scvi.model.TOTALVI#

class scvi.model.TOTALVI(adata, n_latent=20, gene_dispersion='gene', protein_dispersion='protein', gene_likelihood='nb', latent_distribution='normal', empirical_protein_background_prior=None, override_missing_proteins=False, **model_kwargs)[source]#

total Variational Inference [GayosoSteier21].

Parameters
adata : AnnData

AnnData object that has been registered via setup_anndata().

n_latent : int (default: 20)

Dimensionality of the latent space.

gene_dispersion : {‘gene’, ‘gene-batch’, ‘gene-label’, ‘gene-cell’}Literal[‘gene’, ‘gene-batch’, ‘gene-label’, ‘gene-cell’] (default: 'gene')

One of the following:

  • 'gene' - genes_dispersion parameter of NB is constant per gene across cells

  • 'gene-batch' - genes_dispersion can differ between different batches

  • 'gene-label' - genes_dispersion can differ between different labels

protein_dispersion : {‘protein’, ‘protein-batch’, ‘protein-label’}Literal[‘protein’, ‘protein-batch’, ‘protein-label’] (default: 'protein')

One of the following:

  • 'protein' - protein_dispersion parameter is constant per protein across cells

  • 'protein-batch' - protein_dispersion can differ between different batches NOT TESTED

  • 'protein-label' - protein_dispersion can differ between different labels NOT TESTED

gene_likelihood : {‘zinb’, ‘nb’}Literal[‘zinb’, ‘nb’] (default: 'nb')

One of:

  • 'nb' - Negative binomial distribution

  • 'zinb' - Zero-inflated negative binomial distribution

latent_distribution : {‘normal’, ‘ln’}Literal[‘normal’, ‘ln’] (default: 'normal')

One of:

  • 'normal' - Normal distribution

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

empirical_protein_background_prior : bool | NoneOptional[bool] (default: None)

Set the initialization of protein background prior empirically. This option fits a GMM for each of 100 cells per batch and averages the distributions. Note that even with this option set to True, this only initializes a parameter that is learned during inference. If False, randomly initializes. The default (None), sets this to True if greater than 10 proteins are used.

override_missing_proteins : bool (default: False)

If True, will not treat proteins with all 0 expression in a particular batch as missing.

**model_kwargs

Keyword args for TOTALVAE

Examples

>>> adata = anndata.read_h5ad(path_to_anndata)
>>> scvi.model.TOTALVI.setup_anndata(adata, batch_key="batch", protein_expression_obsm_key="protein_expression")
>>> vae = scvi.model.TOTALVI(adata)
>>> vae.train()
>>> adata.obsm["X_totalVI"] = vae.get_latent_representation()

Notes

See further usage examples in the following tutorials:

  1. CITE-seq analysis with totalVI

  2. Integration of CITE-seq and scRNA-seq data

  3. Reference mapping with scvi-tools

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.

history

Returns computed metrics during training.

is_trained

Whether the model has been trained.

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#

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

A unified method for differential expression analysis.

get_anndata_manager(adata[, required])

Retrieves the AnnDataManager for a given AnnData object specific to this model instance.

get_elbo([adata, indices, batch_size])

Return the ELBO for 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_latent_library_size([adata, indices, ...])

Returns the latent library size for each cell.

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

Return the latent representation for each cell.

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

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

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

Return the marginal LL for the data.

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

Returns the normalized gene expression and protein expression.

get_protein_background_mean(adata, indices, ...)

get_protein_foreground_probability([adata, ...])

Returns the foreground probability for proteins.

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

Return the reconstruction error for the data.

load(dir_path[, adata, use_gpu, prefix])

Instantiate a model from the saved output.

load_query_data(adata, reference_model[, ...])

Online update of a reference model with scArches algorithm [Lotfollahi21].

posterior_predictive_sample([adata, ...])

Generate observation samples from the posterior predictive distribution.

prepare_query_anndata(adata, reference_model)

Prepare data for query integration.

register_manager(adata_manager)

Registers an AnnDataManager instance with this model class.

save(dir_path[, prefix, overwrite, save_anndata])

Save the state of the model.

setup_anndata(adata, protein_expression_obsm_key)

Sets up the AnnData object for this model.

to_device(device)

Move model to device.

train([max_epochs, lr, use_gpu, train_size, ...])

