netmap.model.nbautoencoder¶

Negative Binomial autoencoder model for scRNA-seq count data.

This module implements a Negative Binomial (NB) autoencoder with dual decoder heads for the mean (mu) and dispersion (theta) parameters of the NB distribution. Forward-mode flags (forward_mu_only, forward_theta_only, latent_only) redirect NegativeBinomialAutoencoder.forward() to return a single tensor, which is required by Captum attribution methods.

Functions

`get_mus`	Return the mean predicted mean expression (mu) across all cells.
`get_mus_grouping`	Return the mean predicted mu per observation group.
`get_thetas`	Return the mean predicted dispersion (theta) across all cells.
`get_thetas_grouping`	Return the mean predicted theta per observation group.

Classes

`NegativeBinomialAutoencoder`	Autoencoder with dual mu/theta decoder heads for NB-distributed scRNA-seq data.
`NegativeBinomialLoss`