scGPT (single-cell foundation model)

Overview

scGPT (Cui et al., Nature Methods 2024; bowang-lab/scGPT) is a transformer foundation model pretrained on tens of millions of cells. It provides zero-shot and fine-tuned cell-type annotation, gene and cell embeddings, batch integration, and gene-regulatory / perturbation inference — all operating on AnnData (.h5ad) objects.

Its niche vs. the existing single-cell skills: scGPT is the pretrained-transformer route. For probabilistic latent-variable models use alterlab-scvi-tools; for the conventional Scanpy analysis pipeline use alterlab-scanpy; scGPT complements both.

When to Use This Skill