Molecular Crystal Structure Prediction from Conditional Flow on the Unit Cells
Abstract
A molecular crystal structure is jointly described by its space group symmetry, unit cell, and the molecular alignment within the asymmetric unit. Concurrently predicting all three variables is a daunting task, as it mixes discrete symmetry choices with a high-dimensional search in the continuous space. To address this challenge, we decouple these variables using a three-step generation process. Specifically, we train a flow model to learn the conditional distribution of invariant lattice descriptors (e.g. direct- and reciprocal-lattice successive minima and Selling scalars) from a molecular graph, a Hall setting, and the number of molecules in the asymmetric unit (Z'). Using a two sequential quasi-random sampling processes, we first reconstruct the cell parameters that match the predicted lattice invariants and density requirements, and then conduct a molecular packing search within the give symmetry and unit cell constraint. On 84 single-component systems with Z' ≤ 1, our approach reproduces experimental matches for 83 systems; the remaining failure stems from force-field limitations in preserving the experimental structure. These results demonstrate that learned cell proposals can effectively support crystal structure prediction (CSP) for a given Hall setting and Z', which may be extended to fully blind prediction with variable symmetry and Z' settings in the future.
Related
- Benchmarking Universal Machine Learning Force Fields for Crystal Structure Prediction of High-Energy Molecular Systems
- Riemannian Flow Models with Reinforcement Learning for Molecular Crystal Structure Prediction
- Crystal Structure Based Graph Neural Network And LLM Multi-Modal Approach for Material Magnetic Ordering Prediction
- EP-Flow: Disordered Crystal Structure Prediction without Site-Level Annotations
- Deep Generative Crystal Structure Prediction: A Benchmark Study and a Controlled Test of Prototype Dependence
BibTeX
@misc{zhu2026molecular,
title = {{Molecular Crystal Structure Prediction from Conditional Flow on the Unit Cells}},
author = {Qiang Zhu and Yihan Weng},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.04193},
eprint = {2610.04193},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.04193},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Molecular Crystal Structure Prediction from Conditional Flow on the Unit Cells
AU - Qiang Zhu
AU - Yihan Weng
PY - 2026
DA - 2026/10/03
PB - arXiv
DO - 10.48550/arxiv.2610.04193
UR - https://arxiv.org/abs/2610.04193
AB - A molecular crystal structure is jointly described by its space group symmetry, unit cell, and the molecular alignment within the asymmetric unit. Concurrently predicting all three variables is a daunting task, as it mixes discrete symmetry choices with a high-dimensional search in the continuous space. To address this challenge, we decouple these variables using a three-step generation process. Specifically, we train a flow model to learn the conditional distribution of invariant lattice descriptors (e.g. direct- and reciprocal-lattice successive minima and Selling scalars) from a molecular graph, a Hall setting, and the number of molecules in the asymmetric unit (Z'). Using a two sequential quasi-random sampling processes, we first reconstruct the cell parameters that match the predicted lattice invariants and density requirements, and then conduct a molecular packing search within the give symmetry and unit cell constraint. On 84 single-component systems with Z' ≤ 1, our approach reproduces experimental matches for 83 systems; the remaining failure stems from force-field limitations in preserving the experimental structure. These results demonstrate that learned cell proposals can effectively support crystal structure prediction (CSP) for a given Hall setting and Z', which may be extended to fully blind prediction with variable symmetry and Z' settings in the future.
ER -