Classification of psychedelics and psychoactive drugs based on brain-wide imaging of cellular c-Fos expression.
Farid Aboharb, Pasha A Davoudian, Ling-Xiao Shao, Clara Liao, Gillian N Rzepka, Cassandra Wojtasiewicz, Jonathan Indajang, Mark Dibbs, Jocelyne Rondeau, Alexander M Sherwood, Alfred P Kaye, Alex C Kwan
bioRxiv : the preprint server for biology November 23, 2024 preprint DOI: 10.1101/2024.05.23.590306 via PubMed
Summary
AI-generated from the abstractA 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.
Study at a glance
| Characteristics | Preclinical experimental study |
|---|---|
| Population | Male and female mice |
| Interventions | Psilocybin Ketamine 5-MeO-DMT 6-fluoro-DET MDMA acute fluoxetine chronic fluoxetine vehicle |
| Topics | Ketamine MDMA Neuroplasticity Psilocybin |
| Keywords | Antidepressant Drug discovery Entactogen |
| Citations | 3 |
| Key finding | A machine learning pipeline using immediate early gene expression patterns in mouse brain tissues classified psychoactive drugs with 67% accuracy overall and discriminated psilocybin from other compounds with over 95% accuracy. |
Abstract
Psilocybin, ketamine, and MDMA are psychoactive compounds that exert behavioral effects with distinguishable but also overlapping features. The growing interest in using these compounds as therapeutics necessitates preclinical assays that can accurately screen psychedelics and related analogs. We posit that a promising approach may be to measure drug action on markers of neural plasticity in native brain tissues. We therefore developed a pipeline for drug classification using light sheet fluorescence microscopy of immediate early gene expression at cellular resolution followed by machine learning. We tested male and female mice with a panel of drugs, including psilocybin, ketamine, 5-MeO-DMT, 6-fluoro-DET, MDMA, acute fluoxetine, chronic fluoxetine, and vehicle. In one-versus-rest classification, the exact drug was identified with 67% accuracy, significantly above the chance level of 12.5%. In one-versus-one classifications, psilocybin was discriminated from 5-MeO-DMT, ketamine, MDMA, or acute fluoxetine with >95% accuracy. We used Shapley additive explanation to pinpoint the brain regions driving the machine learning predictions. Our results support a novel approach for characterizing and validating psychoactive drugs with psychedelic properties.