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

---

Leveraging large language models for predictive chemistry

Nature Machine Intelligence, Journal Year: 2024, Volume and Issue: 6(2), P. 161 - 169

Published: Feb. 6, 2024

Abstract Machine learning has transformed many fields and recently found applications in chemistry materials science. The small datasets commonly sparked the development of sophisticated machine approaches that incorporate chemical knowledge for each application and, therefore, require specialized expertise to develop. Here we show GPT-3, a large language model trained on vast amounts text extracted from Internet, can easily be adapted solve various tasks science by fine-tuning it answer questions natural with correct answer. We compared this approach dedicated models spanning properties molecules yield reactions. Surprisingly, our fine-tuned version GPT-3 perform comparably or even outperform conventional techniques, particular low-data limit. In addition, inverse design simply inverting questions. ease use high performance, especially datasets, impact fundamental using material sciences. addition literature search, querying pre-trained might become routine way bootstrap project leveraging collective encoded these foundation models, provide baseline predictive tasks.

Language: Английский

---

Roadmap on photonic metasurfaces

Applied Physics Letters, Journal Year: 2024, Volume and Issue: 124(26)

Published: June 24, 2024

Here we present a roadmap on Photonic metasurfaces. This document consists of number perspective articles different applications, challenge areas or technologies underlying photonic Each will introduce the topic, state art as well give an insight into future direction subfield.

Language: Английский

---

Self-Driving Laboratories for Chemistry and Materials Science

Chemical Reviews, Journal Year: 2024, Volume and Issue: 124(16), P. 9633 - 9732

Published: Aug. 13, 2024

Self-driving laboratories (SDLs) promise an accelerated application of the scientific method. Through automation experimental workflows, along with autonomous planning, SDLs hold potential to greatly accelerate research in chemistry and materials discovery. This review provides in-depth analysis state-of-the-art SDL technology, its applications across various disciplines, implications for industry. additionally overview enabling technologies SDLs, including their hardware, software, integration laboratory infrastructure. Most importantly, this explores diverse range domains where have made significant contributions, from drug discovery science genomics chemistry. We provide a comprehensive existing real-world examples different levels automation, challenges limitations associated each domain.

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

---

Recent advances in artificial intelligence boosting materials design for electrochemical energy storage

Chemical Engineering Journal, Journal Year: 2024, Volume and Issue: 490, P. 151625 - 151625

Published: April 24, 2024

In the rapidly evolving landscape of electrochemical energy storage (EES), advent artificial intelligence (AI) has emerged as a keystone for innovation in material design, propelling forward design and discovery batteries, fuel cells, supercapacitors, many other functional materials. This review paper elucidates burgeoning role AI materials from foundational machine learning (ML) techniques to its current pivotal advancing frontiers science storage, including enhancing performance, durability, safety battery technologies, cell efficiency longevity, fine-tuning supercapacitors achieve superior capabilities. Collectively, we present comprehensive overview recent advancements that have significantly accelerated development next-generation EES, offering insights into future research trajectories potential unlock new horizons science.

Language: Английский

---

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

Digital Discovery, Journal Year: 2024, Volume and Issue: 3(7), P. 1257 - 1272

Published: Jan. 1, 2024

This perspective paper explores the potential of Large Language Models (LLMs) in materials science, highlighting their abilities to handle ambiguous tasks, automate processes, and extract knowledge at scale across various disciplines.

Language: Английский

---

Generative AI and process systems engineering: The next frontier

Computers & Chemical Engineering, Journal Year: 2024, Volume and Issue: 187, P. 108723 - 108723

Published: May 9, 2024

Language: Английский

---

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

Digital Discovery, Journal Year: 2024, Volume and Issue: 3(3), P. 491 - 501

Published: Jan. 1, 2024

The integration of artificial intelligence into scientific research opens new avenues with the advent GPT-4V, a large language model equipped vision capabilities.

Language: Английский

---

ProtAgents: protein discovery via large language model multi-agent collaborations combining physics and machine learning

Digital Discovery, Journal Year: 2024, Volume and Issue: 3(7), P. 1389 - 1409

Published: Jan. 1, 2024

ProtAgents is a de novo protein design platform based on multimodal LLMs, where distinct AI agents with expertise in knowledge retrieval, structure analysis, physics-based simulations, and results analysis tackle tasks dynamic setting.

Language: Английский

---