High-performance computers are required to simulate complex systems that allow to study the behavior of molecules under real conditions. This project combines artificial intelligence and parallel algorithms to calculate molecules more precisely and efficiently on a supercomputer. We are aiming to implement and develop novel computational approaches to facilitate drug discovery and optimization.
HPC offers the immense computing power needed in drug discovery and machine learning, in turn, can analyze this data, recognize patterns and make decisions about the properties of potential drug candidates. Beyond ligand docking and ligand design we seek for advanced binding pose prediction via Molecular Dynamics Simulations, which allows to take protein flexibility and solvent effects into account. Also
molecular simulation can provide information about the stability of the ligands or the identification of allosteric binding sites. However, as the accuracy of the binding process increases, the computational power also increases. In this project, virtual screening with advanced machine learning-based molecular simulations (ISOKANN) is used.
