摘要
针对目前关键基因预测不准确和预测算法缺乏等问题,本文提出一种基于控制理论的关键基因预测算法。首先,从TCGA数据库收集结直肠癌数据,使用计算机工具预处理数据,并利用结直肠癌数据和LncMAP数据库数据构建lncRNATF-gene调控网络。然后,设计一种新的筛选方法,基于控制理论中的最小驱动节点集思想和可控性动态分类理论,筛选得到关键节点基因集;将突变得分和网络拓扑分析方法得分融合分析,得到潜在关键基因集。最后,对关键节点基因集和潜在关键基因集取交集,得到关键基因集。结合相关文献和CGC数据库对关键基因集进行验证,证实了该预测算法的有效性,为预测结直肠癌关键基因提供了一种新的思路和方法。
Aiming at the problems of inaccurate prediction of key genes and lack of prediction algorithm,this paper proposes a key gene prediction algorithm based on control theory.Firstly,the data of colorectal cancer were collected from TCGA database,and preprocessed by computer tools.The lncRNA-TF-gene regulatory network was constructed using colorectal cancer data and Lnc⁃MAP database data.Then,a new screening method is designed,based on the idea of minimum driven node set in control theory and controllable dynamic classification theory,the key node gene set is screened;the mutation score and network topology analysis score are fused to get the potential key gene set.Finally,the intersection of key node gene set and potential key gene set is ob⁃tained.Combined with the relevant literature and CGC database to verify the key gene set,the effectiveness of the prediction algo⁃rithm is confirmed,which provides a new idea and method for predicting the key genes of colorectal cancer.
作者
宋子健
岳欣蕾
李建伟
SONG Zi-jian;YUE Xin-lei;LI Jian-wei(School of Artificial Intelligence and Data Science,Hebei University of Technology,Tianjin 300130,China)
出处
《电脑知识与技术》
2021年第30期28-32,共5页
Computer Knowledge and Technology
基金
国家自然科学基金(编号:81672113)。
