Comprehensive Characterization of Oxidative Stress-Modulating Chemicals Using GPT-Based Text Mining
Environmental Science & Technology · 19.11.2024 · 58 (46) · 20540-20552
DOI: 10.1021/acs.est.4c07390 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Science & Technology, online erschienen am 08.11.2024. Verfasst von Wenqing Liang und 7 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Environmental Chemistry and Ecotoxicology, Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences, Beiji…. Hauptthemen laut MEDLINE: Data Mining, Oxidative Stress. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: Youth Innovation Promotion Association of the Chinese Academy of Sciences, National Natural Science Foundation of China, Chinese Academy of Sciences.
Abstract (Originalsprache)
The screening of hazardous environmental pollutants is hindered by the limited availability of toxicological databases. Large language model (LLM)-based text mining holds the potential to automatically extract complex toxicological information from the literature. Due to its relevance to diseases and the challenge of comprehensive characterization, oxidative stress serves as a suitable case for research by texting mining. In this study, a robust workflow utilizing a LLM (i.e., GPT-4) was developed to extract information on oxidative stress tests, including data collection, text preprocessing, prompt engineering, and performance evaluation procedures. A total of 17,780 relevant records were extracted from 7166 articles, covering 2558 unique compounds. A rising interest in oxidative stress was observed over the past two decades. A list of known prooxidants (n = 1416) and antioxidants (n = 1102) was established, with the leading chemical categories being pharmaceuticals, pesticides, and metals for prooxidants and pharmaceuticals and flavonoids for antioxidants. Structural alert analysis identified potential prooxidant (e.g., chlorobenzene, nitrobenzene, and tertiary amines) and antioxidant (e.g., flavonoid and thiol) substructures. These findings illustrate the feasibility of building toxicological databases through LLM-based text mining in a cost-efficient manner, and the information obtained from the technique holds significant promise for future applications in environmental and health research.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- State Key Laboratory of Environmental Chemistry and Ecotoxicology, Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences, Beijing 100085, China.
- University of Chinese Academy of Sciences, Beijing 100049, China.
- Hubei Key Laboratory of Environmental and Health Effects of Persistent Toxic Substances, School of Environment and Health, Jianghan University, Wuhan 430056, China.
ORCID-Profile: Wenqing Liang, Wenyuan Su, Laijin Zhong, Zhendong Yang, Tingyu Li, Yong Liang, Ting Ruan, Guibin Jiang
Förderung
- Youth Innovation Promotion Association of the Chinese Academy of Sciences
- National Natural Science Foundation of China
- Chinese Academy of Sciences
Zitieren
APA
Liang, W., Su, W., Zhong, L., Yang, Z., Li, T., Liang, Y., Ruan, T., & Jiang, G. (2024). Comprehensive Characterization of Oxidative Stress-Modulating Chemicals Using GPT-Based Text Mining. Environmental Science & Technology, 58(46), 20540-20552. https://doi.org/10.1021/acs.est.4c07390
Vancouver
Liang W, Su W, Zhong L, Yang Z, Li T, Liang Y, et al. Comprehensive Characterization of Oxidative Stress-Modulating Chemicals Using GPT-Based Text Mining. Environmental Science & Technology. 2024;58(46):20540-20552. doi:10.1021/acs.est.4c07390
BibTeX
@article{Liang2024,
author = {Liang, Wenqing and Su, Wenyuan and Zhong, Laijin and Yang, Zhendong and Li, Tingyu and Liang, Yong and Ruan, Ting and Jiang, Guibin},
title = {Comprehensive Characterization of Oxidative Stress-Modulating Chemicals Using GPT-Based Text Mining},
journal = {Environmental Science & Technology},
year = {2024},
volume = {58},
number = {46},
pages = {20540--20552},
doi = {10.1021/acs.est.4c07390}
}
EUVIMED