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

arXiv: https://arxiv.org/abs/2605.18576 · HTML: https://mlsanity.com/paper/2605.18576/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 39 references that are in the map.
- First posted on arXiv 18 May 2026.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [Learning Identifiable Factorized Causal Representations of Cellular Responses](https://mlsanity.com/paper/2410.22472/) (2024)
- [CRADLE-VAE: Enhancing Single-Cell Gene Perturbation Modeling with Counterfactual Reasoning-based Artifact Disentanglement](https://mlsanity.com/paper/2409.05484/) (2024)

## Abstract (arXiv)

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.