AI-Driven Antiparasitic Therapeutic Discovery

The global burden of parasitic diseases remains one of the most persistent challenges in public health, driven by drug resistance, diagnostic limitations, and the complex biology of parasite-host interactions. Conditions range from protozoan diseases, including malaria, leishmaniasis, and toxoplasmosis, to helminthic infections, including schistosomiasis and filariasis, and continue to disproportionately affect communities in low- and middle-income countries with the fewest resources to manage them. Parasites continuously adapt to evade host immunity, overcome existing drugs, and survive in changing environments, placing sustained pressure on a limited arsenal of treatment options.Overcoming these challenges requires a renewed pipeline of antiparasitic candidates. Synthetic molecules can be evaluated against a wide range of parasite targets, including enzymes, transporters, receptors, protein–protein interactions, metabolic pathways, and developmental processes. Phenotypic and target-based screening can identify compounds active against specific life-cycle stages and drug-resistant isolates, while drug repurposing offers a faster route to new antiparasitic applications for existing compounds. Compounding these scientific challenges, the economics of drug development remain a critical but often overlooked limiting factor, as populations most affected by parasitic disease offer little commercial incentive for investment, leaving many conditions chronically underfunded relative to their global burden.Artificial intelligence (AI), machine learning (ML), and cheminformatics approaches such as quantitative structure–activity relationship (QSAR) modeling are increasingly used to prioritize promising chemical candidates, and have already been applied to characterize antimalarial drug activity and parasite phenotypes. These methods are complemented by computer-aided virtual screening, pharmacophore modeling, and structure-based modeling, which probe molecular interactions between candidate compounds and parasite targets in greater depth. Computational models of host–parasite interactions further help identify mechanisms of immune evasion and highlight new drug targets. Multi-omics approaches provide a strong foundation for target discovery, enabling investigation of essential genes, metabolic dependencies, and resistance mechanisms, while single-cell technologies and high-resolution mapping add insight into cellular heterogeneity and host susceptibility at single-cell resolution. This Research Topic brings together studies that explore these advances through computational, molecular, and applied approaches, and aims to encourage cross-disciplinary collaboration among parasitology, computational biology, pharmacology, and drug development researchers.We welcome original research articles, systematic reviews, methodological studies, and perspectives addressing computation-driven strategies for antiparasitic therapeutic discovery.Specific themes of interest include, but are not limited to:• Drug resistance mechanisms: Molecular, genomic, and epidemiological approaches to characterizing resistance in parasitic helminths and protozoa.• Computational drug discovery: AI/ML, cheminformatics, virtual screening, and pharmacophore modeling approaches for prioritizing and profiling antiparasitic candidates.• Target identification and validation: Research on parasite-specific molecular targets amenable to therapeutic intervention, including enzymes central to virulence and survival.• Multi-omics and single-cell approaches: Investigation of essential genes, metabolic dependencies, and cellular heterogeneity underlying resistance and host susceptibility.• Host–parasite interactions: Computational approaches to immune evasion, host-directed therapy, and digital twin modeling of infection dynamics.• Drug repurposing and combination strategies: Integrating computational and existing treatment frameworks to address resistance.• Predictive and surveillance modelling: Machine learning applications for drug–target interaction prediction, resistance surveillance, and outbreak forecasting.• Economics of drug development: Analysis of the commercial, funding, and market access barriers that shape antiparasitic drug pipelines, and strategies to incentivise investment in treatments for neglected and underserved populations. Topic editors: Tanmoy Jana, Shivani Choudhary, Harouna SORE, Ikram GUIZANI Source: https://www.frontiersin.org/research-topics/85378/ai-driven-antiparasitic-therapeutic-discovery