Text-Augmented Multimodal LLMs for Chemical Reaction Condition Recommendation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918147600154624 |
|---|---|
| author | Zhang, Yu Yu, Ruijie Zeng, Kaipeng Li, Ding Zhu, Feng Yang, Xiaokang Jin, Yaohui Xu, Yanyan |
| author_facet | Zhang, Yu Yu, Ruijie Zeng, Kaipeng Li, Ding Zhu, Feng Yang, Xiaokang Jin, Yaohui Xu, Yanyan |
| contents | Identifying reaction conditions that are broadly applicable across diverse substrates is a longstanding challenge in chemical and pharmaceutical research. While many methods are available to generate conditions with acceptable performance, a universal approach for reliably discovering effective conditions during reaction exploration is rare. Consequently, current reaction optimization processes are often labor-intensive, time-consuming, and costly, relying heavily on trial-and-error experimentation. Nowadays, large language models (LLMs) are capable of tackling chemistry-related problems, such as molecule design and chemical reasoning tasks. Here, we report the design, implementation and application of Chemma-RC, a text-augmented multimodal LLM to identify effective conditions through task-specific dialogue and condition generation. Chemma-RC learns a unified representation of chemical reactions by aligning multiple modalities-including text corpus, reaction SMILES, and reaction graphs-within a shared embedding module. Performance benchmarking on datasets showed high precision in identifying optimal conditions, with up to 17% improvement over the current state-of-the-art methods. A palladium-catalysed imidazole C-H arylation reaction was investigated experimentally to evaluate the functionalities of the Chemma-RC in practice. Our findings suggest that Chemma-RC holds significant potential to accelerate high-throughput condition screening in chemical synthesis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15141 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Text-Augmented Multimodal LLMs for Chemical Reaction Condition Recommendation Zhang, Yu Yu, Ruijie Zeng, Kaipeng Li, Ding Zhu, Feng Yang, Xiaokang Jin, Yaohui Xu, Yanyan Artificial Intelligence Machine Learning Chemical Physics Identifying reaction conditions that are broadly applicable across diverse substrates is a longstanding challenge in chemical and pharmaceutical research. While many methods are available to generate conditions with acceptable performance, a universal approach for reliably discovering effective conditions during reaction exploration is rare. Consequently, current reaction optimization processes are often labor-intensive, time-consuming, and costly, relying heavily on trial-and-error experimentation. Nowadays, large language models (LLMs) are capable of tackling chemistry-related problems, such as molecule design and chemical reasoning tasks. Here, we report the design, implementation and application of Chemma-RC, a text-augmented multimodal LLM to identify effective conditions through task-specific dialogue and condition generation. Chemma-RC learns a unified representation of chemical reactions by aligning multiple modalities-including text corpus, reaction SMILES, and reaction graphs-within a shared embedding module. Performance benchmarking on datasets showed high precision in identifying optimal conditions, with up to 17% improvement over the current state-of-the-art methods. A palladium-catalysed imidazole C-H arylation reaction was investigated experimentally to evaluate the functionalities of the Chemma-RC in practice. Our findings suggest that Chemma-RC holds significant potential to accelerate high-throughput condition screening in chemical synthesis. |
| title | Text-Augmented Multimodal LLMs for Chemical Reaction Condition Recommendation |
| topic | Artificial Intelligence Machine Learning Chemical Physics |
| url | https://arxiv.org/abs/2407.15141 |