End‐to‐End Crystal Structure Prediction from Powder X‐Ray Diffraction
Advanced Science · 2025-02 · 12 (8)
DOI: 10.1002/advs.202410722 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, online erschienen am 04.01.2025. Verfasst von Qingsi Lai und 11 weiteren Autor:innen. Beteiligte Einrichtung: DP Technology, Beijing, 100080, China. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Science and Technology Major Project, National Science Foundation of China.
Abstract (Originalsprache)
Powder X‐ray diffraction (PXRD) is a prevalent technique in materials characterization. While the analysis of PXRD often requires extensive human manual intervention, and most automated method only achieved at coarse‐grained level. The more difficult and important task of fine‐grained crystal structure prediction from PXRD remains unaddressed. This study introduces XtalNet, the first equivariant deep generative model for end‐to‐end crystal structure prediction from PXRD. Unlike previous crystal structure prediction methods that rely solely on composition, XtalNet leverages PXRD as an additional condition, eliminating ambiguity and enabling the generation of complex organic structures with up to 400 atoms in the unit cell. XtalNet comprises two modules: a Contrastive PXRD‐Crystal Pretraining (CPCP) module that aligns PXRD space with crystal structure space, and a Conditional Crystal Structure Generation (CCSG) module that generates candidate crystal structures conditioned on PXRD patterns. Evaluation on two MOF datasets (hMOF‐100 and hMOF‐400) demonstrates XtalNet's effectiveness. XtalNet achieves a top‐10 Match Rate of 90.2% and 79% for hMOF‐100 and hMOF‐400 in conditional crystal structure prediction task, respectively. XtalNet enables the direct prediction of crystal structures from experimental measurements, eliminating the need for manual intervention and external databases. This opens up new possibilities for automated crystal structure determination and the accelerated discovery of novel materials.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- DP Technology, Beijing, 100080, China.
- Center for Data Science, Peking University, Beijing, 100871, China.
- College of Chemistry and Chemical Engineering, Xiamen University, Xiamen, 361005, China.
- School of Intelligence Science and Technology, Peking University, Beijing, 100871, China.
- AI for Science Institute, Beijing, 100084, China.
ORCID-Profile: Qingsi Lai, Lin Yao
Förderung
- National Natural Science Foundation of China
- National Science and Technology Major Project
- National Science Foundation of China
Zitieren
APA
Lai, Q., Xu, F., Yao, L., Gao, Z., Liu, S., Wang, H., Lu, S., He, D., Wang, L., Zhang, L., Wang, C., & Ke, G. (2025). End‐to‐End Crystal Structure Prediction from Powder X‐Ray Diffraction. Advanced Science, 12(8). https://doi.org/10.1002/advs.202410722
Vancouver
Lai Q, Xu F, Yao L, Gao Z, Liu S, Wang H, et al. End‐to‐End Crystal Structure Prediction from Powder X‐Ray Diffraction. Advanced Science. 2025;12(8). doi:10.1002/advs.202410722
BibTeX
@article{Lai2025,
author = {Lai, Qingsi and Xu, Fanjie and Yao, Lin and Gao, Zhifeng and Liu, Siyuan and Wang, Hongshuai and Lu, Shuqi and He, Di and Wang, Liwei and Zhang, Linfeng and Wang, Cheng and Ke, Guolin},
title = {End‐to‐End Crystal Structure Prediction from Powder X‐Ray Diffraction},
journal = {Advanced Science},
year = {2025},
volume = {12},
number = {8},
doi = {10.1002/advs.202410722}
}
EUVIMED