GEM-GPT Enables Personalized Cell Type-Resolved Therapeutic Design for Systems Pharmacology
- 1Northeastern University
Abstract
Generative AI is transforming drug discovery, yet most approaches follow one-drug-one-target paradigms ill-suited to the heterogeneity of chronic, systemic diseases. Systems pharmacology offers an alternative, but generative tools designed for it remain scarce. We introduce GEM-GPT, a transcriptomics-guided framework that generates personalized therapeutic candidate molecules intended to shift cell type-specific disease states toward healthy phenotypes. GEM-GPT uses a biology-inspired deep fusion architecture that couples a single-cell RNA-sequencing foundation model with a molecular GPT, modeling cell type-specific chemical-gene interactions throughout molecule generation rather than through fixed conditioning. Across bulk and single-cell chemical perturbations and CRISPR knock-out signatures, GEM-GPT outperforms state-of-the-art baselines, produces cell type-resolved molecules, and generalizes to unseen cellular contexts. In a case study on opioid use disorder (OUD), it generates novel candidates, recovers FDA-approved OUD-related drugs absent from training, and yields predicted binders to OUD-related targets. GEM-GPT bridges single-cell omics and molecular generation for personalized, cell-type-resolved, systems-aware therapeutic design.
Related
- Quantitative systems pharmacology modeling of class I–III BRAF-mutant NSCLC enables subgroup treatment analysis and combination therapy design
- A mechanistic quantitative systems pharmacology framework enriched by multiscale data enables model-informed translational development of mesenchymal stem cell therapy in lupus nephritis.
- Personalized Therapeutic Strategies in Glioblastoma: Bridging Molecular Markers and In Vivo Observations for Targeted Treatment
- From digital reminders to artificial intelligence–enabled understanding: can personalized treatment predictions improve therapeutic adherence?
- Optimizing the Therapeutic Index: Sequential Intraarterial–Intravenous PRRT with Personalized Volumetric-Adjusted Dosing
BibTeX
@misc{zhang2026gemgpt,
title = {{GEM-GPT Enables Personalized Cell Type-Resolved Therapeutic Design for Systems Pharmacology}},
author = {S. Zhang and R. Ohlan and M. Mottaqi and L. Xie},
howpublished = {bioRxiv},
year = {2026},
month = jul,
doi = {10.64898/2026.07.17.739269},
url = {https://www.biorxiv.org/content/10.64898/2026.07.17.739269v2},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - GEM-GPT Enables Personalized Cell Type-Resolved Therapeutic Design for Systems Pharmacology
AU - S. Zhang
AU - R. Ohlan
AU - M. Mottaqi
AU - L. Xie
PY - 2026
DA - 2026/07/17
PB - bioRxiv
DO - 10.64898/2026.07.17.739269
UR - https://www.biorxiv.org/content/10.64898/2026.07.17.739269v2
AB - Generative AI is transforming drug discovery, yet most approaches follow one-drug-one-target paradigms ill-suited to the heterogeneity of chronic, systemic diseases. Systems pharmacology offers an alternative, but generative tools designed for it remain scarce. We introduce GEM-GPT, a transcriptomics-guided framework that generates personalized therapeutic candidate molecules intended to shift cell type-specific disease states toward healthy phenotypes. GEM-GPT uses a biology-inspired deep fusion architecture that couples a single-cell RNA-sequencing foundation model with a molecular GPT, modeling cell type-specific chemical-gene interactions throughout molecule generation rather than through fixed conditioning. Across bulk and single-cell chemical perturbations and CRISPR knock-out signatures, GEM-GPT outperforms state-of-the-art baselines, produces cell type-resolved molecules, and generalizes to unseen cellular contexts. In a case study on opioid use disorder (OUD), it generates novel candidates, recovers FDA-approved OUD-related drugs absent from training, and yields predicted binders to OUD-related targets. GEM-GPT bridges single-cell omics and molecular generation for personalized, cell-type-resolved, systems-aware therapeutic design.
ER -