arXiv：cs.LG· Jianan Wei, Jiajun Hong, Guikun Chen, Ning Yang, Lifeng Fan, Wenguan Wang·· 3 小时前AI 评分31
scEGFlow：用能量引导流匹配实现可泛化的单细胞扰动响应预测
Generalizable single-cell perturbation response prediction using energy-guided flow matching
AI 导读
scEGFlow 是一个能量引导的流匹配框架，通过条件流匹配建模从对照组细胞到扰动状态的连续转变，并用条件特异性能量梯度校正和引导预测，无需重新训练流模型即可灵活调整。在覆盖成像表型和转录组图谱的基准上，它在已见和未见扰动条件下均优于现有方法，能保持细胞流形几何与群体异质性，在仅有少量实测细胞的新条件下提升预测准确率，并准确重现共识基因表达特征中的上调和下调模式。
正文
Abstract:Predicting phenotypic and transcriptional responses to perturbations at single-cell resolution provides a powerful tool for probing biological systems. However, existing methods typically rely on fixed mappings learned during training, making it challenging to calibrate distribution shifts or adapt to novel perturbation conditions during inference. Here, we present scEGFlow, an energy-guided flow matching framework that dynamically bridges control and perturbed cellular states. scEGFlow models continuous transitions from control cell populations to perturbed states using conditional flow matching. It then applies condition-specific energy gradients to correct and steer these predictions, enabling flexible adjustments without retraining the flow model. Evaluations across benchmarks spanning imaging phenotypes and transcriptomic profiles show that scEGFlow outperforms existing methods in reconstructing response distributions under both seen and unseen perturbation conditions, faithfully preserving cellular manifold geometry and population heterogeneity. This advantage is notable when adapting to new conditions with only a few measured cells, consistently improving prediction accuracy. Furthermore, scEGFlow accurately recapitulates perturbation-induced up- and down-regulation patterns across consensus gene expression signatures, where energy guidance improves the agreement between predicted and observed regulatory directions. Ultimately, these findings demonstrate that scEGFlow provides a modular, generalizable, and steerable solution for single-cell perturbation modeling. By grounding generative flows in learned biological landscapes, this architecture establishes a new computational paradigm for navigating and manipulating cellular behavior in silico.
| Subjects: | Genomics (q-bio.GN); Machine Learning (cs.LG); Cell Behavior (q-bio.CB) |
| Cite as: | arXiv:2610.02232 [q-bio.GN] |
| (or arXiv:2610.02232v1 [q-bio.GN] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02232 arXiv-issued DOI via DataCite |
Submission history
From: Jian Wei [view email]
[v1]
Sun, 27 Sep 2026 03:53:41 UTC (5,402 KB)
来源：arXiv：cs.LG · arxiv.org