drvi.model.DRVI

drvi.model.DRVI#

class drvi.model.DRVI(adata=None, registry=None, n_latent=32, categorical_embedding_dims=None, **model_kwargs)[source]#

DRVI model based on scvi-tools framework for disentangled representation learning.

Parameters:

adata (AnnData | None (default: None)) – AnnData object that has been registered via setup_anndata().
n_latent (int (default: 32)) – Dimensionality of the latent space.
categorical_embedding_dims (dict[str, int] | None (default: None)) – Dictionary mapping categorical covariate names to their embedding dimensions. Used only if covariate_modeling_strategy passed to DRVIModule is based on embedding (not onehot encoding). Keys should match the covariate names used in setup_anndata(). If not provided, default embedding dimension of 10 is used for all covariates.
**model_kwargs – Additional keyword arguments passed to DRVIModule.

Examples

>>> adata = anndata.read_h5ad(path_to_anndata)
>>> drvi.model.DRVI.setup_anndata(adata, categorical_covariate_keys=["batch"])
>>> vae = drvi.model.DRVI(adata)
>>> vae.train()
>>> adata.obsm["latent"] = vae.get_latent_representation()

Attributes table#

`adata`	Data attached to model instance.
`adata_manager`	Manager instance associated with self.adata.
`device`	The current device that the module's params are on.
`get_normalized_function_name`	What the get normalized functions name is
`history`	Returns computed metrics during training.
`is_trained`	Whether the model has been trained.
`registry`	Data attached to model instance.
`run_id`	Returns the run id of the model.
`run_name`	Returns the run name of the model.
`summary_string`	Summary string of the model.
`test_indices`	Observations that are in test set.
`train_indices`	Observations that are in train set.
`validation_indices`	Observations that are in validation set.

Methods table#

`calculate_interpretability_scores`(embed[, ...])	Calculate interpretability scores for each split.
`convert_legacy_save`(dir_path, output_dir_path)	Converts a legacy saved model (<v0.15.0) to the updated save format.
`data_registry`(registry_key)	Returns the object in AnnData associated with the key in the data registry.
`decode_latent_samples`(z[, lib, ...])	Return the distribution produced by the decoder for the given latent samples.
`deregister_manager`([adata])	Deregisters the `AnnDataManager` instance associated with `adata`.
`differential_abundance`([adata, sample_key, ...])	Compute the differential abundance between samples.
`differential_expression`([adata, groupby, ...])	A unified method for differential expression analysis.
`generate_sparse_latent_representation`([...])	Iterate over the data and generate the sparse latent representation for each cell.
`get_aggregated_posterior`([adata, indices, ...])	Compute the aggregated posterior over the `u` latent representations.
`get_anndata_manager`(adata[, required])	Retrieves the `AnnDataManager` for a given AnnData object.
`get_effect_of_splits_out_of_distribution`(embed)	Return the effect of each split on reconstructed expression by traversing out of distribution.
`get_effect_of_splits_within_distribution`([...])	Return the maximum effect of each split on the reconstructed expression params for all genes.
`get_elbo`([adata, indices, batch_size, ...])	Compute the evidence lower bound (ELBO) on the data.
`get_feature_correlation_matrix`([adata, ...])	Generate gene-gene correlation matrix using scvi uncertainty and expression.
`get_from_registry`(adata, registry_key)	Returns the object in AnnData associated with the key in the data registry.
`get_importance_weights`(adata, indices, qz, ...)	Computes importance weights for the given samples.
`get_interpretability_scores`(embed, adata[, ...])	Extract interpretability scores as a DataFrame.
`get_latent_library_size`([adata, indices, ...])	Returns the latent library size for each cell.
`get_latent_representation`([adata, indices, ...])	Compute the latent representation of the data.
`get_likelihood_parameters`([adata, indices, ...])	Estimates for the parameters of the likelihood $p(x \mid z)$ .
`get_marginal_ll`([adata, indices, ...])	Compute the marginal log-likehood of the data.
`get_normalized_expression`([adata, indices, ...])	Returns the normalized (decoded) gene expression.
`get_reconstruction_effect_of_each_split`([...])	Return the effect of each split on the reconstructed expression per sample.
`get_reconstruction_error`([adata, indices, ...])	Compute the reconstruction error on the data.
`get_setup_arg`(setup_arg)	Returns the string provided to setup of a specific setup_arg.
`get_sparse_latent_representation`([adata, ...])	Return the sparse latent representation for each cell.
`get_state_registry`(registry_key)	Returns the state registry for the AnnDataField registered with this instance.
`get_var_names`([legacy_mudata_format])	Variable names of input data.
`iterate_on_ae_output`(adata[, datamodule, ...])	Iterate over autoencoder outputs as a generator.
`iterate_on_decoded_latent_samples`(z[, lib, ...])	Iterate over decoder outputs as a generator.
`iterate_on_effect_of_splits_within_distribution`([...])	Iterate over the maximum effect of each split on the reconstructed expression params for all genes.
`iterate_on_encoded_input`(adata[, ...])	Iterate over inference outputs as a generator.
`load`(dir_path[, adata, accelerator, device, ...])	Instantiate a model from the saved output.
`load_query_data`([adata, reference_model, ...])	Online update of a reference model with scArches algorithm [LNL+22].
`load_registry`(dir_path[, prefix])	Return the full registry saved with the model.
`plot_interpretability_scores`(embed, adata[, ...])	Plot interpretability scores as horizontal bar plots.
`posterior_predictive_sample`([adata, ...])	Generate predictive samples from the posterior predictive distribution.
`prepare_query_anndata`(adata, reference_model)	Prepare data for query integration.
`prepare_query_mudata`(mdata, reference_model)	Prepare multimodal dataset for query integration.
`register_manager`(adata_manager)	Registers an `AnnDataManager` instance with this model class.
`save`(dir_path[, prefix, overwrite, ...])	Save the state of the model.
`set_latent_dimension_stats`(embed[, adata, ...])	Set the latent dimension statistics of a DRVI embedding into var of an AnnData.
`setup_anndata`(adata[, layer, is_count_data, ...])	Sets up the `AnnData` object for this model.
`to_device`(device)	Move the model to the device.
`train`([max_epochs, accelerator, devices, ...])	Train the model.
`transfer_fields`(adata, **kwargs)	Transfer fields from a model to an AnnData object.
`update_setup_method_args`(setup_method_args)	Update setup method args.
`view_anndata_setup`([adata, ...])	Print summary of the setup for the initial AnnData or a given AnnData object.
`view_registry`([hide_state_registries])	Prints summary of the registry.
`view_setup_args`(dir_path[, prefix])	Print args used to setup a saved model.
`view_setup_method_args`()	Prints setup kwargs used to produce a given registry.

Attributes#

DRVI.adata#: Data attached to model instance.

DRVI.adata_manager#: Manager instance associated with self.adata.

DRVI.device#: The current device that the module’s params are on.

DRVI.get_normalized_function_name#: What the get normalized functions name is

DRVI.history#: Returns computed metrics during training.

DRVI.is_trained#: Whether the model has been trained.

DRVI.registry#: Data attached to model instance.

DRVI.run_id#: Returns the run id of the model. Used in MLFlow

DRVI.run_name#: Returns the run name of the model. Used in MLFlow

DRVI.summary_string#: Summary string of the model.

DRVI.test_indices#: Observations that are in test set.

DRVI.train_indices#: Observations that are in train set.

DRVI.validation_indices#: Observations that are in validation set.

Methods#

DRVI.calculate_interpretability_scores(embed, methods='OOD', directional=True, add_to_counts=1.0, inplace=True, **kwargs)#

Calculate interpretability scores for each split.

Parameters:

embed (AnnData) – AnnData object containing latent dimension statistics in .var. Must have columns: original_dim_id, min, max.
methods (Sequence[str] | str (default: 'OOD')) – Options are: - “ALL”: all methods are used - “IND”: in-distribution interpretability methods are used - “OOD”: out-of-distribution interpretability methods are used - A sequence of specific method names
directional (bool (default: True)) – Whether to consider the directional effect of each split.
add_to_counts (float (default: 1.0)) – Value to add to the counts before computing the logarithm. Used for numerical stability in log-space calculations.
inplace (bool (default: True)) – Whether to add the results to the embed.varm in place. If False, returns a dictionary instead.
**kwargs (Any) – Additional keyword arguments for the get_effect_of_splits_within_distribution or get_effect_of_splits_out_of_distribution methods.

