Home-cage AI monitoring finds social and nest-building deficits in SPTAN1 R1098Q mice, with wild-type co-housing partially reducing hyperactivity and restoring rest patterns
The authors built a non-invasive, high-content home-cage phenotyping framework combining SLEAP.ai markerless multi-animal pose estimation, DeepOF automated classification of autonomous and social behaviors, and SAM2 segmentation and quantification of nest-building material, and used long-term monitoring of the early infantile epileptic encephalopathy (EIEE5) model SPTAN1 R1098Q to show impaired spatial habituation in mutant-mutant pairs, persistent unreciprocated trailing of cage mates, and a pronounced reduction in nest-building, while co-housing with a wild-type littermate attenuated mutant hyperactivity and restored a more typical rest pattern.