scvi.module.TOTALVAE#

class scvi.module.TOTALVAE(n_input_genes, n_input_proteins, n_batch=0, n_labels=0, n_hidden=256, n_latent=20, n_layers_encoder=2, n_layers_decoder=1, n_continuous_cov=0, n_cats_per_cov=None, dropout_rate_decoder=0.2, dropout_rate_encoder=0.2, gene_dispersion='gene', protein_dispersion='protein', log_variational=True, gene_likelihood='nb', latent_distribution='normal', protein_batch_mask=None, encode_covariates=True, protein_background_prior_mean=None, protein_background_prior_scale=None, use_size_factor_key=False, use_observed_lib_size=True, library_log_means=None, library_log_vars=None, use_batch_norm='both', use_layer_norm='none', extra_encoder_kwargs=None, extra_decoder_kwargs=None)[source]#

Bases: BaseModuleClass

Total variational inference for CITE-seq data.

Implements the totalVI model of [Gayoso et al., 2021].

Parameters:
  • n_input_genes (int) – Number of input genes

  • n_input_proteins (int) – Number of input proteins

  • n_batch (int (default: 0)) – Number of batches

  • n_labels (int (default: 0)) – Number of labels

  • n_hidden (Tunable_[int] (default: 256)) – Number of nodes per hidden layer for encoder and decoder

  • n_latent (Tunable_[int] (default: 20)) – Dimensionality of the latent space

  • n_layers – Number of hidden layers used for encoder and decoder NNs

  • n_continuous_cov (int (default: 0)) – Number of continuous covarites

  • n_cats_per_cov (Optional[Iterable[int]] (default: None)) – Number of categories for each extra categorical covariate

  • dropout_rate – Dropout rate for neural networks

  • gene_dispersion (Tunable_[Literal['gene', 'gene-batch', 'gene-label']] (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 (Tunable_[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

  • log_variational (bool (default: True)) – Log(data+1) prior to encoding for numerical stability. Not normalization.

  • gene_likelihood (Tunable_[Literal['zinb', 'nb']] (default: 'nb')) –

    One of

    • 'nb' - Negative binomial distribution

    • 'zinb' - Zero-inflated negative binomial distribution

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

    One of

    • 'normal' - Isotropic normal

    • 'ln' - Logistic normal with normal params N(0, 1)

  • protein_batch_mask (dict[Union[str, int], ndarray] (default: None)) – Dictionary where each key is a batch code, and value is for each protein, whether it was observed or not.

  • encode_covariates (bool (default: True)) – Whether to concatenate covariates to expression in encoder

  • protein_background_prior_mean (Optional[ndarray] (default: None)) – Array of proteins by batches, the prior initialization for the protein background mean (log scale)

  • protein_background_prior_scale (Optional[ndarray] (default: None)) – Array of proteins by batches, the prior initialization for the protein background scale (log scale)

  • use_size_factor_key (bool (default: False)) – Use size_factor AnnDataField defined by the user as scaling factor in mean of conditional distribution. Takes priority over use_observed_lib_size.

  • use_observed_lib_size (bool (default: True)) – Use observed library size for RNA as scaling factor in mean of conditional distribution

  • library_log_means (Optional[ndarray] (default: None)) – 1 x n_batch array of means of the log library sizes. Parameterizes prior on library size if not using observed library size.

  • library_log_vars (Optional[ndarray] (default: None)) – 1 x n_batch array of variances of the log library sizes. Parameterizes prior on library size if not using observed library size.

  • use_batch_norm (Tunable_[Literal['encoder', 'decoder', 'none', 'both']] (default: 'both')) – Whether to use batch norm in layers.

  • use_layer_norm (Tunable_[Literal['encoder', 'decoder', 'none', 'both']] (default: 'none')) – Whether to use layer norm in layers.

  • extra_encoder_kwargs (Optional[dict] (default: None)) – Extra keyword arguments passed into EncoderTOTALVI.

  • extra_decoder_kwargs (Optional[dict] (default: None)) – Extra keyword arguments passed into DecoderTOTALVI.

Attributes table#

training

Methods table#

generative(z, library_gene, batch_index, label)

Run the generative step.

get_reconstruction_loss(x, y, px_dict, py_dict)

Compute reconstruction loss.

get_sample_dispersion(x, y[, batch_index, ...])

