Wenyu Zhang, Mason A. Guy, Jerrica Yang, Lucy Hao, Junliang Liu, Joel M. Hawkins, Jason Mustakis, Sebastien Monfette and Jason E. Hein
{"title":"利用 GPT-4 将化学从纸面转化为实践†。","authors":"Wenyu Zhang, Mason A. Guy, Jerrica Yang, Lucy Hao, Junliang Liu, Joel M. Hawkins, Jason Mustakis, Sebastien Monfette and Jason E. Hein","doi":"10.1039/D4DD00248B","DOIUrl":null,"url":null,"abstract":"<p >Large Language Models (LLMs) have revolutionized numerous industries as well as accelerated scientific research. However, their application in planning and conducting experimental science, has been limited. In this study, we introduce an adaptable prompt-set with GPT-4, converting literature experimental procedures into actionable experimental steps for a Mettler Toledo EasyMax automated laboratory reactor. Through prompt engineering, we developed a 2-step sequential prompt: the first prompt converts literature synthesis procedures into step-by-step instructions for reaction planning; the second prompt generates an XML script to communicate these instructions to the EasyMax reactor, automating experimental design and execution. We successfully automated the reproduction of three distinct literature-based synthetic procedures and validated the reactions by monitoring and characterizing the products. This approach bridges the gap between text-to-procedure transcription and automated execution, and streamlines literature procedure reproduction.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":null,"pages":null},"PeriodicalIF":6.2000,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00248b?page=search","citationCount":"0","resultStr":"{\"title\":\"Leveraging GPT-4 to transform chemistry from paper to practice†\",\"authors\":\"Wenyu Zhang, Mason A. Guy, Jerrica Yang, Lucy Hao, Junliang Liu, Joel M. Hawkins, Jason Mustakis, Sebastien Monfette and Jason E. Hein\",\"doi\":\"10.1039/D4DD00248B\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p >Large Language Models (LLMs) have revolutionized numerous industries as well as accelerated scientific research. However, their application in planning and conducting experimental science, has been limited. In this study, we introduce an adaptable prompt-set with GPT-4, converting literature experimental procedures into actionable experimental steps for a Mettler Toledo EasyMax automated laboratory reactor. Through prompt engineering, we developed a 2-step sequential prompt: the first prompt converts literature synthesis procedures into step-by-step instructions for reaction planning; the second prompt generates an XML script to communicate these instructions to the EasyMax reactor, automating experimental design and execution. We successfully automated the reproduction of three distinct literature-based synthetic procedures and validated the reactions by monitoring and characterizing the products. This approach bridges the gap between text-to-procedure transcription and automated execution, and streamlines literature procedure reproduction.</p>\",\"PeriodicalId\":72816,\"journal\":{\"name\":\"Digital discovery\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":6.2000,\"publicationDate\":\"2024-10-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00248b?page=search\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Digital discovery\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://pubs.rsc.org/en/content/articlelanding/2024/dd/d4dd00248b\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CHEMISTRY, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Digital discovery","FirstCategoryId":"1085","ListUrlMain":"https://pubs.rsc.org/en/content/articlelanding/2024/dd/d4dd00248b","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
摘要
大型语言模型(LLM)给许多行业带来了革命性的变化,也加速了科学研究的发展。然而,它们在规划和开展实验科学方面的应用却很有限。在本研究中,我们采用 GPT-4 引入了一个可调整的提示集,将文献中的实验程序转换为梅特勒-托利多 EasyMax 自动实验室反应器的可操作实验步骤。通过提示工程,我们开发了一个两步顺序提示:第一步提示将文献合成程序转换为反应规划的分步说明;第二步提示生成一个 XML 脚本,将这些说明传达给 EasyMax 反应器,实现实验设计和执行的自动化。我们成功地自动复制了三种不同的基于文献的合成程序,并通过监测和表征产物验证了反应。这种方法缩小了文本到程序转录和自动执行之间的差距,简化了文献程序的复制。
Leveraging GPT-4 to transform chemistry from paper to practice†
Large Language Models (LLMs) have revolutionized numerous industries as well as accelerated scientific research. However, their application in planning and conducting experimental science, has been limited. In this study, we introduce an adaptable prompt-set with GPT-4, converting literature experimental procedures into actionable experimental steps for a Mettler Toledo EasyMax automated laboratory reactor. Through prompt engineering, we developed a 2-step sequential prompt: the first prompt converts literature synthesis procedures into step-by-step instructions for reaction planning; the second prompt generates an XML script to communicate these instructions to the EasyMax reactor, automating experimental design and execution. We successfully automated the reproduction of three distinct literature-based synthetic procedures and validated the reactions by monitoring and characterizing the products. This approach bridges the gap between text-to-procedure transcription and automated execution, and streamlines literature procedure reproduction.