A machine-learning pipeline using light sheet fluorescence microscopy to measure immediate early gene expression in mouse brain tissues classified psychoactive drugs with 67% accuracy across eight conditions, significantly above the 12.5% chance level. Psilocybin was discriminated from 5-MeO-DMT, ketamine, MDMA, or acute fluoxetine with over 95% accuracy. Shapley additive explanation identified brain regions driving predictions, suggesting a novel approach for characterizing and validating psychoactive drugs with psychedelic properties.
A pipeline using light sheet fluorescence microscopy to measure immediate early gene expression in mouse brain tissues, combined with machine learning, can classify psychoactive drugs including psilocybin, ketamine, and MDMA. In one-versus-rest tests, the exact drug was identified with 67% accuracy, far above the 12.5% chance level. Psilocybin was discriminated from 5-MeO-DMT, ketamine, MDMA, or acute fluoxetine with over 95% accuracy in pairwise comparisons. Shapley additive explanation identified brain regions driving the predictions. The approach offers a novel way to characterize and validate psychedelic and related compounds.