Journal
IEEE ACCESS
Volume 7, Issue -, Pages 58849-58856Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2019.2914533
Keywords
Disease-related lncRNAs; lncRNA-disease association; network consistency projection; similarity measure
Categories
Funding
- 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]
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available