Return type:

dict[str, ndarray] | None

Returns:

dict[str, np.ndarray] | None If inplace=False, returns a dictionary containing interpretability scores for each method. Keys are formatted as “{method}_{aggregation}_{direction}” where direction is “positive” or “negative” if directional=True, otherwise omitted. If inplace=True, returns None and stores results in embed.varm.

classmethod DRVI.convert_legacy_save(dir_path, output_dir_path, overwrite=False, prefix=None, **save_kwargs)#

Converts a legacy saved model (<v0.15.0) to the updated save format.

Parameters:

dir_path (str) – Path to the directory where the legacy model is saved.
output_dir_path (str) – Path to save converted save files.
overwrite (bool (default: False)) – Overwrite existing data or not. If False and directory already exists at output_dir_path, an error will be raised.
prefix (str | None (default: None)) – Prefix of saved file names.
**save_kwargs – Keyword arguments passed into save().

Return type:

None

DRVI.data_registry(registry_key)#

Returns the object in AnnData associated with the key in the data registry.

Parameters:: registry_key (str) – key of an object to get from self.data_registry
Return type:: ndarray | DataFrame
Returns:: The requested data.

DRVI.decode_latent_samples(z, lib=None, batch_values=None, cat_values=None, cont_values=None, batch_size=128, map_cat_values=False, return_in_log_space=True)#

Return the distribution produced by the decoder for the given latent samples.

This method computes $p(x \mid z)$ , the reconstruction distribution for given latent samples. It returns the mean of the reconstruction distribution for each sample.

A user may use model.get_normalized_expression to get the normalized expression within distribution in count space in a more probabilistic way.

Parameters:

z (ndarray) – Latent samples with shape (n_samples, n_latent).
lib (ndarray | None (default: None)) – Library size array with shape (n_samples,). If None, defaults to 1e4 for all samples.
batch_values (ndarray | None (default: None)) – Batch values with shape (n_samples,). If None, defaults to 0 for all samples.
cat_values (ndarray | None (default: None)) – Categorical covariates with shape (n_samples, n_cat_covs). Required if model has categorical covariates.
cont_values (ndarray | None (default: None)) – Continuous covariates with shape (n_samples, n_cont_covs).
batch_size (int (default: 128)) – Minibatch size for data loading into model.
map_cat_values (bool (default: False)) – Whether to map categorical covariates to integers based on the AnnData manager pipeline.
return_in_log_space (bool (default: True)) – Whether to return the means in log space.

Return type:

ndarray

Returns:

np.ndarray Reconstructed means with shape (n_samples, n_genes).

Notes

This method is equivalent to computing the expected value of the reconstruction distribution $E[p(x \mid z)]$ . It’s useful for: - Generating synthetic data from latent samples - Analyzing model reconstructions - Visualizing the generative capabilities of the model

Examples

>>> import numpy as np
>>> # Generate random latent samples
>>> z = np.random.randn(100, 32)  # assuming 32 latent dimensions
>>> # Decode to get reconstructed means
>>> reconstructed = model.decode_latent_samples(z)
>>> print(reconstructed.shape)  # (100, n_genes)
>>> # With categorical covariates
>>> cat_covs = np.array([0, 1, 0, 1] * 25)  # batch labels
>>> reconstructed = model.decode_latent_samples(z, cat_values=cat_covs)

DRVI.deregister_manager(adata=None)#

Deregisters the AnnDataManager instance associated with adata.

If adata is None, deregisters all AnnDataManager instances in both the class and instance-specific manager stores, except for the one associated with this model instance.

DRVI.differential_abundance(adata=None, sample_key=None, batch_size=128, num_cells_posterior=None, dof=None)#

Compute the differential abundance between samples.

Computes the log probabilities of each sample conditioned on the estimated aggregate posterior distribution of each cell.

Parameters:

adata (AnnData | MuData | None (default: None)) – The data object to compute the differential abundance for. For very large datasets, this should be a subset of the original data object.
sample_key (str | None (default: None)) – Key for the sample covariate.
batch_size (int (default: 128)) – Minibatch size for computing the differential abundance.
num_cells_posterior (int | None (default: None)) – Maximum number of cells used to compute aggregated posterior for each sample.
dof (float | None (default: None)) – Degrees of freedom for the Student’s t-distribution components for aggregated posterior. If None, components are Normal.

DRVI.differential_expression(adata=None, groupby=None, group1=None, group2=None, idx1=None, idx2=None, mode='vanilla', delta=0.25, batch_size=None, all_stats=True, batch_correction=False, batchid1=None, batchid2=None, fdr_target=0.05, silent=False, weights='uniform', filter_outlier_cells=False, importance_weighting_kwargs=None, **kwargs)#

A unified method for differential expression analysis.

Implements 'vanilla' DE [] and 'change' mode DE [].

Parameters:

adata (AnnData | None (default: None)) – AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.
groupby (str | None (default: None)) – The key of the observations grouping to consider.
group1 (list[str] | None (default: None)) – Subset of groups, e.g. ['g1', 'g2', 'g3'], to which comparison shall be restricted, or all groups in groupby (default).
group2 (str | None (default: None)) – If None, compare each group in group1 to the union of the rest of the groups in groupby. If a group identifier, compare with respect to this group.
idx1 (list[int] | list[bool] | str | None (default: None)) – idx1 and idx2 can be used as an alternative to the AnnData keys. Custom identifier for group1 that can be of three sorts: (1) a boolean mask, (2) indices, or (3) a string. If it is a string, then it will query indices that verifies conditions on adata.obs, as described in pandas.DataFrame.query() If idx1 is not None, this option overrides group1 and group2.
idx2 (list[int] | list[bool] | str | None (default: None)) – Custom identifier for group2 that has the same properties as idx1. By default, includes all cells not specified in idx1.
mode (Literal['vanilla', 'change'] (default: 'vanilla')) – Method for differential expression. See user guide for full explanation.
delta (float (default: 0.25)) – specific case of region inducing differential expression. In this case, we suppose that $R \setminus [-\delta, \delta]$ does not induce differential expression (change model default case).
batch_size (int | None (default: None)) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
all_stats (bool (default: True)) – Concatenate count statistics (e.g., mean expression group 1) to DE results.
batch_correction (bool (default: False)) – Whether to correct for batch effects in DE inference.
batchid1 (list[str] | None (default: None)) – Subset of categories from batch_key registered in setup_anndata, e.g. ['batch1', 'batch2', 'batch3'], for group1. Only used if batch_correction is True, and by default all categories are used.
batchid2 (list[str] | None (default: None)) – Same as batchid1 for group2. batchid2 must either have null intersection with batchid1, or be exactly equal to batchid1. When the two sets are exactly equal, cells are compared by decoding on the same batch. When sets have null intersection, cells from group1 and group2 are decoded on each group in group1 and group2, respectively.
fdr_target (float (default: 0.05)) – Tag features as DE based on posterior expected false discovery rate.
silent (bool (default: False)) – If True, disables the progress bar. Default: False.
weights (Literal['uniform', 'importance'] | None (default: 'uniform')) – Weights to use for sampling. If None, defaults to "uniform".
filter_outlier_cells (bool (default: False)) – Whether to filter outlier cells with filter_outlier_cells().
importance_weighting_kwargs (dict | None (default: None)) – Keyword arguments passed into get_importance_weights().
**kwargs – Keyword args for scvi.model.base.DifferentialComputation.get_bayes_factors()

Return type:

DataFrame

Returns:

Differential expression DataFrame.

DRVI.generate_sparse_latent_representation(adata=None, datamodule=None, indices=None, batch_size=None, zero_threshold=0.0, **kwargs)#

Iterate over the data and generate the sparse latent representation for each cell.

This method computes the sparse latent representation by applying sparsity constraints to the latent variables. The sparsity is controlled by the model’s sparsity configuration.

