scvi.external.CYTOVI#

class scvi.external.CYTOVI(adata, n_hidden=128, n_latent=None, n_layers=1, dropout_rate=0.1, protein_likelihood='normal', latent_distribution='normal', encode_backbone_only=None, encoder_marker_list=None, prior_mixture=True, prior_mixture_k=None, **model_kwargs)[source]#

Variational inference for cytometry (CytoVI).

Parameters:
adata AnnData

AnnData object that has been registered via setup_anndata().

n_hidden int (default: 128)

Number of nodes per hidden layer.

n_latent int | None (default: None)

Dimensionality of the latent space. If None, will be set using a heuristic based on number of input features.

n_layers int (default: 1)

Number of hidden layers used for encoder and decoder NNs.

dropout_rate float (default: 0.1)

Dropout rate for neural networks.

protein_likelihood Literal['normal', 'beta'] (default: 'normal')

Likelihood function used for modeling protein expression. One of:

  • 'normal' - Normal distribution

  • 'beta' - Beta distribution (requires expression in (0, 1))

latent_distribution Literal['normal', 'ln'] (default: 'normal')

Distribution of the latent space. One of:

  • 'normal' - Normal distribution

  • 'ln' - Logistic normal distribution (Normal(0, I) transformed by softmax)

encode_backbone_only bool | None (default: None)

If True, only encode backbone markers (i.e., those present in all samples). This is required when analyzing overlapping panels with missing values.

encoder_marker_list list | None (default: None)

Optional list of markers to use for encoding. Must be a subset of backbone markers if encode_backbone_only is True.

prior_mixture bool | None (default: True)

If True, uses a mixture of Gaussians as a prior in the latent space (MoG prior).

prior_mixture_k int | None (default: None)

Number of mixture components in the MoG prior. Defaults to n_latent if None.

**model_kwargs

Keyword arguments passed to CytoVAE.

Examples

>>> adata = anndata.read_h5ad(path_to_anndata)
>>> scvi.external.CYTOVI.setup_anndata(adata, batch_key="batch")
>>> model = scvi.external.CYTOVI(adata)
>>> model.train()
>>> adata.obsm["X_CytoVI"] = model.get_latent_representation()
>>> adata.layers["imputed"] = model.get_normalized_expression()

Notes

When analyzing overlapping cytometry panels (i.e., samples with partially shared markers), CytoVI uses the shared “backbone” markers for encoding and reconstructs the full set. An adversarial classifier loss can be used to encourage batch-invariance in the latent space. If the data includes missing values, ensure that nan_layer is correctly registered using setup_anndata(). This is handled automatically when using scvi.external.cytovi.merge_batches().

See further usage examples in the following tutorials:

  1. Quick start tutorial for CytoVI

  2. Advanced Tutorial: Multi-Panel Integration and Downstream Analysis with CytoVI

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#

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.

deregister_manager([adata])

Deregisters the AnnDataManager instance associated with adata.

differential_abundance([adata, groupby, ...])

Compute differential abundance (DA) scores across experimental conditions.

differential_expression([adata, groupby, ...])

A unified method for differential expression analysis.

get_aggregated_posterior([adata, sample, ...])

Compute the aggregated posterior over the z latent representations.

get_anndata_manager(adata[, required])

Retrieves the AnnDataManager for a given AnnData object.

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_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) protein expression.

get_reconstruction_error([adata, indices, ...])

Compute the reconstruction error on the data.

get_sample_logprobs([adata, batch_size, ...])

Compute the differential abundance log probabilities for each sample.

get_setup_arg(setup_arg)

Returns the string provided to setup of a specific setup_arg.

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.

impute_categories_from_reference(...[, ...])

Impute missing categories from a reference dataset using a shared representation.

impute_rna_from_reference(reference_batch, ...)

Impute RNA expression in a query dataset using a reference and a shared representation.

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 [Lotfollahi et al., 2021].

load_registry(dir_path[, prefix])

Return the full registry saved with the model.

posterior_predictive_sample([adata, ...])

Generate observation 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.

setup_annbatch([collection_path, paths, ...])

Set up a model from on-disk AnnData files via the annbatch streaming loader.

setup_anndata(adata[, layer, batch_key, ...])

Sets up the AnnData object for this model.

to_device(device)

Move the model to the device.

train([max_epochs, lr, accelerator, ...])

Trains the model using amortized variational inference.

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#

CYTOVI.adata#

Data attached to model instance.

