Federated-inspired Single-cell Batch Integration in Latent Space

TL;DR

scBatchProx is a federated-inspired method that refines cell embeddings in single-cell RNA sequencing data, improving batch correction and biological signal preservation without centralized data sharing.

Contribution

Introduces scBatchProx, a lightweight, post-hoc optimization technique for batch correction in latent space inspired by federated learning, applicable to arbitrary upstream methods.

Findings

Achieves 3-8% improvement in embedding quality.

Improves batch correction in 90% of cases.

Enhances biological conservation in 85% of data-method pairs.

Abstract

Advances in single-cell RNA sequencing enable the rapid generation of massive, high-dimensional datasets, yet the accumulation of data across experiments introduces batch effects that obscure true biological signals. Existing batch correction approaches either insufficiently correct batch effects or require centralized retraining on the complete dataset, limiting their applicability in distributed and continually evolving single-cell data settings. We introduce scBatchProx, a post-hoc optimization method inspired by federated learning principles for refining cell-level embeddings produced by arbitrary upstream methods. Treating each batch as a client, scBatchProx learns batch-conditioned adapters under proximal regularization, correcting batch structure directly in latent space without requiring raw expression data or centralized optimization. The method is lightweight and deployable, optimizing batch-specific adapter parameters only. Extensive experiments show that scBatchProx consistently yields relative gains of approximately 3-8% in overall embedding quality, with batch correction and biological conservation improving in 90% and 85% of data-method pairs, respectively. We envision this work as a step toward the practical refinement of learned representations in dynamic single-cell data systems.