An Adapted Similarity Kernel and Generalized Convex Hull for Molecular Crystal Structure Prediction

2025/10/23 by Jennie Martin, Michele Ceriotti, Graeme M. Day · 1 voice
Chemistry · Computer Science · Materials Science · #Computational Drug Discovery Methods #Crystallography and molecular interactions #Machine Learning in Materials Science

paper · pdf · doi:10.1021/acs.cgd.5c01220

openalex created_date 2025/10/23 · openalex publication_date 2025/10/23 · openalex updated_date 2026/08/01

Abstract

We adapted an existing approach to identifying stabilizable crystal structures from prediction setsthe Generalized Convex Hull (GCH)to improve its application to molecular crystal structures. This was achieved by modifying the Smooth Overlap of Atomic Positions (SOAP) kernel to define the similarity of molecular crystal structures in a more physically motivated way. The use of the adapted similarity kernel was assessed for several organic molecular crystal landscapes, demonstrating improved interpretability of the resulting machine-learned descriptors. We also demonstrate that the adapted kernel results in improved performance in predicting lattice energies using Gaussian process regression. Our overall findings highlight a sensitivity of similarity kernel-based landscape analysis methods to kernel construction, which should be considered when applying these methods.

Citations

• Efficient iterative schemes forab initiototal-energy calculations using a plane-wave basis set
• Ab initiomolecular dynamics for liquid metals
• Polymorphic ROYalty: The 14th ROY Polymorph Discovered via High-Throughput Crystallization

Discussions

• This Crystal Growth & Design @pubs.acs.org article presents an altered method for molecular crystal structure prediction. By adapting a structural similarity kernel, the authors show better interpre [bsky, 0 points, 0 comments]