Interpretable Neural ODEs for Gene Regulatory Network Discovery under Perturbations
Department of Computer Science, Columbia University, New York, U.S.（哥伦比亚大学计算机科学系）；Department of Industrial Engineering and Operations Research, Columbia University, New York, U.S.（哥伦比亚大学工业工程与运筹学系）；Department of Applied Mathematics and Applied Physics, Columbia University, New York, U.S.（哥伦比亚大学应用数学与应用物理系）；New York Genome Center, New York, U.S.（纽约基因组中心）；Irving Institute of Cancer Dynamics, New York, U.S.（伊万·罗伯特癌症动力学研究所）；Institute of Computational Biology, Helmholtz Munich, Munich, Germany（海德堡医学院计算生物学研究所）；Department of Mathematics, Technische Universität München, Munich, Germany（慕尼黑技术大学数学系）
Zaikang Lin, Sei Chang, Aaron Zweig, Minseo Kang, Fabian J. Theis, Elham Azizi, David A. Knowles
Modern high-throughput biological datasets containing thousands of perturbations enable large-scale discovery of causal graphs that represent regulatory interactions between genes. Differentiable causal graphical models and regression-based methods have been developed to infer gene regulatory networks (GRNs) from interventional datasets. However, existing approaches fail to capture the non-linear dynamics of biological processes such as cellular differentiation. To address this limitation, we propose PerturbODE, a novel framework that employs interpretable neural ordinary differential equations (neural ODEs) to model cell state trajectories under perturbations and derive the underlying causal GRN from the neural ODE parameters, enabling downstream simulation of unseen genetic interventions. The GRN is encoded via a single-hidden-layer feedforward network, implicitly grouping genes into interpretable co-regulated modules. We demonstrate PerturbODE's efficacy in GRN inference and extension to perturbation response prediction across both simulated and real overexpression datasets.
Towards Universal Gene Regulatory Network Inference: Unlocking Generalizable Regulatory Knowledge in Single-cell Foundation Models
Computer Network Information Center, Chinese Academy of Sciences, Beijing, China（中国科学院计算机网络信息中心，北京，中国）；Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, China（中国科学院大学杭州高等研究院，杭州，中国）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）
Switched Flow Matching: Eliminating Singularities via Switching ODEs
Research Institute of Intelligent Complex Systems, Fudan University（复旦大学智能复杂系统研究院）；Institutes of Brain Science, Fudan University（复旦大学脑科学研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Learning POD of Complex Dynamics Using Heavy-ball Neural ODEs
University of Utah（犹他大学）
适当的正交分解（POD）允许在一个实质性的水平上的复杂的动力系统的降阶建模，同时保持在建模的基础动力系统的高度准确性。机器学习算法的进步使得能够从数据中学习基于POD的动态，并对动态系统进行准确快速的预测。在本文中，我们利用最近提出的重球神经ODE（HBNODE）[Xia et al. NeurIPS，2021]在POD上下文中学习数据驱动的降阶降阶模型（ROM），特别是学习时变系数的动态特性，这些时变系数是通过对求解全阶模型生成的训练快照进行POD分析而生成的。HBNODE在学习基于POD的ROM方面具有几个实际优势，并具有理论保证，包括1）HBNODE可以从顺序观察中有效地学习长期依赖关系，2）HBNODE在训练和测试方面都具有计算效率。我们比较HBNODE与其他流行的ROM上的几个复杂的动力系统，包括冯卡门街流，Kurganov-Petrova-Popov方程，和一维欧拉方程的流体建模。
