用多时延信息论构建基因调控网络  

Multiple time lagged information theoretic approaches to infer gene regulatory networks

作　　者：高红艳[1] 

机构地区：[1]宝鸡文理学院物理与信息技术系,陕西宝鸡721016

出　　处：《信息技术》2015年第6期23-27,31,共6页Information Technology

基　　金：宝鸡市科技计划资助项目(2013R5-5)

摘　　要：最近涌现出大量基因调控网络重构的模型和方法,但是都没有涉及到基因数据尺寸大小对算法精度的影响问题。文中研究了基因数据尺寸大小对信息论方法构建基因调控网络精度的影响,实验表明基因调控网络构建的精度会在一定数据尺寸规模下达到一个稳态。为了克服互信息的一些缺点,引入文中多时延互信息值来计算两个基因之间的调控关系,所构建的基因调控网络取得了很好的查全率和查准率。并应用它对两个真实的生物分子网络进行重构,结果表明基于多时延的策略下,所构建的基因调控网络取得了很高的特异度和精确度。A number of models and algorithms have been proposed in the past for gene regulatory network（ GRN） inference; however, none of them address the effects of the size of time-series microarray expression data in terms of the number of time-points. This paper studies on this problem by analyzing the behaviour of the algorithm based on information theory. The experiments show that the inference accuracy of these algorithms reaches a saturation point after a specific data size brought about by a saturation in the pair-wise mutual information（ MI） metric. To circumvent the limitations of the MI metric,it introduces a new method of computing time lags between any pair of genes and present the pairwise time lagged mutual information（ TLMI）. Next it uses these new metrics to propose novel GRN inference schemes which provides higher inference accuracy based on the precision and recall parameters. The proposed algorithms were compared to existing approaches on two different biological networks. The results show that the time lags of regulatory effects between any pair of genes play an important role in GRN inference schemes.

关 键 词：生物信息学 基因调控网络 多时延 互信息 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]