Antimicrobial resistance is a growing global health challenge, creating an urgent need for new antibacterial agents with alternative and resistance-robust modes of action. Our research aims to develop a scalable discovery framework for identifying novel compounds that perturb bacterial translation. The project builds on our laboratory's expertise in molecular phenotyping of ribosome dynamics using 5PSeq and is carried out in collaboration with the Chemical Biology Consortium Sweden (CBCS), combining genomics, computational chemistry, and machine learning to accelerate antimicrobial discovery. A central component of the project is the identification of novel small molecules predicted to interact with bacterial ribosomes and associated translation factors. We will perform large-scale structure-based virtual screening of chemically diverse compound collections against experimentally determined and predicted structures of bacterial translation-related targets. Candidate compounds identified through molecular docking and rescoring pipelines will subsequently be prioritised for experimental validation and molecular phenotyping. The requested NAISS resources will support molecular docking, ligand preparation, post-processing, ranking, and analysis of millions of protein-ligand interactions. In a follow-up step, computational workflows will be integrated with cheminformatics and machine-learning approaches to prioritize compounds for downstream biological testing. The resulting framework will enable efficient exploration of chemical space and contribute to the discovery of novel antimicrobial compounds targeting bacterial translation mechanisms.