ZHMolTopoRPI: A Commutative Algebra-Driven Deep Learning Framework for Robust RNA-Protein Interaction Prediction
Journal of Chemical Information and Modeling · 13.07.2026 · 66 (13) · 7772-7788
DOI: 10.1021/acs.jcim.6c01199 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 26.06.2026. Verfasst von Long Chen und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Biophysics and Department of Physics, Central China Normal University, Wuhan 430079, China. Hauptthemen laut MEDLINE: Deep Learning, RNA, Proteins, Computational Biology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: Central China Normal University, Science Fund for Distinguished Young Scholars of Hubei Province, National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate prediction of RNA-protein interactions (RPIs) is crucial for understanding post-transcriptional regulation. Most existing models depend on implicit embeddings within large language models, which limits their physical interpretability. This study introduces ZHMolTopoRPI, a computational framework that integrates persistent commutative algebra with dual-tower neural networks. We employ the persistent Stanley-Reisner theory (PSRT) to extract multiscale mathematical features from RNA sequences. For feature fusion and RPI prediction, we use a contrastive learning-enhanced gated attention dual-tower network (CL-GADTN) to combine RNA features with protein semantic information from ESM2. Evaluation on six benchmark data sets (NPInter2, RPI7317, RPI488, RPI1807, RPI2241, and NPInter v2.0) demonstrated MCC scores of 92.29, 84.83, 81.55, 88.42, 89.23, and 92.63%, respectively. Additionally, the model's analysis of commutative algebra perturbations revealed motif changes caused by pathogenic single nucleotide polymorphisms (SNPs). We further validated ZHMolTopoRPI's practical utility in functional target screening of the human proteome. Overall, it offers a quantitative and interpretable approach for precise RPI prediction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Institute of Biophysics and Department of Physics, Central China Normal University, Wuhan 430079, China.
ORCID-Profile: Yunjie Zhao
Förderung
- Central China Normal University
- Science Fund for Distinguished Young Scholars of Hubei Province
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central China Normal Universities
Zitieren
APA
Chen, L., Liu, H., & Zhao, Y. (2026). ZHMolTopoRPI: A Commutative Algebra-Driven Deep Learning Framework for Robust RNA-Protein Interaction Prediction. Journal of Chemical Information and Modeling, 66(13), 7772-7788. https://doi.org/10.1021/acs.jcim.6c01199
Vancouver
Chen L, Liu H, Zhao Y. ZHMolTopoRPI: A Commutative Algebra-Driven Deep Learning Framework for Robust RNA-Protein Interaction Prediction. Journal of Chemical Information and Modeling. 2026;66(13):7772-7788. doi:10.1021/acs.jcim.6c01199
BibTeX
@article{Chen2026,
author = {Chen, Long and Liu, Haoquan and Zhao, Yunjie},
title = {ZHMolTopoRPI: A Commutative Algebra-Driven Deep Learning Framework for Robust RNA-Protein Interaction Prediction},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
volume = {66},
number = {13},
pages = {7772--7788},
doi = {10.1021/acs.jcim.6c01199}
}
EUVIMED