Structured information extraction from scientific text with large language models

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: Feb. 15, 2024

Extracting structured knowledge from scientific text remains a challenging task for machine learning models. Here, we present simple approach to joint named entity recognition and relation extraction demonstrate how pretrained large language models (GPT-3, Llama-2) can be fine-tuned extract useful records of complex knowledge. We test three representative tasks in materials chemistry: linking dopants host materials, cataloging metal-organic frameworks, general composition/phase/morphology/application information extraction. Records are extracted single sentences or entire paragraphs, the output returned as English more format such list JSON objects. This represents simple, accessible, highly flexible route obtaining databases specialized research papers.

Language: Английский

---

Structural Design for EMI Shielding: From Underlying Mechanisms to Common Pitfalls

Advanced Materials, Journal Year: 2024, Volume and Issue: 36(24)

Published: March 12, 2024

Abstract Modern human civilization deeply relies on the rapid advancement of cutting‐edge electronic systems that have revolutionized communication, education, aviation, and entertainment. However, electromagnetic interference (EMI) generated by digital poses a significant threat to society, potentially leading future crisis. While numerous efforts are made develop nanotechnological shielding mitigate detrimental effects EMI, there is limited focus creating absorption‐dominant solutions. Achieving EMI shields requires careful structural design engineering, starting from smallest components considering most effective wave attenuating factors. This review offers comprehensive overview structures, emphasizing critical elements design, mechanisms, limitations both traditional shields, common misconceptions about foundational principles science. systematic serves as scientific guide for designing structures prioritize absorption, highlighting an often‐overlooked aspect

Language: Английский

---

A GPT‐4 Reticular Chemist for Guiding MOF Discovery**

Angewandte Chemie International Edition, Journal Year: 2023, Volume and Issue: 62(46)

Published: Oct. 6, 2023

We present a new framework integrating the AI model GPT-4 into iterative process of reticular chemistry experimentation, leveraging cooperative workflow interaction between and human researcher. This Reticular Chemist is an integrated system composed three phases. Each these utilizes in various capacities, wherein provides detailed instructions for chemical experimentation feedback on experimental outcomes, including both success failures, in-context learning next iteration. human-AI enabled to learn from much like experienced chemist, by prompt-learning strategy. Importantly, based natural language development operation, eliminating need coding skills, thus, make it accessible all chemists. Our collaboration with guided discovery isoreticular series MOFs, each synthesis fine-tuned through expert suggestions. presents potential broader applications scientific research harnessing capability large models enhance feasibility efficiency activities.

Language: Английский

---

ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs

ACS Central Science, Journal Year: 2023, Volume and Issue: 9(11), P. 2161 - 2170

Published: Nov. 10, 2023

We leveraged the power of ChatGPT and Bayesian optimization in development a multi-AI-driven system, backed by seven large language model-based assistants equipped with machine learning algorithms, that seamlessly orchestrates multitude research aspects chemistry laboratory (termed Research Group). Our approach accelerated discovery optimal microwave synthesis conditions, enhancing crystallinity MOF-321, MOF-322, COF-323 achieving desired porosity water capacity. In this human researchers gained assistance from these diverse AI collaborators, each unique role within environment, spanning strategy planning, literature search, coding, robotic operation, labware design, safety inspection, data analysis. Such comprehensive enables single researcher working concert to achieve productivity levels analogous those an entire traditional scientific team. Furthermore, reducing biases screening experimental conditions deftly balancing exploration exploitation parameters, our search precisely zeroed on pool 6 million significantly shortened time scale. This work serves as compelling proof concept for AI-driven revolution laboratory, painting future where becomes efficient collaborator, liberating us routine tasks focus pushing boundaries innovation.

Language: Английский

---

Shaping the Water-Harvesting Behavior of Metal–Organic Frameworks Aided by Fine-Tuned GPT Models

Journal of the American Chemical Society, Journal Year: 2023, Volume and Issue: 145(51), P. 28284 - 28295

Published: Dec. 13, 2023

We construct a data set of metal-organic framework (MOF) linkers and employ fine-tuned GPT assistant to propose MOF linker designs by mutating modifying the existing structures. This strategy allows model learn intricate language chemistry in molecular representations, thereby achieving an enhanced accuracy generating structures compared with its base models. Aiming highlight significance design strategies advancing discovery water-harvesting MOFs, we conducted systematic variant expansion upon state-of-the-art MOF-303 utilizing multidimensional approach that integrates extension multivariate tuning strategies. synthesized series isoreticular aluminum termed Long-Arm MOFs (LAMOF-1 LAMOF-10), featuring bear various combinations heteroatoms their five-membered ring moiety, replacing pyrazole either thiophene, furan, or thiazole rings combination two. Beyond consistent robust architecture, as demonstrated permanent porosity thermal stability, LAMOF offers generalizable synthesis strategy. Importantly, these 10 LAMOFs establish new benchmarks for water uptake (up 0.64 g g-1) operational humidity ranges (between 13 53%), expanding diversity MOFs.

