Qualitative and Quantitative Prediction of Blood–Brain Barrier Permeability of Chemicals via an SE(3)-Transformer-Based Model with LLM-Assisted Explanation
Environmental Science & Technology · 18.08.2026 · 60 (32) · 22653-22664
DOI: 10.1021/acs.est.6c06459 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Science & Technology, online erschienen am 04.08.2026. Verfasst von Lilai Shen und 7 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Soil Pollution Control and Safety, and Women's Hospital, School of Medicine, Zhejiang University, Hangzhou310058, China. Hauptthemen laut MEDLINE: Blood-Brain Barrier. Die Arbeit nennt 68 Literaturangaben. Gefördert von: Natural Science Foundation of Zhejiang Province, National Natural Science Foundation of China (NSFC).
Abstract (Originalsprache)
The blood–brain barrier (BBB) regulates the entry of chemicals into the central nervous system, and contaminants with high permeability can accumulate in the brain, posing neurotoxicity risks. Given the urgent need for high-throughput neurotoxicity assessment, this study proposes a multifeature fusion framework for identifying and quantifying the BBB permeability to neurotoxic chemicals. BBBProfiler leverages an SE(3)-Transformer to encode the three-dimensional molecular geometry and a deep neural network to encode collision cross-section (CCS) and fingerprint, followed by adaptive integration of modality representations through gating weights. Under the scaffold-split evaluation, BBBProfiler achieves high performance with an area under the receiver operating characteristic curve (AUC) of 93.72% and a recall of 89.19% for classification, and a coefficient of determination (R2) of 0.72 for regression. Its predictive performance was validated using a BBB bioassay (11 chemicals) and an external data set (2023 chemicals), in which the model achieved 94.42% AUC. Substructure mask explanation analysis revealed CCS as an influential feature that correlated well with BBB permeability to chemicals (R2 = 0.84). Model predictions were supplemented with natural-language explanations generated from a large language model. BBBProfiler is deployed on a publicly accessible platform (https://www.ai4environ.cn/BBBProfiler) to facilitate the development of new approach methodologies for neurotoxicity evaluation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- State Key Laboratory of Soil Pollution Control and Safety, and Women's Hospital, School of Medicine, Zhejiang University, Hangzhou310058, China.
- College of Chemistry and Materials Engineering, and State Key Laboratory for Development and Utilization of Forest Food Resources, Zhejiang a & F University, Hangzhou, 311300, China.
- Department of Environmental Sciences, University of Houston-Clear Lake, Houston, Texas77058, United States.
ORCID-Profile: Chunlong Zhang, Shulin Zhuang
Förderung
- Natural Science Foundation of Zhejiang Province
- National Natural Science Foundation of China (NSFC)
Zitieren
APA
Shen, L., Chen, Z., Huan, W., Huang, Y., Wu, P., Guo, H., Zhang, C., & Zhuang, S. (2026). Qualitative and Quantitative Prediction of Blood–Brain Barrier Permeability of Chemicals via an SE(3)-Transformer-Based Model with LLM-Assisted Explanation. Environmental Science & Technology, 60(32), 22653-22664. https://doi.org/10.1021/acs.est.6c06459
Vancouver
Shen L, Chen Z, Huan W, Huang Y, Wu P, Guo H, et al. Qualitative and Quantitative Prediction of Blood–Brain Barrier Permeability of Chemicals via an SE(3)-Transformer-Based Model with LLM-Assisted Explanation. Environmental Science & Technology. 2026;60(32):22653-22664. doi:10.1021/acs.est.6c06459
BibTeX
@article{Shen2026,
author = {Shen, Lilai and Chen, Ziyu and Huan, Weiwei and Huang, Yizhou and Wu, Peirong and Guo, Hou and Zhang, Chunlong and Zhuang, Shulin},
title = {Qualitative and Quantitative Prediction of Blood–Brain Barrier Permeability of Chemicals via an SE(3)-Transformer-Based Model with LLM-Assisted Explanation},
journal = {Environmental Science & Technology},
year = {2026},
volume = {60},
number = {32},
pages = {22653--22664},
doi = {10.1021/acs.est.6c06459}
}
EUVIMED