In this project we will use the computational resources to develop, evaluate and apply computational methods and protocols for drug design and discovery. The current focus will be to investigate the use of machine learning methods to increase the throughput of virtual screening of ultra-large compound libraries with the aim to identify novel starting points for antimicrobial drugs, PET tracers and enzyme inhibitors. Furthermore, we will use molecular dynamics to investigate ligand binding poses, support ligand design in our medicinal chemistry projects and investigate bacterial protein dynamics for antibacterial drug design. Specifically, the computational resources will be mainly used for a) ligand preparation for docking b) docking of medium-sized (10M) compound libraries to obtain machine learning model training data, c) docking of large-size (100M) compound libraries for machine learning model evaluation and validation, d) machine learning predictions of giga-scale compound libraries, e) molecular dynamics simulations for investigating ligand binding poses, f) MD simulations of bacterial proteins.