Accurate prediction of synthesizability and precursors of 3D crystal structures via large language models

Abstract Accessing the synthesizability of crystal structures is crucial for transforming theoretical materials into real-world applications. Nevertheless, there is a significant gap between actual synthesizability and thermodynamic or kinetic stability commonly used to screen synthesizable structur...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhilong Song, Shuaihua Lu, Minggang Ju, Qionghua Zhou, Jinlan Wang
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-61778-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235115309268992
author Zhilong Song
Shuaihua Lu
Minggang Ju
Qionghua Zhou
Jinlan Wang
author_facet Zhilong Song
Shuaihua Lu
Minggang Ju
Qionghua Zhou
Jinlan Wang
author_sort Zhilong Song
collection DOAJ
description Abstract Accessing the synthesizability of crystal structures is crucial for transforming theoretical materials into real-world applications. Nevertheless, there is a significant gap between actual synthesizability and thermodynamic or kinetic stability commonly used to screen synthesizable structures. Herein, we develop the Crystal Synthesis Large Language Models (CSLLM) framework, which utilizes three specialized LLMs to predict the synthesizability of arbitrary 3D crystal structures, possible synthetic methods, and suitable precursors, respectively. We construct a comprehensive dataset including synthesizable/non-synthesizable crystal structures and develop an efficient text representation for crystal structures to fine-tune LLMs. Our Synthesizability LLM achieves state-of-the-art accuracy (98.6%), significantly outperforming traditional synthesizability screening based on thermodynamic and kinetic stability. Its outstanding generalization ability is further demonstrated in experimental structures with complexity considerably exceeding that of the training data. Furthermore, both the Method and Precursor LLMs exceed 90% accuracy in classifying possible synthetic methods and identifying solid-state synthetic precursors for common binary and ternary compounds, respectively. Leveraging CSLLM, tens of thousands of synthesizable theoretical structures are successfully identified, with their 23 key properties predicted using accurate graph neural network models.
format Article
id doaj-art-baf27e5cfd4f490ca1a9257b87bc6a67
institution Kabale University
issn 2041-1723
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-baf27e5cfd4f490ca1a9257b87bc6a672025-08-20T04:02:55ZengNature PortfolioNature Communications2041-17232025-07-0116111110.1038/s41467-025-61778-yAccurate prediction of synthesizability and precursors of 3D crystal structures via large language modelsZhilong Song0Shuaihua Lu1Minggang Ju2Qionghua Zhou3Jinlan Wang4Key Laboratory of Quantum Materials and Devices of Ministry of Education, School of Physics, Southeast UniversityKey Laboratory of Quantum Materials and Devices of Ministry of Education, School of Physics, Southeast UniversityKey Laboratory of Quantum Materials and Devices of Ministry of Education, School of Physics, Southeast UniversityKey Laboratory of Quantum Materials and Devices of Ministry of Education, School of Physics, Southeast UniversityKey Laboratory of Quantum Materials and Devices of Ministry of Education, School of Physics, Southeast UniversityAbstract Accessing the synthesizability of crystal structures is crucial for transforming theoretical materials into real-world applications. Nevertheless, there is a significant gap between actual synthesizability and thermodynamic or kinetic stability commonly used to screen synthesizable structures. Herein, we develop the Crystal Synthesis Large Language Models (CSLLM) framework, which utilizes three specialized LLMs to predict the synthesizability of arbitrary 3D crystal structures, possible synthetic methods, and suitable precursors, respectively. We construct a comprehensive dataset including synthesizable/non-synthesizable crystal structures and develop an efficient text representation for crystal structures to fine-tune LLMs. Our Synthesizability LLM achieves state-of-the-art accuracy (98.6%), significantly outperforming traditional synthesizability screening based on thermodynamic and kinetic stability. Its outstanding generalization ability is further demonstrated in experimental structures with complexity considerably exceeding that of the training data. Furthermore, both the Method and Precursor LLMs exceed 90% accuracy in classifying possible synthetic methods and identifying solid-state synthetic precursors for common binary and ternary compounds, respectively. Leveraging CSLLM, tens of thousands of synthesizable theoretical structures are successfully identified, with their 23 key properties predicted using accurate graph neural network models.https://doi.org/10.1038/s41467-025-61778-y
spellingShingle Zhilong Song
Shuaihua Lu
Minggang Ju
Qionghua Zhou
Jinlan Wang
Accurate prediction of synthesizability and precursors of 3D crystal structures via large language models
Nature Communications
title Accurate prediction of synthesizability and precursors of 3D crystal structures via large language models
title_full Accurate prediction of synthesizability and precursors of 3D crystal structures via large language models
title_fullStr Accurate prediction of synthesizability and precursors of 3D crystal structures via large language models
title_full_unstemmed Accurate prediction of synthesizability and precursors of 3D crystal structures via large language models
title_short Accurate prediction of synthesizability and precursors of 3D crystal structures via large language models
title_sort accurate prediction of synthesizability and precursors of 3d crystal structures via large language models
url https://doi.org/10.1038/s41467-025-61778-y
work_keys_str_mv AT zhilongsong accuratepredictionofsynthesizabilityandprecursorsof3dcrystalstructuresvialargelanguagemodels
AT shuaihualu accuratepredictionofsynthesizabilityandprecursorsof3dcrystalstructuresvialargelanguagemodels
AT minggangju accuratepredictionofsynthesizabilityandprecursorsof3dcrystalstructuresvialargelanguagemodels
AT qionghuazhou accuratepredictionofsynthesizabilityandprecursorsof3dcrystalstructuresvialargelanguagemodels
AT jinlanwang accuratepredictionofsynthesizabilityandprecursorsof3dcrystalstructuresvialargelanguagemodels