Text-Augmented Multimodal LLMs for Chemical Reaction Condition Recommendation

• Main Authors: Zhang, Yu, Yu, Ruijie, Zeng, Kaipeng, Li, Ding, Zhu, Feng, Yang, Xiaokang, Jin, Yaohui, Xu, Yanyan
• Format: Journal Article
• Language: English
• Published: 21.07.2024
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Learning; Physics - Chemical Physics
• DOI: 10.48550/arxiv.2407.15141

High-throughput reaction condition (RC) screening is fundamental to chemical synthesis. However, current RC screening suffers from laborious and costly trial-and-error workflows. Traditional computer-aided synthesis planning (CASP) tools fail to find suitable RCs due to data sparsity and inadequate reaction representations. Nowadays, large language models (LLMs) are capable of tackling chemistry-related problems, such as molecule design, and chemical logic Q\&A tasks. However, LLMs have not yet achieved accurate predictions of chemical reaction conditions. Here, we present MM-RCR, a text-augmented multimodal LLM that learns a unified reaction representation from SMILES, reaction graphs, and textual corpus for chemical reaction recommendation (RCR). To train MM-RCR, we construct 1.2 million pair-wised Q\&A instruction datasets. Our experimental results demonstrate that MM-RCR achieves state-of-the-art performance on two open benchmark datasets and exhibits strong generalization capabilities on out-of-domain (OOD) and High-Throughput Experimentation (HTE) datasets. MM-RCR has the potential to accelerate high-throughput condition screening in chemical synthesis.