Enhanced Sampling of Crystal Nucleation with Graph Representation Learnt Variables

Zou, Ziyue; Tiwary, Pratyush

doi:10.1021/acs.jpcb.4c00080

Cited by 6 publications

(2 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, graph neural network (GNN) approaches are attractive in their generality, allowing one to use a single flexible model for most systems. GNNs have also been used to describe condensed-phase systems, in which the relevant features are learned in a “ground up” fashion from basic atomistic information. ,,− …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Classification of Local Environments in Molecular Crystals

Kuroshima,

Kilgour,

Tuckerman

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

Identifying local structural motifs and packing patterns of molecular solids is a challenging task for both simulation and experiment. We demonstrate two novel approaches to characterize local environments in different polymorphs of molecular crystals using learning models that employ either flexibly learned or handcrafted molecular representations. In the first case, we follow our earlier work on graph learning in molecular crystals, deploying an atomistic graph convolutional network combined with molecule-wise aggregation to enable per-molecule environmental classification. For the second model, we develop a new set of descriptors based on symmetry functions combined with a point-vector representation of the molecules, encoding information about the positions and relative orientations of the molecule. We demonstrate very high classification accuracy for both approaches on urea and nicotinamide crystal polymorphs and practical applications to the analysis of dynamical trajectory data for nanocrystals and solid−solid interfaces. Both architectures are applicable to a wide range of molecules and diverse topologies, providing an essential step in the exploration of complex condensed matter phenomena.

show abstract

Section: Introductionmentioning

confidence: 99%

“…GNNs have also been used to describe condensed-phase systems, in which the relevant features are learned in a “ground up” fashion from basic atomistic information. 26 , 27 , 29 − 38 …”

Section: Introductionmentioning

confidence: 99%

Machine Learning Classification of Local Environments in Molecular Crystals

Kuroshima,

Kilgour,

Tuckerman

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

show abstract

Descriptor-Free Collective Variables from Geometric Graph Neural Networks

Zhang,

Bonati,

Trizio

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

Enhanced sampling simulations make the computational study of rare events feasible. A large family of such methods crucially depends on the definition of some collective variables (CVs) that could provide a low-dimensional representation of the relevant physics of the process. Recently, many methods have been proposed to semiautomatize the CV design by using machine learning tools to learn the variables directly from the simulation data. However, most methods are based on feedforward neural networks and require some user-defined physical descriptors. Here, we propose bypassing this step using a graph neural network to directly use the atomic coordinates as input for the CV model. This way, we achieve a fully automatic approach to CV determination that provides variables invariant under the relevant symmetries, especially the permutational one. Furthermore, we provide different analysis tools to favor the physical interpretation of the final CV. We prove the robustness of our approach using different methods from the literature for the optimization of the CV, and we prove its efficacy on several systems, including a small peptide, an ion dissociation in explicit solvent, and a simple chemical reaction.

show abstract