An automatic end-to-end chemical synthesis development platform powered by large language models
Yixiang Ruan, Chenyin Lu, Ning Xu, Yuchen He, Yixin Chen, Jian Zhang, Jun Xuan, Jianzhang Pan, Qun Fang, Hanyu Gao, Xiaodong Shen, Ning Ye, Qiang Zhang, Yiming Mo · 2024
Read An automatic end-to-end chemical synthesis development platform powered by large language models by Yixiang Ruan, Chenyin Lu, Ning Xu, Yuchen He, Yixin Chen, Jian Zhang, Jun Xuan, Jianzhang Pan, Qun Fang, Hanyu Gao, Xiaodong Shen, Ning Ye, Qiang Zhang, Yiming Mo (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11585555.txt.
Description
Ruan and colleagues published this study in twenty twenty-four on using large language models to run chemistry work. Their system, called LLM-RDF, links six software agents, each built on GPT-4 and given one job. The jobs cover searching past research, planning tests, running lab hardware, reading spectra, guiding separation, and explaining results. Chemists use the system through a web page and plain language, with no coding needed.
The team used the system to develop a reaction that turns alcohols into aldehydes with copper and oxygen. It handled each step, from the first search to scaling up and cleaning the product. The system also worked on three other kinds of reactions. The study points to a future where much routine lab development runs itself.
Catalog record
| CREATOR | Yixiang Ruan, Chenyin Lu, Ning Xu, Yuchen He, Yixin Chen, Jian Zhang, Jun Xuan, Jianzhang Pan, Qun Fang, Hanyu Gao, Xiaodong Shen, Ning Ye, Qiang Zhang, Yiming Mo |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 74 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |