Abstract
Recently, many biological experiments have indicated that microRNAs (miRNAs) are a newly discovered small molecule (SM) drug targets that play an important role in the development and progression of human complex diseases. More and more computational models have been developed to identify potential associations between SMs and target miRNAs, which would be a great help for disease therapy and clinical applications for known drugs in the field of medical research. In this study, we proposed a computational model of triple layer heterogeneous network based small molecule–MiRNA association prediction (TLHNSMMA) to uncover potential SM–miRNA associations by integrating integrated SM similarity, integrated miRNA similarity, integrated disease similarity, experimentally verified SM–miRNA associations and miRNA–disease associations into a heterogeneous graph. To evaluate the performance of TLHNSMMA, we implemented global and two types of local leave-one-out cross validation as well as fivefold cross validation to compare TLHNSMMA with one previous classical computational model (SMiR-NBI). As a result, for Dataset 1, TLHNSMMA obtained the AUCs of 0.9859, 0.9845, 0.7645 and 0.9851 ± 0.0012, respectively; for Dataset 2, the AUCs are in turn 0.8149, 0.8244, 0.6057 and 0.8168 ± 0.0022. As the result of case studies shown, among the top 10, 20 and 50 potential SM-related miRNAs, there were 2, 7 and 14 SM–miRNA associations confirmed by experiments, respectively. Therefore, TLHNSMMA could be effectively applied to the prediction of SM–miRNA associations.
Highlights
MicroRNA is a small non-coding RNA molecule discovered in plants, animals, human beings and even some viruses, that functions in RNA silencing and post-transcriptional regulation of gene expression [1, 2]
Performance evaluation We used global and local leave-one-out cross validation (LOOCV) as well as fivefold cross validation based on the known small mol‐ ecule (SM)–miRNA associations in SM2miR v1.0 database to evaluate the performance of TLHNSMMA
More and more attentions have focused on the identification of miRNA– SM associations in diseases, which would be helpful for developing a novel effective miRNA-associated therapeutic strategy
Summary
MicroRNA (miRNA) is a small non-coding RNA molecule (about 22 nucleotides) discovered in plants, animals, human beings and even some viruses, that functions in RNA silencing and post-transcriptional regulation of gene expression [1, 2]. MiRNAs were not recognized as a distinct class of biological regulators until the early 2000s [5, 6]. Regulation of miRNAs by synthesized oligonucleotides or small molecules is an efficient means to modulate endogenous miRNA function and treat miRNA-related diseases. They are being considered as a novel type of bio-markers or potential therapeutic targets for various diseases [21]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
