XDXD: End-to-end crystal structure determination with low resolution X-ray diffraction

2025-10-20

AI Summary

This study addresses the longstanding challenge of determining complete atomic structures from low-resolution (≥2.0 Å) single-crystal X-ray diffraction data, where conventional methods fail due to ambiguous electron density maps requiring extensive manual interpretation. We propose the first end-to-end deep learning framework that directly generates chemically plausible 3D crystal structure models from measured diffraction intensities—bypassing electron density estimation entirely. Methodologically, we integrate a diffusion-based generative model with crystallographic priors, including space-group symmetry constraints and valence-bonding rules, enabling conditional modeling of diffraction patterns. Evaluated on 24,000 experimentally determined structures, our method achieves a 70.4% structure match rate at 2.0 Å resolution and an atomic position root-mean-square error of <0.05 Å. These results demonstrate a substantial improvement in both automation and reliability for low-resolution crystal structure solution.

Technology Category

• Machine Learning: Structured Learning
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Determining crystal structures from X-ray diffraction data is fundamental across diverse scientific fields, yet remains a significant challenge when data is limited to low resolution. While recent deep learning models have made breakthroughs in solving the crystallographic phase problem, the resulting low-resolution electron density maps are often ambiguous and difficult to interpret. To overcome this critical bottleneck, we introduce XDXD, to our knowledge, the first end-to-end deep learning framework to determine a complete atomic model directly from low-resolution single-crystal X-ray diffraction data. Our diffusion-based generative model bypasses the need for manual map interpretation, producing chemically plausible crystal structures conditioned on the diffraction pattern. We demonstrate that XDXD achieves a 70.4% match rate for structures with data limited to 2.0~Å resolution, with a root-mean-square error (RMSE) below 0.05. Evaluated on a benchmark of 24,000 experimental structures, our model proves to be robust and accurate. Furthermore, a case study on small peptides highlights the model's potential for extension to more complex systems, paving the way for automated structure solution in previously intractable cases.

Problem

• Determining crystal structures from low-resolution X-ray diffraction data
• Overcoming ambiguity in interpreting low-resolution electron density maps
• Automating atomic model generation without manual map interpretation

Innovation

• End-to-end deep learning framework for crystal structures
• Diffusion-based generative model bypasses manual interpretation
• Produces atomic models directly from diffraction data