CoChat
Sign Up
Cited by 172Machine Learning in Materials ScienceMetal-Organic Frameworks: Synthesis and ApplicationsMicrowave-Assisted Synthesis and Applications

ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs

Open access
Zheng, Zhiling, Zhang, Oufan, Nguyen, Ha L., Rampal, Nakul, Alawadhi, Ali H., Rong, Zichao, Head-Gordon, Teresa, Borgs, Christian +2 more·2023·ACS Central Science
DOI 10.1021/acscentsci.3c01087PMC PMC10683477
Open this paper in CoChat — free accountOpen PDF

Abstract

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.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1021/acscentsci.3c01087

Cites

9 of 9 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Zheng et al. (2023) utilizes multiple LLM-based agents for science experiments, each focusing on specific tasks, and all agents interact with humans to optimize the synthesis process of complex materials.

    “[Zheng et al., 2023] utilizes multiple LLM-based agents, each focusing on specific tasks for the science experiments including strategy planning, literature search, coding, robotic operations, and labware design.All these agents interact with humans to work collaboratively to optimize the synthesis process of complex materials.”

    From Large Language Model based Multi-Agents: A Survey of Progress and Challenges (2024) · cites this paper as Zheng et al., 2023

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 62

  1. Williams W. L.; Zeng L.; Gensch T.; Sigman M. S.; Doyle A. G.; Anslyn E. V. The evolution of data-driven modeling in organic chemistry. ACS Cent. Sci. 2021, 7 (10), 1622– 1637. 10.1021/acscentsci.1c00535. 34729406 PMC8554870 · DOI
  2. Baum Z. J.; Yu X.; Ayala P. Y.; Zhao Y.; Watkins S. P.; Zhou Q. Artificial intelligence in chemistry: current trends and future directions. J. Chem. Inf. Model. 2021, 61 (7), 3197– 3212. 10.1021/acs.jcim.1c00619. 34264069 · DOI
  3. Davenport T. H.; Ronanki R. Artificial intelligence for the real world. Harv. Bus. Rev. 2018, 96 (1), 108– 116.
  4. de Almeida A. F.; Moreira R.; Rodrigues T. Synthetic organic chemistry driven by artificial intelligence. Nat. Rev. Chem. 2019, 3 (10), 589– 604. 10.1038/s41570-019-0124-0. · DOI
  5. Wahl C. B.; Aykol M.; Swisher J. H.; Montoya J. H.; Suram S. K.; Mirkin C. A. Machine learning–accelerated design and synthesis of polyelemental heterostructures. Sci. Adv. 2021, 7 (52), eabj5505 10.1126/sciadv.abj5505. 34936439 PMC8694626 · DOI
  6. Ahneman D. T.; Estrada J. G.; Lin S.; Dreher S. D.; Doyle A. G. Predicting reaction performance in C–N cross-coupling using machine learning. Science 2018, 360 (6385), 186– 190. 10.1126/science.aar5169. 29449509 · DOI · Paper page
  7. Yaghi O. M.; O’Keeffe M.; Ockwig N. W.; Chae H. K.; Eddaoudi M.; Kim J. Reticular synthesis and the design of new materials. Nature 2003, 423 (6941), 705– 714. 10.1038/nature01650. 12802325 · DOI
  8. Luo Y.; Bag S.; Zaremba O.; Cierpka A.; Andreo J.; Wuttke S.; Friederich P.; Tsotsalas M. MOF synthesis prediction enabled by automatic data mining and machine learning. Angew. Chem., Int. Ed. 2022, 61 (19), e202200242 10.1002/anie.202200242. PMC9310626 35104033 · DOI
  9. Hase F.; Roch L. M.; Kreisbeck C.; Aspuru-Guzik A. Phoenics: a Bayesian optimizer for chemistry. ACS Cent. Sci. 2018, 4 (9), 1134– 1145. 10.1021/acscentsci.8b00307. 30276246 PMC6161047 · DOI · Paper page
  10. Vert J.-P. How will generative AI disrupt data science in drug discovery?. Nat. Biotechnol. 2023, 41 (6), 750– 751. 10.1038/s41587-023-01789-6. 37156917 · DOI · Paper page
  11. Chong S.; Lee S.; Kim B.; Kim J. Applications of machine learning in metal-organic frameworks. Coord. Chem. Rev. 2020, 423, 213487 10.1016/j.ccr.2020.213487. · DOI
