Artificial Intelligence in Antifungal Drug Discovery Against WHO Critical-Priority Pathogens: Toward a WHO-Aligned, Selectivity-Integrated Discovery Pipeline
Year: 2026
Type: preprint
Abstract: Artificial intelligence has demonstrated real power in medicinal chemistry generally, yet it remains almost entirely absent from actual antifungal drug development, a gap made more urgent by rising antifungal resistance and a drug pipeline that has produced almost no genuinely new chemical classes in two decades. Invasive fungal infections, rising antifungal resistance, and a critically depleted drug pipeline together constitute a public health emergency that recent burden estimates suggest rivals tuberculosis in annual mortality. Since 2022, the WHO Fungal Priority Pathogen List has offered a strategic plan for prioritizing resources; however, the use of artificial intelligence in the discovery of antifungals is still scattered, and even the most recent and extensive scoping review of the literature (106 primary studies) outlined existing applications but did not suggest how to unify them. This review concludes that the gap must be addressed by shifting the focus of antifungal AI research from two concepts to two principles: pathogen prioritization that is directly taken from the WHO list, and therapeutic selectivity that is considered a scored, quantitative constraint that is applied at every pipeline stage instead of as an afterthought when potential compounds are already identified. We are proposing a conceptual pipeline with 6 steps: pathogen stratification, AI-enabled target validation, generative molecular design, multi-objective optimization, forward ADMET and resistance predictions, and experimental prioritization. We operationalize this with two tools: a scored Priority-Selectivity Matrix, demonstrated here with a worked numerical example across five real antifungal targets, and a Stage-Specific AI Toolkit. We further provide a critical appraisal of the specific published tools that already exist in this space, HitList, Fung-AI, FungAMR, and a 2026 pooled CRISPRi screen, showing precisely where each stops short of an integrated, selectivity-first system, and we identify a structural blind spot largely absent from prior antifungal AI literature: the highest-value antifungal targets are integral membrane proteins, the exact protein class that current structure-prediction and docking models handle least reliably. Finally, we remark that all the antifungal agents developed in the last five years have been developed by traditional medicinal chemistry, not AI, so the regulatory process for an AI-generated antifungal has never been tested. This synthesis is designed to translate the scene of a series of disconnected computational demonstrations to a prioritized, discovery-focused, quantitatively assessed effort in the realm of antifungals.
Source: ChemRxiv
Institution: Marwadi University
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7204247940