def from_scvi_model(cls,
scvi_model: SCVI,
adata: Optional[AnnData] = None):
"""
Instantiate a SOLO model from an scvi model.
Parameters
----------
scvi_model
Pre-trained model of :class:`~scvi.model.SCVI`. This model
should have been trained on data comprising one lane. The
adata object used to initialize this model should have only
been setup with count data, i.e., no `batch_key`,
`labels_key`, etc.
adata
Optional anndata to use that is compatible with scvi_model.
Returns
-------
SOLO model
"""
_validate_scvi_model(scvi_model)
doublet_adata = cls.create_doublets(scvi_model.adata)
# if model is using observed lib size, needs to get lib sample
# which is just observed lib size on log scale
give_mean_lib = not scvi_model.module.use_observed_lib_size
# get latent representations and make input anndata
latent_rep = scvi_model.get_latent_representation()
lib_size = scvi_model.get_latent_library_size(give_mean=give_mean_lib)
latent_adata = AnnData(np.concatenate([latent_rep, lib_size], axis=1))
latent_adata.obs[LABELS_KEY] = "singlet"
logger.info("Creating doublets, preparing SOLO model.")
f = io.StringIO()
with redirect_stdout(f):
setup_anndata(doublet_adata)
doublet_latent_rep = scvi_model.get_latent_representation(
doublet_adata)
doublet_lib_size = scvi_model.get_latent_library_size(
doublet_adata, give_mean=give_mean_lib)
doublet_adata = AnnData(
np.concatenate([doublet_latent_rep, doublet_lib_size], axis=1))
doublet_adata.obs[LABELS_KEY] = "doublet"
full_adata = latent_adata.concatenate(doublet_adata)
setup_anndata(full_adata, labels_key=LABELS_KEY)
return cls(full_adata)
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 from_scvi_model(
cls,
scvi_model: SCVI,
adata: Optional[AnnData] = None,
restrict_to_batch: Optional[str] = None,
doublet_ratio: int = 2,
**classifier_kwargs,
):
"""
Instantiate a SOLO model from an scvi model.
Parameters
----------
scvi_model
Pre-trained model of :class:`~scvi.model.SCVI`. The
adata object used to initialize this model should have only
been setup with count data, and optionally a `batch_key`;
i.e., no extra covariates or labels, etc.
adata
Optional anndata to use that is compatible with scvi_model.
restrict_to_batch
Batch category in `batch_key` used to setup adata for scvi_model
to restrict Solo model to. This allows to train a Solo model on
one batch of a scvi_model that was trained on multiple batches.
doublet_ratio
Ratio of generated doublets to produce relative to number of
cells in adata or length of indices, if not `None`.
**classifier_kwargs
Keyword args for :class:`~scvi.module.Classifier`
Returns
-------
SOLO model
"""
_validate_scvi_model(scvi_model, restrict_to_batch=restrict_to_batch)
orig_adata_manager = scvi_model.adata_manager
orig_batch_key = orig_adata_manager.get_state_registry(
REGISTRY_KEYS.BATCH_KEY).original_key
if adata is not None:
adata_manager = orig_adata_manager.transfer_setup(adata)
cls.register_manager(adata_manager)
else:
adata_manager = orig_adata_manager
adata = adata_manager.adata
if restrict_to_batch is not None:
batch_mask = adata.obs[orig_batch_key] == restrict_to_batch
if np.sum(batch_mask) == 0:
raise ValueError(
"Batch category given to restrict_to_batch not found.\n" +
"Available categories: {}".format(
adata.obs[orig_batch_key].astype(
"category").cat.categories))
# indices in adata with restrict_to_batch category
batch_indices = np.where(batch_mask)[0]
else:
# use all indices
batch_indices = None
# anndata with only generated doublets
doublet_adata = cls.create_doublets(adata_manager,
indices=batch_indices,
doublet_ratio=doublet_ratio)
# if scvi wasn't trained with batch correction having the
# zeros here does nothing.
doublet_adata.obs[orig_batch_key] = (
restrict_to_batch if restrict_to_batch is not None else 0)
# if model is using observed lib size, needs to get lib sample
# which is just observed lib size on log scale
give_mean_lib = not scvi_model.module.use_observed_lib_size
# get latent representations and make input anndata
latent_rep = scvi_model.get_latent_representation(
adata, indices=batch_indices)
lib_size = scvi_model.get_latent_library_size(adata,
indices=batch_indices,
give_mean=give_mean_lib)
latent_adata = AnnData(
np.concatenate([latent_rep, np.log(lib_size)], axis=1))
latent_adata.obs[LABELS_KEY] = "singlet"
orig_obs_names = adata.obs_names
latent_adata.obs_names = (orig_obs_names[batch_indices]
if batch_indices is not None else
orig_obs_names)
logger.info("Creating doublets, preparing SOLO model.")
f = io.StringIO()
with redirect_stdout(f):
scvi_model.setup_anndata(doublet_adata, batch_key=orig_batch_key)
doublet_latent_rep = scvi_model.get_latent_representation(
doublet_adata)
doublet_lib_size = scvi_model.get_latent_library_size(
doublet_adata, give_mean=give_mean_lib)
doublet_adata = AnnData(
np.concatenate([doublet_latent_rep,
np.log(doublet_lib_size)],
axis=1))
doublet_adata.obs[LABELS_KEY] = "doublet"
full_adata = latent_adata.concatenate(doublet_adata)
cls.setup_anndata(full_adata, labels_key=LABELS_KEY)
return cls(full_adata, **classifier_kwargs)
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])