AI-Driven Antimicrobial Drug Discovery

The global rise of antimicrobial resistance (AMR) among pathogenic microorganisms is widely recognised as one of the most pressing challenges in contemporary clinical medicine. As pathogens continually acquire mechanisms to evade newly developed therapeutics, the traditional antimicrobial discovery and development pipeline, already slow, costly, and characterised by high attrition, struggles to keep pace. This widening gap underscores an urgent need for innovative approaches. In recent years, artificial intelligence (AI) has emerged as a transformative force, reshaping the strategies for discovering, designing, optimising, and ultimately bringing novel antimicrobials to clinical application.

AI’s most significant contribution to antimicrobial discovery stems from its ability to analyse vast, complex datasets at scales and speeds far beyond human capability. The first dataset type comprises chemical libraries. Traditional drug discovery relies on the physical screening of thousands of compounds—a laborious and resource-intensive process that can span years and often yields only a small number of viable candidates. In contrast, AI-driven approaches, particularly those employing deep learning, can computationally assess hundreds of millions of chemical structures within days. These models learn to recognise structural and physicochemical features associated with antimicrobial activity, enabling the rapid prioritisation of compounds with high therapeutic potential.

Another major category of datasets comprises the extensive genomic, transcriptomic, proteomic, and metabolomic data generated for pathogenic microorganisms. These resources remain largely underutilised, yet they offer substantial potential when integrated into AI-driven pipelines. AI models can leverage these datasets to identify and prioritise essential genes and novel therapeutic targets, predict druggable bacterial pathways, and analyse the vulnerabilities of these pathways. Such approaches enable a deeper, systems-level understanding of microbial biology and open new avenues for antimicrobial development.

Beyond screening existing compound libraries, AI is increasingly being employed to design entirely new molecules de novo. Generative AI models can predict which chemical modifications are likely to enhance antimicrobial efficacy or reduce human toxicity. This establishes an iterative feedback loop in which AI proposes candidate molecules, experimental testing validates their activity, and the resulting data are fed back into the model to refine future predictions.

Another important capability of AI lies in predicting resistance and evolutionary dynamics. In this domain, models can be developed to forecast probable resistance mutations and identify bacterial adaptations before they become clinically significant. AI-driven analysis of bacterial genomes can detect early indicators of emerging resistance, enabling proactive intervention. When integrated with surveillance systems, antimicrobial stewardship efforts, and rational drug design strategies that avoid high-risk targets, AI can help preserve the long-term effectiveness of antimicrobial agents.

Thus, the aim of this Research Topic is intentionally broad and encompasses the many ongoing efforts in the fields of antimicrobials and resistance, where AI-driven approaches can make significant contributions. We also welcome articles addressing AI's role in biofilm-associated and polymicrobial biofilm-associated infections like Diabetic foot ulcers, cystic fibrosis lung infections, and catheter-related infections etc..:

In this Research Topic, the key areas focus on, but are not limited to, the following sub-themes:

• AI for the identification and prioritisation of compounds with high antimicrobial potential, including hit identification, lead optimisation, drug repurposing and rediscovery, and prediction of mechanisms of action.

• AI for identifying and prioritising essential genes and novel therapeutic targets, predicting druggable bacterial pathways, and analysing the vulnerabilities of these pathways.

• AI in the de novo design of entirely new antimicrobial molecules, including chemical modifications to enhance efficacy or reduce toxicity to humans.

• Integration of AI with surveillance systems, antimicrobial stewardship initiatives, and rational drug design strategies to avoid high-risk targets and preserve long-term antimicrobial effectiveness.

• AI–supported approaches for the detection and treatment of biofilms

• Computational and AI-driven drug screening and repositioning

For this Research Topic, we invite submissions of all article types permitted within this section. Authors are reminded that experimental or laboratory validation of AI-derived findings is essential for the original research papers.

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Review
• Systematic Review
• Technology and Code

Keywords: Artificial intelligence, machine learning, antimicrobial drug discovery, target identification, antimicrobial resistance, antimicrobial stewardship, antimicrobial resistance surveillance, biofilm

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.