EUVIMEDEUVIMED entdecken
Crossref

FGTN: Fragment-based graph transformer network for predicting reproductive toxicity

Jia-Nan Ren, Qiang Chen, Hong-Yu-Xiang Ye, Cheng Cao, Ya-Min Guo, Jin-Rong Yang, Hao Wang, Muhammad Zafar Irshad Khan, Jian-Zhong Chen iD

Archives of Toxicology · 2024

DOI: 10.1007/s00204-024-03866-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Archives of Toxicology, 2024. Verfasst von Jia-Nan Ren und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Pharmaceutical Sciences, Zhejiang University, 866 Yuhangtang Rd., Hangzhou, 310058, Zhejiang, China. Hauptthemen laut MEDLINE: Quantitative Structure-Activity Relationship, Reproduction, Neural Networks, Computer. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reproductive toxicity is one of the important issues in chemical safety. Traditional laboratory testing methods are costly and time-consuming with raised ethical issues. Only a few in silico models have been reported to predict human reproductive toxicity, but none of them make full use of the topological information of compounds. In addition, most existing atom-based graph neural network methods focus on attributing model predictions to individual nodes or edges rather than chemically meaningful fragments or substructures. In current studies, we develop a novel fragment-based graph transformer network (FGTN) approach to generate the QSAR model of human reproductive toxicity by considering internal topological structure information of compounds. In the FGTN model, the compound is represented by a graph architecture using fragments to be nodes and bonds linking two fragments to be edges. A super molecule-level node is further proposed to connect all fragment nodes by undirected edges, obtaining global molecular features from fragment embeddings. The FGTN model achieved an accuracy (ACC) of 0.861 and an area under the receiver operating characteristic curve (AUC) value of 0.914 on nonredundant blind tests, outperforming traditional fingerprint-based machine learning models and atom-based GCN model. The FGTN model can attribute toxic predictions to fragments, generating specific structural alerts for the positive compound. Moreover, FGTN may also have the capability to distinguish various chemical isomers. We believe that FGTN can be used as a reliable and effective tool for human reproductive toxicity prediction in contribution to the advancement of chemical safety assessment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Quantitative Structure-Activity RelationshipReproductionNeural Networks, ComputerHumansComputer SimulationToxicity Tests

Stichwörter der Autor:innen

FragmentGraph transformer networkReproductive toxicityStructure alerts

Autor:innen und Institutionen

  • College of Pharmaceutical Sciences, Zhejiang University, 866 Yuhangtang Rd., Hangzhou, 310058, Zhejiang, China.
  • Polytechnic Institute, Zhejiang University, 269 Shixiang Rd., Hangzhou, 310015, Zhejiang, China.
  • College of Pharmaceutical Sciences, Zhejiang University, 866 Yuhangtang Rd., Hangzhou, 310058, Zhejiang, China. chjz@zju.edu.cn.

ORCID-Profile: Jian-Zhong Chen

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Ren, J. N., Chen, Q., Ye, H. Y., Cao, C., Guo, Y. M., Yang, J. R., Wang, H., Khan, M. Z. I., & Chen, J. Z. (2024). FGTN: Fragment-based graph transformer network for predicting reproductive toxicity. Archives of Toxicology. https://doi.org/10.1007/s00204-024-03866-4

Vancouver

Ren JN, Chen Q, Ye HY, Cao C, Guo YM, Yang JR, et al. FGTN: Fragment-based graph transformer network for predicting reproductive toxicity. Archives of Toxicology. 2024. doi:10.1007/s00204-024-03866-4

BibTeX
@article{Ren2024,
  author = {Ren, Jia-Nan and Chen, Qiang and Ye, Hong-Yu-Xiang and Cao, Cheng and Guo, Ya-Min and Yang, Jin-Rong and Wang, Hao and Khan, Muhammad Zafar Irshad and Chen, Jian-Zhong},
  title = {FGTN: Fragment-based graph transformer network for predicting reproductive toxicity},
  journal = {Archives of Toxicology},
  year = {2024},
  doi = {10.1007/s00204-024-03866-4}
}
Kostenlos starten →