  12. Xie Y.; Zhang C.; Deng H.; Zheng B.; Su J.-W.; Shutt K.; Lin J. Accelerate synthesis of metal–organic frameworks by a robotic platform and bayesian optimization. ACS Appl. Mater. Interfaces 2021, 13 (45), 53485– 53491. 10.1021/acsami.1c16506. 34709793 · DOI
  13. Packwood D.; Nguyen L. T. H.; Cesana P.; Zhang G.; Staykov A.; Fukumoto Y.; Nguyen D. H. Machine learning in materials chemistry: An invitation. MLWA 2022, 8, 100265 10.1016/j.mlwa.2022.100265. · DOI
  14. Hope T.; Downey D.; Weld D. S.; Etzioni O.; Horvitz E. A computational inflection for scientific discovery. Commun. ACM 2023, 66 (8), 62– 73. 10.1145/3576896. · DOI
  15. Freund R.; Canossa S.; Cohen S. M.; Yan W.; Deng H.; Guillerm V.; Eddaoudi M.; Madden D. G.; Fairen-Jimenez D.; Lyu H. 25 years of reticular chemistry. Angew. Chem., Int. Ed. 2021, 60 (45), 23946– 23974. 10.1002/anie.202101644. 33783111 · DOI
  16. Parameswaran A. G.; Shankar S.; Asawa P.; Jain N.; Wang Y. Revisiting Prompt Engineering via Declarative Crowdsourcing. arXiv 2308, 03854, 10.48550/arXiv.2308.03854. · DOI
  17. Wu T.; He S.; Liu J.; Sun S.; Liu K.; Han Q.-L.; Tang Y. A brief overview of ChatGPT: The history, status quo and potential future development. IEEE/CAA J. Autom. Sin. 2023, 10 (5), 1122– 1136. 10.1109/JAS.2023.123618. · DOI · Paper page
  18. Wang Y.; Kordi Y.; Mishra S.; Liu A.; Smith N. A.; Khashabi D.; Hajishirzi H. Self-instruct: Aligning language model with self generated instructions. arXiv: 2212. 10560.
  19. OpenAI GPT-4 technical report. 10.48550/arXiv:2303.08774v3 (accessed 03-27-2023). · DOI
  20. Bubeck S.; Chandrasekaran V.; Eldan R.; Gehrke J.; Horvitz E.; Kamar E.; Lee P.; Lee Y. T.; Li Y.; Lundberg S. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv 10.48550/arXiv:2303.12712 (accessed 04-13-2023). · DOI
  21. Zhou Y.; Muresanu A. I.; Han Z.; Paster K.; Pitis S.; Chan H.; Ba J. Large language models are human-level prompt engineers. arXiv 2211, 01910, 10.48550/arXiv.2211.01910. · DOI · Paper page
  22. Park J. S.; O’Brien J. C.; Cai C. J.; Morris M. R.; Liang P.; Bernstein M. S. Generative agents: Interactive simulacra of human behavior. arXiv 2304, 03442, 10.48550/arXiv.2304.03442. · DOI · Paper page
  23. Bran A. M.; Cox S.; White A. D.; Schwaller P. ChemCrow: Augmenting large-language models with chemistry tools. arXiv 2304, 05376. PMC11116106 38799228
  24. Deshwal A.; Simon C. M.; Doppa J. R. Bayesian optimization of nanoporous materials. Mol. Syst. Des. Eng. 2021, 6 (12), 1066– 1086. 10.1039/D1ME00093D. · DOI
  25. Hanikel N.; Kurandina D.; Chheda S.; Zheng Z.; Rong Z.; Neumann S. E.; Sauer J.; Siepmann J. I.; Gagliardi L.; Yaghi O. M. MOF Linker Extension Strategy for Enhanced Atmospheric Water Harvesting. ACS Cent. Sci. 2023, 9 (3), 551– 557. 10.1021/acscentsci.3c00018. 36968524 PMC10037441 · DOI
  26. Zheng Z.; Nguyen H. L.; Hanikel N.; Li K. K.-Y.; Zhou Z.; Ma T.; Yaghi O. M. High-yield, green and scalable methods for producing MOF-303 for water harvesting from desert air. Nat. Protoc. 2023, 18, 136– 156. 10.1038/s41596-022-00756-w. 36289405 · DOI
  27. Gongora A. E.; Xu B.; Perry W.; Okoye C.; Riley P.; Reyes K. G.; Morgan E. F.; Brown K. A. A Bayesian experimental autonomous researcher for mechanical design.. Sci. Adv. 2020, 6 (15), eaaz1708 10.1126/sciadv.aaz1708. 32300652 PMC7148087 · DOI
  28. Langner S.; Häse F.; Perea J. D.; Stubhan T.; Hauch J.; Roch L. M.; Heumueller T.; Aspuru-Guzik A.; Brabec C. J. Beyond ternary OPV: high-throughput experimentation and self-driving laboratories optimize multicomponent systems. Adv. Mater. 2020, 32 (14), 1907801 10.1002/adma.201907801. 32049386 · DOI
  29. Wahab H.; Jain V.; Tyrrell A. S.; Seas M. A.; Kotthoff L.; Johnson P. A. Machine-learning-assisted fabrication: Bayesian optimization of laser-induced graphene patterning using in-situ Raman analysis. Carbon 2020, 167, 609– 619. 10.1016/j.carbon.2020.05.087. · DOI