Parameters:

adata (AnnData | None (default: None)) – AnnData object with observations. If None, uses the AnnData object from model setup.
datamodule (LightningDataModule | None (default: None)) – LightningDataModule object with equivalent structure to initial AnnData. adata will be ignored if datamodule is provided.
indices (Sequence[int] | None (default: None)) – Indices of cells to include. If None, all cells are used.
batch_size (int | None (default: None)) – Minibatch size for data loading. If None, uses the full data.
zero_threshold (float (default: 0.0)) – Threshold for zeroing out the latent variables. Exact zero by default.
**kwargs (Any) – Additional keyword arguments passed to the iteration method.

Return type:

tuple[ndarray, ndarray]

Returns:

generator[tuple[sparse.csr_matrix, sparse.csr_matrix]] returns a generator of (sparse latent means, sparse latent variances) for each cell. Both are scipy sparse matrices in CSR format.

DRVI.get_aggregated_posterior(adata=None, indices=None, batch_size=None, dof=3.0)#

Compute the aggregated posterior over the u latent representations.

Parameters:

adata (default: None) – AnnData object to use. Defaults to the AnnData object used to initialize the model.
indices (default: None) – Indices of cells to use.
batch_size (default: None) – Batch size to use for computing the latent representation.
dof (default: 3.0) – Degrees of freedom for the Student’s t-distribution components. If None, components are Normal.

Returns:

A mixture distribution of the aggregated posterior.

DRVI.get_anndata_manager(adata, required=False)#

Retrieves the AnnDataManager for a given AnnData object.

Requires self.id has been set. Checks for an AnnDataManager specific to this model instance.

Parameters:

adata (AnnData | MuData) – AnnData object to find a manager instance for.
required (bool (default: False)) – If True, errors on missing manager. Otherwise, returns None when manager is missing.

Return type:

AnnDataManager | None

DRVI.get_effect_of_splits_out_of_distribution(embed, n_steps=20, n_samples=100, add_to_counts=1.0, directional=True, batch_size=128)#

Return the effect of each split on reconstructed expression by traversing out of distribution.

This method efficiently computes differential effects by iterating over batch/categorical covariate combinations and processing each dimension separately, avoiding large sparse matrices.

Parameters:

embed (AnnData) – AnnData object containing latent dimension statistics in .var. Must have columns: original_dim_id, min, max.
n_steps (int (default: 20)) – Number of steps in the traversal. Must be even (half negative, half positive).
n_samples (int (default: 100)) – Number of samples to generate for each step.
add_to_counts (float (default: 1.0)) – Small value added to counts to avoid log(0) issues in log-space calculations.
directional (bool (default: True)) – Whether to consider the directional effect of each split.
batch_size (int (default: 128)) – Minibatch size for data loading into model.

Return type:

dict[str, ndarray]

Returns:

dict[str, np.ndarray] Dictionary containing: - “min_possible”: (n_splits, n_genes) or (2, n_splits, n_genes) min possible LFC effects - “max_possible”: (n_splits, n_genes) or (2, n_splits, n_genes) max possible LFC effects - “combined”: (n_splits, n_genes) or (2, n_splits, n_genes) combined multiplicative effects

DRVI.get_effect_of_splits_within_distribution(adata=None, datamodule=None, add_to_counts=1.0, deterministic=True, directional=True, aggregations='ALL', skip_threshold=1.0, **kwargs)#

Return the maximum effect of each split on the reconstructed expression params for all genes.

This method computes the maximum contribution of each split across all samples in the dataset, providing a global view of split importance. When directional=True, for each latent dimension, effects are calculated independently for positive and negative values of that dimension.

Parameters:

adata (AnnData | None (default: None)) – AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.
datamodule (LightningDataModule | None (default: None)) – LightningDataModule object with equivalent structure to initial AnnData. adata will be ignored if datamodule is provided.
add_to_counts (float (default: 1.0)) – Value to add to the counts before computing the logarithm. Used for numerical stability in log-space calculations.
deterministic (bool (default: True)) – Makes model fully deterministic (e.g., no sampling in the bottleneck).
directional (bool (default: True)) – Whether to consider the directional effect of each split. If True, effects are computed separately for positive and negative latent values. If False, effects are computed over all samples.
aggregations (Sequence[Literal['max', 'linear_weighted_mean', 'exp_weighted_mean']] | str (default: 'ALL')) – Aggregation methods to use across batches. If “ALL”, all methods are used. If a string, only the method is used. If a sequence, only the methods in the sequence are used.
skip_threshold (float (default: 1.0)) – Minimum threshold for latent values when computing weighted means. Values below this threshold are clipped before computing weights.
**kwargs (Any) – Additional keyword arguments for the iterate_on_ae_output method.

Return type:

dict[str, ndarray]

Returns:

dict[str, np.ndarray] Dictionary containing: - “{aggregation_key}”: (n_splits, n_genes) or (2, n_splits, n_genes) score for each split for each gene

Notes

The calculation depends on the model’s split_aggregation: - “logsumexp”: Uses log-space softmax aggregation - “sum”: Uses absolute value summation

When directional=True, the score is computed separately: - Over samples where each dimension is positive (index 0 in first dimension) - Over samples where each dimension is negative (index 1 in first dimension)

Examples

>>> # Get empirical scores (2, n_split, n_genes)
>>> scores = model.get_effect_of_splits_within_distribution(add_to_counts=1.0)
>>>
>>> var_info = (
...     pd.concat([embed.var.assign(direction="+"), embed.var.assign(direction="-")])
...     .reset_index(drop=True)
...     .assign(title=lambda df: df["title"] + df["direction"])
... )
>>>
>>> effect_data = (
...     pd.DataFrame(
...         np.concatenate([scores["max_possible"][0], scores["max_possible"][1]]),
...         columns=model.adata.var_names,
...         index=var_info["title"],
...     )
...     .loc[var_info.sort_values(["order", "direction"])["title"]]
...     .T
... )
>>> plot_info = list(effect_data.to_dict(orient="series").items())
>>> drvi.utils.plotting._interpretability._bar_plot_top_differential_vars(plot_info)

DRVI.get_elbo(adata=None, indices=None, batch_size=None, dataloader=None, return_mean=True, data_loader_kwargs=None, **kwargs)#

Compute the evidence lower bound (ELBO) on the data.

The ELBO is the reconstruction error plus the Kullback-Leibler (KL) divergences between the variational distributions and the priors. It is different from the marginal log-likelihood; specifically, it is a lower bound on the marginal log-likelihood plus a term that is constant with respect to the variational distribution. It still gives good insights on the modeling of the data and is fast to compute.

Parameters:

adata (AnnData | None (default: None)) – AnnData object with var_names in the same order as the ones used to train the model. If None and dataloader is also None, it defaults to the object used to initialize the model.
indices (Sequence[int] | None (default: None)) – Indices of observations in adata to use. If None, defaults to all observations. Ignored if dataloader is not None.
batch_size (int | None (default: None)) – Minibatch size for the forward pass. If None, defaults to scvi.settings.batch_size. Ignored if dataloader is not None.
dataloader (Iterator[dict[str, Tensor | None]] | None (default: None)) – An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of Tensor with keys as expected by the model. If None, a dataloader is created from adata.
return_mean (bool (default: True)) – Whether to return the mean of the ELBO or the ELBO for each observation.
data_loader_kwargs (dict | None (default: None)) – Keyword args for data loader, in dict form.
**kwargs – Additional keyword arguments to pass into the forward method of the module.

Return type:

float

Returns:

Evidence lower bound (ELBO) of the data.

Notes

This is not the negative ELBO, so higher is better.

DRVI.get_feature_correlation_matrix(adata=None, indices=None, n_samples=10, batch_size=64, rna_size_factor=1000, transform_batch=None, correlation_type='spearman', silent=True)#

Generate gene-gene correlation matrix using scvi uncertainty and expression.