Trains the model using amortized variational inference.

view_anndata_setup([adata, ...])

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

view_setup_args(dir_path[, prefix])

Print args used to setup a saved model.

Attributes#

adata#

TOTALVI.adata#

Data attached to model instance.

Return type

AnnData

adata_manager#

TOTALVI.adata_manager#

Manager instance associated with self.adata.

Return type

AnnDataManager

device#

TOTALVI.device#

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

Return type

str

history#

TOTALVI.history#

Returns computed metrics during training.

is_trained#

TOTALVI.is_trained#

Whether the model has been trained.

Return type

bool

test_indices#

TOTALVI.test_indices#

Observations that are in test set.

Return type

ndarray

train_indices#

TOTALVI.train_indices#

Observations that are in train set.

Return type

ndarray

validation_indices#

TOTALVI.validation_indices#

Observations that are in validation set.

Return type

ndarray

Methods#

differential_expression#

TOTALVI.differential_expression(adata=None, groupby=None, group1=None, group2=None, idx1=None, idx2=None, mode='change', delta=0.25, batch_size=None, all_stats=True, batch_correction=False, batchid1=None, batchid2=None, fdr_target=0.05, silent=False, protein_prior_count=0.1, scale_protein=False, sample_protein_mixing=False, include_protein_background=False, **kwargs)[source]#

A unified method for differential expression analysis.

Implements “vanilla” DE [Lopez18] and “change” mode DE [Boyeau19].

Parameters
adata : AnnData | NoneOptional[AnnData] (default: None)

AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.

groupby : str | NoneOptional[str] (default: None)

The key of the observations grouping to consider.

group1 : Iterable[str] | NoneOptional[Iterable[str]] (default: None)

Subset of groups, e.g. [‘g1’, ‘g2’, ‘g3’], to which comparison shall be restricted, or all groups in groupby (default).

group2 : str | NoneOptional[str] (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 : Sequence[int] | Sequence[bool] | str | NoneUnion[Sequence[int], Sequence[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 : Sequence[int] | Sequence[bool] | str | NoneUnion[Sequence[int], Sequence[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 : {‘vanilla’, ‘change’}Literal[‘vanilla’, ‘change’] (default: 'change')

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 | NoneOptional[int] (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 : Iterable[str] | NoneOptional[Iterable[str]] (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 : Iterable[str] | NoneOptional[Iterable[str]] (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.

protein_prior_count : float (default: 0.1)

Prior count added to protein expression before LFC computation

scale_protein : bool (default: False)

Force protein values to sum to one in every single cell (post-hoc normalization)

sample_protein_mixing : bool (default: False)

Sample the protein mixture component, i.e., use the parameter to sample a Bernoulli that determines if expression is from foreground/background.

include_protein_background : bool (default: False)

Include the protein background component as part of the protein expression

**kwargs

Keyword args for scvi.model.base.DifferentialComputation.get_bayes_factors()

Return type

DataFrame

Returns

Differential expression DataFrame.

get_anndata_manager#

TOTALVI.get_anndata_manager(adata, required=False)#

Retrieves the AnnDataManager for a given AnnData object specific to this model instance.

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

Parameters
adata : AnnData

AnnData object to find manager instance for.

required : bool (default: False)

If True, errors on missing manager. Otherwise, returns None when manager is missing.

Return type

AnnDataManager | NoneOptional[AnnDataManager]

get_elbo#

TOTALVI.get_elbo(adata=None, indices=None, batch_size=None)#

Return the ELBO for the data.

The ELBO is a lower bound on the log likelihood of the data used for optimization of VAEs. Note, this is not the negative ELBO, higher is better.

Parameters
adata : AnnData | NoneOptional[AnnData] (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] | NoneOptional[Sequence[int]] (default: None)

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

batch_size : int | NoneOptional[int] (default: None)

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

Return type

float

get_feature_correlation_matrix#

TOTALVI.get_feature_correlation_matrix(adata=None, indices=None, n_samples=10, batch_size=64, rna_size_factor=1000, transform_batch=None, correlation_type='spearman', log_transform=False)[source]#

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

Parameters
adata

AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.

indices

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 : Sequence[Union[TypeVar`(``Number`, int, float), str]] | NoneOptional[Sequence[Union[TypeVar`(``Number`, int, float), str]]] (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 : {‘spearman’, ‘pearson’}Literal[‘spearman’, ‘pearson’] (default: 'spearman')

One of “pearson”, “spearman”.

log_transform : bool (default: False)

Whether to log transform denoised values prior to correlation calculation.