  30. Klinowski J.; Paz F. A. A.; Silva P.; Rocha J. Microwave-assisted synthesis of metal–organic frameworks. Dalton Trans. 2011, 40 (2), 321– 330. 10.1039/C0DT00708K. 20963251 · DOI
  31. Phan P. T.; Hong J.; Tran N.; Le T. H. The Properties of Microwave-Assisted Synthesis of Metal–Organic Frameworks and Their Applications. Nanomaterials 2023, 13 (2), 352 10.3390/nano13020352. 36678105 PMC9864337 · DOI
  32. Zheng Z.; Hanikel N.; Lyu H.; Yaghi O. M. Broadly Tunable Atmospheric Water Harvesting in Multivariate Metal–Organic Frameworks. J. Am. Chem. Soc. 2022, 144 (49), 22669– 22675. 10.1021/jacs.2c09756. 36446081 · DOI
  33. Xu W.; Yaghi O. M. Metal–organic frameworks for water harvesting from air, anywhere, anytime. ACS Cent. Sci. 2020, 6 (8), 1348– 1354. 10.1021/acscentsci.0c00678. 32875075 PMC7453559 · DOI
  34. Hanikel N.; Prévot M. S.; Yaghi O. M. MOF water harvesters. Nat. Nanotechnol. 2020, 15 (5), 348– 355. 10.1038/s41565-020-0673-x. 32367078 · DOI
  35. Song W.; Zheng Z.; Alawadhi A. H.; Yaghi O. M. MOF water harvester produces water from Death Valley desert air in ambient sunlight. Nat. Water 2023, 1 (7), 626– 634. 10.1038/s44221-023-00103-7. · DOI
  36. DeSantis D.; Mason J. A.; James B. D.; Houchins C.; Long J. R.; Veenstra M. Techno-economic analysis of metal–organic frameworks for hydrogen and natural gas storage. Energy Fuels 2017, 31 (2), 2024– 2032. 10.1021/acs.energyfuels.6b02510. · DOI
  37. Gaab M.; Trukhan N.; Maurer S.; Gummaraju R.; Müller U. The progression of Al-based metal-organic frameworks–From academic research to industrial production and applications. Microporous Mesoporous Mater. 2012, 157, 131– 136. 10.1016/j.micromeso.2011.08.016. · DOI
  38. Zheng Z.; Alawadhi A. H.; Yaghi O. M. Green Synthesis and Scale-Up of MOFs for Water Harvesting from Air. Mol. Front. J. 2023, 1– 20. 10.1142/S2529732523400011. · DOI
  39. Zheng Z.; Zhang O.; Borgs C.; Chayes J. T.; Yaghi O. M. ChatGPT Chemistry Assistant for Text Mining and Prediction of MOF Synthesis. J. Am. Chem. Soc. 2023, 145 (32), 18048– 18062. 10.1021/jacs.3c05819. 37548379 PMC11073615 · DOI
  40. Zheng Z.; Rong Z.; Rampal N.; Borgs C.; Chayes J. T.; Yaghi O. M. A GPT-4 Reticular Chemist for Guiding MOF Discovery.. Angew. Chem., Int. Ed. 2023, 135, e202311983 10.1002/ange.202311983. 37798813 · DOI
  41. Zhou W.; Jiang Y. E.; Cui P.; Wang T.; Xiao Z.; Hou Y.; Cotterell R.; Sachan M. RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text. arXiv 2305, 13304, 10.48550/arXiv.2305.13304. · DOI · Paper page
  42. White J.; Fu Q.; Hays S.; Sandborn M.; Olea C.; Gilbert H.; Elnashar A.; Spencer-Smith J.; Schmidt D. C. A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv 2302, 11382, 10.48550/arXiv.2302.11382. · DOI · Paper page
  43. Yaghi O. M.; Kalmutzki M. J.; Diercks C. S. Introduction to Reticular Chemistry: Metal-Organic Frameworks and Covalent Organic Frameworks; John Wiley & Sons: 2019.
  44. Furukawa H.; Cordova K. E.; O’Keeffe M.; Yaghi O. M. The chemistry and applications of metal-organic frameworks. Science 2013, 341 (6149), 1230444 10.1126/science.1230444. 23990564 · DOI
  45. Stock N.; Biswas S. Synthesis of metal-organic frameworks (MOFs): routes to various MOF topologies, morphologies, and composites. Chem. Rev. 2012, 112 (2), 933– 969. 10.1021/cr200304e. 22098087 · DOI
  46. Kirlikovali K. O.; Hanna S. L.; Son F. A.; Farha O. K. Back to the Basics: Developing Advanced Metal–Organic Frameworks Using Fundamental Chemistry Concepts. ACS Nanoscience Au 2023, 3 (1), 37– 45. 10.1021/acsnanoscienceau.2c00046. 37101466 PMC10125349 · DOI
  47. Gropp C.; Canossa S.; Wuttke S.; Gándara F.; Li Q.; Gagliardi L.; Yaghi O. M. Standard practices of reticular chemistry. ACS Cent. Sci. 2020, 6, 1255 10.1021/acscentsci.0c00592. 32875067 PMC7453418 · DOI
