DANCE: An open-source analysis pipeline and low-cost hardware to quantify aggression and courtship inDrosophila

Quantifying animal behaviors is pivotal for identifying the underlying neuronal and genetic mechanisms. Computational approaches have enabled automated analysis of complex behaviors such as aggression and courtship inDrosophila. However, existing approaches rely on rigid, rule-based algorithms and expensive hardware, limiting sensitivity to behavioral variations and accessibility. Here, we describe the DANCE (DrosophilaAggression and Courtship Evaluator), a low-cost, open-source platform combining machine learning-based classifiers and inexpensive hardware to quantify aggression and courtship. DANCE consists of six novel behavioral classifiers trained using a supervised machine learning algorithm. DANCE classifiers outperform existing rule-based algorithms by capturing dynamic behavioral variations. DANCE hardware is constructed using repurposed medicine blister packs and acrylic sheets, with recordings performed using smartphones, making it affordable and accessible. Benchmarking demonstrated that DANCE hardware performs comparably to sophisticated, high-cost setups. We validated DANCE in diverse contexts, including social isolation versus enrichment that modulate aggression and courtship, RNAi-mediated down-regulation of neuropeptide Dsk, and optogenetic silencing of dopaminergic neurons which promoted aggression. DANCE provides a cost-effective and portable solution for studyingDrosophilabehaviors in resource-limited settings or closer to natural habitats. Its accessibility and robust performance democratizes behavioral neuroscience, enabling rapid screening of genes and neuronal circuits underlying complex social behaviors.