Learning stable and predictive structures in kinetic systems

Significance Many real-world systems can be described by a set of differential equations. Knowing these equations allows researchers to predict the system’s behavior under interventions, such as manipulations of initial or environmental conditions. For many complex systems, the differential equations are unknown. Deriving them by hand is infeasible for large systems, and data science is used to learn them from observational data. Existing techniques yield models that predict the observational data well, but fail to explain the effect of interventions. We propose an approach, CausalKinetiX, that explicitly takes into account stability across different experiments. This allows us to draw a more realistic picture of the system’s underlying causal structure and is a first step toward increasing reproducibility. Learning kinetic systems from data is one of the core challenges in many fields. Identifying stable models is essential for the generalization capabilities of data-driven inference. We introduce a computationally efficient framework, called CausalKinetiX, that identifies structure from discrete time, noisy observations, generated from heterogeneous experiments. The algorithm assumes the existence of an underlying, invariant kinetic model, a key criterion for reproducible research. Results on both simulated and real-world examples suggest that learning the structure of kinetic systems benefits from a causal perspective. The identified variables and models allow for a concise description of the dynamics across multiple experimental settings and can be used for prediction in unseen experiments. We observe significant improvements compared to well-established approaches focusing solely on predictive performance, especially for out-of-sample generalization.