Returns the tensors of dispersions for genes and proteins.

inference(x, y[, batch_index, label, ...])

Internal helper function to compute necessary inference quantities.

loss(tensors, inference_outputs, ...[, ...])

Returns the reconstruction loss and the Kullback divergences.

marginal_ll(tensors, n_mc_samples[, return_mean])

Computes the marginal log likelihood of the data under the model.

sample(tensors[, n_samples])

Sample from the generative model.

Attributes#

TOTALVAE.training: bool#

Methods#

TOTALVAE.generative(z, library_gene, batch_index, label, cont_covs=None, cat_covs=None, size_factor=None, transform_batch=None)[source]#

Run the generative step.

Return type:

dict[str, Union[Tensor, dict[str, Tensor]]]

TOTALVAE.get_reconstruction_loss(x, y, px_dict, py_dict, pro_batch_mask_minibatch=None)[source]#

Compute reconstruction loss.

Return type:

tuple[Tensor, Tensor]

TOTALVAE.get_sample_dispersion(x, y, batch_index=None, label=None, n_samples=1)[source]#

Returns the tensors of dispersions for genes and proteins.

Parameters:
  • x (Tensor) – tensor of values with shape (batch_size, n_input_genes)

  • y (Tensor) – tensor of values with shape (batch_size, n_input_proteins)

  • batch_index (Optional[Tensor] (default: None)) – array that indicates which batch the cells belong to with shape batch_size

  • label (Optional[Tensor] (default: None)) – tensor of cell-types labels with shape (batch_size, n_labels)

  • n_samples (int (default: 1)) – number of samples

Return type:

tuple[Tensor, Tensor]

Returns:

type tensors of dispersions of the negative binomial distribution

TOTALVAE.inference(x, y, batch_index=None, label=None, n_samples=1, cont_covs=None, cat_covs=None)[source]#

Internal helper function to compute necessary inference quantities.

We use the dictionary px_ to contain the parameters of the ZINB/NB for genes. The rate refers to the mean of the NB, dropout refers to Bernoulli mixing parameters. scale refers to the quanity upon which differential expression is performed. For genes, this can be viewed as the mean of the underlying gamma distribution.

We use the dictionary py_ to contain the parameters of the Mixture NB distribution for proteins. rate_fore refers to foreground mean, while rate_back refers to background mean. scale refers to foreground mean adjusted for background probability and scaled to reside in simplex. back_alpha and back_beta are the posterior parameters for rate_back. fore_scale is the scaling factor that enforces rate_fore > rate_back.

px_["r"] and py_["r"] are the inverse dispersion parameters for genes and protein, respectively.

Parameters:
  • x (Tensor) – tensor of values with shape (batch_size, n_input_genes)

  • y (Tensor) – tensor of values with shape (batch_size, n_input_proteins)

  • batch_index (Optional[Tensor] (default: None)) – array that indicates which batch the cells belong to with shape batch_size

  • label (Optional[Tensor] (default: None)) – tensor of cell-types labels with shape (batch_size, n_labels)

  • n_samples (default: 1) – Number of samples to sample from approximate posterior

  • cont_covs (default: None) – Continuous covariates to condition on

  • cat_covs (default: None) – Categorical covariates to condition on

Return type:

dict[str, Union[Tensor, dict[str, Tensor]]]

TOTALVAE.loss(tensors, inference_outputs, generative_outputs, pro_recons_weight=1.0, kl_weight=1.0)[source]#

Returns the reconstruction loss and the Kullback divergences.

Parameters:
  • x – tensor of values with shape (batch_size, n_input_genes)

  • y – tensor of values with shape (batch_size, n_input_proteins)

  • batch_index – array that indicates which batch the cells belong to with shape batch_size

  • label – tensor of cell-types labels with shape (batch_size, n_labels)

Return type:

tuple[FloatTensor, FloatTensor, FloatTensor, FloatTensor]

Returns:

type the reconstruction loss and the Kullback divergences

TOTALVAE.marginal_ll(tensors, n_mc_samples, return_mean=True)[source]#

Computes the marginal log likelihood of the data under the model.

TOTALVAE.sample(tensors, n_samples=1)[source]#

Sample from the generative model.