Crystal Structure Prediction Meets Artificial Intelligence DOI
Zian Chen, Zijun Meng, Tao He

et al.

The Journal of Physical Chemistry Letters, Journal Year: 2025, Volume and Issue: unknown, P. 2581 - 2591

Published: March 3, 2025

Crystal structure prediction (CSP) represents a fundamental research frontier in computational materials science and chemistry, aiming to predict thermodynamically stable periodic structures from given chemical compositions. Traditional methods often face challenges such as high costs local minima trapping. Recently, artificial intelligence methods, represented by generative adversarial networks (GANs), variational autoencoders (VAEs), diffusion models, large language models (LLMs), have revolutionized the traditional paradigm. These frameworks efficiently extract rules structural features crystal databases, significantly reducing while maintaining accuracy. This Perspective systematically evaluates advantages limitations of various explores their synergies with conventional approaches, discusses future prospects accelerating discovery development, providing new insights for directions.

Language: Английский

A Perspective on Foundation Models in Chemistry DOI Creative Commons
Junyoung Choi,

Gunwook Nam,

Jaesik Choi

et al.

JACS Au, Journal Year: 2025, Volume and Issue: unknown

Published: March 25, 2025

Foundation models are an emerging paradigm in artificial intelligence (AI), with successful examples like ChatGPT transforming daily workflows. Generally, foundation large-scale, pretrained capable of adapting to various downstream tasks by leveraging extensive data and model scaling. Their success has inspired researchers develop for a wide range chemical challenges, from materials discovery understanding structure-property relationships, areas where conventional machine learning (ML) often face limitations. In addition, hold promise addressing persistent ML challenges chemistry, such as scarcity poor generalization. this perspective, we review recent progress the development chemistry across applications varying scope. We also discuss trends provide outlook on promising approaches advancing chemistry.

Language: Английский

Citations

0
Crystal Structure Prediction Meets Artificial Intelligence DOI
Zian Chen, Zijun Meng, Tao He

et al.

The Journal of Physical Chemistry Letters, Journal Year: 2025, Volume and Issue: unknown, P. 2581 - 2591

Published: March 3, 2025

Crystal structure prediction (CSP) represents a fundamental research frontier in computational materials science and chemistry, aiming to predict thermodynamically stable periodic structures from given chemical compositions. Traditional methods often face challenges such as high costs local minima trapping. Recently, artificial intelligence methods, represented by generative adversarial networks (GANs), variational autoencoders (VAEs), diffusion models, large language models (LLMs), have revolutionized the traditional paradigm. These frameworks efficiently extract rules structural features crystal databases, significantly reducing while maintaining accuracy. This Perspective systematically evaluates advantages limitations of various explores their synergies with conventional approaches, discusses future prospects accelerating discovery development, providing new insights for directions.

Language: Английский

Citations

0