Lira: Rotational Invariant Shape and Electrostatic Descriptors for Small Molecules and Protein Pockets based on Real Spherical Harmonics

Abstract

AbstractMotivationModern AI-based tools are increasing the number of protein structures available, creating an opportunity and a challenge for automated high-throughput drug discovery pipelines. The amount of data is overwhelming for the current methods, thus demanding new high-performance approaches for Machine Learning-based rational drug design. As shape and electrostatics are the main components for understanding protein-ligand interaction; they are the primary targets for efficient AI-compatible descriptors and their associated comparison methods.ResultsThe Lira toolbox is a set of components devised for describing, comparing and analysing shape and electrostatics for small ligands, peptides and protein pockets. It can generate databases with descriptors for tens of millions of shapes in a few hours, which can then be queried in seconds. The Lira design, focused on performance and reliability, makes its integration into AI-driven rational drug design pipelines simple.Availability and implementationLira packages, available for download at https://pinheirolab.com/, are free to use for research and educational purposes.