APP下载

基于控制理论的关键基因预测算法

2021-11-28宋子健岳欣蕾李建伟

电脑知识与技术 2021年30期

宋子健 岳欣蕾 李建伟

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lncRNA-TF-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。

关键词:控制理论;关键基因;结直肠癌;最小驱动节点集

中图分类号:TP301      文献标识码:A

文章编号:1009-3044(2021)30-0028-05

开放科学(资源服务)标识码(OSID):

Key Gene Prediction Algorithm Based on Control Theory

SONG Zi-jian, YUE Xin-lei, LI Jian-wei

(School of Artificial Intelligence and Data Science, Hebei University of Technology, Tianjin 300130, China)

Abstract: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 LncMAP 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 obtained. Combined with the relevant literature and CGC database to verify the key gene set, the effectiveness of the prediction algorithm is confirmed, which provides a new idea and method for predicting the key genes of colorectal cancer.

Key words:control theory; key genes; colorectal cancer; minimum driven node set

1 引言

癌癥是严重危害中国人民健康的公共卫生问题,且近几年来罹患癌症人数处于不断增长状态。而作为第三大恶性肿瘤的结直肠癌由于具有恶性程度高、病程进展迅速、易复发和转移等特点,对人类健康和生命安全构成重大威胁。结直肠癌的形成始于正常上皮粘膜向过度增生上皮的转化,这些过度增殖的肠上皮细胞由于失去其组织和结构,所以具有形成腺瘤的能力。少部分的结直肠癌病例是遗传性的,而绝大部分是散发性的[1]。研究表明[2],结直肠癌的发生发展与多基因及多因素有关。……

登录APP查看全文