Machine Learning Clustering of Water-Water Interactions in the Cambridge Structural Database

Abstract

This study investigated the application of clustering machine learning techniques to analyze water-water contacts in crystal structures deposited in the Cambridge Structural Database. The initial dataset was divided into three groups regarding interaction energies between water molecules, and were separately analyzed. The application of machine learning methods enabled finding similar groups of contacts and defining their geometrical parameters. By carefully scrutinizing geometric parameters and visually examining clustering results, we demonstrated how valuable insights into the diverse spectrum of interactions between water molecules can be gained. Expanding the applicability of clustering methods can be achieved by integrating them into existing software for visualizing crystal structures. This approach has the potential to discover new types of interactions and enhance our understanding of molecular behavior.