Abstract::The application of Artificial Intelligence (AI) and other technologies in drug discovery
has received substantial attention, as they streamline the process and overcome challenges that
traditionally make it time-consuming and resource-intensive. Research in antimicrobial drug discovery
has become increasingly urgent due to the accelerating emergence of antimicrobial resistance
(AMR), a significant threat to public health worldwide that makes existing antibiotics less
effective. To address this demanding need, ML algorithms are being applied to design novel drug
candidates at various stages of drug design. To enhance efficiency, accuracy, and overall quality of
results, ML and Deep Learning (DL) algorithms are increasingly used in structure-based drug development,
drug target identification, and novel drug development. Recurrent Neural Networks
(RNNs), Adversarial Autoencoders (AAEs), Support Vector Machines (SVMs), and other AI models
have shown valuable in de novo drug design, physicochemical and pharmacokinetic parameter
(ADMET) analysis, drug repurposing, and ligand- and structure-based virtual screening. Drug discovery
has become increasingly accessible with the emergence of open-source AI platforms and
software, which enable researchers worldwide to create and validate new-generation compounds in
a cost-effective and collaborative manner. Drugs like Halicin and Abaucin, which have considerable
potential against resistant infections, have recently been discovered using AI-assisted methods.
However, challenges remain, including restricted datasets, model interpretability, and integration
into experimental processes despite these advancements. Future advancements are likely to focus
on expanding open-access datasets, advancing AI-driven AMR prevention strategies, and improving
predictive accuracy.