Crystallographic structure identification is crucial for understanding material properties; however, current methodologies often depend on labor-intensive and time-consuming analyses of 2D X-ray diffraction (XRD) patterns. To address these limitations, this study employs synthetic 2D XRD patterns combined with deep learning (DL) techniques to enable automated and high-throughput classification of the seven crystal systems and 230 space groups. We introduce the novel Auto Diffraction Pipeline, designed to generate synthetic 2D XRD spot patterns from crystallographic information files under diverse conditions, including varying zone axes, atomic substitution, atomic depletion and mechanical loading. These conditions enhance the realism of synthetic data, mitigating the scarcity of experimental datasets and enabling the creation of large representative training sets. Convolutional neural networks were trained and validated on these synthetic datasets to classify crystallographic structures across multiple scenarios. Our results demonstrate that integrating synthetic 2D XRD patterns with DL facilitates rapid, accurate and automated crystallographic classification, promoting the wider adoption of data-driven approaches in materials science.

Crystallographic refinement by simulated annealing. Application to a 2.8 A resolution structure of aspartate aminotransferase. Crystallographic refinement by simulated annealing with molecular dynamics has been applied to a 2.8 A (1 A = 0.1 nm) resolution X-ray structure of aspartate aminotransferase. Comparison of the refined structure and a structure obtained by combined restrained least-squares refinement and manual re-fitting shows a similar R factor, stereochemistry, and mean difference from the isomorphous replacement phase centroids. Crystallographic refinement by simulated annealing accomplished structural changes and improvements of the electron density maps that were not possible by using restrained least-squares refinement without manual re-fitting. Crystallographic refinement by simulated annealing can generate an ensemble of structures, each of which agrees with the diffraction information. Regions of large variations of the ensemble indicate either erroneously fitted or disordered segments of the macromolecule. Published in Journal of molecular biology (1988)

Crystal structure refinement with SHELXL - PMC Acta Crystallogr C Struct Chem . 2015 Jan 1;71(Pt 1):3–8. doi: 10.1107/S2053229614024218 # Crystal structure refinement with SHELXL George M Sheldrick a,* - Author information - Article notes - Copyright and License information aDepartment of Structural Chemistry, Georg-August Universität Göttingen, Tammannstraße 4, Göttingen 37077, Germany * Correspondence e-mail: gsheldr@shelx.uni-ac.gwdg.de Received 2014 Oct 21; Accepted 2014 Nov 2; Collection date 2015 Jan 1. © G. M. Sheldrick 2015 This is an open-access article distributed under the terms of the Creative Commons Attribution Licence, which permits unrestricted use, distribution, and reproduction in any medium, provided the original authors and source are cited. PMC Copyright notice PMCID: PMC4294323 PMID: 25567568 --- New features added to the refinement program SHELXL since 2008 are described and explained. Keywords: SHELXL, crystal structure refinement, X-ray and neutron diffraction, SHREDCIF ## Abstract The improvements in the crystal structure refinement program SHELXL have been closely coupled with the development and increasing importance of the CIF (Crysta