ToxDL 2.0: Protein toxicity prediction using a pretrained language model and graph neural networks
Computational and Structural Biotechnology Journal · 01.01.2025 · 27 · 1538-1549
DOI: 10.1016/j.csbj.2025.04.002 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational and Structural Biotechnology Journal, online erschienen am 12.04.2025. Verfasst von Lin Zhu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Science and Technology Commission of Shanghai Municipality, National Natural Science Foundation of China.
Abstract (Originalsprache)
Motivation Assessing the potential toxicity of proteins is crucial for both therapeutic and agricultural applications. Traditional experimental methods for protein toxicity evaluation are time-consuming, expensive, and labor-intensive, highlighting the requirement for efficient computational approaches. Recent advancements in language models and deep learning have significantly improved protein toxicity prediction, yet current models often lack the ability to integrate evolutionary and structural information, which is crucial for accurate toxicity assessment of proteins. Results In this study, we present ToxDL 2.0, a novel multimodal deep learning model for protein toxicity prediction that integrates both evolutionary and structural information derived from a pretrained language model and AlphaFold2. ToxDL 2.0 consists of three key modules: (1) a Graph Convolutional Network (GCN) module for generating protein graph embeddings based on AlphaFold2-predicted structures, (2) a domain embedding module for capturing protein domain representations, and (3) a dense module that combines these embeddings to predict the toxicity. After constructing a comprehensive toxicity benchmark dataset, we obtained experimental results on both an original non-redundant test set (comprising pre-2022 protein sequences) and an independent non-redundant test set (a holdout set of post-2022 protein sequences), demonstrating that ToxDL 2.0 outperforms existing state-of-the-art methods. Additionally, we utilized Integrated Gradients to discover known toxic motifs associated with protein toxicity. A web server for ToxDL 2.0 is publicly available at www.csbio.sjtu.edu.cn/bioinf/ToxDL2/ .
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.
- Department of Automation, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai 200240, China.
- Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240, China.
- Department for Electronics and Information Systems, IDLab, Ghent University, Ghent 9000, Belgium.
- Department of Environmental Technology, Food Technology and Molecular Biotechnology, Center for Biotech Data Science, Ghent University Global Campus, Songdo, Incheon 305-701, South Korea.
Förderung
- Science and Technology Commission of Shanghai Municipality
- National Natural Science Foundation of China
Zitieren
APA
Zhu, L., Fang, Y., Liu, S., Shen, H. B., De Neve, W., & Pan, X. (2025). ToxDL 2.0: Protein toxicity prediction using a pretrained language model and graph neural networks. Computational and Structural Biotechnology Journal, 27, 1538-1549. https://doi.org/10.1016/j.csbj.2025.04.002
Vancouver
Zhu L, Fang Y, Liu S, Shen HB, De Neve W, Pan X. ToxDL 2.0: Protein toxicity prediction using a pretrained language model and graph neural networks. Computational and Structural Biotechnology Journal. 2025;27:1538-1549. doi:10.1016/j.csbj.2025.04.002
BibTeX
@article{Zhu2025,
author = {Zhu, Lin and Fang, Yi and Liu, Shuting and Shen, Hong-Bin and De Neve, Wesley and Pan, Xiaoyong},
title = {ToxDL 2.0: Protein toxicity prediction using a pretrained language model and graph neural networks},
journal = {Computational and Structural Biotechnology Journal},
year = {2025},
volume = {27},
pages = {1538--1549},
doi = {10.1016/j.csbj.2025.04.002}
}
EUVIMED