scvi.external.velovi.VELOVAE#

class scvi.external.velovi.VELOVAE(n_input, true_time_switch=None, n_hidden=128, n_latent=10, n_layers=1, dropout_rate=0.1, log_variational=False, latent_distribution='normal', use_batch_norm='both', use_layer_norm='both', use_observed_lib_size=True, var_activation=Softplus(beta=1.0, threshold=20.0), model_steady_states=True, gamma_unconstr_init=None, alpha_unconstr_init=None, alpha_1_unconstr_init=None, lambda_alpha_unconstr_init=None, switch_spliced=None, switch_unspliced=None, t_max=20, penalty_scale=0.2, dirichlet_concentration=0.25, linear_decoder=False, time_dep_transcription_rate=False)[source]#

Bases: BaseModuleClass

Variational auto-encoder model.

This is an implementation of the veloVI model described in [Gayoso et al., 2023].

Parameters:
n_input int

Number of input genes.

n_hidden int (default: 128)

Number of nodes per hidden layer.

n_latent int (default: 10)

Dimensionality of the latent space.

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.

log_variational bool (default: False)

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

latent_distribution str (default: 'normal')

One of the following:

  • "normal" - Isotropic normal.

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

use_layer_norm Literal['encoder', 'decoder', 'none', 'both'] (default: 'both')

Whether to use layer norm in layers.

use_observed_lib_size bool (default: True)

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

var_activation callable | None (default: Softplus(beta=1.0, threshold=20.0))

Callable used to ensure positivity of the variational distributions’ variance. When None, defaults to exp().

Attributes table#

Methods table#

generative(z, gamma, beta, alpha, alpha_1, ...)

Runs the generative model.

get_loadings()

Extract per-gene weights in the linear decoder.

get_px(px_pi, px_rho, px_tau, scale, gamma, ...)

inference(spliced, unspliced[, n_samples])

High-level inference method.

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

Compute the loss for a minibatch of data.

sample()

Not implemented.

Attributes#

VELOVAE.training: bool#

Methods#

VELOVAE.generative(z, gamma, beta, alpha, alpha_1, lambda_alpha, latent_dim=None)[source]#

Runs the generative model.

VELOVAE.get_loadings()[source]#

Extract per-gene weights in the linear decoder.

Return type:

ndarray

VELOVAE.get_px(px_pi, px_rho, px_tau, scale, gamma, beta, alpha, alpha_1, lambda_alpha)[source]#
Return type:

Tensor

VELOVAE.inference(spliced, unspliced, n_samples=1)[source]#

High-level inference method.

Runs the inference (encoder) model.

VELOVAE.loss(tensors, inference_outputs, generative_outputs, kl_weight=1.0, n_obs=1.0)[source]#

Compute the loss for a minibatch of data.

This function uses the outputs of the inference and generative functions to compute a loss. This many optionally include other penalty terms, which should be computed here.

This function should return an object of type LossOutput.

VELOVAE.sample()[source]#

Not implemented.

Return type:

ndarray