The use of machine learning in the design of novel molecules with diverse biological properties has gained significant attention in recent years. Multidrug-resistant bacterial infections continue to pose a major challenge, leading to substantial healthcare costs, prolonged hospital stays and significant loss of lives. The urgent need to discover new antibiotics has prompted the exploration of alternative approaches and machine learning has emerged as a promising tool in the pharmaceutical and biotechnology sectors. While various computational methods and tools have been developed and are currently employed, there is still ample room for improvement and increased accessibility to these technologies in different stages of the drug discovery process. This work aims to address these gaps by refining computational methods, enhancing tools and fostering wider utilization of machine learning in drug discovery, thereby contributing to the development of effective antibiotics and tackling the issue of antibiotic resistance