Automated, predictive, and interpretable inference of C. elegans escape dynamics

TL;DR

This paper presents an automated AI-driven approach to infer interpretable dynamical models of C. elegans escape behavior from experimental data, capturing complex responses without mechanistic modeling.

Contribution

It introduces a fully automated method using Sir Isaac to infer biologically interpretable models of worm escape dynamics from data, incorporating unobserved variables.

Findings

The inferred model accurately predicts escape behavior dynamics.

The model includes an unobserved dynamical variable.

The approach demonstrates AI's power in modeling complex biological systems.

Abstract

The roundworm C. elegans exhibits robust escape behavior in response to rapidly rising temperature. The behavior lasts for a few seconds, shows history dependence, involves both sensory and motor systems, and is too complicated to model mechanistically using currently available knowledge. Instead we model the process phenomenologically, and we use the Sir Isaac dynamical inference platform to infer the model in a fully automated fashion directly from experimental data. The inferred model requires incorporation of an unobserved dynamical variable, and is biologically interpretable. The model makes accurate predictions about the dynamics of the worm behavior, and it can be used to characterize the functional logic of the dynamical system underlying the escape response. This work illustrates the power of modern artificial intelligence to aid in discovery of accurate and interpretable models of complex natural systems.