基于网络相似性整合算法的lncRNA与miRNA相互作用预测研究  

Prediction of potential lncRNA-miRNA interactions through a Network similarity integration method

作　　者：丁尉哲 南洋 吴卷书 崔迪 张力[1,2,3] 刘宏生 DING Wei-zhe(School of life science,Liaoning University,Shenyang 110036,China)

机构地区：[1]辽宁大学生命科学院 [2]辽宁省生物大分子计算模拟与信息处理工程技术研究中心 [3]辽宁省药物分子模拟与设计工程实验室,辽宁沈阳110036

出　　处：《牡丹江医学院学报》2021年第4期62-65,103,共5页Journal of Mudanjiang Medical University

基　　金：辽宁省教育厅科学研究经费项目(青年科技人才“育苗”项目)(LQN201906)。

摘　　要：目的提出一种基于网络相似性算法的lncRNA-miRNA相互作用预测新方法。方法在lncRNASNP2、LNCipedia、miRBase、NONCODE、microRNA、miRTarBase 7.0数据库中筛选lncRNA-miRNA互作关系及lncRNA和miRNA的序列、表达谱、功能数据后,应用Needleman-Wunsch算法分析lncRNA和miRNA的序列相似度并整合到不同的相似度矩阵中,最终使用NSILMI模型处理并得到预测的lncRNA-miRNA互作得分。结果当α为0.7时,基于序列相似度的NSILMI获得了最高的预测性能;在5折交叉验证中,其ROC曲线下面积为0.9814,显示出较好的预测准确性;基于功能相似度和表达谱相似度计算的AUC值分别为0.8831和0.8654;同时,通过NSILMI模型预测得到的20个lncRNA-miRNA互作对中的16个已被实验验证。结论本研究提出一种用于预测lncRNA-miRNA相互作用的NSILMI模型;该模型为lncRNA-miRNA关联的预测提供了新手段,也为复杂疾病的研究提供新方法和思路。Objective A new method for predicting lncRNA-miRNA interactions based on a network similarity algorithm is proposed,which provides a new theoretical basis for further research on the mechanism of lncRNA-miRNA regulation of diseases.Methods After screening the lncRNA-miRNA interaction data and the sequence,expression profile,and function data of lncRNAs and miRNAs in the lncRNASNP2,LNCipedia,miRbase,NONCODE,microRNA,and miRTarBase 7.0 database,the Needleman-Wunsch algorithm applied to analyze the sequence similarity of lncRNAs and miRNAs and integrate them into different similarity matrices.Finally,the NSILMI model was used for processing,and the predicted lncRNA-miRNA interaction score was got.Results Whenαwas 0.7,NSILMI based on sequence similarity achieved the highest prediction performance.In the 5-fold cross-validation,the area under the ROC curve was 0.9814,which showed a good prediction accuracy.AUC values calculated based on functional similarity and expression profile similarity were 0.8831 and 0.8654,respectively.Meanwhile,16 of the 20 lncRNA-miRNA interaction pairs predicted by the NSILMI model had been verified experimentally.Conclusion In this study,a NSILMI model was proposed to predict lncRNA-miRNA interactions.This model provides a new means for predicting lncRNA-miRNA association and provides new methods and new ideas for the study of complex diseases.

关 键 词：lncRNA-miRNA 网络相似性整合算法 相互作用预测 归一化处理 

分 类 号：R341[医药卫生—基础医学]