图神经网络及其当前在生物信息学中的应用,Frontiers in Genetics

当前位置： X-MOL 学术 › Front. Genet. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

图神经网络及其当前在生物信息学中的应用
Frontiers in Genetics ( IF 2.8 ) Pub Date : 2021-05-28 , DOI: 10.3389/fgene.2021.690049
Xiao-Meng Zhang ₁ , Li Liang ₁ , Lin Liu _{1,

2} , Ming-Jing Tang _{2,

3}

Affiliation

图神经网络（GNN）作为非欧几里得空间深度学习的一个分支，在处理图结构数据的各种任务中表现得特别好。随着生物网络数据的快速积累，GNN也成为生物信息学的重要工具。在这项研究中，从多个角度对 GNN 及其在生物信息学方面的进展进行了系统的调查。我们首先介绍一些常用的GNN模型及其基本原理。然后，基于 GNN 可以学习的三个层次的结构信息，提出了三个代表性任务：节点分类、链接预测和图生成。同时，根据各种组学数据的具体应用，我们从疾病预测、药物发现和生物医学成像三个方面对相关研究进行分类和讨论。在此基础上，我们展望了当前研究的不足，并指出了其发展前景。尽管目前GNN在许多生物任务中取得了优异的成果，但仍面临低质量数据处理、方法论和可解释性方面的挑战，还有很长的路要走。我们相信 GNN 可能是解决生物信息学研究中各种生物学问题的绝佳方法。

"点击查看英文标题和摘要"

Graph neural networks and their current applications in bioinformatics

Graph neural networks (GNNs), as a branch of deep learning in non-Euclidean space, perform particularly well in various tasks that process graph structure data. With the rapid accumulation of biological network data, GNNs have also become an important tool in bioinformatics. In this research, a systematic survey of GNNs and their advances in bioinformatics is presented from multiple perspectives. We first introduce some commonly used GNN models and their basic principles. Then, three representative tasks are proposed based on the three levels of structural information that can be learned by GNNs: node classification, link prediction and graph generation. Meanwhile, according to the specific applications for various omics data, we categorize and discuss the related studies in three aspects: disease prediction, drug discovery and biomedical imaging. Based on the analysis, we outlook on the shortcomings of current studies and point out their developing prospect. Although GNNs have achieved excellent results in many biological tasks at present, it still faces challenges in terms of low-quality data processing, methodology and interpretability, and has a long road ahead. We believe that GNNs are potentially a wonderful method that solves various biological problems in bioinformatics research.

更新日期：2021-05-28

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文本刊介绍/投稿指南