AFPDeepPred: A Deep Learning Framework for Accurate Identification of Antifreeze Proteins
Journal of Chemical Information and Modeling · 24.11.2025 · 65 (22) · 12256-12267
DOI: 10.1021/acs.jcim.5c02024 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 31.10.2025. Verfasst von Xingqiao Lin und 12 weiteren Autor:innen. Beteiligte Einrichtung: School of Informatics, Xiamen University, 361005 Xiamen, China. Hauptthemen laut MEDLINE: Deep Learning, Antifreeze Proteins, Computational Biology. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: University of Hong Kong, Basic and Applied Basic Research Foundation of Guangdong Province, University Grants Committee.
Abstract (Originalsprache)
Antifreeze proteins (AFPs) are essential for the survival of organisms in subzero environments and have significant potential in biomedical and agricultural applications. However, their high sequence diversity poses a significant challenge for accurate high-throughput identification. To address this, we propose AFPDeepPred, a novel multimodal deep learning framework that explicitly integrates global and local sequence information for AFP prediction. Specifically, AFPDeepPred combines evolutionary scale modeling, which captures long-range evolutionary dependencies, with chaos game representation, which highlights local motif distributions by transforming protein sequences into image-like matrices. These heterogeneous features are then fused using a bilinear attention network, allowing high-order interaction across both local and global features. Experimental results demonstrate that AFPDeepPred achieves state-of-the-art performance on reviewed Swiss-Prot-based data sets, with an accuracy of 93.46%. Moreover, the model consistently outperforms existing methods in all evaluation metrics, offering a robust and generalizable solution for AFP identification.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Informatics, Xiamen University, 361005 Xiamen, China.
- Kobilka Institute of Innovative Drug Discovery, School of Medicine, The Chinese University of Hong Kong, Shenzhen, 2001 Longxiang Road, 518172 Shenzhen, China.
- Division of Applied Oral Sciences and Community Dental Care, Faculty of Dentistry, The University of Hong Kong, Pok Fu Lam, Hong Kong 999077, China.
- Faculty of Applied Sciences, Macao Polytechnic University, R. de Lúıs Gonzaga Gomes, 999078 Macao, China.
- Institute of Bioinformatics and Systems Biology, National Yang Ming Chiao Tung University, 300093 Hsinchu, Taiwan.
ORCID-Profile: Leyi Wei, Ying-Chih Chiang, Junwen Wang, Lantian Yao
Förderung
- University of Hong Kong
- Basic and Applied Basic Research Foundation of Guangdong Province
- University Grants Committee
- National Natural Science Foundation of China
- Kobilka Institute of Innovative Drug Discovery, Chinese University of Hong Kong
- School of Informatics, Xiamen University
Zitieren
APA
Lin, X., Guan, J., Wang, F., Xie, P., Zhao, Y., Zhao, Z., Xiang, M., Wei, L., Liu, X., Lee, T. Y., Chiang, Y. C., Wang, J., & Yao, L. (2025). AFPDeepPred: A Deep Learning Framework for Accurate Identification of Antifreeze Proteins. Journal of Chemical Information and Modeling, 65(22), 12256-12267. https://doi.org/10.1021/acs.jcim.5c02024
Vancouver
Lin X, Guan J, Wang F, Xie P, Zhao Y, Zhao Z, et al. AFPDeepPred: A Deep Learning Framework for Accurate Identification of Antifreeze Proteins. Journal of Chemical Information and Modeling. 2025;65(22):12256-12267. doi:10.1021/acs.jcim.5c02024
BibTeX
@article{Lin2025,
author = {Lin, Xingqiao and Guan, Jiahui and Wang, Feng and Xie, Peilin and Zhao, Yiyang and Zhao, Zhihao and Xiang, Mingyi and Wei, Leyi and Liu, Xiangrong and Lee, Tzong-Yi and Chiang, Ying-Chih and Wang, Junwen and Yao, Lantian},
title = {AFPDeepPred: A Deep Learning Framework for Accurate Identification of Antifreeze Proteins},
journal = {Journal of Chemical Information and Modeling},
year = {2025},
volume = {65},
number = {22},
pages = {12256--12267},
doi = {10.1021/acs.jcim.5c02024}
}
EUVIMED