EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

MegSite: an accurate nucleic acid-binding residue prediction method based on multimodal protein language model

Feng Hu iD, Wenwu Zeng, Shaoliang Peng

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf524 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Feng Hu und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, China. Hauptthemen laut MEDLINE: RNA, Computational Biology, DNA, RNA-Binding Proteins. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Key Technologies R&D Program of Guangdong Province, Top 10 Technical Key Project in Hunan Province, Key R&D Program of Hunan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate identification of nucleic acid-binding residues is crucial for understanding protein–nucleic acid interactions, which play a key role in gene expression research and the discovery of regulatory mechanisms. Despite numerous computational efforts to address this challenge, achieving high accuracy remains difficult due to the complexity of extracting meaningful insights from proteins. Here, we introduce MegSite, a novel multimodal protein language model-informed method that integrates discriminative knowledge from protein sequence, structure, and function. This work presents the first integration of ESM3 multimodal features for nucleic acid-binding site prediction. MegSite significantly outperforms existing prediction methods, as evidenced by its performance on multiple independent test sets. The Matthews correlation coefficient values achieved by MegSite on DNA-129_Test, DNA-181_Test, RNA-117_Test, and RNA-285_Test are 0.567, 0.444, 0.411, and 0.421, representing the improvements of 2.72%, 7.66%, 1.22% and 6.58% over the second-best method separately. Notably, MegSite demonstrates robust performance even on proteins with low structural similarity, surpassing the previous structure-based methods. Furthermore, this method is seamlessly extendable to the predicted protein structure and a newly released RNA-binding residue test set with high accuracy, highlighting its broad applicability. Comprehensive experimental results reveal that the superior performance of MegSite is attributed to its effective integration of multimodal protein knowledge.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RNAComputational BiologyDNARNA-Binding ProteinsSoftwareProteinsNucleic AcidsBinding SitesProtein BindingAlgorithms

Stichwörter der Autor:innen

E(n)-equivariant graph neural networkmultimodal protein language modelnucleic acid binding site prediction

Substanzen

RNADNARNA-Binding ProteinsProteinsNucleic Acids

Autor:innen und Institutionen

  • College of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, China.
  • College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China.

ORCID-Profile: Feng Hu

Förderung

  • Key Technologies R&D Program of Guangdong Province
  • Top 10 Technical Key Project in Hunan Province
  • Key R&D Program of Hunan Province
  • The Innovative Research Group Project of Hunan Province
  • National Key R&D Program of China
  • NSFC-FDCT

Zitieren

APA

Hu, F., Zeng, W., & Peng, S. (2025). MegSite: an accurate nucleic acid-binding residue prediction method based on multimodal protein language model. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf524

Vancouver

Hu F, Zeng W, Peng S. MegSite: an accurate nucleic acid-binding residue prediction method based on multimodal protein language model. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf524

BibTeX
@article{Hu2025,
  author = {Hu, Feng and Zeng, Wenwu and Peng, Shaoliang},
  title = {MegSite: an accurate nucleic acid-binding residue prediction method based on multimodal protein language model},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf524}
}
Kostenlos starten →