Generative Refinement:A New Paradigm for Determining Single Crystal Structures Directly from HKL Data

TL;DR

RefrActor is a novel deep learning framework that determines crystal structures directly from HKL data, eliminating manual refinement and enabling fully automated, high-throughput crystallography.

Contribution

This work introduces RefrActor, the first end-to-end deep learning system that predicts refined crystal structures directly from diffraction data without initial guesses.

Findings

Achieves low R1-factors across diverse crystal types

Successfully resolves hydrogen positions and elemental assignments

Demonstrates robustness in low-symmetry and disordered crystals

Abstract

Single-crystal X-ray diffraction (SC-XRD) is the gold standard technique to characterize crystal structures in solid state. Despite significant advances in automation for structure solution, the refinement stage still depends heavily on expert intervention and subjective judgment, limiting accessibility and scalability. Herein, we introduce RefrActor, an end-to-end deep learning framework that enables crystal structure determination directly from HKL data. By coupling a physics-informed reciprocal-space encoder (ReciEncoder) with a symmetry-aware diffusion-based generator (StruDiffuser), RefrActor produces fully refined atomic models without requiring initial structural guesses or manual input. Comprehensive evaluations on the GenRef-10k benchmark demonstrates that RefrActor achieves low R1-factors across diverse systems, including low-symmetry, light-atom, and heavy-atom crystals. Case studies further confirm that RefrActor can correctly resolve hydrogen positions, elemental assignments, and moderate disorder. This work establishes a new data-driven paradigm for autonomous crystallographic analysis, offering a foundation for fully automated, high-throughput crystal structure determination.