用基因几何结构指导细胞扰动预测，提升药物组合效果的模拟精度。
Control-Anchored Residual Flow Matching Conditioned on Gene Geometry for Virtual Cell Perturbation Modeling
- 基于基因网络构建多尺度几何特征，动态选择关键结构信息
- 在诺曼加性基准上达0.8979的皮尔逊Δ分数，药物组合测试达0.9088
- 无需图传播即可实现精准响应预测，适合生物机制建模研究者
虚拟细胞建模的核心任务是预测单细胞转录组对未知基因扰动和药物组合的响应，生物网络为基因关系提供了重要先验。现有图模型通常使用同一网络同时构建基因表示并传递互作信息，将稳定关联误当作扰动响应路径。基因本体（Gene Ontology）与控制组共表达网络反映的是相对稳定的基因关系，而非干预特异的响应方向或强度。为此，我们提出GeneGeoFlow，将控制锚定的残差流匹配方法条件于由生物网络导出的基因粒度几何结构，以学习干预特异的转录响应。GeneGeoFlow从基因本体和控制组共表达网络中提取多尺度谱坐标，通过扰动条件的基因级门控模块选择相关结构尺度与网络来源，生成干预特异的基因几何。该几何条件化控制锚定的残差流，无需显式沿图传播目标信号。条件最优传输用于配对未配准的对照与扰动群体进行训练，而Delta相关性目标则对齐预测与观测的条件级表达变化方向。GeneGeoFlow在Norman加性基准上取得0.8979的皮尔逊Δ分数，在固定ComboSciPlex测试集的五个保留药物组合上达0.9088。结果表明，扰动条件的基因几何是干预特异响应预测的有效结构先验，避免将稳定基因关系与响应传播混淆。
原文摘要 · Abstract (English)
A central task in virtual cell modeling is predicting single-cell transcriptional responses to unseen genetic perturbations and drug combinations, and biological networks provide valuable priors on gene relationships. Existing graph-based models commonly use the same network to structure gene representations and mediate intergene interactions, thereby implicitly treating stable associations as perturbation-response pathways. Gene Ontology and control-derived coexpression networks encode relatively stable relationships rather than intervention-specific response directions or magnitudes. We therefore propose GeneGeoFlow, which conditions a control-anchored residual flow on gene-wise geometry derived from biological networks to learn intervention-specific transcriptional responses. GeneGeoFlow derives multi-scale spectral coordinates from Gene Ontology and control-derived coexpression networks. A perturbation-conditioned, gene-wise gating module selects relevant structural scales and network sources, yielding intervention-specific gene geometry. The resulting geometry conditions a control-anchored residual flow without explicitly propagating target-derived signals along the graph. Condition-wise optimal transport couples unpaired control and perturbed populations for training, while a Delta-correlation objective aligns the predicted and observed condition-level expression-shift directions. GeneGeoFlow achieves Pearson Delta scores of 0.8979 on the Norman additive benchmark and 0.9088 on five held-out drug combinations in the fixed ComboSciPlex test split. These results support perturbation-conditioned gene geometry as an effective structural prior for intervention-specific response prediction, without conflating stable gene relationships with response propagation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。