CYTOVI.adata_manager#

Manager instance associated with self.adata.

CYTOVI.device#

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

CYTOVI.get_normalized_function_name#

What the get normalized functions name is

CYTOVI.history#

Returns computed metrics during training.

CYTOVI.is_trained#

Whether the model has been trained.

CYTOVI.registry#

Data attached to model instance.

CYTOVI.run_id#

Returns the run id of the model. Used in MLFlow

CYTOVI.run_name#

Returns the run name of the model. Used in MLFlow

CYTOVI.summary_string#

Summary string of the model.

CYTOVI.test_indices#

Observations that are in test set.

CYTOVI.train_indices#

Observations that are in train set.

CYTOVI.validation_indices#

Observations that are in validation set.

Methods#

classmethod CYTOVI.convert_legacy_save(dir_path, output_dir_path, overwrite=False, prefix=None, **save_kwargs)[source]#

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

CYTOVI.data_registry(registry_key)[source]#

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.

CYTOVI.deregister_manager(adata=None)[source]#

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.

CYTOVI.differential_abundance(adata=None, groupby=None, batch_size=128, downsample_cells=None, dof=None, aggregation_fn=<function log_median>, return_log_probs=False)[source]#

Compute differential abundance (DA) scores across experimental conditions.

This function estimates differential abundance by comparing aggregated log-sample-probabilities between groups defined by groupby. The aggregation is performed using the specified aggregation_fn, typically log_median or logsumexp, across posterior sample log-probabilities.

Parameters:
adata anndata.AnnData | None (default: None)

AnnData object to use. If None, defaults to the model’s internal AnnData.

groupby str | None (default: None)

Key in adata.obs that contains condition or group labels. Each sample must have exactly one non-missing condition, and at least two conditions must be present. If not provided, returns log-probabilities per sample without aggregation.

batch_size int (default: 128)

Mini-batch size for computing log-probabilities. Default: 128.

downsample_cells int | None (default: None)

If provided, randomly subsample this many cells before computing log-probabilities.

dof float | None (default: None)

Degrees of freedom to use in the sampling distribution, if applicable.

aggregation_fn Callable[[ndarray], float] (default: <function log_median>)

Function used to aggregate log-probabilities across samples. Common choices include log_median or logsumexp. Default: log_median.

return_log_probs bool (default: False)

If True, skip aggregation and return per-sample log-probabilities directly. Default: False.

Return type:

DataFrame

Returns:

If return_log_probs=True or groupby=None, returns a DataFrame of

shape (n_cells, n_samples) containing log-sample-probabilities.

Otherwise, returns a DataFrame of shape (n_cells, n_conditions) where each column corresponds to the differential abundance log-ratio for one condition compared to all others.

Examples

>>> da_scores = model.differential_abundance(adata, groupby="condition")
>>> da_scores.head()
>>> log_probs = model.differential_abundance(adata, return_log_probs=True)
CYTOVI.differential_expression(adata=None, groupby=None, group1=None, group2=None, idx1=None, idx2=None, mode='change', test_mode='two', delta=0.25, batch_size=None, all_stats=False, batch_correction=False, batchid1=None, batchid2=None, fdr_target=0.05, silent=False, weights='uniform', filter_outlier_cells=False, lfc_clipping=True, clipping_range=(0, 1), balance_samples=None, importance_weighting_kwargs=None, **kwargs)[source]#

A unified method for differential expression analysis.

Implements 'vanilla' DE [Lopez et al., 2018] and 'change' mode DE [Boyeau et al., 2019].

Parameters:
adata anndata.AnnData | None (default: None)

Annotated data matrix, by default None

groupby str | None (default: None)

Key in adata.obs containing the groups, by default None

group1 list[str] | None (default: None)

List of group names for group 1, by default None

group2 list[str] | None (default: None)

List of group names for group 2, by default None

idx1 list[int] | list[bool] | str | None (default: None)

Indices or boolean mask for group 1, by default None

idx2 list[int] | list[bool] | str | None (default: None)

Indices or boolean mask for group 2, by default None

mode Literal['vanilla', 'change'] (default: 'change')

Differential expression mode, by default “change”

test_mode Literal['two', 'three'] (default: 'two')

Test mode for differential expression, by default “two”

delta float (default: 0.25)

Minimum fold change for differential expression, by default 0.25

batch_size int | None (default: None)

Batch size for computation, by default None

all_stats bool (default: False)

Whether to compute all statistics, by default False

batch_correction bool (default: False)

