AlphaCrystal-II: Distance matrix based crystal structure prediction using deep learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Song, Yuqi, Dong, Rongzhi, Wei, Lai, Li, Qin, Hu, Jianjun
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916197324292096
author Song, Yuqi
Dong, Rongzhi
Wei, Lai
Li, Qin
Hu, Jianjun
author_facet Song, Yuqi
Dong, Rongzhi
Wei, Lai
Li, Qin
Hu, Jianjun
contents Computational prediction of stable crystal structures has a profound impact on the large-scale discovery of novel functional materials. However, predicting the crystal structure solely from a material's composition or formula is a promising yet challenging task, as traditional ab initio crystal structure prediction (CSP) methods rely on time-consuming global searches and first-principles free energy calculations. Inspired by the recent success of deep learning approaches in protein structure prediction, which utilize pairwise amino acid interactions to describe 3D structures, we present AlphaCrystal-II, a novel knowledge-based solution that exploits the abundant inter-atomic interaction patterns found in existing known crystal structures. AlphaCrystal-II predicts the atomic distance matrix of a target crystal material and employs this matrix to reconstruct its 3D crystal structure. By leveraging the wealth of inter-atomic relationships of known crystal structures, our approach demonstrates remarkable effectiveness and reliability in structure prediction through comprehensive experiments. This work highlights the potential of data-driven methods in accelerating the discovery and design of new materials with tailored properties.
format Preprint
id arxiv_https___arxiv_org_abs_2404_04810
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AlphaCrystal-II: Distance matrix based crystal structure prediction using deep learning
Song, Yuqi
Dong, Rongzhi
Wei, Lai
Li, Qin
Hu, Jianjun
Materials Science
Machine Learning
Computational prediction of stable crystal structures has a profound impact on the large-scale discovery of novel functional materials. However, predicting the crystal structure solely from a material's composition or formula is a promising yet challenging task, as traditional ab initio crystal structure prediction (CSP) methods rely on time-consuming global searches and first-principles free energy calculations. Inspired by the recent success of deep learning approaches in protein structure prediction, which utilize pairwise amino acid interactions to describe 3D structures, we present AlphaCrystal-II, a novel knowledge-based solution that exploits the abundant inter-atomic interaction patterns found in existing known crystal structures. AlphaCrystal-II predicts the atomic distance matrix of a target crystal material and employs this matrix to reconstruct its 3D crystal structure. By leveraging the wealth of inter-atomic relationships of known crystal structures, our approach demonstrates remarkable effectiveness and reliability in structure prediction through comprehensive experiments. This work highlights the potential of data-driven methods in accelerating the discovery and design of new materials with tailored properties.
title AlphaCrystal-II: Distance matrix based crystal structure prediction using deep learning
topic Materials Science
Machine Learning
url https://arxiv.org/abs/2404.04810