High-throughput behavioral screening in Caenorhabditis elegans using machine learning for drug repurposing

Caenorhabditis elegans is a widely used animal model for researching new disease treatments. In recent years, automated methods have been developed to extract mobility phenotypes and analyse, using statistical methods, whether there are differences between control strains and disease model strains. However, these methods present certain limitations in detecting subtle and non-linear patterns. In this study, we propose a high-throughput screening method based on machine learning, using classifiers that provide a recovery percentage as a measure of treatment effect. We evaluate two main approaches: traditional machine learning models based on behavioral features extracted from the worm's skeleton using Tierpsy Tracker, and deep neural networks that directly analyse video sequences. The results indicate that a Random Forest classifier trained with features extracted by Tierpsy Tracker offers higher accuracy and explainability, making it more suitable than deep learning models for drug testing experiments. Finally, to assess the applicability of our method, we processed data from a published drug repurposing study on unc-80 mutants based on statistical methods. The results highlight the potential of machine learning models to enhance automated phenotypic screening in animal models, providing a more robust and quantitative evaluation of treatment effects by considering more complex and subtle patterns.