GRASSP: RNA language model–enhanced graph attention with adaptive gating for RNA–small molecule binding site prediction
Bioinformatics · 31.08.2026 · 42 (9)
DOI: 10.1093/bioinformatics/btag638 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 22.08.2026. Verfasst von Thi Lan Nguyen und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical Engineering and Computer Science, The University of Queensland, St Lucia, Brisbane, QLD 4072, Australia. Hauptthemen laut MEDLINE: RNA, Computational Biology, Software, Deep Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council.
Abstract (Originalsprache)
Motivation RNA–small molecule binding site prediction is crucial for targeted drug discovery. Sequence-based methods are efficient but often fail to capture structural dependencies between nucleotides, whereas structure-aware graph models can better represent spatial interactions but typically rely on complex structural annotations and multi-stage preprocessing pipelines. We therefore developed GRASSP, a streamlined hybrid deep learning framework that integrates pretrained RNA language model (LM) representations with adaptive graph refinement. Results GRASSP leverages nucleotide embeddings and predicted secondary-structure features from a pretrained RNA LM to construct spatial RNA graphs, followed by a lightweight two-step graph attention refinement module with adaptive gating to capture local and contextual nucleotide dependencies. Across four benchmark datasets (TE18, HARIBOSS, TL12, and JL10), GRASSP generally outperformed state-of-the-art baselines, with improvements of up to 24.1% in AUC and 44.5% in MCC. Ablation analyses showed that pretrained RNA representations provided the dominant predictive contribution, while spatial graph refinement offered complementary but dataset-dependent benefits. These results demonstrate that GRASSP provides a competitive framework for integrating pretrained RNA representations with spatial structural context while reducing reliance on additional handcrafted structural annotations. Availability Code and datasets are publicly available at https://github.com/langiocn/GRASSP, with an archival snapshot available on Zenodo at https://doi.org/10.5281/zenodo.21888291.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Electrical Engineering and Computer Science, The University of Queensland, St Lucia, Brisbane, QLD 4072, Australia.
- AIBioMed Lab, Taipei Medical University, Taipei 110, Taiwan.
- In-Service Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei 110, Taiwan.
- Translational Imaging Research Center, Taipei Medical University Hospital, Taipei 110, Taiwan.
ORCID-Profile: Thi Lan Nguyen, Nguyen Quoc Khanh Le
Förderung
- National Science and Technology Council
Zitieren
APA
Nguyen, T. L., & Le, N. Q. K. (2026). GRASSP: RNA language model–enhanced graph attention with adaptive gating for RNA–small molecule binding site prediction. Bioinformatics, 42(9). https://doi.org/10.1093/bioinformatics/btag638
Vancouver
Nguyen TL, Le NQK. GRASSP: RNA language model–enhanced graph attention with adaptive gating for RNA–small molecule binding site prediction. Bioinformatics. 2026;42(9). doi:10.1093/bioinformatics/btag638
BibTeX
@article{Nguyen2026,
author = {Nguyen, Thi Lan and Le, Nguyen Quoc Khanh},
title = {GRASSP: RNA language model–enhanced graph attention with adaptive gating for RNA–small molecule binding site prediction},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {9},
doi = {10.1093/bioinformatics/btag638}
}
EUVIMED