Packora is a flow-based generative model designed for molecular crystal structure prediction (CSP). It jointly predicts atomic coordinates and lattice parameters from molecular graphs, supporting multi-component and organometallic crystals and allowing conditioning on conformers, stereochemistry, and space-group data. In evaluations inspired by the CCDC CSP blind test, Packora outperforms baselines on generation and ranking benchmarks, achieving superior matched-budget coverage, higher experimental-form recovery, lower ranks, and faster convergence.
Molecular crystal structure prediction (CSP) is important in pharmaceuticals, agrochemicals, and organic electronics, where subtle differences in molecular conformation and packing can strongly affect...
The paper introduces CG-OMatG, an equivariant Riemannian flow-based generative model that predicts molecular crystal structures using a coarse-grained, hierarchical representation. It treats molecules as rigid bodies, performs inter- and intra-molecular message passing, and learns to reconstruct molecule centroids, orientations, and lattice parameters conditioned on chemical species and conformer geometry. The model is trained on OMC25 and CSD datasets, fine-tuned with policy gradient reinforcement learning to favor low-energy structures, and validated against a CSP blind test benchmark using COMPACK packing-similarity analysis.
The study benchmarks 12 deep generative crystal structure prediction models against the template-based TCSP 2.0 on 180 test structures, finding that template retrieval achieves the highest top‑1 success (68.3%). Most generative predictions overlap with template substitutions, and removing entire stoichiometric prototype families from training reduces accuracy by 50‑78%, indicating strong prototype dependence. Only a small subset of predictions remain after such removal, suggesting limited genuine de‑novo capability.
AtomSteer is a test‑time inference framework that steers pretrained atomistic generative models to satisfy structural constraints such as crystallographic symmetry, geometry, and stereochemistry. It applies bounded local projections, graph‑rigid stereochemical transformations, and periodic symmetry projections during sampling, accepting updates that improve constraint satisfaction while preserving the rest of the structure. The method is demonstrated on three backbones—FlowMM, ET‑Flow, and Boltz‑2—across tasks including de novo crystal generation, crystal structure prediction, molecular conformer generation, and protein‑ligand complex prediction, yielding improvements in space‑group coverage, stereochemical accuracy, and ligand E/Z error rates.
arXiv:2606. 03199v1 Announce Type: new Abstract: Organic crystal structure prediction (CSP) is a requirement for computational modelling of organic solids, but traditionally costs several CPU-years per molecule.
uFlowCSP is a MeanFlow-based crystal structure prediction model that learns the average probability‑flow velocity, enabling it to generate complete crystal structures in one to five network evaluations. It achieves inference speeds 5×–58× faster than diffusion and flow‑matching methods while matching or surpassing their performance, with a chemistry‑ and symmetry‑aware Transformer that uses canonical atom ordering and per‑token chemistry embeddings. On the MP‑20 benchmark, uFlowCSP attains comparable or higher accuracy with far fewer evaluations and significantly lower wall‑clock time, demonstrating improved accuracy per network evaluation.
arXiv:2601. 09285v2 Announce Type: replace Abstract: Metal-organic frameworks (MOFs) are porous crystalline materials with broad applications such as carbon capture and drug delivery, yet accurately predicting their 3D structures remains a significant challenge.
arXiv:2607. 28553v1 Announce Type: new Abstract: Predicting the 3D structures of atomic systems is fundamental to advancing material science and drug discovery.
CrystalREPA is a plug‑and‑play framework that aligns the atom‑wise hidden states of crystal generative encoders with frozen universal machine‑learning interatomic potential (MLIP) representations using an element‑aware contrastive objective. By doing so, it transfers stability‑aware atomistic priors to generative models with minimal training overhead and no extra inference cost, consistently improving thermodynamic stability, structural validity, and fidelity across multiple generative frameworks and benchmark datasets. The study also shows that an MLIP’s suitability as a teacher is better predicted by the distinguishability of its atom‑wise representation space than by its leaderboard accuracy, providing a practical, accuracy‑independent selection criterion. whyItMatters":"The approach demonstrates a practical method to enhance crystal generative models’ ability to produce stable, realistic structures by leveraging existing MLIP knowledge without incurring additional inference costs."
arXiv:2610.02186v1 Announce Type: cross Abstract: Molecular learning models are strongly shaped by their underlying representations. Yet standard sequential and graph formalisms struggle to explicitl...
arXiv:2508. 02641v2 Announce Type: replace-cross Abstract: Molecular crystal structure prediction (CSP) is essential for applications in pharmaceuticals and organic electronics.
arXiv:2610.08367v1 Announce Type: new Abstract: Several discrete design tasks, such as molecular discovery, require diverse collections of useful candidates at low computational cost. High validity a...