scvi-linearscvi

What problem does it solve?

Trains an interpretable linear decoder model to uncover gene-to-factor loadings from raw scRNA-seq counts, enabling direct interpretation of latent factors and gene programs.

Core Features & Use Cases

• Interpretable factor analysis: derive gene loadings for each latent dimension to define biological programs.
• Compare with PCA on counts, benefiting from count-aware modeling and batch-friendly training.
• Use cases: identify drivers of population structure, extract gene-signature lists, and annotate latent factors across samples.

Quick Start

Initialize an AnnData object with raw counts, configure LinearSCVI with a chosen number of latent factors, train the model, and retrieve the gene loadings.