Interpretable Neural ODEs for Gene Regulatory Network Discovery under Perturbations

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 $\textit{PerturbODE}$, 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.

Understanding how genes regulate one another and predicting how cells respond to genetic perturbations, such as CRISPR-based gene editing, have traditionally been treated as separate tasks. In reality, these processes are closely connected: perturbing one gene can trigger a cascade of regulatory changes through a gene regulatory network, ultimately altering gene expression and potentially cell fate. We introduce PerturbODE, which models cellular changes over time using ordinary differential equations. Within this framework, genetic perturbations and regulatory interactions between genes are represented explicitly and interpretably. This allows the model not only to predict how cells respond to perturbations, but also to provide insight into the regulatory cascades that may drive these responses. In the long term, a deeper understanding of these regulatory mechanisms could support the development of more effective therapies and clarify how potential drugs exert their effects within cells.