Deciphering gene regulation from gene expression dynamics using deep neural network

TL;DR

This paper demonstrates that deep neural networks can effectively infer gene regulation networks from gene expression dynamics, providing accurate simulations and insights into biological functions with minimal experimental data.

Contribution

The authors introduce an interpretable deep neural network approach to uncover gene regulation networks directly from gene expression data, reducing reliance on extensive experiments.

Findings

DNN successfully identifies key network motifs for biochemical adaptation.

DNN accurately predicts mutant behaviors in fruit fly embryogenesis.

The inferred gene regulation network closely matches experimental results.

Abstract

Complex biological functions are carried out by the interaction of genes and proteins. Uncovering the gene regulation network behind a function is one of the central themes in biology. Typically, it involves extensive experiments of genetics, biochemistry and molecular biology. In this paper, we show that much of the inference task can be accomplished by a deep neural network (DNN), a form of machine learning or artificial intelligence. Specifically, the DNN learns from the dynamics of the gene expression. The learnt DNN behaves like an accurate simulator of the system, on which one can perform in-silico experiments to reveal the underlying gene network. We demonstrate the method with two examples: biochemical adaptation and the gap-gene patterning in fruit fly embryogenesis. In the first example, the DNN can successfully find the two basic network motifs for adaptation - the negative feedback and the incoherent feed-forward. In the second and much more complex example, the DNN can accurately predict behaviors of essentially all the mutants. Furthermore, the regulation network it uncovers is strikingly similar to the one inferred from experiments. In doing so, we develop methods for deciphering the gene regulation network hidden in the DNN "black box". Our interpretable DNN approach should have broad applications in genotype-phenotype mapping.