  48. Jablonka K. M.; Ongari D.; Moosavi S. M.; Smit B. Big-data science in porous materials: materials genomics and machine learning. Chem. Rev. 2020, 120 (16), 8066– 8129. 10.1021/acs.chemrev.0c00004. 32520531 PMC7453404 · DOI
  49. Tannert N.; Jansen C.; Nießing S.; Janiak C. Robust synthesis routes and porosity of the Al-based metal–organic frameworks Al-fumarate, CAU-10-H and MIL-160. Dalton Trans. 2019, 48 (9), 2967– 2976. 10.1039/C8DT04688C. 30741280 · DOI
  50. Chen L. H.; Han W. K.; Yan X.; Zhang J.; Jiang Y.; Gu Z. G. A Highly Stable Ortho-Ketoenamine Covalent Organic Framework with Balanced Hydrophilic and Hydrophobic Sites for Atmospheric Water Harvesting. ChemSusChem 2022, 15 (24), e202201824 10.1002/cssc.202201824. 36215080 · DOI
  51. Sun C.; Zhu Y.; Shao P.; Chen L.; Huang X.; Zhao S.; Ma D.; Jing X.; Wang B.; Feng X. 2D Covalent Organic Framework for Water Harvesting with Fast Kinetics and Low Regeneration Temperature. Angew. Chem. 2023, 135 (11), e202217103 10.1002/ange.202217103. 36640156 · DOI
  52. Bourda L.; Krishnaraj C.; Van Der Voort P.; Van Hecke K. Conquering the crystallinity conundrum: Efforts to increase quality of covalent organic frameworks. Materials Advances 2021, 2 (9), 2811– 2845. 10.1039/D1MA00008J. · DOI
  53. Chandra S.; Kundu T.; Dey K.; Addicoat M.; Heine T.; Banerjee R. Interplaying intrinsic and extrinsic proton conductivities in covalent organic frameworks. Chem. Mater. 2016, 28 (5), 1489– 1494. 10.1021/acs.chemmater.5b04947. · DOI
  54. Khattak A. M.; Ghazi Z. A.; Liang B.; Khan N. A.; Iqbal A.; Li L.; Tang Z. A redox-active 2D covalent organic framework with pyridine moieties capable of faradaic energy storage. J. Mater. Chem. A 2016, 4 (42), 16312– 16317. 10.1039/C6TA05784E. · DOI
  55. Wang C.; Liu F.; Yan S.; Liu C.; Yu Z.; Chen J.; Lyu R.; Wang Z.; Xu M.; Dai S. Assemble 2D redox-active covalent organic framework/graphene hybrids as high-performance capacitive materials. Carbon 2022, 190, 412– 421. 10.1016/j.carbon.2022.01.026. · DOI
  56. Zhou X.; Lu H.; Zhao F.; Yu G. Atmospheric water harvesting: a review of material and structural designs. ACS Mater. Lett. 2020, 2 (7), 671– 684. 10.1021/acsmaterialslett.0c00130. · DOI
  57. Nguyen H. L.; Hanikel N.; Lyle S. J.; Zhu C.; Proserpio D. M.; Yaghi O. M. A porous covalent organic framework with voided square grid topology for atmospheric water harvesting. J. Am. Chem. Soc. 2020, 142 (5), 2218– 2221. 10.1021/jacs.9b13094. 31944678 · DOI
  58. Nguyen H. L.; Gropp C.; Hanikel N.; Möckel A.; Lund A.; Yaghi O. M. Hydrazine-hydrazide-linked covalent organic frameworks for water harvesting. ACS Cent. Sci. 2022, 8 (7), 926– 932. 10.1021/acscentsci.2c00398. 35912353 PMC9336147 · DOI
  59. Stegbauer L.; Hahn M. W.; Jentys A.; Savasci G. k.; Ochsenfeld C.; Lercher J. A.; Lotsch B. V. Tunable water and CO2 sorption properties in isostructural azine-based covalent organic frameworks through polarity engineering. Chem. Mater. 2015, 27 (23), 7874– 7881. 10.1021/acs.chemmater.5b02151. · DOI
  60. Biswal B. P.; Kandambeth S.; Chandra S.; Shinde D. B.; Bera S.; Karak S.; Garai B.; Kharul U. K.; Banerjee R. Pore surface engineering in porous, chemically stable covalent organic frameworks for water adsorption. J. Mater. Chem. A 2015, 3 (47), 23664– 23669. 10.1039/C5TA07998E. · DOI
  61. Karak S.; Kandambeth S.; Biswal B. P.; Sasmal H. S.; Kumar S.; Pachfule P.; Banerjee R. Constructing ultraporous covalent organic frameworks in seconds via an organic terracotta process. J. Am. Chem. Soc. 2017, 139 (5), 1856– 1862. 10.1021/jacs.6b08815. 28106987 · DOI
  62. Tan K. T.; Tao S.; Huang N.; Jiang D. Water cluster in hydrophobic crystalline porous covalent organic frameworks. Nat. Commun. 2021, 12 (1), 6747 10.1038/s41467-021-27128-4. 34799574 PMC8604923 · DOI

