WormSpot: a machine learning-powered viability scoring platform in C. elegans for Candida pathogenicity studies

Invasive Candida infections pose a critical health challenge, exacerbated by emerging antifungal resistance. Caenorhabditis elegans (C. elegans) offers a genetically tractable and scalable model for studying Candida pathogenicity, yet conventional viability assays remain labor-intensive, limiting high-throughput applications. In this study, we developed a machine learning-driven worm viability scoring platform, WormSpot, using representative images of Candida-infected worms, and the robust YOLOv8-based framework. By analyzing static morphological features, our model accurately classifies worm viability post-infection, achieving strong concordance with manual scoring, while requiring minimal image input. Validation with well-characterized Candida albicans mutants and antifungal agents confirms the platform's robustness in predicting worm survival trends. Notably, WormSpot performs efficiently with diverse image formats and is compatible with standard multi-well microscopy workflows, enabling automated data analysis, and scalable application in various experimental setups. In conclusion, WormSpot provides a data-efficient, reproducible tool for assessing Candida virulence using C. elegans, supporting both basic pathogenicity studies and antifungal discovery in high-throughput settings.

Invasive Candida infections represent an increasing threat to public health, driven in part by the emergence of antifungal resistance. Although C. elegans is a powerful and genetically tractable model for studying fungal virulence in vivo, its use has been limited by labor-intensive and poorly scalable viability assays. Here, we present WormSpot, a machine learning-powered platform that enables automated, data-efficient scoring of worm survival from static images. By accurately analyzing high-density worm populations and integrating seamlessly with standard multi-well imaging workflows, WormSpot substantially reduces experimental effort while maintaining robustness and reproducibility. This platform expands the scalability of C. elegans infection models for virulence assessment and antifungal screening and provides a generalizable framework for host-pathogen phenotyping in microbiology research.