Inference of dynamical gene regulatory networks from single-cell data with physics informed neural networks
This addresses the limited predictive power of existing GRN inference methods in developmental biology, offering a more mechanistic approach, though it appears incremental as it applies an existing neural network technique (PINNs) to a specific domain.
The paper tackled the problem of inferring predictive, dynamical gene regulatory networks (GRNs) from single-cell data, showing that physics-informed neural networks (PINNs) outperform regular feed-forward neural networks in parameter inference tasks for scenarios with and without cell communication.
One of the main goals of developmental biology is to reveal the gene regulatory networks (GRNs) underlying the robust differentiation of multipotent progenitors into precisely specified cell types. Most existing methods to infer GRNs from experimental data have limited predictive power as the inferred GRNs merely reflect gene expression similarity or correlation. Here, we demonstrate, how physics-informed neural networks (PINNs) can be used to infer the parameters of predictive, dynamical GRNs that provide mechanistic understanding of biological processes. Specifically we study GRNs that exhibit bifurcation behavior and can therefore model cell differentiation. We show that PINNs outperform regular feed-forward neural networks on the parameter inference task and analyze two relevant experimental scenarios: 1. a system with cell communication for which gene expression trajectories are available and 2. snapshot measurements of a cell population in which cell communication is absent. Our analysis will inform the design of future experiments to be analyzed with PINNs and provides a starting point to explore this powerful class of neural network models further.