Parameters:

adata (AnnData | None (default: None)) – AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.
indices (list[int] | None (default: None)) – Indices of cells in adata to use. If None, all cells are used.
n_samples (int (default: 10)) – Number of posterior samples to use for estimation.
batch_size (int (default: 64)) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
rna_size_factor (int (default: 1000)) – size factor for RNA prior to sampling gamma distribution.
transform_batch (list[int | float | str] | None (default: None)) –
Batches to condition on. If transform_batch is:
- None, then real observed batch is used.
- int, then batch transform_batch is used.
- list of int, then values are averaged over provided batches.
correlation_type (Literal['spearman', 'pearson'] (default: 'spearman')) – One of “pearson”, “spearman”.
%(de_silent)s

Return type:

DataFrame

Returns:

Gene-gene correlation matrix

DRVI.get_from_registry(adata, registry_key)#

Returns the object in AnnData associated with the key in the data registry.

AnnData object should be registered with the model prior to calling this function via the self._validate_anndata method.

Parameters:

registry_key (str) – key of object to get from the data registry.
adata (AnnData | MuData) – AnnData to pull data from.

Return type:

ndarray

Returns:

The requested data as a NumPy array.

DRVI.get_importance_weights(adata, indices, qz, px, zs, max_cells=1024, truncation=False, n_mc_samples=500, n_mc_samples_per_pass=250, **data_loader_kwargs)#

Computes importance weights for the given samples.

This method computes importance weights for every latent code in zs as a way to encourage latent codes providing high likelihoods across many cells in the considered subpopulation.

Parameters:

adata (AnnData | None) – Data to use for computing importance weights.
indices (list[int] | None) – Indices of cells in adata to use.
distributions – Dictionary of distributions associated with indices.
qz (Distribution) – Variational posterior distributions of the cells, aligned with indices.
px (Distribution) – Count distributions of the cells, aligned with indices.
zs (Tensor) – Samples associated with indices.
max_cells (int (default: 1024)) – Maximum number of cells used to estimated the importance weights
truncation (bool (default: False)) – Whether importance weights should be truncated. If True, the importance weights are truncated as described in []. In particular, the provided value is used to threshold importance weights as a way to reduce the variance of the estimator.
n_mc_samples (int (default: 500)) – Number of Monte Carlo samples to use for estimating the importance weights, by default 500
n_mc_samples_per_pass (int (default: 250)) – Number of Monte Carlo samples to use for each pass, by default 250
**data_loader_kwargs – Keyword args for data loader.

Return type:

ndarray

Returns:

importance_weights Numpy array containing importance weights aligned with the provided indices.

Notes

This method assumes a normal prior on the latent space.

DRVI.get_interpretability_scores(embed, adata, key='OOD_combined', directional=True, gene_symbols=None, order_col='order', title_col='title', hide_vanished=True)#

Extract interpretability scores as a DataFrame.

Parameters:

embed (AnnData) – AnnData object containing interpretability scores in .varm. For directional=True, expects {key}_positive and {key}_negative keys.
adata (AnnData) – AnnData object for gene information.
key (str (default: 'OOD_combined')) – Base key name for scores in embed.varm. Default: “OOD_combined”.
directional (bool (default: True)) – Whether to include directional effects. If True, creates columns like “DR 1+”, “DR 1-”. If False, creates columns like “DR 1”.
gene_symbols (str | None (default: None)) – Column name in adata.var for gene symbols. If None, uses adata.var_names.
order_col (str (default: 'order')) – Column name in embed.var for dimension ordering.
title_col (str (default: 'title')) – Column name in embed.var for dimension titles.
hide_vanished (bool (default: True)) – Whether to hide vanished dimensions from the plot.

Return type:

DataFrame

Returns:

pd.DataFrame DataFrame with genes as rows and dimensions as columns.

DRVI.get_latent_library_size(adata=None, indices=None, give_mean=True, batch_size=None, dataloader=None, **data_loader_kwargs)#

Returns the latent library size for each cell.

This is denoted as $\ell_n$ in the scVI paper.

Parameters:

adata (AnnData | None (default: None)) – AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.
indices (list[int] | None (default: None)) – Indices of cells in adata to use. If None, all cells are used.
give_mean (bool (default: True)) – Return the mean or a sample from the posterior distribution.
batch_size (int | None (default: None)) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
dataloader (Iterator[dict[str, Tensor | None]] | None (default: None)) – An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of Tensor with keys as expected by the model. If None, a dataloader is created from adata.
**data_loader_kwargs – Keyword args for data loader.

Return type:

ndarray

DRVI.get_latent_representation(adata=None, indices=None, give_mean=True, mc_samples=5000, batch_size=None, return_dist=False, dataloader=None, **data_loader_kwargs)#

Compute the latent representation of the data.

This is typically denoted as $z_n$ .

Parameters:

adata (AnnData | None (default: None)) – AnnData object with var_names in the same order as the ones used to train the model. If None and dataloader is also None, it defaults to the object used to initialize the model.
indices (Sequence[int] | None (default: None)) – Indices of observations in adata to use. If None, defaults to all observations. Ignored if dataloader is not None
give_mean (bool (default: True)) – If True, returns the mean of the latent distribution. If False, returns an estimate of the mean using mc_samples Monte Carlo samples.
mc_samples (int (default: 5000)) – Number of Monte Carlo samples to use for the estimator for distributions with no closed-form mean (e.g., the logistic normal distribution). Not used if give_mean is True or if return_dist is True.
batch_size (int | None (default: None)) – Minibatch size for the forward pass. If None, defaults to scvi.settings.batch_size. Ignored if dataloader is not None
return_dist (bool (default: False)) – If True, returns the mean and variance of the latent distribution. Otherwise, returns the mean of the latent distribution.
dataloader (Iterator[dict[str, Tensor | None]] (default: None)) – An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of Tensor with keys as expected by the model. If None, a dataloader is created from adata.
**data_loader_kwargs – Keyword args for data loader.

Return type:

ndarray[tuple[Any, ...], dtype[TypeVar(_ScalarT, bound= generic)]] | tuple[ndarray[tuple[Any, ...], dtype[TypeVar(_ScalarT, bound= generic)]], ndarray[tuple[Any, ...], dtype[TypeVar(_ScalarT, bound= generic)]]]

Returns:

An array of shape (n_obs, n_latent) if return_dist is False. Otherwise, returns a tuple of arrays (n_obs, n_latent) with the mean and variance of the latent distribution.

DRVI.get_likelihood_parameters(adata=None, indices=None, n_samples=1, give_mean=False, batch_size=None, dataloader=None, **data_loader_kwargs)#

Estimates for the parameters of the likelihood $p(x \mid z)$ .

Parameters:

adata (AnnData | None (default: None)) – AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.
indices (list[int] | None (default: None)) – Indices of cells in adata to use. If None, all cells are used.
n_samples (int | None (default: 1)) – Number of posterior samples to use for estimation.
give_mean (bool | None (default: False)) – Return expected value of parameters or a samples
batch_size (int | None (default: None)) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
dataloader (Iterator[dict[str, Tensor | None]] | None (default: None)) – An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of Tensor with keys as expected by the model. If None, a dataloader is created from adata.
**data_loader_kwargs – Keyword args for data loader.

Return type:

dict[str, ndarray]

DRVI.get_marginal_ll(adata=None, indices=None, n_mc_samples=1000, batch_size=None, return_mean=True, dataloader=None, data_loader_kwargs=None, **kwargs)#

Compute the marginal log-likehood of the data.

The computation here is a biased estimator of the marginal log-likelihood of the data.

Parameters:

adata (AnnData | None (default: None)) – AnnData object with var_names in the same order as the ones used to train the model. If None and dataloader is also None, it defaults to the object used to initialize the model.
indices (Sequence[int] | None (default: None)) – Indices of observations in adata to use. If None, defaults to all observations. Ignored if dataloader is not None.
n_mc_samples (int (default: 1000)) – Number of Monte Carlo samples to use for the estimator. Passed into the module’s marginal_ll method.
batch_size (int | None (default: None)) – Minibatch size for the forward pass. If None, defaults to scvi.settings.batch_size. Ignored if dataloader is not None.
return_mean (bool (default: True)) – Whether to return the mean of the marginal log-likelihood or the marginal-log likelihood for each observation.
dataloader (Iterator[dict[str, Tensor | None]] (default: None)) – An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of Tensor with keys as expected by the model. If None, a dataloader is created from adata.
data_loader_kwargs (dict | None (default: None)) – Keyword args for data loader, in dict form.
**kwargs – Additional keyword arguments to pass into the module’s marginal_ll method.

