Synergistic Antibacterial Combination Discovery (Manuscript Under Review)

Problem and Research Question

Antimicrobial resistance (AMR) is a growing global health threat, and discovering new antibacterial combinations is a critical strategy for staying ahead of resistant pathogens. However, the space of possible drug combinations, concentrations, and conditions is vast — exhaustive screening is infeasible under realistic assay cost, feasibility, and safety constraints. The central question: how can an experimental system choose which antibacterial combinations, concentrations, or conditions to test next — under assay cost, feasibility, and safety constraints — so that each experiment maximises information about synergistic interactions rather than merely screening exhaustively?

Conventional high-throughput screening tests many conditions but does not learn from results during the experiment. A closed-loop approach that selects the next experiment based on what has already been observed could dramatically reduce the number of assays needed to identify promising synergistic combinations.

Method

This manuscript describes an AI-driven platform for accelerating the discovery of synergistic antibacterial combinations, with potential for hydrogel-based topical delivery. The platform connects three methodological pillars:

• Adaptive decision-making — prioritising experimental conditions that are expected to be most informative given current evidence and uncertainty, under safety and cost constraints.
• Uncertainty-aware inference — using calibrated uncertainty to distinguish well-established findings from exploratory results, avoiding premature conclusions from sparse data.
• Closed-loop experimentation — connecting automated selection, execution, and inference into a feedback loop where expert review gates actions that require safety judgment.

The platform targets synergistic antibacterial combination discovery against MRSA (methicillin-resistant Staphylococcus aureus), with hydrogel-based topical delivery as a translational application.

Personal Contribution

Frederik Banis contributes the uncertainty-aware decision and inference methodology — framing experiment selection as a sequential decision problem under uncertainty, connecting it to the broader adaptive sensing and control framework developed in prior energy-systems work. Full author list and individual contribution details will be disclosed upon publication.

Validation and Key Results

• Manuscripts describing the platform and related work are under review. They are not counted as published outputs.
• Specific quantitative results are pending peer review and are not reported here to avoid presenting proposed outcomes as completed work.
• Detailed results and the full platform description will be available upon publication.

Related Outputs

• Manuscripts (under review): Details will be disclosed upon publication.
• Software: None released at this time.

Collaborators and Institutions

• Collaborating research team at Hangzhou Institute of Technology, Xidian University.
• Further collaborator details will be provided upon publication of the associated manuscripts.

Status and Next Steps

Status: Under review. The manuscript has been submitted to a peer-reviewed journal. Details, author list, and results will be disclosed upon publication.

Transfer to current research: The closed-loop experimentation cycle — measure, infer, decide, act — with an expert review gate is the same feedback structure demonstrated in laboratory microgrid control (published). The shift is from energy hardware to biomedical hardware, but the closed-loop validation methodology is shared.

See the related project page for the broader research context, the Methods page for the methodological pillars, and the Research page for the research program overview.