LncRNA-Top : Controlled Deep Learning Approaches for LncRNA Gene Regulatory Relationship Annotations across Different Platforms

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations


Original languageEnglish
Article number108197
Journal / PublicationiScience
Issue number11
Online published12 Oct 2023
Publication statusPublished - 17 Nov 2023



By acting as competitive endogenous RNAs (ce-RNAs) through soaking microRNAs (miRNAs), long non-coding RNAs (lncRNAs) have the potential to control gene expression. Few methods have been created based on this mechanism to anticipate the lncRNA-gene relationship prediction. Hence, we present lncRNA-Top to forecast potential lncRNA-gene regulation relationships originating from the regulatory mechanism. Specifically, we constructed controlled deep-learning methods using 12417 lncRNAs and 16127 genes. We have provided retrospective and innovative views among negative sampling, random seeds, cross-validation, metrics, and independent datasets. The AUC, AUPR, and our defined precision@k were leveraged to evaluate performance. In-depth case studies demonstrate that 47 out of 100 projected top unknown pairings were recorded in publications, supporting the predictive power of the suggested technique. Our additional software can present the score with target candidates by inputting a lncRNA and gene ensembl. The lncRNA-Top will be a helpful tool to uncover prospective lncRNA targets and better comprehend the regulatory processes of lncRNAs. The source code and software can be downloaded at http://lncrna.cs.cityu.edu.hk/
© 2023 The Author(s).

Research Area(s)

  • lncRNA, lncRNA-Gene, Controlled Deep-Learning, ensemble methods

Citation Format(s)

Download Statistics

No data available