scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement

TL;DR

scHelix is a novel gene-level disentanglement framework for single-cell RNA sequencing integration that effectively removes batch effects while preserving biological signals.

Contribution

It introduces a dual-stream asymmetric architecture with explicit gene partitioning and a novel alignment-refinement protocol for improved data integration.

Findings

scHelix outperforms existing methods in benchmarking tests.

The gene partitioning improves the balance between batch correction and biological fidelity.

The approach effectively prevents over-correction and preserves subtle biological signals.

Abstract

A critical challenge in single-cell RNA sequencing (scRNA-seq) integration is resolving the tension between eliminating batch effects and maintaining biological fidelity. While recent evidence indicates that batch effects manifest heterogeneously across genes, most existing methods process the transcriptome uniformly, frequently resulting in over-correction and loss of subtle biological signals. To address this, we present scHelix, a dataset-adaptive framework that fundamentally changes how features are processed by explicitly partitioning genes into domain-invariant Anchors and domain-sensitive Variants at the input level. scHelix utilizes a dual-stream sparse diffusion encoder equipped with stop-gradient graph caching to efficiently learn multi-scale structural representations. The core of our approach is a novel asymmetric Align-Refine-Fuse protocol: the unstable Variant stream is first aligned to the robust topology of the Anchor stream, followed by a conservative refinement phase where the Anchor stream absorbs denoised details via bounded residual gating. This divide-and-conquer architecture prevents shortcut learning and ensures robust batch removal without compromising the integrity of biological clusters. Extensive benchmarking demonstrates that scHelix outperforms state-of-the-art methods.