Swimming into the future: Machine learning in zebrafish behavioral research.

The zebrafish (Danio rerio) has emerged as a powerful organism in behavioral neuroscience, offering invaluable insights into the neural circuits and molecular pathways underlying complex behaviors. Although the knowledge of zebrafish behavioral repertoire is expanding rapidly, fundamental questions regarding complex behaviors remain poorly explored. Recent advances in machine learning offer potential for enhancing zebrafish behavioral analysis, enabling more precise, scalable, and unbiased assessments when compared to the traditional method. Thus, machine learning automates tracking and pattern recognition, uncovering new behavioral phenotypes and streamlining analysis typically manually assessed. Here, we highlight the potential use of machine learning tools in zebrafish-based models uncovering nuanced behavioral phenotypes to accelerate discoveries in translational neurobehavioral research, addressing the challenges and ethical considerations in the field. We emphasize that associating machine learning with zebrafish behavioral research, significant advances to elucidate neural and molecular mechanisms driving complex behaviors are expected. Collectively, the progressive refinement of these methods by enabling more detailed and efficient analysis will not only enhance the utility of zebrafish in translational neuroscience, but also contribute to develop more effective models of human disorders and in the search of potential neuroprotective strategies.