Predicting the Hallucinogenic Potential of Molecules Using Artificial Intelligence

New drugs for serious mental health disorders should avoid causing psychedelic experiences. Analogs of psychedelic drugs called psychoplastogens show promise for treating opioid use disorder by reducing drug dependence, with rare serious side effects. This effect is linked to increased neuritogenesis and neuroplasticity. Some psychoplastogens act through the 5HT 2A receptor, but others have different pharmacology, making prediction of hallucinogenic potential difficult. Researchers developed machine learning classification models to predict psychedelic effects using in vitro PsychLight data (support vector classification, AUC 0.74) and in vivo human data from Shulgin and Shulgin (SVC, AUC 0.72). The models predicted known 5HT 2A agonists' psychedelic potential with AUCs of 0.97 and 0.71, respectively, aiding design of non-hallucinogenic psychoplastogens.

Study at a glance

Abstract

The development of new drugs addressing serious mental health and other disorders should avoid the psychedelic experience. Analogs of psychedelic drugs can have clinical utility and are termed “psychoplastogens”. These represent promising candidates for treating opioid use disorder to reduce drug dependence, with rarely reported serious adverse effects. This drug abuse cessation is linked to the induction of neuritogenesis and increased neuroplasticity, a hallmark of psychedelic molecules, such as lysergic acid diethylamine. Some, but not all psychoplastogens may act through the G-protein coupled receptor (GPCR) 5HT 2A whereas others may display very different polypharmacology making prediction of hallucinogenic potential challenging. In the process of developing tools to help design new psychoplastogens, we have used artificial intelligence in the form of machine learning classification models for predicting psychedelic effects using a published in vitro data set from PsychLight (support vector classification (SVC), area under the curve (AUC) 0.74) and in vivo human data derived from books from Shulgin and Shulgin (SVC, AUC, 0.72) with nested five-fold cross validation. We have also explored conformal predictors with ECFP6 and electrostatic descriptors in an effort to optimize them. These models have been used to predict known 5HT 2A agonists to assess their potential to act as psychedelics and induce hallucinations for PsychLight (SVC, AUC 0.97) and Shulgin and Shulgin (random forest, AUC 0.71). We have tested these models with head twitch data from the mouse. This predictive capability is desirable to reliably design new psychoplastogens that lack in vivo hallucinogenic potential and help assess existing and future molecules for this potential. These efforts also provide useful insights into understanding the psychedelic structure activity relationship.