Return type:

float | Tensor

Returns:

If True, returns the mean marginal log-likelihood. Otherwise returns a tensor of shape (n_obs,) with the marginal log-likelihood for each observation.

Notes

This is not the negative log-likelihood, so higher is better.

DRVI.get_normalized_expression(adata=None, indices=None, transform_batch=None, gene_list=None, library_size=1, n_samples=1, n_samples_overall=None, weights=None, batch_size=None, return_mean=True, return_numpy=None, silent=True, dataloader=None, data_loader_kwargs=None, **importance_weighting_kwargs)#

Returns the normalized (decoded) gene expression.

This is denoted as $\rho_n$ in the scVI paper.

Parameters:

adata (AnnData | None (default: None)) – AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.
indices (list[int] | None (default: None)) – Indices of cells in adata to use. If None, all cells are used.
transform_batch (list[int | float | str] | None (default: None)) – Batch to condition on. If transform_batch is: - None, then real observed batch is used. - int, then batch transform_batch is used. - Otherwise based on string
gene_list (list[str] | None (default: None)) – Return frequencies of expression for a subset of genes. This can save memory when working with large datasets and few genes are of interest.
library_size (float | Literal['latent'] (default: 1)) – Scale the expression frequencies to a common library size. This allows gene expression levels to be interpreted on a common scale of relevant magnitude. If set to "latent", use the latent library size.
n_samples (int (default: 1)) – Number of posterior samples to use for estimation.
n_samples_overall (int (default: None)) – Number of posterior samples to use for estimation. Overrides n_samples.
weights (Literal['uniform', 'importance'] | None (default: None)) – Weights to use for sampling. If None, defaults to "uniform".
batch_size (int | None (default: None)) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
return_mean (bool (default: True)) – Whether to return the mean of the samples.
return_numpy (bool | None (default: None)) – Return a ndarray instead of a DataFrame. DataFrame includes gene names as columns. If either n_samples=1 or return_mean=True, defaults to False. Otherwise, it defaults to True.
%(de_silent)s
dataloader (Iterator[dict[str, Tensor | None]] | None (default: None)) – An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of Tensor with keys as expected by the model. If None, a dataloader is created from adata.
data_loader_kwargs (dict | None (default: None)) – Keyword args for data loader, in dict form.
importance_weighting_kwargs – Keyword arguments passed into get_importance_weights().

Return type:

ndarray | DataFrame

Returns:

If n_samples is provided and return_mean is False, this method returns a 3d tensor of shape (n_samples, n_cells, n_genes). If n_samples is provided and return_mean is True, it returns a 2d tensor of shape (n_cells, n_genes). In this case, return type is DataFrame unless return_numpy is True. Otherwise, the method expects n_samples_overall to be provided and returns a 2d tensor of shape (n_samples_overall, n_genes).

DRVI.get_reconstruction_effect_of_each_split(adata=None, datamodule=None, add_to_counts=1.0, aggregate_over_cells=True, deterministic=True, directional=False, **kwargs)#

Return the effect of each split on the reconstructed expression per sample.

This method analyzes how different model splits contribute to the reconstruction of gene expression values.

Parameters:

adata (AnnData | None (default: None)) – AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.
datamodule (LightningDataModule | None (default: None)) – LightningDataModule object with equivalent structure to initial AnnData. adata will be ignored if datamodule is provided.
add_to_counts (float (default: 1.0)) – Value to add to the counts before computing the logarithm. Used for numerical stability in log-space calculations.
aggregate_over_cells (bool (default: True)) – Whether to aggregate the effect over cells and return a value per dimension. If False, returns per-cell effects.
deterministic (bool (default: True)) – Makes model fully deterministic (e.g., no sampling in the bottleneck).
directional (bool (default: False)) – Whether to consider the directional effect of each split.
**kwargs (Any) – Additional keyword arguments for the iterate_on_ae_output method.

Return type:

ndarray

Returns:

np.ndarray Effect of each split on reconstruction. Shape depends on aggregate_over_cells and directional: - If True and directional=False: (n_splits,) - aggregated effects per split - If True and directional=True: (2, n_splits) - aggregated effects per split for positive and negative values - If False and directional=False: (n_cells, n_splits) - per-cell effects per split - If False and directional=True: (n_cells, 2, n_splits) - per-cell effects per split for positive and negative values

Notes

This method computes the contribution of each model split to the reconstruction. The calculation depends on the model’s split_aggregation:

“logsumexp”: Uses log-space softmax aggregation
“sum”: Uses absolute value summation

The effect is computed by analyzing how each split contributes to the final reconstruction parameters.

Examples

>>> # Get aggregated effects across all cells
>>> effects = model.get_reconstruction_effect_of_each_split()
>>> print(effects.shape)  # (n_splits,)
>>> print("Effect of each split:", effects)
>>> # Get per-cell effects
>>> cell_effects = model.get_reconstruction_effect_of_each_split(aggregate_over_cells=False)
>>> print(cell_effects.shape)  # (n_cells, n_splits)

DRVI.get_reconstruction_error(adata=None, indices=None, batch_size=None, dataloader=None, return_mean=True, data_loader_kwargs=None, **kwargs)#

Compute the reconstruction error on the data.

The reconstruction error is the negative log likelihood of the data given the latent variables. It is different from the marginal log-likelihood, but still gives good insights on the modeling of the data and is fast to compute. This is typically written as $p(x \mid z)$ , the likelihood term given one posterior sample.

Parameters:

adata (AnnData | None (default: None)) – AnnData object with var_names in the same order as the ones used to train the model. If None and dataloader is also None, it defaults to the object used to initialize the model.
indices (Sequence[int] | None (default: None)) – Indices of observations in adata to use. If None, defaults to all observations. Ignored if dataloader is not None
batch_size (int | None (default: None)) – Minibatch size for the forward pass. If None, defaults to scvi.settings.batch_size. Ignored if dataloader is not None
dataloader (Iterator[dict[str, Tensor | None]] | None (default: None)) – An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of Tensor with keys as expected by the model. If None, a dataloader is created from adata.
return_mean (bool (default: True)) – Whether to return the mean reconstruction loss or the reconstruction loss for each observation.
data_loader_kwargs (dict | None (default: None)) – Keyword args for data loader, in dict form.
**kwargs – Additional keyword arguments to pass into the forward method of the module.

Return type:

dict[str, float]

Returns:

Reconstruction error for the data.

Notes

This is not the negative reconstruction error, so higher is better.

DRVI.get_setup_arg(setup_arg)#

Returns the string provided to setup of a specific setup_arg.

Return type:: attrdict

DRVI.get_sparse_latent_representation(adata=None, datamodule=None, indices=None, batch_size=None, zero_threshold=0.0, return_dist=False, **kwargs)#

Return the sparse latent representation for each cell.

This method computes the sparse latent representation by applying sparsity constraints to the latent variables. The sparsity is controlled by the model’s sparsity configuration.

Parameters:

adata (AnnData | None (default: None)) – AnnData object with observations. If None, uses the AnnData object from model setup.
datamodule (LightningDataModule | None (default: None)) – LightningDataModule object with equivalent structure to initial AnnData. adata will be ignored if datamodule is provided.
indices (Sequence[int] | None (default: None)) – Indices of cells to include. If None, all cells are used.
batch_size (int | None (default: None)) – Minibatch size for data loading. If None, uses the full data.
zero_threshold (float (default: 0.0)) – Threshold for zeroing out the latent variables. Exact zero by default.
return_dist (bool (default: False)) – Whether to return both mean and variance of the latent distribution. If False, only returns the mean.
**kwargs (Any) – Additional keyword arguments passed to the iteration method.

Return type:

ndarray | tuple[ndarray, ndarray]

Returns:

sparse.csr_matrix | tuple[sparse.csr_matrix, sparse.csr_matrix] If return_dist=False, returns sparse matrix of latent means. If return_dist=True, returns tuple of (sparse latent means, sparse latent variances).

DRVI.get_state_registry(registry_key)#

Returns the state registry for the AnnDataField registered with this instance.

Return type:: attrdict

DRVI.get_var_names(legacy_mudata_format=False)#

Variable names of input data.