Whether to perform batch correction, by default False

batchid1 list[str] | None (default: None)

List of batch IDs for group 1, by default None

batchid2 list[str] | None (default: None)

List of batch IDs for group 2, by default None

fdr_target float (default: 0.05)

Target false discovery rate, by default 0.05

silent bool (default: False)

Whether to suppress progress bar and messages, by default False

weights Literal['uniform', 'importance'] | None (default: 'uniform')

Weights to use for sampling, by default “uniform”

filter_outlier_cells bool (default: False)

Whether to filter outlier cells, by default False

lfc_clipping bool (default: True)

Whether to clip log fold change values, by default True

clipping_range tuple (default: (0, 1))

Range for clipping log fold change values, by default (0, 1)

balance_samples bool | None (default: None)

Whether to subsample equal amount of cells per sample based on sample_key. If None, defaults to True if more than one sample is present in the data.

importance_weighting_kwargs dict | None (default: None)

Keyword arguments for importance weighting, by default None

**kwargs

Additional keyword arguments for differential expression computation

Return type:

DataFrame

Returns:

Differential expression DataFrame.

CYTOVI.get_aggregated_posterior(adata=None, sample=None, indices=None, batch_size=None, dof=3.0)[source]#

Compute the aggregated posterior over the z latent representations.

Parameters:
adata AnnData (default: None)

AnnData object to use. Defaults to the AnnData object used to initialize the model.

sample int | str (default: None)

Name or index of the sample to filter on. If None, uses all cells.

indices Sequence[int] (default: None)

Indices of cells to use.

batch_size int (default: None)

Batch size to use for computing the latent representation.

dof float | None (default: 3.0)

Degrees of freedom for the Student’s t-distribution components. If None, components are Normal.

Return type:

Distribution

Returns:

A mixture distribution of the aggregated posterior.

CYTOVI.get_anndata_manager(adata, required=False)[source]#

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

CYTOVI.get_elbo(adata=None, indices=None, batch_size=None, dataloader=None, return_mean=True, data_loader_kwargs=None, **kwargs)[source]#

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.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, torch.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.

CYTOVI.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)[source]#

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

Parameters:
adata anndata.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”.

silent bool (default: True)

If True, disables the progress bar. Default: False.

Return type:

DataFrame

Returns:

Gene-gene correlation matrix

CYTOVI.get_from_registry(adata, registry_key)[source]#

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.

CYTOVI.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)[source]#

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.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 [Ionides, 2008]. 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.

CYTOVI.get_latent_library_size(adata=None, indices=None, give_mean=True, batch_size=None, dataloader=None, **data_loader_kwargs)[source]#

Returns the latent library size for each cell.

This is denoted as \(\ell_n\) in the scVI paper.

Parameters:
adata anndata.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, torch.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

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

Compute the latent representation of the data.

This is typically denoted as \(z_n\).

Parameters:
adata anndata.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, torch.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[NDArray, NDArray]

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.

CYTOVI.get_likelihood_parameters(adata=None, indices=None, n_samples=1, give_mean=False, batch_size=None, dataloader=None, **data_loader_kwargs)[source]#

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

Parameters:
adata anndata.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, torch.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]

CYTOVI.get_marginal_ll(adata=None, indices=None, n_mc_samples=1000, batch_size=None, return_mean=True, dataloader=None, data_loader_kwargs=None, **kwargs)[source]#

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.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, torch.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 | torch.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.

CYTOVI.get_normalized_expression(adata=None, indices=None, transform_batch='all', protein_list=None, n_samples=1, n_samples_overall=None, weights=None, batch_size=None, return_mean=True, return_numpy=None, nan_warning=True, **importance_weighting_kwargs)[source]#

Returns the normalized (decoded) protein expression.

The model’s reconstructed (normalized) expression is written as :math:hat{x} = p(x mid z).

Parameters:
adata anndata.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 Sequence[int] | None (default: None)

Indices of cells in adata to use. If None, all cells are used.

transform_batch Sequence[int | float | str] | None (default: 'all')

Batch to condition on. If transform_batch is: - ‘all’, then the mean across batches is used - None, then real observed batch is used. - int, then batch transform_batch is used. This behaviour affects only proteins that are detected across multiple batches. Unobserved proteins are decoded in the batch(es), in which they were measured.

protein_list Sequence[str] | None (default: None)

Return frequencies of expression for a subset of protein. This can save memory when working with large datasets and few proteins are of interest.

