期刊
IEEE ACCESS
卷 7, 期 -, 页码 58849-58856出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2019.2914533
关键词
Disease-related lncRNAs; lncRNA-disease association; network consistency projection; similarity measure
资金
- National Natural Science Foundation of China [61862025, 61873089, 61602283, 11862006, 61861017, 61862023]
- Jiangxi Provincial Natural Science Foundation [20181BAB211016, 2018ACB21032, 20181BAB211013, 20181BAB202007]
- Scientific and Technological Research Project of Education Department in Jiangxi Province [GJJ170383, GJJ170381, GJJ170414]
- Hunan Provincial Natural Science Foundation [2018JJ2024]
A growing body of research has uncovered the role of long noncoding RNAs (lncRNAs) in multiple biological processes and tumorigenesis. Predicting novel interactions between diseases and lncRNAs could help decipher disease pathology and discover new drugs. However, because of a lack of data, inferring disease-lncRNA associations accurately and efficiently remains a challenge. In this paper, we present a novel network consistency projection for LncRNA-disease association prediction (NCPLDA) model by integrating the lncRNA-disease association probability matrix with the integrated disease similarity and lncRNA similarity. The lncRNA-disease association probability matrix is calculated based on known lncRNA-disease associations and disease semantic similarity. The integrated disease similarity and lncRNA similarity are computed based on disease semantic similarity, lncRNA functional similarity and Gaussian interaction profile kernel similarity. In leave-one-out cross validation experiments, NCPLDA achieved outstanding AUCs of 0.8900, 0.8996, and 0.9012 for three datasets. Furthermore, prostate cancer and ovarian cancer case studies demonstrated that the NCPLDA can effectively infer undiscovered lncRNAs.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据