scvi.external.totalanvi.TOTALANVAE#
- class scvi.external.totalanvi.TOTALANVAE(n_input_genes, n_input_proteins, n_batch=1, n_labels=1, 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, extra_payload_autotune=False, library_log_means=None, library_log_vars=None, n_panel=None, panel_key='batch', use_batch_norm='both', use_layer_norm='none', extra_encoder_kwargs=None, extra_decoder_kwargs=None, y_prior=None, labels_groups=None, linear_classifier=False, classifier_parameters=None)[source]#
Bases:
SupervisedModuleClass,TOTALVAETotal variational inference for CITE-seq data.
Implements a combination of scANVI and totalVI model of [Gayoso et al., 2021].
- Parameters:
n_input_genes (
int) – Number of input genesn_input_proteins (
int) – Number of input proteinsn_batch (
int(default:1)) – Number of batchesn_labels (
int(default:1)) – Number of labelsn_hidden (
int(default:256)) – Number of nodes per hidden layer for encoder and decodern_latent (
int(default:20)) – Dimensionality of the latent spacen_layers – Number of hidden layers used for encoder and decoder NNs
n_continuous_cov (
int(default:0)) – Number of continuous covariatesn_cats_per_cov (
Iterable[int] |None(default:None)) – Number of categories for each extra categorical covariatedropout_rate – Dropout rate for neural networks
gene_dispersion (
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 (
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 (
Literal['zinb','nb'] (default:'nb')) –One of
'nb'- Negative binomial distribution'zinb'- Zero-inflated negative binomial distribution
latent_distribution (
Literal['normal','ln'] (default:'normal')) –One of
'normal'- Isotropic normal'ln'- Logistic normal with normal params N(0, 1)
protein_batch_mask (
dict[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 encoderprotein_background_prior_mean (
ndarray|None(default:None)) – Array of proteins by batches, the prior initialization for the protein background mean (log scale)protein_background_prior_scale (
ndarray|None(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 a 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 a scaling factor in mean of conditional distributionextra_payload_autotune (
bool(default:False)) – IfTrue, returns extra matrices in the loss output to be used during autotunelibrary_log_means (
ndarray|None(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 (
ndarray|None(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 (
Literal['encoder','decoder','none','both'] (default:'both')) – Whether to use batch norm in layers.use_layer_norm (
Literal['encoder','decoder','none','both'] (default:'none')) – Whether to use layer norm in layers.extra_encoder_kwargs (
dict|None(default:None)) – Extra keyword arguments passed intoEncoderTOTALVI.extra_decoder_kwargs (
dict|None(default:None)) – Extra keyword arguments passed intoDecoderTOTALVI.linear_classifier (
bool(default:False)) – IfTrue, uses a single linear layer for classification instead of a multi-layer perceptron.
Attributes table#
Methods table#
Attributes#
- TOTALANVAE.training: bool#
Methods#
- TOTALANVAE.classify(x, y, batch_index=None, cont_covs=None, cat_covs=None, use_posterior_mean=True)[source]#
Forward pass through the encoder and classifier.
- Parameters:
x (
Tensor) – Tensor of shape(n_obs, n_genes).y (
Tensor) – Tensor of shape(n_obs, n_proteins).batch_index (
Tensor|None(default:None)) – Tensor of shape(n_obs,)denoting batch indices.cont_covs (
Tensor|None(default:None)) – Tensor of shape(n_obs, n_continuous_covariates).cat_covs (
Tensor|None(default:None)) – Tensor of shape(n_obs, n_categorical_covariates).use_posterior_mean (
bool(default:True)) – Whether to use the posterior mean of the latent distribution for classification.
- Return type:
- Returns:
Tensor of shape
(n_obs, n_labels)denoting logit scores per label. Before v1.1, this method by default returned probabilities per label, see #2301 for more details.