A Transformer-Based Delta Expression Encoder for Psilocybin Transcriptional Response: Architecture, Representations, and Biological Validation
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.
Related
- Language-associated brain representations covary with disruption of selfhood under psilocybin
- FloREN: Decoding Immune Regulatory Networks through Interpretable Graph Transformer Patient Representations
- Self-supervised representations reveal the genetic architecture of human cortical folding
- Distinct gradients of cortical architecture capture visual representations and behavior across the lifespan
- Modeling Gene Expression Noise: From Transcriptional Dynamics to Cell Growth and Division
BibTeX
@misc{jayakumar2026transformerbased,
title = {{A Transformer-Based Delta Expression Encoder for Psilocybin Transcriptional Response: Architecture, Representations, and Biological Validation}},
author = {Sai Jayakumar},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.08165},
eprint = {2609.08165},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.08165},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - A Transformer-Based Delta Expression Encoder for Psilocybin Transcriptional Response: Architecture, Representations, and Biological Validation
AU - Sai Jayakumar
PY - 2026
DA - 2026/09/08
PB - arXiv
DO - 10.48550/arxiv.2609.08165
UR - https://arxiv.org/abs/2609.08165
AB - 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.
ER -