Return type:: dict

DRVI.iterate_on_ae_output(adata, datamodule=None, indices=None, batch_size=None, deterministic=False)#

Iterate over autoencoder outputs as a generator.

This method processes data through the full autoencoder (encoder + decoder) and yields the outputs for each batch.

Parameters:

adata (AnnData) – AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.
datamodule (LightningDataModule | None (default: None)) – LightningDataModule object with equivalent structure to initial AnnData. adata will be ignored if datamodule is provided.
indices (Sequence[int] | None (default: None)) – Indices of cells in adata to use. If None, all cells are used.
batch_size (int | None (default: None)) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
deterministic (bool (default: False)) – Makes model fully deterministic (e.g., no sampling in the bottleneck).

Yields:

tuple[dict[str, Any], dict[str, Any], Any] – Tuple of (inference_outputs, generative_outputs, losses) for each batch.

Notes

This method processes data through both the encoder and decoder components of the model. The calling function should handle processing and aggregation of the yielded outputs.

When deterministic=True, the model operates without stochastic sampling, which is useful for reproducible analysis.

Examples

>>> import anndata as ad
>>> # Process data through autoencoder and aggregate results
>>> store = []
>>> for inference_outputs, generative_outputs, losses in model.iterate_on_ae_output(
...     adata=adata, deterministic=True
... ):
...     store.append(inference_outputs["qzm"].detach().cpu())
>>> latents = torch.cat(store, dim=0).numpy()
>>> print(latents.shape)  # (n_cells, n_latent)

DRVI.iterate_on_decoded_latent_samples(z, lib=None, batch_values=None, cat_values=None, cont_values=None, batch_size=128, map_cat_values=False)#

Iterate over decoder outputs as a generator.

This method processes latent samples through the generative model in batches and yields the generative outputs for each batch.

Parameters:

z (ndarray) – Latent samples with shape (n_samples, n_latent).
lib (ndarray | None (default: None)) – Library size array with shape (n_samples,). If None, defaults to 1e4 for all samples.
batch_values (ndarray | None (default: None)) – Batch values with shape (n_samples,). If None, defaults to 0 for all samples.
cat_values (ndarray | None (default: None)) – Categorical covariates with shape (n_samples, n_cat_covs). Required if model has categorical covariates.
cont_values (ndarray | None (default: None)) – Continuous covariates with shape (n_samples, n_cont_covs).
batch_size (int (default: 128)) – Minibatch size for data loading into model.
map_cat_values (bool (default: False)) – Whether to map categorical covariates to integers based on the AnnData manager pipeline.

Yields:

dict[str, Any] – Generative outputs for each batch.

Notes

This method operates in inference mode and processes data in batches to manage memory usage. The calling function should handle processing and aggregation of the yielded outputs.

If map_cat_values is True, categorical values are automatically mapped to integers using the model’s category mappings.

Examples

>>> import numpy as np
>>> # Process latent samples and aggregate results
>>> z = np.random.randn(50, 32)  # assuming 32 latent dimensions
>>> store = []
>>> for gen_output in model.iterate_on_decoded_latent_samples(z=z):
...     store.append(gen_output["px"].mean.detach().cpu())
>>> result = torch.cat(store, dim=0).numpy()
>>> print(result.shape)  # (50, n_genes)

DRVI.iterate_on_effect_of_splits_within_distribution(adata=None, datamodule=None, add_to_counts=1.0, deterministic=True, directional=True, **kwargs)#

Iterate over the maximum effect of each split on the reconstructed expression params for all genes.

This method computes the maximum contribution of each split across all samples in the dataset, providing a global view of split importance. For each latent dimension, effects are calculated independently for positive and negative values of that dimension.

Parameters:

adata (AnnData | None (default: None)) – AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.
datamodule (LightningDataModule | None (default: None)) – LightningDataModule object with equivalent structure to initial AnnData. adata will be ignored if datamodule is provided.
add_to_counts (float (default: 1.0)) – Value to add to the counts before computing the logarithm. Used for numerical stability in log-space calculations.
deterministic (bool (default: True)) – Makes model fully deterministic (e.g., no sampling in the bottleneck).
directional (bool (default: True)) – Whether to consider the directional effect of each split.
**kwargs (Any) – Additional keyword arguments for the iterate_on_ae_output method.

Returns:

Generator[np.ndarray] Generator of maximum effect of each split on the reconstructed expression params.

Notes

This function is experimental. Please use interpretability pipeline or DE instead.

The calculation depends on the model’s split_aggregation: - “logsumexp”: Uses log-space softmax aggregation - “sum”: Uses absolute value summation

DRVI.iterate_on_encoded_input(adata, datamodule=None, indices=None, batch_size=None, deterministic=False)#

Iterate over inference outputs as a generator.

This method processes data through the encoder (inference) component only and yields the inference outputs for each batch.

Parameters:

adata (AnnData) – AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.
datamodule (LightningDataModule | None (default: None)) – LightningDataModule object with equivalent structure to initial AnnData. adata will be ignored if datamodule is provided.
indices (Sequence[int] | None (default: None)) – Indices of cells in adata to use. If None, all cells are used.
batch_size (int | None (default: None)) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
deterministic (bool (default: False)) – Makes model fully deterministic (e.g., no sampling in the bottleneck).

Yields:

dict[str, Any] – Inference outputs for each batch, containing latent variables and other encoder outputs.

Notes

This method processes data through only the encoder (inference) component of the model, without running the decoder. The calling function should handle processing and aggregation of the yielded outputs.

When deterministic=True, the model operates without stochastic sampling, which is useful for reproducible analysis.

Examples

>>> import anndata as ad
>>> # Process data through encoder and aggregate results
>>> store = []
>>> for inference_outputs in model.iterate_onencoded_input(adata=adata, deterministic=True):
...     store.append(inference_outputs["qzm"].detach().cpu())
>>> latents = torch.cat(store, dim=0).numpy()
>>> print(latents.shape)  # (n_cells, n_latent)

classmethod DRVI.load(dir_path, adata=None, accelerator='auto', device='auto', prefix=None, backup_url=None, datamodule=None, allowed_classes_names_list=None)#

Instantiate a model from the saved output.

Parameters:

dir_path (str) – Path to saved outputs.
adata (AnnData | MuData | None (default: None)) – AnnData organized in the same way as data used to train model. It is not necessary to run setup_anndata, as AnnData is validated against the saved scvi setup dictionary. If None, will check for and load anndata saved with the model. If False, will load the model without AnnData.
accelerator (str (default: 'auto')) – Supports passing different accelerator types ("cpu", "gpu", "tpu", "ipu", "hpu", "mps, "auto") as well as custom accelerator instances.
device (int | str (default: 'auto')) – The device to use. Can be set to a non-negative index (int or str) or "auto" for automatic selection based on the chosen accelerator. If set to "auto" and accelerator is not determined to be "cpu", then device will be set to the first available device.
prefix (str | None (default: None)) – Prefix of saved file names.
backup_url (str | None (default: None)) – URL to retrieve saved outputs from if not present on disk.
datamodule (LightningDataModule | None (default: None)) – EXPERIMENTAL A LightningDataModule instance to use for training in place of the default DataSplitter. Can only be passed in if the model was not initialized with AnnData.
allowed_classes_names_list (list[str] | None (default: None)) – list of allowed classes names to be loaded (besides the original class name)

Returns:

Model with loaded state dictionaries.

Examples

>>> model = ModelClass.load(save_path, adata)
>>> model.get_....

classmethod DRVI.load_query_data(adata=None, reference_model=None, registry=None, inplace_subset_query_vars=False, accelerator='auto', device='auto', unfrozen=False, freeze_dropout=False, freeze_shared_emb=True, freeze_encoder=True, freeze_decoder=True, reset_encoder=False, reset_decoder=False, freeze_batchnorm_encoder=True, freeze_batchnorm_decoder=False, datamodule=None)#

Online update of a reference model with scArches algorithm [LNL+22].

