BatGPT-Chem: A Foundation Large Model for Chemical Engineering
Research · 2025-01 · 8
DOI: 10.34133/research.0827 ↗Kurz gefasst
Fachartikel in der Zeitschrift Research, online erschienen am 10.09.2025. Verfasst von Yifei Yang und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Joint Research Project of Yangtze River Delta Science and Technology Innovation Community, Joint Funds of the National Natural Science Foundation of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Large language models (LLMs) have showcased remarkable capabilities in the realm of AI for Science, and chemistry has greatly benefited from the advancement of AI tools. With a strong capacity for learning sequential data like natural language, LLMs offer immense potential. Despite this promise, the application of LLMs in chemistry remains limited, with few models specifically designed for chemical data and tasks. Hence, we propose leveraging LLMs to comprehensively model both chemical sequences and natural language sequences, aiming to tackle diverse chemical tasks. We introduce BatGPT-Chem, a general foundation large-scale model with 15 billion parameters tailored for chemical engineering. Built on a corpus of over 100 million chemical instances, BatGPT-Chem specializes in 5 core tasks: retrosynthesis prediction, molecule design, molecule description, product inference, and yield prediction. BatGPT-Chem comprehensively models the information flow between chemical language and natural language, enabling full-spectrum prediction across chemical tasks. It is one of the largest bilingual chemistry-specific LLMs, supporting both English and Chinese for input and output. BatGPT-Chem is also the first automated retrosynthesis tool capable of explicitly predicting reaction conditions, a critical but often overlooked aspect in previous models. Through rigorous zero-shot evaluations, BatGPT-Chem demonstrates state-of-the-art performance, surpassing both existing chemical LLMs and general-purpose models in accuracy and validity across a diverse range of tasks. Notably, it demonstrates superior ability in predicting both reactants and reaction conditions, as well as strong generalization in low-data settings. These results suggest that BatGPT-Chem is among the most advanced and practical chemical LLMs, with strong potential to support real-world applications in synthesis planning, drug discovery, and materials design.
Autor:innen und Institutionen
- School of Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China.
- Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.
- Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3, Shanghai, China.
- School of Artificial Intelligence, Wuhan University, Wuhan 430070, China.
- School of Artificial Intelligence and Computer Science, Nantong University, Nantong 226019, China.
- RIKEN Center for Advanced Intelligence Project, Tokyo 103-0027, Japan.
ORCID-Profile: Yifei Yang, Runhan Shi, Zuchao Li, Shu Jiang, Bao-Liang Lu, Qibin Zhao, Yang Yang, Hai Zhao
Förderung
- Joint Research Project of Yangtze River Delta Science and Technology Innovation Community
- Joint Funds of the National Natural Science Foundation of China
- National Natural Science Foundation of China
- General Program of the Natural Science Research of Higher Education of Jiangsu Province
Zitieren
APA
Yang, Y., Shi, R., Li, Z., Jiang, S., Lu, B. L., Zhao, Q., Yang, Y., & Zhao, H. (2025). BatGPT-Chem: A Foundation Large Model for Chemical Engineering. Research, 8. https://doi.org/10.34133/research.0827
Vancouver
Yang Y, Shi R, Li Z, Jiang S, Lu BL, Zhao Q, et al. BatGPT-Chem: A Foundation Large Model for Chemical Engineering. Research. 2025;8. doi:10.34133/research.0827
BibTeX
@article{Yang2025,
author = {Yang, Yifei and Shi, Runhan and Li, Zuchao and Jiang, Shu and Lu, Bao-Liang and Zhao, Qibin and Yang, Yang and Zhao, Hai},
title = {BatGPT-Chem: A Foundation Large Model for Chemical Engineering},
journal = {Research},
year = {2025},
volume = {8},
doi = {10.34133/research.0827}
}
EUVIMED