scvi.module.LDVAE#

class scvi.module.LDVAE(n_input, n_batch=0, n_labels=0, n_hidden=128, n_latent=10, n_layers_encoder=1, dropout_rate=0.1, dispersion='gene', log_variational=True, gene_likelihood='nb', use_batch_norm=True, bias=False, latent_distribution='normal', use_observed_lib_size=False, **kwargs)[source]#

Bases: VAE

Linear-decoded Variational auto-encoder model.

Implementation of [Svensson et al., 2020].

This model uses a linear decoder, directly mapping the latent representation to gene expression levels. It still uses a deep neural network to encode the latent representation.

Compared to standard VAE, this model is less powerful but can be used to inspect which genes contribute to variation in the dataset. It may also be used for all scVI tasks, like differential expression, batch correction, imputation, etc. However, batch correction may be less powerful as it assumes a linear model.

Parameters:
n_input int

Number of input genes

n_batch int (default: 0)

Number of batches

n_labels int (default: 0)

Number of labels

n_hidden int (default: 128)

Number of nodes per hidden layer (for encoder)

n_latent int (default: 10)

Dimensionality of the latent space

n_layers_encoder int (default: 1)

Number of hidden layers used for encoder NNs

dropout_rate float (default: 0.1)

Dropout rate for neural networks

dispersion str (default: 'gene')

One of the following

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

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

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

  • 'gene-cell' - dispersion can differ for every gene in every cell

log_variational bool (default: True)

Log(data+1) prior to encoding for numerical stability. Not normalization.

gene_likelihood str (default: 'nb')

One of

  • 'nb' - Negative binomial distribution

  • 'zinb' - Zero-inflated negative binomial distribution

  • 'poisson' - Poisson distribution

use_batch_norm bool (default: True)

Bool whether to use batch norm in decoder

bias bool (default: False)

Bool whether to have bias term in linear decoder

latent_distribution str (default: 'normal')

One of

  • 'normal' - Isotropic normal

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

use_observed_lib_size bool (default: False)

Use observed library size for RNA as scaling factor in mean of conditional distribution.

**kwargs

Attributes table#

Methods table#

get_loadings()

Extract per-gene weights in the linear decoder.

Attributes#

LDVAE.training: bool#

Methods#

LDVAE.get_loadings()[source]#

Extract per-gene weights in the linear decoder.

Return type:

ndarray