NeuTox 2.0: A hybrid deep learning architecture for screening potential neurotoxicity of chemicals based on multimodal feature fusion
Environment International · 2025
DOI: 10.1016/j.envint.2024.109244 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environment International, 2025. Verfasst von Xudi Pang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Hubei Key Laboratory of Environmental and Health Effects of Persistent Toxic Substances, School of Environment and Health, Jianghan University, Wuhan…. Hauptthemen laut MEDLINE: Deep Learning, Toxicity Tests, Neurotoxicity Syndromes. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Jianghan University, National Key Research and Development Program of China.
Abstract (Originalsprache)
Chemically induced neurotoxicity is a critical aspect of chemical safety assessment. Traditional and costly experimental methods call for the development of high-throughput virtual screening. However, the small datasets of neurotoxicity have limited the application of advanced deep learning techniques. The current study developed a hybrid deep learning architecture, NeuTox 2.0, through multimodal feature fusion for enhanced prediction accuracy and generalization ability. We incorporated transfer learning based on self-supervised learning, graph neural networks, and molecular fingerprints/descriptors. Four datasets were used to profile neurotoxicity; these were related to blood-brain barrier permeability, neuronal cytotoxicity, microelectrode array-based neural activity, and mammalian neurotoxicity. Comprehensive performance evaluations demonstrated that NeuTox 2.0 has relatively higher predictive capability across all statistical metrics. Specifically, NeuTox 2.0 exhibits remarkable performance in three of the four datasets. In the BBB dataset, although it does not outperform the PaDEL descriptor model, its performance closely approximates that of the top single-modal model. The ablation experiments indicated that NeuTox 2.0 can learn the deeper structural differences of molecules from various feature extractions and capture complex interactions and mapping relationships between various modalities, thereby improving performance for neurotoxicity prediction. Evaluations of anti-noise ability indicated that NeuTox 2.0 has excellent noise resistance relative to traditional machine learning. We applied the NeuTox 2.0 model to predict the neurotoxicity of 315,790 compounds in the REACH database. The results showed that 701 compounds exhibited potential neurotoxicity in the four neurotoxicity-related predictions. In conclusion, NeuTox 2.0 can be used as an efficient tool for early neurotoxicity screening of environmental chemicals.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Hubei Key Laboratory of Environmental and Health Effects of Persistent Toxic Substances, School of Environment and Health, Jianghan University, Wuhan 430056, China.
- Hubei Key Laboratory of Environmental and Health Effects of Persistent Toxic Substances, School of Environment and Health, Jianghan University, Wuhan 430056, China. Electronic address: hmcao1986@126.com.
Förderung
- National Natural Science Foundation of China
- Jianghan University
- National Key Research and Development Program of China
Zitieren
APA
Pang, X., He, X., Yang, Y., Wang, L., Sun, Y., Cao, H., & Liang, Y. (2025). NeuTox 2.0: A hybrid deep learning architecture for screening potential neurotoxicity of chemicals based on multimodal feature fusion. Environment International. https://doi.org/10.1016/j.envint.2024.109244
Vancouver
Pang X, He X, Yang Y, Wang L, Sun Y, Cao H, et al. NeuTox 2.0: A hybrid deep learning architecture for screening potential neurotoxicity of chemicals based on multimodal feature fusion. Environment International. 2025. doi:10.1016/j.envint.2024.109244
BibTeX
@article{Pang2025,
author = {Pang, Xudi and He, Xuejun and Yang, Ying and Wang, Ling and Sun, Yuzhen and Cao, Huiming and Liang, Yong},
title = {NeuTox 2.0: A hybrid deep learning architecture for screening potential neurotoxicity of chemicals based on multimodal feature fusion},
journal = {Environment International},
year = {2025},
doi = {10.1016/j.envint.2024.109244}
}
EUVIMED