Transformer model reveals varied cell responses to psilocybin drug effects
A Transformer-Based Delta Expression Encoder for Psilocybin Transcriptional Response: Architecture, Representations, and Biological Validation
Machine Learning
Summary
People’s brains react differently to psilocybin, a psychedelic drug, and this study looks at how different brain cell types change their gene activity after taking it. The researchers used a special computer model called a Transformer to classify whether genes are turned up, down, or unchanged in various cell types, without relying on known biology. They found that some cells show very consistent patterns, especially when genes are turned down, while others vary more. They also tested a common idea that a particular gene, HTR2A, controls how cells respond, but found the opposite of what was expected.
Transformer modelgene expressionsingle-nucleus RNA sequencingpsilocybincell typesdifferential gene expressionHTR2A receptorattention mechanismdrug responsetranscriptional profiling
Authors
Sai Jayakumar
Abstract
Understanding why individuals respond differently to psilocybin requires modeling the drug's transcriptional perturbation signature at the cell-type level. I present a Transformer-based delta expression encoder that learns to classify differential gene expression status - upregulated, downregulated, or neutral - from single-nucleus RNA-sequencing data, without supervision from pathway annotations or prior biological knowledge. The model is trained on pseudobulk profiles from 623 examples spanning 18 cell types, 2 drug conditions, and 6 timepoints derived from the Liao et al. 2025 dataset, and achieves 69.4% weighted classification accuracy. Three principal findings are reported, alongside one direct test of a published hypothesis that returned a result inconsistent with that hypothesis. First, per-cell-type classification accuracy ranges from 28.3% (L2/3 IT, a primary HTR2A-expressing psilocybin target) to 99.6% (endothelial cells), consistent with known psilocybin response biology. Second, psilocybin-induced transcriptional downregulation is significantly more stereotyped across individuals than upregulation (Mann-Whitney U=18615.0, p<0.0001), a novel finding with a cortical depth gradient across excitatory subtypes. Third, attention-guided gene co-regulation analysis recovers drug-specific modules without pathway supervision. Separately, a direct test of whether baseline HTR2A expression predicts drug-response separability across cell types found a significant negative correlation (Spearman r = -0.7088, p = 0.0021), the opposite of what a simple HTR2A-gating account would predict.