MolCrystalFlow: Molecular Crystal Structure Prediction via Flow Matching
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912957203480576 |
|---|---|
| author | Zeng, Cheng Sullivan, Harry W. Egg, Thomas Martirossyan, Maya M. Höllmer, Philipp Jin, Jirui Hennig, Richard G. Roitberg, Adrian Martiniani, Stefano Tadmor, Ellad B. Liu, Mingjie |
| author_facet | Zeng, Cheng Sullivan, Harry W. Egg, Thomas Martirossyan, Maya M. Höllmer, Philipp Jin, Jirui Hennig, Richard G. Roitberg, Adrian Martiniani, Stefano Tadmor, Ellad B. Liu, Mingjie |
| contents | Molecular crystal structure prediction represents a grand challenge in computational chemistry due to large sizes of constituent molecules and complex intra- and intermolecular interactions. While generative modeling has revolutionized structure discovery for molecules, inorganic solids, and metal-organic frameworks, extending such approaches to fully periodic molecular crystals is still elusive. Here, we present MolCrystalFlow, a flow-based generative model for molecular crystal structure prediction. The framework disentangles intramolecular complexity from intermolecular packing by embedding molecules as rigid bodies and jointly learning the lattice matrix, molecular orientations, and centroid positions. Centroids and orientations are represented on their native Riemannian manifolds, allowing geodesic flow construction and graph neural network operations that respects geometric symmetries. We benchmark our model against a state-of-the-art generative model (MOFFlow) for large-size periodic crystals and a rule-based structure generation method (Genarris) on two open-source molecular crystal datasets. MolCrystalFlow outperforms MOFFlow while achieving competitive performance against Genarris. We also demonstrate an integration of MolCrystalFlow model with universal machine learning potential to accelerate molecular crystal structure prediction, paving the way for data-driven generative discovery of molecular crystals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16020 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MolCrystalFlow: Molecular Crystal Structure Prediction via Flow Matching Zeng, Cheng Sullivan, Harry W. Egg, Thomas Martirossyan, Maya M. Höllmer, Philipp Jin, Jirui Hennig, Richard G. Roitberg, Adrian Martiniani, Stefano Tadmor, Ellad B. Liu, Mingjie Machine Learning Materials Science Molecular crystal structure prediction represents a grand challenge in computational chemistry due to large sizes of constituent molecules and complex intra- and intermolecular interactions. While generative modeling has revolutionized structure discovery for molecules, inorganic solids, and metal-organic frameworks, extending such approaches to fully periodic molecular crystals is still elusive. Here, we present MolCrystalFlow, a flow-based generative model for molecular crystal structure prediction. The framework disentangles intramolecular complexity from intermolecular packing by embedding molecules as rigid bodies and jointly learning the lattice matrix, molecular orientations, and centroid positions. Centroids and orientations are represented on their native Riemannian manifolds, allowing geodesic flow construction and graph neural network operations that respects geometric symmetries. We benchmark our model against a state-of-the-art generative model (MOFFlow) for large-size periodic crystals and a rule-based structure generation method (Genarris) on two open-source molecular crystal datasets. MolCrystalFlow outperforms MOFFlow while achieving competitive performance against Genarris. We also demonstrate an integration of MolCrystalFlow model with universal machine learning potential to accelerate molecular crystal structure prediction, paving the way for data-driven generative discovery of molecular crystals. |
| title | MolCrystalFlow: Molecular Crystal Structure Prediction via Flow Matching |
| topic | Machine Learning Materials Science |
| url | https://arxiv.org/abs/2602.16020 |