scROMA¶

Batch-aware, SVD-based pathway-activity inference for single-cell transcriptomics, natively integrated with the Scanpy/AnnData ecosystem.

scROMA scores each gene set from the coordinated variation among its member genes, returning an L1 overdispersion score, a median-expression shift score, per-cell activity scores, per-gene contribution weights, and permutation-based significance. Its batch-aware extension corrects technical variation inside the gene-set subspace, and it ships with a generative simulation framework producing data with fully specified ground-truth pathway activity.

pip install scroma          # or: uv add scroma

Contents:

Quick start
Tutorials
API reference