arXiv cs.AI· Haojie Yang, Ran Su·· 3 天前AI 评分22
MRFlow：机制结构化残差流匹配用于虚拟细胞扰动预测
MRFlow: Mechanism-Structured Residual Flow Matching for Virtual Cell Perturbation Prediction
AI 导读
MRFlow 将虚拟细胞预测建模为单细胞经验分布间的条件传输，通过流匹配向量场把对照细胞群输运至扰动细胞群，场分解为机制结构化仿射字典与谱控残差场。基因扰动经调控图 GCN 编码，化学扰动经 Morgan 指纹编码，二者共用同一条件动力学接口。在八个基因与药物扰动基准上，MRFlow 取得最高综合得分，同时在差异表达与分布指标上保持有竞争力的原始表现。
正文 · 原文
Abstract:Predicting cellular responses to chemical and genetic perturbations is a central test for AI virtual cells, yet many single-cell models reduce each condition to an average expression shift. This target is misaligned with perturbation biology: rare states, resistant subpopulations, and context-dependent effect sizes may coexist under the same intervention. MRFlow treats virtual-cell prediction as conditional transport between empirical single-cell measures. Control and perturbed cells are embedded in a variational latent state space, greedy low-cost supervision is constructed over detached minibatch states, and a conditional flow-matching vector field transports control populations toward perturbed populations. The field decomposes into a mechanism-structured affine dictionary, which recombines shared latent response operators with a low-rank condition-specific correction, and a spectrally controlled residual field for nonlinear cell-level variation. Genetic perturbations are encoded through a regulatory-graph GCN, chemical perturbations through Morgan fingerprints, and both enter the same conditional dynamics interface. Across eight gene and drug perturbation benchmarks, MRFlow attains the highest composite score while preserving competitive raw performance on differential-expression and distributional metrics. The results support latent distribution transport as a principled and empirically effective formulation for perturbation-aware virtual cell modeling.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM) |
| Cite as: | arXiv:2610.13966 [cs.LG] |
| (or arXiv:2610.13966v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13966 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hao'jie Yang [view email]
[v1]
Thu, 10 Sep 2026 09:55:56 UTC (2,613 KB)
来源：arXiv cs.AI · arxiv.org