Parameters:

adata (AnnData (default: None)) – AnnData organized in the same way as data used to train model. It is not necessary to run setup_anndata, as AnnData is validated against the registry.
reference_model (str | BaseModelClass (default: None)) – Either an already instantiated model of the same class, or a path to saved outputs for reference model.
inplace_subset_query_vars (bool (default: False)) – Whether to subset and rearrange query vars inplace based on vars used to train reference model.
%(param_accelerator)s
%(param_device)s
unfrozen (bool (default: False)) – Override all other freeze options for a fully unfrozen model
freeze_dropout (bool (default: False)) – Whether to freeze dropout during training
freeze_shared_emb (bool (default: True)) – Whether to freeze shared embeddings if any
freeze_encoder (bool (default: True)) – Whether to freeze encoder
freeze_decoder (bool (default: True)) – Whether to freeze decoder
freeze_batchnorm_encoder (bool (default: True)) – Whether to freeze encoder batchnorms’ weight and bias during transfer
freeze_batchnorm_decoder (bool (default: False)) – Whether to freeze decoder batchnorms’ weight and bias during transfer

static DRVI.load_registry(dir_path, prefix=None)#

Return the full registry saved with the model.

Parameters:

dir_path (str) – Path to saved outputs.
prefix (str | None (default: None)) – Prefix of saved file names.

Return type:

dict

Returns:

The full registry saved with the model

DRVI.plot_interpretability_scores(embed, adata, ncols=5, n_top_genes=10, score_threshold=0.1, dim_subset=None, show=True, **kwargs)#

Plot interpretability scores as horizontal bar plots.

Parameters:

embed (AnnData) – AnnData object containing interpretability scores.
adata (AnnData) – AnnData object for gene information.
ncols (int (default: 5)) – Number of columns in the subplot grid.
n_top_genes (int (default: 10)) – Number of top genes to display per dimension.
score_threshold (float (default: 0.1)) – Minimum score threshold for dimensions to be plotted.
dim_subset (Sequence[str] | None (default: None)) – Optional list of dimension titles to plot. If None, all dimensions meeting the threshold are plotted.
show (bool (default: True)) – Whether to display the plot. If False, returns the figure.
**kwargs – Additional arguments passed to get_interpretability_scores.

Returns:

matplotlib.figure.Figure or None The figure object if show=False, otherwise None.

DRVI.posterior_predictive_sample(adata=None, indices=None, transform_batch=None, n_samples=1, gene_list=None, batch_size=None, dataloader=None, silent=True, **data_loader_kwargs)#

Generate predictive samples from the posterior predictive distribution.

The posterior predictive distribution is denoted as $p(\hat{x} \mid x)$ , where $x$ is the input data and $\hat{x}$ is the sampled data.

We sample from this distribution by first sampling n_samples times from the posterior distribution $q(z \mid x)$ for a given observation, and then sampling from the likelihood $p(\hat{x} \mid z)$ for each of these.

Parameters:

adata (AnnData | None (default: None)) – AnnData object with an equivalent structure to the model’s dataset. If None, defaults to the AnnData object used to initialize the model.
indices (list[int] | None (default: None)) – Indices of the observations in adata to use. If None, defaults to all the observations.
transform_batch (list[int | float | str] | None (default: None)) – Batch to condition on. If transform_batch is: - None, then real observed batch is used. - int, then batch transform_batch is used. - Otherwise based on string
n_samples (int (default: 1)) – Number of Monte Carlo samples to draw from the posterior predictive distribution for each observation.
gene_list (list[str] | None (default: None)) – Names of the genes to which to subset. If None, defaults to all genes.
batch_size (int | None (default: None)) – Minibatch size to use for data loading and model inference. Defaults to scvi.settings.batch_size. Passed into BaseModelClass._make_data_loader.
dataloader (Iterator[dict[str, Tensor | None]] | None (default: None)) – An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of Tensor with keys as expected by the model. If None, a dataloader is created from adata.
**data_loader_kwargs – Keyword args for data loader.

Return type:

GCXS

Returns:

Sparse multidimensional array of shape (n_obs, n_vars) if n_samples == 1, else (n_obs, n_vars, n_samples).

static DRVI.prepare_query_anndata(adata, reference_model, return_reference_var_names=False, inplace=True)#

Prepare data for query integration.

This function will return a new AnnData object with padded zeros for missing features, as well as correctly sorted features.

Parameters:

adata (AnnData) – AnnData organized in the same way as data used to train model. It is not necessary to run setup_anndata, as AnnData is validated against the registry.
reference_model (str | BaseModelClass) – Either an already instantiated model of the same class or a path to saved outputs for the reference model.
return_reference_var_names (bool (default: False)) – Only load and return reference var names if True.
inplace (bool (default: True)) – Whether to subset and rearrange query vars inplace or return new AnnData.

Return type:

AnnData | Index | None

Returns:

Query adata ready to use in load_query_data unless return_reference_var_names in which case a pd.Index of reference var names is returned.

static DRVI.prepare_query_mudata(mdata, reference_model, return_reference_var_names=False, inplace=True)#

Prepare multimodal dataset for query integration.

This function will return a new MuData object such that the AnnData objects for individual modalities are given padded zeros for missing features, as well as correctly sorted features.

Parameters:

mdata (MuData) – MuData organized in the same way as data used to train the model. It is not necessary to run setup_mudata, as MuData is validated against the registry.
reference_model (str | BaseModelClass) – Either an already instantiated model of the same class or a path to saved outputs for the reference model.
return_reference_var_names (bool (default: False)) – Only load and return reference var names if True.
inplace (bool (default: True)) – Whether to subset and rearrange query vars inplace or return new MuData.

Return type:

MuData | dict[str, Index] | None

Returns:

Query mudata ready to use in load_query_data unless return_reference_var_names in which case a dictionary of pd.Index of reference var names is returned.

classmethod DRVI.register_manager(adata_manager)#

Registers an AnnDataManager instance with this model class.

Stores the AnnDataManager reference in a class-specific manager store. Intended for use in the setup_anndata() class method followed up by retrieval of the AnnDataManager via the _get_most_recent_anndata_manager() method in the model init method.

Notes

Subsequent calls to this method with an AnnDataManager instance referring to the same underlying AnnData object will overwrite the reference to previous AnnDataManager.

DRVI.save(dir_path, prefix=None, overwrite=False, save_anndata=False, save_kwargs=None, legacy_mudata_format=False, datamodule=None, **anndata_write_kwargs)#

Save the state of the model.

Neither the trainer optimizer state nor the trainer history are saved. Model files are not expected to be reproducibly saved and loaded across versions until we reach version 1.0.

Parameters:

dir_path (str) – Path to a directory.
prefix (str | None (default: None)) – Prefix to prepend to saved file names.
overwrite (bool (default: False)) – Overwrite existing data or not. If False and directory already exists at dir_path, an error will be raised.
save_anndata (bool (default: False)) – If True, also saves the anndata
save_kwargs (dict | None (default: None)) – Keyword arguments passed into save().
legacy_mudata_format (bool (default: False)) – If True, saves the model var_names in the legacy format if the model was trained with a MuData object. The legacy format is a flat array with variable names across all modalities concatenated, while the new format is a dictionary with keys corresponding to the modality names and values corresponding to the variable names for each modality.
datamodule (LightningDataModule | None (default: None)) – EXPERIMENTAL A LightningDataModule instance to use for training in place of the default DataSplitter. Can only be passed in if the model was not initialized with AnnData.
anndata_write_kwargs – Kwargs for write()

DRVI.set_latent_dimension_stats(embed, adata=None, datamodule=None, vanished_threshold=0.5)#

Set the latent dimension statistics of a DRVI embedding into var of an AnnData.

Computes and stores various statistics for each latent dimension in the embedding AnnData object: reconstruction effects, ordering, and basic statistical measures (mean, std, min, max) for each dimension.

Parameters:

embed (AnnData) – AnnData object containing the latent representation (embedding) of the model. The latent dimensions should be in the .X attribute.
adata (AnnData | None (default: None)) – AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.
datamodule (LightningDataModule | None (default: None)) – LightningDataModule object with equivalent structure to initial AnnData. adata will be ignored if
vanished_threshold (float (default: 0.5)) – Threshold for determining if a latent dimension has “vanished” (become inactive). Dimensions with max absolute values below this threshold are marked as vanished.

