Cargando…

ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs

[Image: see text] We leveraged the power of ChatGPT and Bayesian optimization in the development of a multi-AI-driven system, backed by seven large language model-based assistants and equipped with machine learning algorithms, that seamlessly orchestrates a multitude of research aspects in a chemist...

Descripción completa

Detalles Bibliográficos
Autores principales: Zheng, Zhiling, Zhang, Oufan, Nguyen, Ha L., Rampal, Nakul, Alawadhi, Ali H., Rong, Zichao, Head-Gordon, Teresa, Borgs, Christian, Chayes, Jennifer T., Yaghi, Omar M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2023
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10683477/
https://www.ncbi.nlm.nih.gov/pubmed/38033801
http://dx.doi.org/10.1021/acscentsci.3c01087
_version_ 1785151205292376064
author Zheng, Zhiling
Zhang, Oufan
Nguyen, Ha L.
Rampal, Nakul
Alawadhi, Ali H.
Rong, Zichao
Head-Gordon, Teresa
Borgs, Christian
Chayes, Jennifer T.
Yaghi, Omar M.
author_facet Zheng, Zhiling
Zhang, Oufan
Nguyen, Ha L.
Rampal, Nakul
Alawadhi, Ali H.
Rong, Zichao
Head-Gordon, Teresa
Borgs, Christian
Chayes, Jennifer T.
Yaghi, Omar M.
author_sort Zheng, Zhiling
collection PubMed
description [Image: see text] We leveraged the power of ChatGPT and Bayesian optimization in the development of a multi-AI-driven system, backed by seven large language model-based assistants and equipped with machine learning algorithms, that seamlessly orchestrates a multitude of research aspects in a chemistry laboratory (termed the ChatGPT Research Group). Our approach accelerated the discovery of optimal microwave synthesis conditions, enhancing the crystallinity of MOF-321, MOF-322, and COF-323 and achieving the desired porosity and water capacity. In this system, human researchers gained assistance from these diverse AI collaborators, each with a unique role within the laboratory environment, spanning strategy planning, literature search, coding, robotic operation, labware design, safety inspection, and data analysis. Such a comprehensive approach enables a single researcher working in concert with AI to achieve productivity levels analogous to those of an entire traditional scientific team. Furthermore, by reducing human biases in screening experimental conditions and deftly balancing the exploration and exploitation of synthesis parameters, our Bayesian search approach precisely zeroed in on optimal synthesis conditions from a pool of 6 million within a significantly shortened time scale. This work serves as a compelling proof of concept for an AI-driven revolution in the chemistry laboratory, painting a future where AI becomes an efficient collaborator, liberating us from routine tasks to focus on pushing the boundaries of innovation.
format Online
Article
Text
id pubmed-10683477
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-106834772023-11-30 ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs Zheng, Zhiling Zhang, Oufan Nguyen, Ha L. Rampal, Nakul Alawadhi, Ali H. Rong, Zichao Head-Gordon, Teresa Borgs, Christian Chayes, Jennifer T. Yaghi, Omar M. ACS Cent Sci [Image: see text] We leveraged the power of ChatGPT and Bayesian optimization in the development of a multi-AI-driven system, backed by seven large language model-based assistants and equipped with machine learning algorithms, that seamlessly orchestrates a multitude of research aspects in a chemistry laboratory (termed the ChatGPT Research Group). Our approach accelerated the discovery of optimal microwave synthesis conditions, enhancing the crystallinity of MOF-321, MOF-322, and COF-323 and achieving the desired porosity and water capacity. In this system, human researchers gained assistance from these diverse AI collaborators, each with a unique role within the laboratory environment, spanning strategy planning, literature search, coding, robotic operation, labware design, safety inspection, and data analysis. Such a comprehensive approach enables a single researcher working in concert with AI to achieve productivity levels analogous to those of an entire traditional scientific team. Furthermore, by reducing human biases in screening experimental conditions and deftly balancing the exploration and exploitation of synthesis parameters, our Bayesian search approach precisely zeroed in on optimal synthesis conditions from a pool of 6 million within a significantly shortened time scale. This work serves as a compelling proof of concept for an AI-driven revolution in the chemistry laboratory, painting a future where AI becomes an efficient collaborator, liberating us from routine tasks to focus on pushing the boundaries of innovation. American Chemical Society 2023-11-10 /pmc/articles/PMC10683477/ /pubmed/38033801 http://dx.doi.org/10.1021/acscentsci.3c01087 Text en © 2023 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by/4.0/Permits the broadest form of re-use including for commercial purposes, provided that author attribution and integrity are maintained (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Zheng, Zhiling
Zhang, Oufan
Nguyen, Ha L.
Rampal, Nakul
Alawadhi, Ali H.
Rong, Zichao
Head-Gordon, Teresa
Borgs, Christian
Chayes, Jennifer T.
Yaghi, Omar M.
ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs
title ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs
title_full ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs
title_fullStr ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs
title_full_unstemmed ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs
title_short ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs
title_sort chatgpt research group for optimizing the crystallinity of mofs and cofs
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10683477/
https://www.ncbi.nlm.nih.gov/pubmed/38033801
http://dx.doi.org/10.1021/acscentsci.3c01087
work_keys_str_mv AT zhengzhiling chatgptresearchgroupforoptimizingthecrystallinityofmofsandcofs
AT zhangoufan chatgptresearchgroupforoptimizingthecrystallinityofmofsandcofs
AT nguyenhal chatgptresearchgroupforoptimizingthecrystallinityofmofsandcofs
AT rampalnakul chatgptresearchgroupforoptimizingthecrystallinityofmofsandcofs
AT alawadhialih chatgptresearchgroupforoptimizingthecrystallinityofmofsandcofs
AT rongzichao chatgptresearchgroupforoptimizingthecrystallinityofmofsandcofs
AT headgordonteresa chatgptresearchgroupforoptimizingthecrystallinityofmofsandcofs
AT borgschristian chatgptresearchgroupforoptimizingthecrystallinityofmofsandcofs
AT chayesjennifert chatgptresearchgroupforoptimizingthecrystallinityofmofsandcofs
AT yaghiomarm chatgptresearchgroupforoptimizingthecrystallinityofmofsandcofs