Cited by

Sorted by citations

Authors
Zheng, Z., Zhang, O., Nguyen, H. L., Rampal, N., Alawadhi, A. H., Rong, Z., Head-Gordon, T., Borgs, C., Chayes, J. T., & Yaghi, O. M.
Affiliations
  • Kavli Energy NanoScience Institute (US)
  • University of California, Berkeley (US)
  • King Abdulaziz City for Science and Technology (SA)
Corresponding author
Yaghi, Omar M.
ORCID
Venue
ACS Central Science
Publisher
American Chemical Society (ACS)
Published
2023-11-10
Volume
9
Issue
11
Pages
2161-2170
ISSN
  • 2374-7943 (ISSN-L)
  • 2374-7951
DOI
10.1021/acscentsci.3c01087
PMC
PMC10683477
OpenAlex
W4388560379
Cited by
172
References
9
Citations by year
2026: 52 · 2025: 76 · 2024: 43 · 2023: 1
FWCI
12.38
Type
journal article
Language
en
Open access
Licence
Locations
  • ACS Central Science (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • eScholarship (California Digital Library) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Defense Advanced Research Projects Agency (HR0011-21-C-0020)
  • Kavli Foundation
  • National Institute of General Medical Sciences (5R01GM127627-05)
  • Bakar Institute of Digital Materials for the Planet
Topics
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
  • Physical Sciences › Chemistry › Inorganic Chemistry › Metal-Organic Frameworks: Synthesis and Applications
  • Physical Sciences › Chemistry › Organic Chemistry › Microwave-Assisted Synthesis and Applications
Keywords
ChatGPT, large language models, Bayesian optimization, metal-organic frameworks, covalent organic frameworks, microwave-assisted synthesis, crystallinity, porosity, water absorption, exploration-exploitation balance

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review