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.

发展生物学的主要目标之一是揭示基因调控网络（GRNs）以实现多能祖细胞向具体细胞类型的准确分化。本文展示了如何使用物理信息神经网络（PINNs）推断预测性和动力学的 GRNs 参数，以提供生物过程的机制理解。我们的分析将为今后使用 PINNs 进行实验设计提供参考，并为进一步探索这一强大类神经网络模型提供起点。

利用物理信息化的神经网络从单细胞数据推断动态基因调控网络

Inference of dynamical gene regulatory networks from single-cell data  with physics informed neural networks

Advances in science and engineering often reveal the limitations of classical
approaches initially used to understand, predict, and control phenomena. With
progress, conceptual categories must often be re-evaluated to better track
recently discovered invariants across disciplines. It is essential to refine
frameworks and resolve conflicting boundaries between disciplines such that
they better facilitate, not restrict, experimental approaches and capabilities.
In this essay, we discuss issues at the intersection of developmental biology,
computer science, and robotics. In the context of biological robots, we explore
changes across concepts and previously distinct fields that are driven by
recent advances in materials, information, and life sciences. Herein, each
author provides their own perspective on the subject, framed by their own
disciplinary training. We argue that as with computation, certain aspects of
developmental biology and robotics are not tied to specific materials; rather,
the consilience of these fields can help to shed light on issues of multi-scale
control, self-assembly, and relationships between form and function. We hope
new fields can emerge as boundaries arising from technological limitations are
overcome, furthering practical applications from regenerative medicine to
useful synthetic living machines.

探讨生物机器人的概念在材料科学、信息科学和生命科学等之间的变化和交叉，以及生物学、计算机科学和机器人学的交叉研究可能带来的多尺度控制、自组装和形态与功能之间关系的问题。