arXiv subjects

Philipp Höllmer

Publications and source records attributed to Philipp Höllmer.

3 recordsLinked to original sources

arXiv2026

Riemannian Flow Models with Reinforcement Learning for Molecular Crystal Structure Prediction

Crystal structure governs material properties, making crystal structure prediction (CSP) a fundamental problem in materials science. Generative models are a promising approach for solving this problem, but the prevalence of polymorphism, coupled with large unit cells and complex packing geometry, makes the molecular CSP task challenging for existing models. To address this, we introduce Coarse-Grained Open Materials Generation (CG-OMatG), an equivariant Riemannian flow-based generative model. CG-OMatG predicts molecular crystal structures \textit{via} a coarse-grained, hierarchical representation. CG-OMatG treats molecules as rigid bodies---performing both inter- and intra-molecular message passing to construct a geometric representation for molecular packings---and learns to reconstruct molecule centroid positions, orientations, and lattice parameters, conditioned on chemical species and conformer geometry. We train the model on subsets of the Open Molecular Crystals (OMC25) and Cambridge Structural Database (CSD) datasets. Further, we fine-tune the model \textit{via} policy gradient reinforcement learning to steer the model towards generating low-energy candidate structures. We validate the generated structures on the CSP blind test benchmark, assessing agreement with experimentally determined crystals using COMPACK packing-similarity analysis. CG-OMatG exhibits strong performance for generative molecular crystal structure prediction, paving the way for accelerated polymorph screening and organic solid-state materials discovery.

cs.LG↗

arXiv2026

PACSim: A Flexible Simulation Framework for Polymer-Attenuated Coulombic Self-Assembly

Polymer-Attenuated Coulombic Self-Assembly (PACS) is a flexible experimental approach for generating crystals from simple colloidal building blocks. The central components are charged spherical particles coated with a polymer brush that prevents irreversible aggregation. Whether oppositely charged colloids crystallize, and which structures they form, depends on several factors, including colloid concentration, charge, and size, as well as the salt concentration of the solution. Molecular dynamics (MD) simulations are a powerful tool for predicting the outcomes of PACS assembly experiments and also provide particle-level insight into the assembly processes. Here, we present an open-source simulation framework, PACSim, that enables MD simulation studies of assembly by PACS across a range of experimentally relevant scenarios. PACSim is built on top of OpenMM, a flexible MD simulation framework that readily supports the implementation of different interaction potentials, as well as integration with other tools such as enhanced-sampling and machine-learning frameworks. We describe the motivation for PACSim, outline its features, report methodological advancements inspired by this framework, and provide examples of its use.

cond-mat.soft↗

arXiv2026

MolCrystalFlow: Molecular Crystal Structure Prediction via Flow Matching

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.

cs.LG↗