Return type

DataFrame

Returns

Gene-protein-gene-protein correlation matrix

get_from_registry#

TOTALVI.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 data registry.

adata : AnnData

AnnData to pull data from.

Return type

ndarray

Returns

The requested data as a NumPy array.

get_latent_library_size#

TOTALVI.get_latent_library_size(adata=None, indices=None, give_mean=True, batch_size=None)[source]#

Returns the latent library size for each cell.

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

Parameters
adata : AnnData | NoneOptional[AnnData] (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] | NoneOptional[Sequence[int]] (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 | NoneOptional[int] (default: None)

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

Return type

ndarray

get_latent_representation#

TOTALVI.get_latent_representation(adata=None, indices=None, give_mean=True, mc_samples=5000, batch_size=None)#

Return the latent representation for each cell.

This is denoted as \(z_n\) in our manuscripts.

Parameters
adata : AnnData | NoneOptional[AnnData] (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] | NoneOptional[Sequence[int]] (default: None)

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

give_mean : bool (default: True)

Give mean of distribution or sample from it.

mc_samples : int (default: 5000)

For distributions with no closed-form mean (e.g., logistic normal), how many Monte Carlo samples to take for computing mean.

batch_size : int | NoneOptional[int] (default: None)

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

Return type

ndarray

Returns

-latent_representation (ndarray) Low-dimensional representation for each cell

get_likelihood_parameters#

TOTALVI.get_likelihood_parameters(adata=None, indices=None, n_samples=1, give_mean=False, batch_size=None)[source]#

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

Parameters
adata : AnnData | NoneOptional[AnnData] (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] | NoneOptional[Sequence[int]] (default: None)

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

n_samples : int | NoneOptional[int] (default: 1)

Number of posterior samples to use for estimation.

give_mean : bool | NoneOptional[bool] (default: False)

Return expected value of parameters or a samples

batch_size : int | NoneOptional[int] (default: None)

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

Return type

{str: ndarray}Dict[str, ndarray]

get_marginal_ll#

TOTALVI.get_marginal_ll(adata=None, indices=None, n_mc_samples=1000, batch_size=None)#

Return the marginal LL for the data.

The computation here is a biased estimator of the marginal log likelihood of the data. Note, this is not the negative log likelihood, higher is better.

Parameters
adata : AnnData | NoneOptional[AnnData] (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] | NoneOptional[Sequence[int]] (default: None)

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

n_mc_samples : int (default: 1000)

Number of Monte Carlo samples to use for marginal LL estimation.

batch_size : int | NoneOptional[int] (default: None)

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

Return type

float

get_normalized_expression#

TOTALVI.get_normalized_expression(adata=None, indices=None, n_samples_overall=None, transform_batch=None, gene_list=None, protein_list=None, library_size=1, n_samples=1, sample_protein_mixing=False, scale_protein=False, include_protein_background=False, batch_size=None, return_mean=True, return_numpy=None)[source]#

Returns the normalized gene expression and protein expression.

This is denoted as \(\rho_n\) in the totalVI paper for genes, and TODO for proteins, \((1-\pi_{nt})\alpha_{nt}\beta_{nt}\).

Parameters
adata

AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.

indices

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

n_samples_overall : int | NoneOptional[int] (default: None)

Number of samples to use in total

transform_batch : Sequence[Union[TypeVar`(``Number`, int, float), str]] | NoneOptional[Sequence[Union[TypeVar`(``Number`, int, float), str]]] (default: None)

Batch to condition on. If transform_batch is:

  • None, then real observed batch is used

  • int, then batch transform_batch is used

  • List[int], then average over batches in list

gene_list : Sequence[str] | NoneOptional[Sequence[str]] (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.