Language: Английский

---

Artificial Intelligence for Surface‐Enhanced Raman Spectroscopy

Small Methods, Journal Year: 2023, Volume and Issue: 8(1)

Published: Oct. 27, 2023

Abstract Surface‐enhanced Raman spectroscopy (SERS), well acknowledged as a fingerprinting and sensitive analytical technique, has exerted high applicational value in broad range of fields including biomedicine, environmental protection, food safety among the others. In endless pursuit ever‐sensitive, robust, comprehensive sensing imaging, advancements keep emerging whole pipeline SERS, from design SERS substrates reporter molecules, synthetic route planning, instrument refinement, to data preprocessing analysis methods. Artificial intelligence (AI), which is created imitate eventually exceed human behaviors, exhibited its power learning high‐level representations recognizing complicated patterns with exceptional automaticity. Therefore, facing up intertwining influential factors explosive size, AI been increasingly leveraged all above‐mentioned aspects presenting elite efficiency accelerating systematic optimization deepening understanding about fundamental physics spectral data, far transcends labors conventional computations. this review, recent progresses are summarized through integration AI, new insights challenges perspectives provided aim better gear toward fast track.

Language: Английский

---

Sustainable moisture energy

Nature Reviews Materials, Journal Year: 2024, Volume and Issue: 9(10), P. 722 - 737

Published: Feb. 1, 2024

Language: Английский

---

ChatMOF: an artificial intelligence system for predicting and generating metal-organic frameworks using large language models

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: June 3, 2024

Abstract ChatMOF is an artificial intelligence (AI) system that built to predict and generate metal-organic frameworks (MOFs). By leveraging a large-scale language model (GPT-4, GPT-3.5-turbo, GPT-3.5-turbo-16k), extracts key details from textual inputs delivers appropriate responses, thus eliminating the necessity for rigid formal structured queries. The comprised of three core components (i.e., agent, toolkit, evaluator) it forms robust pipeline manages variety tasks, including data retrieval, property prediction, structure generations. shows high accuracy rates 96.9% searching, 95.7% predicting, 87.5% generating tasks with GPT-4. Additionally, successfully creates materials user-desired properties natural language. study further explores merits constraints utilizing large models (LLMs) in combination database machine learning material sciences showcases its transformative potential future advancements.

Language: Английский

---

Double-walled Al-based MOF with large microporous specific surface area for trace benzene adsorption

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: April 13, 2024

Abstract Double-walled metal-organic frameworks (MOFs), synthesized using Zn and Co, are potential porous materials for trace benzene adsorption. Aluminum is with low-toxicity abundance in nature, comparison Co. Therefore, a double-walled Al-based MOF, named as ZJU-520(Al), large microporous specific surface area of 2235 m 2 g –1 , pore size distribution the range 9.26–12.99 Å excellent chemical stability, was synthesized. ZJU-520(Al) consisted by helical chain AlO 6 clusters 4,6-Di(4-carboxyphenyl)pyrimidine ligands. Trace adsorption up to 5.98 mmol at 298 K P/P 0 = 0.01. Adsorbed molecules trapped on two types sites. One (site I) near clusters, another II) N atom ligands, Grand Canonical Monte Carlo simulations. can effectively separate from mixed vapor flow cyclohexane, due affinity higher than that cyclohexane. adsorbent benzene/cyclohexane separation.

Language: Английский

---

Covalent Organic Frameworks as Promising Platforms for Efficient Electrochemical Reduction of Carbon Dioxide: A Review

Small Structures, Journal Year: 2024, Volume and Issue: 5(5)

Published: Feb. 5, 2024

In current research, achieving carbon neutrality has become a primary focus through the utilization of various conversion technologies that transform dioxide (CO 2 ) into valuable chemicals or fuels. Covalent organic frameworks (COFs), as emerging crystalline polymers, offer distinct advantages in CO compared to other materials. These include controllable nanoscale pores, predefined functional units, editable framework structures, and rich conjugated systems. The unique characteristics COFs make them highly promising electrocatalysts for conversion. This review provides comprehensive overview pioneering works recent research on COF‐based materials electrochemical reduction reaction. offers analysis design principles reactive sites, skeleton pore functionalities, 3D frameworks, morphologies, composite COFs, aiming enhance electrocatalysis. Finally, this presents some recommendations material design, reaction mechanisms, theoretical computations understanding mechanisms further facilitate high‐performance electrocatalysts.

Language: Английский

---