多层异构生物网络候选疾病基因识别  

Identifying Candidate Disease Genes in Multilayer Heterogeneous Biological Networks

作　　者：丁苍峰 王君[1] 张紫芸 DING Cang-Feng;WANG Jun;ZHANG Zi-Yun(College of Mathematics and Computer Science,Yan'an University,Yan'an 716000)

机构地区：[1]延安大学数学与计算机科学学院,延安716000

出　　处：《自动化学报》2024年第6期1246-1260,共15页Acta Automatica Sinica

基　　金：国家自然科学基金(62262067,62041212,61866038,61763046,61962059);陕西省自然科学基础研究计划(2020JM-548,2020JM547);延安大学基金(YDZ2019-04,YDBK2018-35)资助。

摘　　要：现有大多数用于识别候选疾病基因的随机游走方法通常优先访问高度连接的基因,而可能与已知疾病有关的不知名或连接性差的基因易被忽略或难以识别.此外,这些方法仅访问单个基因网络或各种基因数据的聚合网络,导致偏差和不完整性.因此,设计一种能控制随机游走运动方向和整合多种数据源的候选疾病基因识别方法将是一个迫切需要解决的问题.为此,首先构建多层网络和多层异构基因网络.然后,提出一种游走于多层网络和多层异构网络的拓扑偏置重启随机游走(Biased random walk with restart,BRWR)算法来识别疾病基因.实验结果表明,游走于不同类型网络上的识别候选疾病基因的BRWR算法优于现有的算法.最后,应用于多层异构网络上的BRWR算法能预测未诊断的新生儿类早衰综合征中涉及的疾病基因.Most of existing random walk methods to identify candidate disease genes preferentially visit highly-connected genes,while unwell-known or poorly-connected genes probably relevant to known diseases are more easily ignored or complicated to identify.Moreover,these methods access only a single gene network or an aggregated network of various gene data,leading to bias and incompleteness.Therefore,it is a pressing challenge for controlling the motion direction of random walk and for integrating multiple data sources involving different information for disease-gene identification.To this end,we first construct a multilayer network and multilayer heterogeneous genetic network.Then,we propose a topologically biased random walk with restart(BRWR)algorithm applicable to multilayer and multilayer heterogeneous networks for the identification of candidate disease genes.Experimental results show that the BRWR algorithm to identify candidate disease genes outperforms the state-of-the-art ones on different types of networks.Finally,the BRWR algorithm on multilayer heterogeneous networks is used to predict disease genes implicated in the undiagnosed neonatal progeroid syndrome.

关 键 词：多层异构网络 生物网络 偏置随机游走 候选基因识别 

分 类 号：Q811.4[生物学—生物工程] TP18[自动化与计算机技术—控制理论与控制工程]