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.

nan_warning bool | None (default: True)

Whether to show a warning if missing proteins are detected between batches.

**importance_weighting_kwargs

Additional keyword arguments for importance weighting.

Return type:

ndarray | DataFrame

Returns:

If n_samples > 1 and return_mean is False, then the shape is (samples, cells, genes). Otherwise, shape is (cells, genes). In this case, return type is DataFrame unless return_numpy is True.

CYTOVI.get_reconstruction_error(adata=None, indices=None, batch_size=None, dataloader=None, return_mean=True, data_loader_kwargs=None, **kwargs)[source]#

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.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, torch.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.

CYTOVI.get_sample_logprobs(adata=None, batch_size=128, downsample_cells=None, dof=None)[source]#

Compute the differential abundance log probabilities for each sample.

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

Parameters:
adata anndata.AnnData | None (default: None)

The data object to compute the differential abundance for.

batch_size int (default: 128)

Minibatch size for computing the differential abundance.

downsample_cells int | None (default: None)

Number of cells to subset to before computing the differential abundance.

dof float | None (default: None)

Degrees of freedom for the Student’s t-distribution components for aggregated posterior. If None, components are Normal.

Return type:

DataFrame

Returns:

DataFrame of shape (n_cells, n_samples) containing the log probabilities for each cell across samples. The rows correspond to cell names from adata.obs_names, and the columns correspond to unique sample identifiers.

CYTOVI.get_setup_arg(setup_arg)[source]#

Returns the string provided to setup of a specific setup_arg.

Return type:

attrdict

CYTOVI.get_state_registry(registry_key)[source]#

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

Return type:

attrdict

CYTOVI.get_var_names(legacy_mudata_format=False)[source]#

Variable names of input data.

Return type:

dict

CYTOVI.impute_categories_from_reference(adata_reference, cat_key, use_rep=None, n_neighbors=20, return_uncertainty=False)[source]#

Impute missing categories from a reference dataset using a shared representation.

Parameters:
adata_reference AnnData

Annotated data matrix for the reference dataset. This dataset contains the categories to be imputed onto the query data.

cat_key str

The key in the .obs attribute of adata_reference that specifies the categorical variable (e.g., cell types or clusters) to impute.

use_rep str | None (default: None)

The key in the .obsm attribute to use as the representation space (e.g., latent space). If None, the function will attempt to use a default latent representation X_CytoVI.

n_neighbors int (default: 20)

The number of nearest neighbors to use for imputation. The imputation is based on similarity in the chosen representation space. Default: 20.

return_uncertainty bool (default: False)

If True, the function will also return the uncertainty of the imputation. Default: False.

Returns:

Array of imputed categories for the query dataset, corresponding to the categorical variable specified by cat_key.

Notes

This function assumes that both the query and reference datasets have a precomputed representation in .obsm (typically CytoVI latent space). If not, you must either provide a common representation manually or ensure that one is generated.

CYTOVI.impute_rna_from_reference(reference_batch, adata_rna, layer_key, use_rep=None, n_neighbors=20, compute_uncertainty=False, return_query_only=False)[source]#

Impute RNA expression in a query dataset using a reference and a shared representation.

Parameters:
reference_batch str

Identifier for the reference batch in adata.obs[batch_key].

adata_rna AnnData

Annotated data matrix containing the expression data to impute.

layer_key str

Key in adata_rna.layers for the reference expression data.

use_rep str | None (default: None)

Key in .obsm to use as the representation space (e.g., latent space). If None, defaults to X_CytoVI.

n_neighbors int (default: 20)

Number of nearest neighbors to use for imputation. Default: 20.

compute_uncertainty bool (default: False)

If True, also computes the uncertainty of the imputation. Default: False.

return_query_only bool (default: False)

If True, return only the imputed query dataset as an AnnData object. Default: False.

Returns:

Imputed AnnData object. If return_query_only is True, only the query dataset is returned. If compute_uncertainty is True, an uncertainty matrix is also returned.

classmethod CYTOVI.load(dir_path, adata=None, accelerator='auto', device='auto', prefix=None, backup_url=None, datamodule=None, allowed_classes_names_list=None)[source]#

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 CYTOVI.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_expression=True, freeze_decoder_first_layer=True, freeze_batchnorm_encoder=True, freeze_batchnorm_decoder=False, freeze_classifier=True, transfer_batch=True, datamodule=None)[source]#

Online update of a reference model with scArches algorithm [Lotfollahi et al., 2021].

