Biologically-informed neural networks guide mechanistic modeling from sparse experimental data

TL;DR

This paper introduces biologically-informed neural networks (BINNs) that learn underlying biological dynamics from sparse experimental data by combining neural networks with reaction-diffusion PDEs, providing interpretable mechanistic insights.

Contribution

The work extends physics-informed neural networks to incorporate multilayer perceptrons for reaction and diffusion terms, enabling discovery of biologically meaningful PDE components from limited data.

Findings

Successfully modeled wound healing assays with sparse data

Learned nonlinear reaction and diffusion terms as neural networks

Provided mechanistic insights into biological system dynamics

Abstract

Biologically-informed neural networks (BINNs), an extension of physics-informed neural networks [1], are introduced and used to discover the underlying dynamics of biological systems from sparse experimental data. In the present work, BINNs are trained in a supervised learning framework to approximate in vitro cell biology assay experiments while respecting a generalized form of the governing reaction-diffusion partial differential equation (PDE). By allowing the diffusion and reaction terms to be multilayer perceptrons (MLPs), the nonlinear forms of these terms can be learned while simultaneously converging to the solution of the governing PDE. Further, the trained MLPs are used to guide the selection of biologically interpretable mechanistic forms of the PDE terms which provides new insights into the biological and physical mechanisms that govern the dynamics of the observed system. The method is evaluated on sparse real-world data from wound healing assays with varying initial cell densities [2].