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

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

library_size : float | {‘latent’} | NoneUnion[float, Literal[‘latent’], None] (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.

n_samples : int (default: 1)

Get sample scale from multiple samples.

sample_protein_mixing : bool (default: False)

Sample mixing bernoulli, setting background to zero

scale_protein : bool (default: False)

Make protein expression sum to 1

include_protein_background : bool (default: False)

Include background component for protein expression

batch_size : int | NoneOptional[int] (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 | NoneOptional[bool] (default: None)

Return a np.ndarray instead of a pd.DataFrame. Includes gene names as columns. If either n_samples=1 or return_mean=True, defaults to False. Otherwise, it defaults to True.

Return type

Tuple[Union[ndarray, DataFrame], Union[ndarray, DataFrame]]

Returns

  • gene_normalized_expression - normalized expression for RNA

  • protein_normalized_expression - normalized expression for proteins

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

get_protein_background_mean#

TOTALVI.get_protein_background_mean(adata, indices, batch_size)[source]#

get_protein_foreground_probability#

TOTALVI.get_protein_foreground_probability(adata=None, indices=None, transform_batch=None, protein_list=None, n_samples=1, batch_size=None, return_mean=True, return_numpy=None)[source]#

Returns the foreground probability for proteins.

This is denoted as \((1 - \pi_{nt})\) in the totalVI paper.

Parameters
adata : AnnData | NoneOptional[AnnData] (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] | NoneOptional[Sequence[int]] (default: None)

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

transform_batch : Sequence[Union[TypeVar`(``Number`, int, float), str]] | NoneOptional[Sequence[Union[TypeVar`(``Number`, int, float), str]]] (default: None)

Batch to condition on. If transform_batch is:

  • None, then real observed batch is used

  • int, then batch transform_batch is used

  • List[int], then average over batches in list

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

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

n_samples : int (default: 1)

Number of posterior samples to use for estimation.

batch_size : int | NoneOptional[int] (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 | NoneOptional[bool] (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.

Returns

  • foreground_probability - probability foreground for each protein

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.

get_reconstruction_error#

TOTALVI.get_reconstruction_error(adata=None, indices=None, batch_size=None)#

Return the reconstruction error for the data.

This is typically written as \(p(x \mid z)\), the likelihood term given one posterior sample. Note, this is not the negative likelihood, higher is better.

Parameters
adata : AnnData | NoneOptional[AnnData] (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] | NoneOptional[Sequence[int]] (default: None)

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

batch_size : int | NoneOptional[int] (default: None)

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

Return type

float | {str: float}Union[float, Dict[str, float]]

load#

classmethod TOTALVI.load(dir_path, adata=None, use_gpu=None, prefix=None)#

Instantiate a model from the saved output.

Parameters
dir_path : str

Path to saved outputs.

adata : AnnData | NoneOptional[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 saved scvi setup dictionary. If None, will check for and load anndata saved with the model.

use_gpu : str | int | bool | NoneUnion[str, int, bool, None] (default: None)

Load model on default GPU if available (if None or True), or index of GPU to use (if int), or name of GPU (if str), or use CPU (if False).

prefix : str | NoneOptional[str] (default: None)

Prefix of saved file names.

Returns

Model with loaded state dictionaries.

Examples

>>> model = ModelClass.load(save_path, adata) # use the name of the model class used to save
>>> model.get_....

load_query_data#

classmethod TOTALVI.load_query_data(adata, reference_model, inplace_subset_query_vars=False, use_gpu=None, unfrozen=False, freeze_dropout=False, freeze_expression=True, freeze_decoder_first_layer=True, freeze_batchnorm_encoder=True, freeze_batchnorm_decoder=False, freeze_classifier=True)#

Online update of a reference model with scArches algorithm [Lotfollahi21].

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 | BaseModelClassUnion[str, BaseModelClass]

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.

use_gpu : str | int | bool | NoneUnion[str, int, bool, None] (default: None)

Load model on default GPU if available (if None or True), or index of GPU to use (if int), or name of GPU (if str), or use CPU (if False).

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 corersponding to expression in first layer

freeze_decoder_first_layer : bool (default: True)

Freeze neurons corersponding 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.

posterior_predictive_sample#

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

Generate observation samples from the posterior predictive distribution.

