Image and data mining in reticular chemistry powered by GPT-4V

Zheng, Zhiling; He, Zhiguo; Khattab, Omar; Rampal, Nakul; Zaharia, Matei A.; Borgs, Christian; Chayes, Jennifer T.; Yaghi, Omar M.

doi:10.1039/d3dd00239j

Cited by 5 publications

(3 citation statements)

References 81 publications

(94 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some work using GPT-4V for extracting information from a paper's figures exists, for example analysing graphs (PXRD plots, TGA curves, etc. ) in reticular chemistry papers 136 by treating each page in the .pdf as an image.…”

Section: Llm Workflows In Materials Science: Two Case Studiesmentioning

confidence: 99%

Materials science in the era of large language models: a perspective

Lei,

Docherty,

Cooper

2024

Digital Discovery

View full text Add to dashboard Cite

show abstract

Section: Llm Workflows In Materials Science: Two Case Studiesmentioning

confidence: 99%

Materials science in the era of large language models: a perspective

Lei,

Docherty,

Cooper

2024

Digital Discovery

View full text Add to dashboard Cite

show abstract

“…LLM-based agents, characterized by their strong generalization abilities and broad applicability, have demonstrated significant advancements in language proficiency and interaction with humans 17,18 . Motivated by the outstanding performance of these agent, scholars have explored and exploited their capability in the various tasks of chemical and material research, such as literature mining [19][20][21][22] , molecule and material design [23][24][25] , reaction condition recommendation and optimization 22,[26][27][28] , and lab apparatus automation [27][28][29] . The existing reports of LLM-based agents showed scattered coverage of the stages in chemical synthesis reaction development but have not presented a path to fully exploit the potential of LLMbased agents in the entire development process.…”

Section: Introductionmentioning

confidence: 99%

Accelerated end-to-end chemical synthesis development with large language models

Ruan,

Lu,

et al. 2024

Preprint

View full text Add to dashboard Cite

The rapid emergence of large language model (LLM) technology presents significant opportunities to facilitate the development of synthetic reactions. In this work, we leveraged the power of GPT-4 to build a multi-agent system to handle fundamental tasks involved throughout the chemical synthesis development process. The multi-agent system comprises six specialized LLM-based agents, including Literature Scouter, Experiment Designer, Hardware Executor, Spectrum Analyzer, Separation Instructor, and Result Interpreter, which are pre-prompted to accomplish the designated tasks. A web application was built with the multi-agent system as the backend to allow chemist users to interact with experimental platforms and analyze results via natural language, thus, requiring zero-coding skills to allow easy access for all chemists. We demonstrated this multi-agent system on the development of a recently developed copper/TEMPO catalyzed aerobic alcohol oxidation to aldehyde reaction, and this LLM multi-agent copiloted end-to-end reaction development process includes: literature search and information extraction, substrate scope and condition screening, reaction kinetics study, reaction condition optimization, reaction scale-up and product purification. This work showcases the trilogy among chemist users, LLM-based agents, and automated experimental platforms to reform the traditional expert-centric and labor-intensive reaction development workflow.

show abstract

“…ChatGPT-4 offers a novel method for deciphering complex mathematical and background content in scientific papers, an avenue chemists have not explored in detail. The incorporation of LLMs is swiftly evolving in metal–organic framework (MOFs) science, where users can explore synthetic procedures and MOF properties from the published corpus without being bogged down by the massive literature. − Material science has started to benefit from ChatGPT, where photoswitching properties have been predicted reliably in the low-data regime instead of requiring large data sets for machine learning for training . Guidelines have also been published for standardizing LLMs and protocols to speed up synthesis planning in heterogeneous catalysis .…”

Section: Introductionmentioning

confidence: 99%

Solving Advanced Task-Specific Problems in Measurement Sciences with Generative AI

Wahab,

Handlovic,

Roy

et al. 2024

Anal. Chem.

View full text Add to dashboard Cite

The Generative Pre-Trained Transformer known as ChatGPT-4 has undergone extensive pretraining on a diverse data set, enabling it to generate coherent and contextually relevant text based on the input it receives. This capability allows it to perform tasks from answering questions and has attracted significant interest in material sciences, synthetic chemistry, and drug discovery. In this work, we posed four advanced task-specific problems to ChatGPT, which were recently published in leading journals for topics in analytical chemistry, spectroscopy, bioimage super-resolution, and electrochemistry. ChatGPT-4 successfully implemented the four ideas after assigning the "persona" to the AI and posing targeted questions. We show two cases where "unguided" ChatGPT could complete the assignments with minimal human direction. The construction of a microwave spectrum from a free induction curve and super-resolution of bioimages was accomplished using this approach. Two other specific tasks, correcting a complex baseline with morphological operations of set theory and estimating the diffusion current, required additional input, e.g., equations and specific directions from the user. In each case, the MATLAB code was eventually generated by ChatGPT-4 even when the original authors did not provide any code themselves. We show that a validation test must be implemented to detect and correct mistakes made by ChatGPT-4, followed by feedback correction. These approaches will pave the way for open and transparent science and eliminate the black boxes in measurement science when it comes to advanced data processing.

show abstract

Image and data mining in reticular chemistry powered by GPT-4V

Abstract: The integration of artificial intelligence into scientific research opens new avenues with the advent of GPT-4V, a large language model equipped with vision capabilities. In this study, we demonstrate that...

Cited by 5 publications

References 81 publications

Materials science in the era of large language models: a perspective

Materials science in the era of large language models: a perspective

Accelerated end-to-end chemical synthesis development with large language models

Solving Advanced Task-Specific Problems in Measurement Sciences with Generative AI

Contact Info

Product

Resources

About