scvi.module.VAEC

class scvi.module.VAEC(n_input, n_labels=0, n_hidden=128, n_latent=5, n_layers=2, log_variational=True, ct_weight=None, dropout_rate=0.05, **module_kwargs)

Bases: BaseModuleClass

Conditional Variational auto-encoder model.

This is an implementation of the CondSCVI model

Parameters:

• n_input (int) – Number of input genes

• n_labels (int) – Number of labels

• n_hidden (Tunable_[int]) – Number of nodes per hidden layer

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

• n_layers (Tunable_[int]) – Number of hidden layers used for encoder and decoder NNs

• dropout_rate (Tunable_[float]) – Dropout rate for the encoder and decoder neural network

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

• ct_weight (ndarray) –

Attributes table

Methods table

generative(z, library, y)	Runs the generative model.
inference(x, y[, n_samples])	High level inference method.
loss(tensors, inference_outputs, ...[, ...])	Loss computation.
sample(tensors[, n_samples])	Generate observation samples from the posterior predictive distribution.

Attributes

training

VAEC.training: bool

Methods

generative

VAEC.generative(z, library, y)

Runs the generative model.

inference

VAEC.inference(x, y, n_samples=1)

High level inference method.

Runs the inference (encoder) model.

loss

VAEC.loss(tensors, inference_outputs, generative_outputs, kl_weight=1.0)

Loss computation.

Parameters:

kl_weight (float) –

sample

VAEC.sample(tensors, n_samples=1)

Generate observation samples from the posterior predictive distribution.

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

Parameters:

• tensors – Tensors dict

• n_samples – Number of required samples for each cell

Returns:

x_new : torch.Tensor tensor with shape (n_cells, n_genes, n_samples)

Return type:

ndarray