DeepPANB: integrating protein language model with PaiNN equivariant graph neural networks for prediction of protein–nucleic acid binding sites
Briefings in Bioinformatics · 2026
DOI: 10.1093/bib/bbag450 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Jilong Zhang und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Chemistry and Life Science, Beijing University of Technology, Pingleyuan 100, ChaoYang District, Beijing 100124, China. Hauptthemen laut MEDLINE: Computational Biology, Proteins, Deep Learning, DNA. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Protein–nucleic acid interactions are fundamental to various biological processes, and accurately identifying nucleic acid binding sites on proteins is essential for understanding gene regulation mechanisms and advancing drug design. Here, we present DeepPANB, an effective deep learning model for the issue. DeepPANB is built upon the Polarizable Atom Interaction Neural Network (PaiNN) architecture, an E(3)-equivariant graph neural network, which explicitly couples scalar and vector channels through lightweight message passing, thereby enabling effective modeling of the direction- and distance-dependent residue interactions. DeepPANB integrates multiple feature types including sequence embeddings from the Ankh pretrained model, residue–nucleotide pairwise propensity extracted by us from the large-scale datasets, as well as residue intrinsic disorder, physicochemical properties, and structural descriptors. To our best knowledge, PaiNN and Ankh are first introduced here for protein–nucleic acid binding site prediction. On the protein–DNA test set, DeepPANB achieves state-of-the-art performance, outperforming the existing methods. On protein–RNA test set, DeepPANB, fine-tuned with the feature types unchanged, shows competitive performance. Overall, DeepPANB demonstrates robust and generalizable performance, providing an effective tool for protein–nucleic acid binding site prediction. Freely available at https://github.com/ChunhuaLab/DeepPANB.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- College of Chemistry and Life Science, Beijing University of Technology, Pingleyuan 100, ChaoYang District, Beijing 100124, China.
ORCID-Profile: Chunhua Li
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhang, J., Wu, Z., Su, J., Zhang, X., Li, Y., Li, Z., & Li, C. (2026). DeepPANB: integrating protein language model with PaiNN equivariant graph neural networks for prediction of protein–nucleic acid binding sites. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag450
Vancouver
Zhang J, Wu Z, Su J, Zhang X, Li Y, Li Z, et al. DeepPANB: integrating protein language model with PaiNN equivariant graph neural networks for prediction of protein–nucleic acid binding sites. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag450
BibTeX
@article{Zhang2026,
author = {Zhang, Jilong and Wu, Zhixiang and Su, Jingjie and Zhang, Xinyu and Li, Yue and Li, Zihan and Li, Chunhua},
title = {DeepPANB: integrating protein language model with PaiNN equivariant graph neural networks for prediction of protein–nucleic acid binding sites},
journal = {Briefings in Bioinformatics},
year = {2026},
doi = {10.1093/bib/bbag450}
}
EUVIMED