Return type:

AnnData | None

Returns:

None

Notes

The following columns are added to embed.var:

original_dim_id: Original dimension indices
reconstruction_effect: Reconstruction effect scores from the DRVI model
order: Ranking of dimensions by reconstruction effect (descending)
max_value: Maximum absolute value across all cells for each dimension
mean: Mean value across all cells for each dimension
min: Minimum value across all cells for each dimension
max: Maximum value across all cells for each dimension
std: Standard deviation; std_abs: std of absolute values
title: Dimension titles in format “DR {order+1}”
vanished: Boolean indicating if dimension is “vanished” (max_value < threshold)
vanished_positive_direction: Dimension is “vanished” in the + direction if max < threshold.
vanished_negative_direction: Dimension is “vanished” in the - direction if min > -threshold.

Examples

>>> latent_adata = model.get_latent_representation(adata, return_anndata=True)
>>> model.set_latent_dimension_stats(latent_adata)
>>> print(latent_adata.var[["order", "reconstruction_effect", "vanished"]].head())

classmethod DRVI.setup_anndata(adata, layer=None, is_count_data=True, batch_key=None, labels_key=None, categorical_covariate_keys=None, continuous_covariate_keys=None, **kwargs)[source]#

Sets up the AnnData object for this model.

A mapping will be created between data fields used by this model to their respective locations in adata. None of the data in adata are modified. Only adds fields to adata.

Parameters:

adata (AnnData) – AnnData object. Rows represent cells, columns represent features.
labels_key (str | None (default: None)) – key in adata.obs for label information. Categories will automatically be converted into integer categories and saved to adata.obs['_scvi_labels']. If None, assigns the same label to all the data.
layer (str | None (default: None)) – if not None, uses this as the key in adata.layers for raw count data.
batch_key (str | None (default: None)) – key in adata.obs for batch information. Categories will automatically be converted into integer categories and saved to adata.obs['_scvi_batch']. If None, assigns the same batch to all the data.
categorical_covariate_keys (list[str] | None (default: None)) – keys in adata.obs that correspond to categorical data. These covariates can be added in addition to the batch covariate and are also treated as nuisance factors (i.e., the model tries to minimize their effects on the latent space). Thus, these should not be used for biologically-relevant factors that you do _not_ want to correct for.
continuous_covariate_keys (list[str] | None (default: None)) – keys in adata.obs that correspond to continuous data. These covariates can be added in addition to the batch covariate and are also treated as nuisance factors (i.e., the model tries to minimize their effects on the latent space). Thus, these should not be used for biologically-relevant factors that you do _not_ want to correct for.

Return type:

None

Returns:

None. Adds the following fields:

.uns[‘_scvi’]: scvi setup dictionary
.obs[‘_scvi_labels’]: labels encoded as integers
.obs[‘_scvi_batch’]: batch encoded as integers

DRVI.to_device(device)#

Move the model to the device.

Parameters:: device (str | int | device) – Device to move model to. Options: ‘cpu’ for CPU, integer GPU index (e.g., 0), ‘cuda:X’ where X is the GPU index (e.g. ‘cuda:0’), or a torch.device object (including XLA devices for TPU). See torch.device for more info.

Examples

>>> adata = scvi.data.synthetic_iid()
>>> model = scvi.model.SCVI(adata)
>>> model.to_device("cpu")  # moves model to CPU
>>> model.to_device("cuda:0")  # moves model to GPU 0
>>> model.to_device(0)  # also moves model to GPU 0

DRVI.train(max_epochs=None, accelerator='auto', devices='auto', train_size=None, validation_size=None, shuffle_set_split=True, load_sparse_tensor=False, batch_size=128, early_stopping=False, datasplitter_kwargs=None, plan_config=None, plan_kwargs=None, datamodule=None, trainer_config=None, **trainer_kwargs)#

Train the model.

Parameters:

max_epochs (int | None (default: None)) – The maximum number of epochs to train the model. The actual number of epochs may be less if early stopping is enabled. If None, defaults to a heuristic based on get_max_epochs_heuristic(). Must be passed in if datamodule is passed in, and it does not have an n_obs attribute.
accelerator (str (default: 'auto')) – Supports passing different accelerator types ("cpu", "gpu", "tpu", "ipu", "hpu", "mps, "auto") as well as custom accelerator instances.
devices (int | list[int] | str (default: 'auto')) – The devices to use. Can be set to a non-negative index (int or str), a sequence of device indices (list or comma-separated str), the value -1 to indicate all available devices, or "auto" for automatic selection based on the chosen accelerator. If set to "auto" and accelerator is not determined to be "cpu", then devices will be set to the first available device.
train_size (float | None (default: None)) – Float, or None. Size of training set in the range [0.0, 1.0]. The default is None, which is practically 0.9 and potentially adding a small last batch to validation cells. Passed into DataSplitter. Not used if datamodule is passed in.
validation_size (float | None (default: None)) – Size of the test set. If None, defaults to 1 - train_size. If train_size + validation_size < 1, the remaining cells belong to a test set. Passed into DataSplitter. Not used if datamodule is passed in.
shuffle_set_split (bool (default: True)) – Whether to shuffle indices before splitting. If False, the val, train, and test set are split in the sequential order of the data according to validation_size and train_size percentages. Passed into DataSplitter. Not used if datamodule is passed in.
load_sparse_tensor (bool (default: False)) – EXPERIMENTAL If True, loads data with sparse CSR or CSC layout as a Tensor with the same layout. Can lead to speedups in data transfers to GPUs, depending on the sparsity of the data. Passed into DataSplitter. Not used if datamodule is passed in.
batch_size (int (default: 128)) – Minibatch size to use during training. Passed into DataSplitter. Not used if datamodule is passed in.
early_stopping (bool (default: False)) – Perform early stopping. Additional arguments can be passed in through **kwargs. See Trainer for further options.
datasplitter_kwargs (dict | None (default: None)) – Additional keyword arguments passed into DataSplitter. Values in this argument can be overwritten by arguments directly passed into this method, when appropriate. Not used if datamodule is passed in.
plan_config (Mapping[str, Any] | KwargsConfig | None (default: None)) – Configuration object or mapping used to build TrainingPlan. Values in plan_kwargs and explicit arguments take precedence.
plan_kwargs (Mapping[str, Any] | KwargsConfig | None (default: None)) – Additional keyword arguments passed into TrainingPlan. Values in this argument can be overwritten by arguments directly passed into this method, when appropriate.
datamodule (LightningDataModule | None (default: None)) – EXPERIMENTAL A LightningDataModule instance to use for training in place of the default DataSplitter. Can only be passed in if the model was not initialized with AnnData.
trainer_config (Mapping[str, Any] | KwargsConfig | None (default: None)) – Configuration object or mapping used to build Trainer. Values in trainer_kwargs and explicit arguments take precedence.
**kwargs – Additional keyword arguments passed into Trainer.

DRVI.transfer_fields(adata, **kwargs)#

Transfer fields from a model to an AnnData object.

Return type:: AnnData

DRVI.update_setup_method_args(setup_method_args)#

Update setup method args.

Parameters:: setup_method_args (dict) – This is a bit of a misnomer, this is a dict representing kwargs of the setup method that will be used to update the existing values in the registry of this instance.

DRVI.view_anndata_setup(adata=None, hide_state_registries=False)#

Print summary of the setup for the initial AnnData or a given AnnData object.

Parameters:

adata (AnnData | MuData | None (default: None)) – AnnData object setup with setup_anndata or transfer_fields().
hide_state_registries (bool (default: False)) – If True, prints a shortened summary without details of each state registry.

Return type:

None

DRVI.view_registry(hide_state_registries=False)#

Prints summary of the registry.

Parameters:: hide_state_registries (bool (default: False)) – If True, prints a shortened summary without details of each state registry.
Return type:: None

static DRVI.view_setup_args(dir_path, prefix=None)#

Print args used to setup a saved model.

Parameters:

dir_path (str) – Path to saved outputs.
prefix (str | None (default: None)) – Prefix of saved file names.

Return type:

None

DRVI.view_setup_method_args()#

Prints setup kwargs used to produce a given registry.

Parameters:: registry – Registry produced by an AnnDataManager.
Return type:: None

drvi.model.DRVI

Contents

drvi.model.DRVI#

Attributes table#

Methods table#

Attributes#

Methods#