4.0 Article

Inferring structural and dynamical properties of gene networks from data with deep learning

期刊

NAR GENOMICS AND BIOINFORMATICS
卷 4, 期 3, 页码 -

出版社

OXFORD UNIV PRESS
DOI: 10.1093/nargab/lqac068

关键词

-

资金

  1. National Key R&D Program of China [2019YFA0709502]
  2. National Natural Science Foundation of China [12171102]

向作者/读者索取更多资源

In this study, the challenges of reconstructing gene regulatory networks (GRNs) from data are tackled using deep neural networks (DNNs). The results show that DNN is superior to existing approaches for network inference and can successfully reconstruct the underlying regulatory networks for different systems. Additionally, the study demonstrates how DNN can unravel complex cell fate dynamics and proposes a data-driven method for quantifying the energy landscape of gene regulatory systems.
The reconstruction of gene regulatory networks (GRNs) from data is vital in systems biology. Although different approaches have been proposed to infer causality from data, some challenges remain, such as how to accurately infer the direction and type of interactions, how to deal with complex network involving multiple feedbacks, as well as how to infer causality between variables from real-world data, especially single cell data. Here, we tackle these problems by deep neural networks (DNNs). The underlying regulatory network for different systems (gene regulations, ecology, diseases, development) can be successfully reconstructed from trained DNN models. We show that DNN is superior to existing approaches including Boolean network, Random Forest and partial cross mapping for network inference. Further, by interrogating the ensemble DNN model trained from single cell data from dynamical system perspective, we are able to unravel complex cell fate dynamics during preimplantation development. We also propose a data-driven approach to quantify the energy landscape for gene regulatory systems, by combining DNN with the partial self-consistent mean field approximation (PSCA) approach. We anticipate the proposed method can be applied to other fields to decipher the underlying dynamical mechanisms of systems from data.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.0
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据