EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

CoBRA: compound binding site prediction using RNA language model

Wonkyeong Jang, Woong-Hee Shin iD

Briefings in Bioinformatics · 07.01.2026 · 27 (1)

DOI: 10.1093/bib/bbaf713 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 11.01.2026. Verfasst von Wonkyeong Jang und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, Korea University College of Medicine, 161 Jeongneung-ro, Seongbuk-gu, Seoul 02708, Republic of Korea. Hauptthemen laut MEDLINE: RNA, Deep Learning, Computational Biology, Software. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Institute of Information & Communications Technology Planning & Evaluation (IITP)-ICT Challenge and Advanced Network of HRD (ICAN), Bio & Medical Technology Development Program of the National Research Foundation (NRF), Korea University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RNA performs a variety of functions within cells and is implicated in various human diseases. Because druggable proteins occupy a small portion of the genome, considerable interest has been increasing in developing drugs targeting RNAs. Thus, precise prediction of small-molecule binding sites across different classes of RNAs is important. In this study, a lightweight deep learning program for predicting RNA-drug binding sites, called compound binding site prediction for RNA (CoBRA), is introduced. Our approach utilizes residue-level embeddings derived from a pre-trained RNA language model, without relying on any structural information. These embeddings encapsulate the contextual and statistical properties of each nucleotide and are used as input for a multi-layer perceptron classifier that performs binary classification of binding nucleotides. The model was trained using the TR60 and HARIBOSS datasets and tested on four independent benchmark sets. The performance of CoBRA demonstrates a relative improvement of 22.1% in the Matthew correlation coefficient and a 45.6% increase in sensitivity compared to existing state-of-the-art RNA–ligand binding site prediction methods that utilize structural information. These results demonstrate that sequence-based language model embeddings, which do not require explicit coordinate or distance information, can match or outperform structure-based methods. This makes it a flexible tool for predicting binding sites across diverse RNA targets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RNADeep LearningComputational BiologySoftwareBinding SitesHumansLigandsPrediction Algorithms

Stichwörter der Autor:innen

RNA language modelRNA–small molecule binding site predictionconvolutional neural networkdeep learningpre-trained embedding

Substanzen

RNALigands

Autor:innen und Institutionen

  • Department of Biomedical Informatics, Korea University College of Medicine, 161 Jeongneung-ro, Seongbuk-gu, Seoul 02708, Republic of Korea.
  • Arontier, Co., 241 Gangnam-daero, Seocho-gu, Seoul 06735, Republic of Korea.

ORCID-Profile: Woong-Hee Shin

Förderung

  • Institute of Information & Communications Technology Planning & Evaluation (IITP)-ICT Challenge and Advanced Network of HRD (ICAN)
  • Bio & Medical Technology Development Program of the National Research Foundation (NRF)
  • Korea University
  • Institute of Information & Communications Technology Planning & Evaluation (IITP)—ICT Challenge and Advanced Network of HRD

Zitieren

APA

Jang, W., & Shin, W. H. (2026). CoBRA: compound binding site prediction using RNA language model. Briefings in Bioinformatics, 27(1). https://doi.org/10.1093/bib/bbaf713

Vancouver

Jang W, Shin WH. CoBRA: compound binding site prediction using RNA language model. Briefings in Bioinformatics. 2026;27(1). doi:10.1093/bib/bbaf713

BibTeX
@article{Jang2026,
  author = {Jang, Wonkyeong and Shin, Woong-Hee},
  title = {CoBRA: compound binding site prediction using RNA language model},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  volume = {27},
  number = {1},
  doi = {10.1093/bib/bbaf713}
}
Kostenlos starten →