Parameters:
adata AnnData | MuData (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 the reference model.

inplace_subset_query_vars bool (default: False)

Whether to subset and rearrange query vars inplace based on vars used to train the reference model.

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.

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_expression bool (default: True)

Freeze neurons corresponding to expression in first layer

freeze_decoder_first_layer bool (default: True)

Freeze neurons corresponding to first layer in decoder

freeze_batchnorm_encoder bool (default: True)

Whether to freeze batchnorm weight and bias during training for encoder

freeze_batchnorm_decoder bool (default: False)

Whether to freeze batchnorm weight and bias during training for decoder

freeze_classifier bool (default: True)

Whether to freeze classifier completely. Only applies to SCANVI.

transfer_batch bool (default: True)

Allow for surgery on the batch covariate. Only applies to SYSVI.

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.

static CYTOVI.load_registry(dir_path, prefix=None)[source]#

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

CYTOVI.posterior_predictive_sample(adata=None, indices=None, n_samples=1, protein_list=None, batch_size=None)[source]#

Generate observation samples from the posterior predictive distribution.

The posterior predictive distribution is written as \(p(\hat{x} \mid x)\).

Parameters:
adata anndata.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 Sequence[int] | None (default: None)

Indices of cells in adata to use. If None, all cells are used.

n_samples int (default: 1)

Number of samples for each cell.

protein_list Sequence[str] | None (default: None)

Names of proteins of interest.

batch_size int | None (default: None)

Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.

Returns:

x_new : torch.Tensor Tensor with shape (n_cells, n_proteins, n_samples)

static CYTOVI.prepare_query_anndata(adata, reference_model, return_reference_var_names=False, inplace=True)[source]#

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.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 CYTOVI.prepare_query_mudata(mdata, reference_model, return_reference_var_names=False, inplace=True)[source]#

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 CYTOVI.register_manager(adata_manager)[source]#

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.

CYTOVI.save(dir_path, prefix=None, overwrite=False, save_anndata=False, save_kwargs=None, legacy_mudata_format=False, datamodule=None, **anndata_write_kwargs)[source]#

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()

classmethod CYTOVI.setup_annbatch(collection_path=None, paths=None, batch_key=None, labels_key=None, sample_key=None, unlabeled_category='Unknown', layer=None, categorical_covariate_keys=None, continuous_covariate_keys=None, rebuild=True, batch_size=4096, chunk_size=256, preload_nchunks=32, preload_to_gpu=True, dataset_size='20GB', shuffle=False, var_subset=None, merge=None, adatas=None, use_class_sampler=False, class_sampler_key=None, class_weights=None)[source]#

Set up a model from on-disk AnnData files via the annbatch streaming loader.

Builds (or reuses) a zarr-backed DatasetCollection from the supplied h5ad file paths, then wraps it in a AnnbatchDataModule ready for training.

Parameters:
collection_path str | None (default: None)

Directory where the zarr collection is written (or already exists). If None (default), a path is auto-generated as "./{ModelName}_annbatch.zarr" in the current working directory.

paths list[str] | None (default: None)

Paths to h5ad files that make up the training dataset. If None, an existing collection at collection_path is opened without rebuilding — useful when the zarr store was created by a previous call. Must be provided when the store does not exist yet.

batch_key str | None (default: None)

Column in obs to use as the batch variable.

labels_key str | None (default: None)

Column in obs to use as the cell-type / label variable.

sample_key str | None (default: None)

Column in obs to use as the sample variable. Used by models like MrVI.

unlabeled_category str (default: 'Unknown')

Value used to mark unlabeled cells in labels_key. Required by semi-supervised models such as SCANVI. Defaults to "Unknown".

layer str | None (default: None)

Layer in the h5ad files to use as the count matrix. None uses adata.X (falling back to adata.raw.X when a raw slot exists).

categorical_covariate_keys list[str] | None (default: None)

Additional categorical covariate columns in obs.

continuous_covariate_keys list[str] | None (default: None)

Additional continuous covariate columns in obs.

rebuild bool (default: True)

If True, always rebuild the zarr collection even if it already exists on disk. If False (default), reuse an existing collection and skip the (potentially expensive) add_adatas step.

batch_size int (default: 4096)

Number of cells per batch yielded by the Loader.

chunk_size int (default: 256)

Number of cells loaded from disk contiguously per read.

preload_nchunks int (default: 32)

Number of chunks to preload and shuffle in memory.

preload_to_gpu bool (default: True)

Whether the loader should move data to GPU before yielding.

dataset_size int | str (default: '20GB')

Number of observations to load into memory for shuffling / pre-processing when building the collection, or annbatch’s human-readable size strings, e.g. "20GB".

shuffle bool (default: False)

Whether to pre-shuffle cells when building the collection.

var_subset list[str] | None (default: None)

Optional list of gene names to restrict the collection to (passed as var_subset to add_adatas).

merge Literal['same', 'unique', 'first', 'only'] | None (default: None)

How annbatch should merge var metadata across inputs. Passed through to annbatch.DatasetCollection.add_adatas().

