Long Noncoding RNA function prediction via multiview cross-contrastive learning combined with multiscale semantic adaptive optimization
Briefings in Bioinformatics · 2025
DOI: 10.1093/bib/bbaf650 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Zhixia Teng und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Control Engineering, Northeast Forestry University, No. 26 Hexing Road, Xiangfang District, Harbin, Heilongjiang, China. Hauptthemen laut MEDLINE: RNA, Long Noncoding, Computational Biology, Machine Learning. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Key Technologies Research and Development Program of China, National Natural Science Foundation of China, Science Foundation of Heilongjiang Province.
Abstract (Originalsprache)
Understanding long noncoding RNA (lncRNA) function is essential for revealing molecular mechanisms and developing effective therapies for complex diseases, as lncRNAs play important regulatory roles in many disease-related biological processes. However, existing lncRNA function predictors struggle to extract discriminative features from multimodal omics data and to model the semantic and topological structure of the gene ontology (GO), which severely limits their ability to achieve biologically meaningful and functionally informative predictions. To address these challenges, we propose a novel framework for lncRNA function prediction, namely MiCLSAO. Firstly, MiCLSAO utilizes multiview cross-contrastive learning with attention mechanisms to extract highly discriminative lncRNA features from diverse omics similarity networks. Secondly, graph convolutional networks are applied to learn initial features of GO terms, while multiscale topological and semantic relationships are incorporated to adaptively refine term representations. Finally, an lncRNA function predictor is developed by dynamically integrating the representations of lncRNAs and GO terms using a Kolmogorov–Arnold network. Extensive experiments demonstrate that MiCLSAO consistently outperforms state-of-the-art methods across multiple metrics, with significant capability to recover known functions and uncover novel ones. Moreover, MiCLSAO demonstrates remarkable practical utility and potential value by providing more functionally informative annotations for lncRNAs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- College of Computer and Control Engineering, Northeast Forestry University, No. 26 Hexing Road, Xiangfang District, Harbin, Heilongjiang, China.
- Faculty of Computing, Harbin Institute of Technology, No. 92 Xidazhi Street, Nangang District, Harbin, Heilongjiang, China.
ORCID-Profile: Zhixia Teng, Qingqi Li, Di Liu, Chunyu Wang, Guohua Wang, Yuming Zhao
Förderung
- Key Technologies Research and Development Program of China
- National Natural Science Foundation of China
- Science Foundation of Heilongjiang Province
Zitieren
APA
Teng, Z., Li, Q., Liu, D., Wang, C., Wang, G., & Zhao, Y. (2025). Long Noncoding RNA function prediction via multiview cross-contrastive learning combined with multiscale semantic adaptive optimization. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf650
Vancouver
Teng Z, Li Q, Liu D, Wang C, Wang G, Zhao Y. Long Noncoding RNA function prediction via multiview cross-contrastive learning combined with multiscale semantic adaptive optimization. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf650
BibTeX
@article{Teng2025,
author = {Teng, Zhixia and Li, Qingqi and Liu, Di and Wang, Chunyu and Wang, Guohua and Zhao, Yuming},
title = {Long Noncoding RNA function prediction via multiview cross-contrastive learning combined with multiscale semantic adaptive optimization},
journal = {Briefings in Bioinformatics},
year = {2025},
doi = {10.1093/bib/bbaf650}
}
EUVIMED