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

IF 14.7 1区 综合性期刊 Q1 MULTIDISCIPLINARY SCIENCES
Zhilong Song, Shuaihua Lu, Minggang Ju, Qionghua Zhou, Jinlan Wang
{"title":"Accurate prediction of synthesizability and precursors of 3D crystal structures via large language models.","authors":"Zhilong Song, Shuaihua Lu, Minggang Ju, Qionghua Zhou, Jinlan Wang","doi":"10.1038/s41467-025-61778-y","DOIUrl":null,"url":null,"abstract":"<p><p>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.</p>","PeriodicalId":19066,"journal":{"name":"Nature Communications","volume":"16 1","pages":"6530"},"PeriodicalIF":14.7000,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12264133/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nature Communications","FirstCategoryId":"103","ListUrlMain":"https://doi.org/10.1038/s41467-025-61778-y","RegionNum":1,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
引用次数: 0

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.

通过大语言模型精确预测三维晶体结构的合成能力和前体。
获得晶体结构的可合成性对于将理论材料转化为实际应用至关重要。然而,实际可合成性与通常用于筛选可合成结构的热力学或动力学稳定性之间存在显著差距。在此,我们开发了晶体合成大语言模型(CSLLM)框架,该框架利用三个专门的llm分别预测任意三维晶体结构的可合成性、可能的合成方法和合适的前体。我们构建了一个包括可合成/不可合成晶体结构的综合数据集,并开发了晶体结构的有效文本表示来微调llm。我们的合成能力LLM达到了最先进的精度(98.6%),显著优于传统的基于热力学和动力学稳定性的合成能力筛选。在复杂度大大超过训练数据的实验结构中,进一步证明了其出色的泛化能力。此外,Method和Precursor LLMs在分类可能的合成方法和识别常见二元和三元化合物的固态合成前体方面的准确率分别超过90%。利用CSLLM,我们成功地识别了数以万计的可合成理论结构,并使用精确的图神经网络模型预测了它们的23个关键属性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Nature Communications
Nature Communications Biological Science Disciplines-
CiteScore
24.90
自引率
2.40%
发文量
6928
审稿时长
3.7 months
期刊介绍: Nature Communications, an open-access journal, publishes high-quality research spanning all areas of the natural sciences. Papers featured in the journal showcase significant advances relevant to specialists in each respective field. With a 2-year impact factor of 16.6 (2022) and a median time of 8 days from submission to the first editorial decision, Nature Communications is committed to rapid dissemination of research findings. As a multidisciplinary journal, it welcomes contributions from biological, health, physical, chemical, Earth, social, mathematical, applied, and engineering sciences, aiming to highlight important breakthroughs within each domain.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信