EUVIMEDEUVIMED entdecken
Crossref

MultiRSF: A Deep Learning Approach for Predicting RNA-Small-Molecule Binding Sites Using Surface Characteristics

Jiasai Shu, Wentao Xia, Yingjie Zheng, Yucheng Shu, Zhiyuan Zhao, Mei Feng iD, Yan Wang iD, Xiaogang Wang, Bijun Xu, Xiaojun Xu, Tingting Sun iD

Journal of Chemical Information and Modeling · 28.09.2026 · 66 (18) · 11711-11722

DOI: 10.1021/acs.jcim.6c02039 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 08.09.2026. Verfasst von Jiasai Shu und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physics, Zhejiang University of Science and Technology, Hangzhou310008, China. Hauptthemen laut MEDLINE: RNA, Deep Learning, Small Molecule Libraries. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Zhejiang Province, Zhejiang Sci-Tech University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Identification of RNA-small-molecule binding sites is a critical first step in RNA-targeted drug discovery. Although several machine learning methods have made progress by integrating RNA sequence, secondary structure, and 3-dimensional (3D) atomic arrangement information to identify nucleotide level binding residues, most of them neglect the molecular surface that directly contacts small-molecule compounds and are highly dependent on accurate three-dimensional structures. Here, we present MultiRSF, a multimodal deep learning framework that integrates molecular surface fingerprints, contextual sequence embeddings from a pretrained RNA language model and dot bracket secondary structure encoding to predict ligand binding sites on RNA. MultiRSF fuses these features through a hierarchical Transformer encoder and demonstrates robust predictive performance on both ligand-free RNA structures (apo RNA) and ligand-bound RNA structures (holo RNA). On independent benchmark sets TE18 and APO8, MultiRSF outperforms state-of-the-art methods, achieving precision of 0.765/0.458, recall of 0.698/0.286, and Matthews correlation coefficient (MCC) of 0.535/0.279. Case studies on a ligand-induced riboswitch conformational change and an NMR conformational ensemble further illustrate the model’s robustness to moderate RNA flexibility. In conclusion, MultiRSF provides an accurate and generalizable tool for nucleotide resolution binding sites prediction, with potential to accelerate early-stage RNA-targeted drug discovery.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RNADeep LearningSmall Molecule LibrariesBinding SitesNucleic Acid ConformationLigandsSurface PropertiesModels, Molecular

Substanzen

RNASmall Molecule LibrariesLigands

Autor:innen und Institutionen

  • Department of Physics, Zhejiang University of Science and Technology, Hangzhou310008, China.
  • Institute of Bioinformatics and Medical Engineering, Jiangsu University of Technology, Changzhou213001, China.
  • Zhejiang Key Laboratory of Biomedical Intelligent Computing Technology, Hangzhou310008, China.

ORCID-Profile: Mei Feng, Yan Wang, Tingting Sun

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Zhejiang Province
  • Zhejiang Sci-Tech University

Zitieren

APA

Shu, J., Xia, W., Zheng, Y., Shu, Y., Zhao, Z., Feng, M., Wang, Y., Wang, X., Xu, B., Xu, X., & Sun, T. (2026). MultiRSF: A Deep Learning Approach for Predicting RNA-Small-Molecule Binding Sites Using Surface Characteristics. Journal of Chemical Information and Modeling, 66(18), 11711-11722. https://doi.org/10.1021/acs.jcim.6c02039

Vancouver

Shu J, Xia W, Zheng Y, Shu Y, Zhao Z, Feng M, et al. MultiRSF: A Deep Learning Approach for Predicting RNA-Small-Molecule Binding Sites Using Surface Characteristics. Journal of Chemical Information and Modeling. 2026;66(18):11711-11722. doi:10.1021/acs.jcim.6c02039

BibTeX
@article{Shu2026,
  author = {Shu, Jiasai and Xia, Wentao and Zheng, Yingjie and Shu, Yucheng and Zhao, Zhiyuan and Feng, Mei and Wang, Yan and Wang, Xiaogang and Xu, Bijun and Xu, Xiaojun and Sun, Tingting},
  title = {MultiRSF: A Deep Learning Approach for Predicting RNA-Small-Molecule Binding Sites Using Surface Characteristics},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  volume = {66},
  number = {18},
  pages = {11711--11722},
  doi = {10.1021/acs.jcim.6c02039}
}
Kostenlos starten →