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

Parameters
adata : AnnData | NoneOptional[AnnData] (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] | NoneOptional[Sequence[int]] (default: None)

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

n_samples : int (default: 1)

Number of required samples for each cell

batch_size : int | NoneOptional[int] (default: None)

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

gene_list : Sequence[str] | NoneOptional[Sequence[str]] (default: None)

Names of genes of interest

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

Names of proteins of interest

Return type

ndarray

Returns

x_new : ndarray tensor with shape (n_cells, n_genes, n_samples)

prepare_query_anndata#

static TOTALVI.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 | BaseModelClassUnion[str, BaseModelClass]

Either an already instantiated model of the same class, or a path to saved outputs for 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 | NoneUnion[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.

register_manager#

classmethod TOTALVI.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.

save#

TOTALVI.save(dir_path, prefix=None, overwrite=False, save_anndata=False, **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 | NoneOptional[str] (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, error will be raised.

save_anndata : bool (default: False)

If True, also saves the anndata

anndata_write_kwargs

Kwargs for write()

setup_anndata#

classmethod TOTALVI.setup_anndata(adata, protein_expression_obsm_key, protein_names_uns_key=None, batch_key=None, layer=None, size_factor_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 containing raw counts. Rows represent cells, columns represent features.

protein_expression_obsm_key

key in adata.obsm for protein expression data.

protein_names_uns_key

key in adata.uns for protein names. If None, will use the column names of adata.obsm[protein_expression_obsm_key] if it is a DataFrame, else will assign sequential names to proteins. batch_key

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.

layer

if not None, uses this as the key in adata.layers for raw count data.

size_factor_key

key in adata.obs for size factor information. Instead of using library size as a size factor, the provided size factor column will be used as offset in the mean of the likelihood. Assumed to be on linear scale.

categorical_covariate_keys

keys in adata.obs that correspond to categorical data.

continuous_covariate_keys

keys in adata.obs that correspond to continuous data.

copy

if True, a copy of adata is returned.

Return type

AnnData | NoneOptional[AnnData]

Returns

If copy, will return AnnData. Adds the following fields to adata:

.uns[‘_scvi’]

scvi setup dictionary

.obs[‘_scvi_labels’]

labels encoded as integers

.obs[‘_scvi_batch’]

batch encoded as integers

to_device#

TOTALVI.to_device(device)#

Move model to device.

Parameters
device : str | intUnion[str, int]

Device to move model to. Options: ‘cpu’ for CPU, integer GPU index (eg. 0), or ‘cuda:X’ where X is the GPU index (eg. ‘cuda:0’). 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

train#

TOTALVI.train(max_epochs=400, lr=0.004, use_gpu=None, train_size=0.9, validation_size=None, batch_size=256, early_stopping=True, check_val_every_n_epoch=None, reduce_lr_on_plateau=True, n_steps_kl_warmup=None, n_epochs_kl_warmup=None, adversarial_classifier=None, plan_kwargs=None, **kwargs)[source]#

Trains the model using amortized variational inference.

Parameters
max_epochs : int | NoneOptional[int] (default: 400)

Number of passes through the dataset.

lr : float (default: 0.004)

Learning rate for optimization.

use_gpu : str | int | bool | NoneUnion[str, int, bool, None] (default: None)

Use default GPU if available (if None or True), or index of GPU to use (if int), or name of GPU (if str, e.g., ‘cuda:0’), or use CPU (if False).

train_size : float (default: 0.9)

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

validation_size : float | NoneOptional[float] (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: 256)

Minibatch size to use during training.

early_stopping : bool (default: True)

Whether to perform early stopping with respect to the validation set.

check_val_every_n_epoch : int | NoneOptional[int] (default: None)

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

reduce_lr_on_plateau : bool (default: True)

Reduce learning rate on plateau of validation metric (default is ELBO).

n_steps_kl_warmup : int | NoneOptional[int] (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 | NoneOptional[int] (default: None)

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

adversarial_classifier : bool | NoneOptional[bool] (default: None)

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

plan_kwargs : dict | NoneOptional[dict] (default: None)

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

**kwargs

Other keyword args for Trainer.

view_anndata_setup#

TOTALVI.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 | NoneOptional[AnnData] (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

view_setup_args#

static TOTALVI.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 | NoneOptional[str] (default: None)

Prefix of saved file names.

Return type

None