PepOSX-AI: CPP - an interpretable transformer-based deep learning model for prediction of cell-penetrating peptides
Analytica Chimica Acta · 2026-10 · 1418 · 345991
DOI: 10.1016/j.aca.2026.345991 ↗Kurz gefasst
Fachartikel in der Zeitschrift Analytica Chimica Acta, 2026-10. Verfasst von Haowen Chen und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Food Science and Engineering, South China University of Technology, Guangzhou, 510640, China; Guangdong Provincial Key Laboratory of Large …. Hauptthemen laut MEDLINE: Cell-Penetrating Peptides, Deep Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: Basic and Applied Basic Research Foundation of Guangdong Province, National Key Research and Development Program of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
BACKGROUND: Cell-penetrating peptides (CPPs) are short-chain molecules capable of enhancing the transmembrane delivery of bioactive substances, displaying extensive application potential in the delivery of functional components and the improvement of their bioavailability. Traditional CPP discovery methods, however, rely on a tedious, step-by-step screening process involving cell and animal experiments, which is highly inefficient. METHODS: The deep-learning model, PepOSX-AI: CPP, was developed based on the Transformer architecture and integrative features of six physicochemical descriptors. This involved a series of explorations of model parameters and automated hyperparameter optimization. The model achieved a high area under the curve (AUC) of 0.914 on the dataset. Furthermore, the model effectively captured long-range dependencies in amino acid sequences through a self-attention mechanism, enabling the interpretability of attention patterns. This capability facilitates the identification of key sequence features influencing peptide penetration ability. SIGNIFICANCE AND NOVELTY: In comparison to some existing CPP prediction models, PepOSX-AI: CPP demonstrated an accuracy of 91.00% on the application test set, highlighting its acceptable predictive performance. It provides a novel computational tool and theoretical basis for the screening of CPPs. Based on these findings, an online platform was also developed to facilitate user application.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Food Science and Engineering, South China University of Technology, Guangzhou, 510640, China; Guangdong Provincial Key Laboratory of Large Animal Models for Biomedicine, School of Pharmacy and Food Engineering…
- State Key Laboratory of Food Science and Resources, China-Canada Joint Lab of Food Science and Technology (Nanchang), Nanchang University, Nanchang, 330047, China.
- School of Food Science and Engineering, South China University of Technology, Guangzhou, 510640, China.
- School of Pharmaceutical Sciences, Sun Yat-sen University, Guangzhou, 510006, China.
- Guangdong Provincial Key Laboratory of Large Animal Models for Biomedicine, School of Pharmacy and Food Engineering, Wuyi University, Jiangmen, 529020, China.
- School of Food Science and Engineering, South China University of Technology, Guangzhou, 510640, China. Electronic address: feyoulijun@scut.edu.cn.
Förderung
- Basic and Applied Basic Research Foundation of Guangdong Province
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Chen, H., He, W., Feng, K., Xu, R., Yin, S., Zheng, L., Chen, J., Zhao, M., Xu, J., & You, L. (2026). PepOSX-AI: CPP - an interpretable transformer-based deep learning model for prediction of cell-penetrating peptides. Analytica Chimica Acta, 1418, 345991. https://doi.org/10.1016/j.aca.2026.345991
Vancouver
Chen H, He W, Feng K, Xu R, Yin S, Zheng L, et al. PepOSX-AI: CPP - an interpretable transformer-based deep learning model for prediction of cell-penetrating peptides. Analytica Chimica Acta. 2026;1418:345991. doi:10.1016/j.aca.2026.345991
BibTeX
@article{Chen2026,
author = {Chen, Haowen and He, Weiwei and Feng, Kaiyan and Xu, Rong and Yin, Sheng and Zheng, Lin and Chen, Jing and Zhao, Mouming and Xu, Jucai and You, Lijun},
title = {PepOSX-AI: CPP - an interpretable transformer-based deep learning model for prediction of cell-penetrating peptides},
journal = {Analytica Chimica Acta},
year = {2026},
volume = {1418},
pages = {345991},
doi = {10.1016/j.aca.2026.345991}
}
EUVIMED