PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes

Cao He, Shao Yanjun, Liu Zhiyuan, Liu Zijing, Tang Xiangru, Yao Yuan, Li Yu. Arxiv 2024

[Paper] [Code]    
Applications Has Code Multimodal Models Pretraining Methods RAG Tools Training Techniques

Multimodal Large Language Models (MLLMs) have seen growing adoption across various scientific disciplines. These advancements encourage the investigation of molecule-text modeling within synthetic chemistry, a field dedicated to designing and conducting chemical reactions to synthesize new compounds with desired properties and applications. Current approaches, however, often neglect the critical role of multiple molecule graph interaction in understanding chemical reactions, leading to suboptimal performance in synthetic chemistry tasks. This study introduces PRESTO(Progressive Pretraining Enhances Synthetic Chemistry Outcomes), a new framework that bridges the molecule-text modality gap by integrating a comprehensive benchmark of pretraining strategies and dataset configurations. It progressively improves multimodal LLMs through cross-modal alignment and multi-graph understanding. Our extensive experiments demonstrate that PRESTO offers competitive results in downstream synthetic chemistry tasks. The code can be found at https://github.com/IDEA-XL/PRESTO.

Similar Work