Returns:

AnnbatchDataModule A configured datamodule whose registry can be passed directly to the model constructor, e.g. model = SCVI(registry=dm.registry).

Notes

After training, saving and reloading the model requires reconstructing the datamodule manually and passing it to load() via the datamodule argument — the same pattern used by all custom datamodules.

classmethod CYTOVI.setup_anndata(adata, layer=None, batch_key=None, labels_key=None, sample_key=None, categorical_covariate_keys=None, continuous_covariate_keys=None, nan_layer=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.

layer str | None (default: None)

if not None, uses this as the key in adata.layers for the transformed protein expression 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.

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.

sample_key str | None (default: None)

key in adata.obs for sample information. Categories will automatically be converted into integer categories and saved to adata.obs['_scvi_sample']. If None, assigns the same sample 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.

nan_layer str | None (default: None)

Optional layer key containing binary NaN feature mask to handle overlapping antibody panels.

CYTOVI.to_device(device)[source]#

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
CYTOVI.train(max_epochs=1000, lr=0.001, accelerator='auto', devices='auto', train_size=0.9, validation_size=None, batch_size=128, early_stopping=True, check_val_every_n_epoch=None, n_steps_kl_warmup=None, n_epochs_kl_warmup=400, adversarial_classifier=None, plan_kwargs=None, early_stopping_patience=30, **kwargs)[source]#

Trains the model using amortized variational inference.

Parameters:
max_epochs int | None (default: 1000)

Number of passes through the dataset, by default 1000.

lr float (default: 0.001)

Learning rate for optimization, by default 1e-3.

accelerator str (default: 'auto')

Accelerator to use for training, by default “auto”.

devices int | list[int] | str (default: 'auto')

Devices to use for training, by default “auto”.

train_size float (default: 0.9)

Size of the training set in the range [0.0, 1.0], by default 0.9.

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.

batch_size int (default: 128)

Minibatch size to use during training, by default 128.

early_stopping bool (default: True)

Whether to perform early stopping with respect to the validation set, by default True.

check_val_every_n_epoch int | None (default: None)

Check validation set every n train epochs. By default, the validation set is not checked, unless early_stopping is True or reduce_lr_on_plateau is True. If either of the latter conditions are met, the validation set is checked every epoch.

n_steps_kl_warmup int | None (default: None)

Number of training steps (minibatches) to scale weight on KL divergences from 0 to 1. Only activated when n_epochs_kl_warmup is set to None. If None, defaults to floor(0.75 * adata.n_obs).

n_epochs_kl_warmup int | None (default: 400)

Number of epochs to scale weight on KL divergences from 0 to 1. Overrides n_steps_kl_warmup when both are not None, by default 400.

adversarial_classifier bool | None (default: None)

Whether to use an adversarial classifier in the latent space. This helps mixing when there are missing proteins in any of the batches. Defaults to True if missing proteins are detected.

plan_kwargs dict | None (default: None)

Keyword arguments for the AdversarialTrainingPlan class. Keyword arguments passed to train() will overwrite values present in plan_kwargs, when appropriate.

early_stopping_patience int | None (default: 30)

Number of epochs to wait before early stopping, by default 30.

**kwargs

Other keyword arguments for the Trainer class.

Returns:

-runner (object) The runner object used for training.

CYTOVI.transfer_fields(adata, **kwargs)[source]#

Transfer fields from a model to an AnnData object.

Return type:

AnnData

CYTOVI.update_setup_method_args(setup_method_args)[source]#

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.

CYTOVI.view_anndata_setup(adata=None, hide_state_registries=False)[source]#

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

CYTOVI.view_registry(hide_state_registries=False)[source]#

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 CYTOVI.view_setup_args(dir_path, prefix=None)[source]#

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

CYTOVI.view_setup_method_args()[source]#

Prints setup kwargs used to produce a given registry.

Parameters:
registry

Registry produced by an AnnDataManager.

Return type:

None