ReactGPT: Understanding of Chemical Reactions via In-Context Tuning
Open Access
- 11 April 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (1) , 84-92
Abstract
The interdisciplinary field of chemistry and artificial intelligence (AI) is an active area of research aimed at accelerating scientific discovery. Large language Models (LLMs) have shown significant promise in biochemical tasks, especially the molecule caption translation, which aims to align between molecules and natural language texts. However, existing works mainly focus on single molecules, while alignment between chemical reactions and natural language text remains largely unexplored. Additionally, the description of reactions is an essential part in biochemical patents and literature, and research on this aspect not only can help better understand chemical reactions but also promote research on automating chemical synthesis and retrosynthesis. In this work, we propose \textbf{ReactGPT}, a framework aiming to bridge the gap between chemical reaction and text. ReactGPT allows a new task: reaction captioning, by adapting LLMs to learn reaction-text alignment from context examples via In-Context Tuning. Specifically, ReactGPT jointly leverages a Fingerprints-based Reaction Retrieval module, a Domain-Specific Prompt Design module, and a two-stage In-Context Tuning module. We evaluate the effectiveness of ReactGPT on reaction captioning and experimental procedure prediction, both of these tasks can reflect the understanding of chemical reactions. Experimental results show that compared to previous models, ReactGPT exhibits competitive capabilities in resolving chemical reactions and generating high-quality text with correct structure.Keywords
This publication has 15 references indexed in Scilit:
- Large Language Models are In-Context Molecule LearnersIEEE Transactions on Knowledge and Data Engineering, 2025
- Empowering Molecule Discovery for Molecule-Caption Translation With Large Language Models: A ChatGPT PerspectiveIEEE Transactions on Knowledge and Data Engineering, 2024
- Taiyi: a bilingual fine-tuned large language model for diverse biomedical tasksJournal of the American Medical Informatics Association, 2024
- Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language ProcessingACM Computing Surveys, 2023
- Meta-learning via Language Model In-context Tuning2022
- The Open Reaction DatabaseJournal of the American Chemical Society, 2021
- Inferring experimental procedures from text-based representations of chemical reactionsNature Communications, 2021
- Mapping the space of chemical reactions using attention-based neural networksNature Machine Intelligence, 2021
- SMILES. 2. Algorithm for generation of unique SMILES notationJournal of Chemical Information and Computer Sciences, 1989
- SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rulesJournal of Chemical Information and Computer Sciences, 1988