, 3])
# test transfer_anndata_setup
adata2 = synthetic_iid(run_setup_anndata=False)
transfer_anndata_setup(adata, adata2)
model.get_elbo(adata2)
# test automatic transfer_anndata_setup + on a view
adata = synthetic_iid()
model = SCVI(adata)
adata2 = synthetic_iid(run_setup_anndata=False)
model.get_elbo(adata2[:10])
# test that we catch incorrect mappings
adata = synthetic_iid()
adata2 = synthetic_iid(run_setup_anndata=False)
transfer_anndata_setup(adata, adata2)
adata2.uns["_scvi"]["categorical_mappings"]["_scvi_labels"][
"mapping"] = pd.Index(
data=["undefined_1", "undefined_0", "undefined_2"])
with pytest.raises(ValueError):
model.get_elbo(adata2)
# test mismatched categories raises ValueError
adata2 = synthetic_iid(run_setup_anndata=False)
adata2.obs.labels.cat.rename_categories(["a", "b", "c"], inplace=True)
with pytest.raises(ValueError):
model.get_elbo(adata2)
# test differential expression
model.differential_expression(groupby="labels", group1="undefined_1")
model.differential_expression(groupby="labels",
group1="undefined_1",
group2="undefined_2",
mode="change")
model.differential_expression(groupby="labels")
model.differential_expression(idx1=[0, 1, 2], idx2=[3, 4, 5])
model.differential_expression(idx1=[0, 1, 2])
use_cuda = False
n_hidden = int(args[5])
n_latent = int(args[6])
n_layers = int(args[7])
#vae = VAE(loom_dataset.nb_genes, n_batch=loom_dataset.n_batches, dropout_rate = 0.5, n_hidden = n_hidden, n_latent = n_latent, n_layers = n_layers, dispersion='gene-batch')
#vae = VAE(loom_dataset.nb_genes, n_batch=loom_dataset.n_batches, n_latent = n_latent, dropout_rate = 0.1, dispersion='gene-batch')
vae = SCVI(adata,
n_hidden=n_hidden,
n_latent=n_latent,
n_layers=n_layers,
dispersion='gene-batch',
use_cuda=True)
vae
vae.train(n_epochs=n_epochs, n_epochs_kl_warmup=1)
# extract
latent = vae.get_latent_representation()
normalized_values = vae.get_normalized_expression()
with open(args[1] + ".csv", 'wb') as f:
np.savetxt(f, latent, delimiter=",")
if args[8] == 'IMPUTE':
out = pd.DataFrame(imputed_values)
out.columns = loom_dataset.gene_names
out.index = loom_dataset.CellID
out.to_hdf(args[1] + '.impute.hdf', key='index')
if args[8] == 'NORM':
out = pd.DataFrame(normalized_values)
out.columns = loom_dataset.gene_names