Deep learning-mediated detection of accelerated water drinking after aquaresis in V1b vasopressin receptor knockout mice

Abstract

How water intake is initiated and maintained following V2 vasopressin receptor antagonism remains poorly understood. To elucidate the role of the V1b receptor in managing dehydration stress induced by V2 antagonism, we used deep learning-based computer vision to analyze drinking behavior in V1b knockout (V1bKO) and wild-type (WT) mice. While total water access and intake volume were comparable between genotypes, V1bKO mice exhibited distinct temporal dynamics. Modeling cumulative intake with the Hill equation revealed that the time required to reach 50\% of maximal water access was significantly shorter in V1bKO mice than in WT mice. This accelerated drinking effectively mitigated increases in serum osmolality and body weight loss. A reduced Hill's coefficient in V1bKO mice indicates a reduction of the rapid, cooperative-like water accumulation seen in WT mice. Furthermore, elevated basal hemoglobin levels in V1bKO mice were independent of dehydration, as confirmed via bone marrow transplant. Analysis of movement trajectories revealed that V1bKO mice exhibit a lower proportion of vertical movement (required for nozzle access) despite similar total distances traveled. Collectively, our results demonstrate that the V1b receptor critically regulates water-seeking behavior and osmotic homeostasis.