{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T18:03:21Z","timestamp":1789668201170,"version":"4.0.1"},"posted":{"date-parts":[[2026,7,22]]},"group-title":"Pharmacology and Toxicology","reference-count":54,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"National Institutes of Health","award":["R01GM122845"],"award-info":[{"award-number":["R01GM122845"]}]},{"name":"National Institutes of Health","award":["R01AG057555"],"award-info":[{"award-number":["R01AG057555"]}]},{"name":"National Institutes of Health","award":["R33AG083302"],"award-info":[{"award-number":["R33AG083302"]}]},{"name":"National Institutes of Health","award":["R41DA062978"],"award-info":[{"award-number":["R41DA062978"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>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.<\/jats:p>","DOI":"10.64898\/2026.07.17.739269","type":"posted-content","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T02:35:18Z","timestamp":1784774118000},"source":"Crossref","is-referenced-by-count":0,"title":["GEM-GPT Enables Personalized Cell Type-Resolved Therapeutic Design for Systems Pharmacology"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9497-6263","authenticated-orcid":false,"given":"Shuo","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science, Hunter College, The City University of New York, New York City, NY, 10065, U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahul","family":"Ohlan","sequence":"additional","affiliation":[{"name":"Ph.D. Programs in Computer Science, The Graduate Center, The City University of New York, New York City, NY, 10016, U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1398-7540","authenticated-orcid":false,"given":"Mohammadsadeq","family":"Mottaqi","sequence":"additional","affiliation":[{"name":"Ph.D. Programs in Biochemistry, The Graduate Center, The City University of New York, New York City, NY, 10016, U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Ph.D. Programs in Computer Science, The Graduate Center, The City University of New York, New York City, NY, 10016, U.S.A."},{"name":"School of Pharmacy and Pharmaceutical Sciences & Center for Drug Discovery, Northeastern University, Boston, MA, 02115, U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026091710051120000_2026.07.17.739269v2.1","doi-asserted-by":"crossref","first-page":"3049","DOI":"10.1016\/j.apsb.2022.02.002","article-title":"Why 90% of clinical drug development fails and how to improve it?","volume":"12","year":"2022","journal-title":"Acta Pharmaceutica Sinica B"},{"key":"2026091710051120000_2026.07.17.739269v2.2","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.2786"},{"key":"2026091710051120000_2026.07.17.739269v2.3","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1038\/nchembio.118","article-title":"Network pharmacology: the next paradigm in drug discovery","volume":"4","year":"2008","journal-title":"Nature chemical biology"},{"key":"2026091710051120000_2026.07.17.739269v2.4","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.pharmthera.2013.01.016","article-title":"Structure and dynamics of molecular networks: a novel paradigm of drug discovery: a comprehensive review","volume":"138","year":"2013","journal-title":"Pharmacology & therapeutics"},{"key":"2026091710051120000_2026.07.17.739269v2.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2013.03.002"},{"key":"2026091710051120000_2026.07.17.739269v2.6","doi-asserted-by":"publisher","DOI":"10.1038\/nrg2918"},{"key":"2026091710051120000_2026.07.17.739269v2.7","doi-asserted-by":"publisher","DOI":"10.1038\/nrd3480"},{"key":"2026091710051120000_2026.07.17.739269v2.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2026.02.016"},{"key":"2026091710051120000_2026.07.17.739269v2.9","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-pharmtox-010611-134520"},{"key":"2026091710051120000_2026.07.17.739269v2.10","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1500523"},{"key":"2026091710051120000_2026.07.17.739269v2.11","doi-asserted-by":"publisher","DOI":"10.1038\/nrg.2016.86"},{"key":"2026091710051120000_2026.07.17.739269v2.12","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15153837"},{"key":"2026091710051120000_2026.07.17.739269v2.13","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gku555"},{"key":"2026091710051120000_2026.07.17.739269v2.14","doi-asserted-by":"publisher","DOI":"10.1038\/s41573-023-00688-4"},{"key":"2026091710051120000_2026.07.17.739269v2.15","doi-asserted-by":"publisher","DOI":"10.1038\/s41573-022-00472-w"},{"key":"2026091710051120000_2026.07.17.739269v2.16","doi-asserted-by":"crossref","unstructured":"Wu, Y. , Bourne, P. E. & Xie, L . Ai-powered programmable virtual humans toward human physiologically-based drug discovery. Drug Discovery Today 104497 (2025).","DOI":"10.1016\/j.drudis.2025.104497"},{"key":"2026091710051120000_2026.07.17.739269v2.17","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-13807-w"},{"key":"2026091710051120000_2026.07.17.739269v2.18","first-page":"13455","volume":"38","year":"2024","journal-title":"Gxvaes: Two joint vaes generate hit molecules from gene expression profiles"},{"key":"2026091710051120000_2026.07.17.739269v2.19","doi-asserted-by":"crossref","first-page":"bbae525","DOI":"10.1093\/bib\/bbae525","article-title":"Gexmolgen: cross-modal generation of hit-like molecules via large language model encoding of gene expression signatures","volume":"25","year":"2024","journal-title":"Briefings in bioinformatics"},{"key":"2026091710051120000_2026.07.17.739269v2.20","doi-asserted-by":"crossref","unstructured":"Ohlan, R. , et al. MolGene-E: Inverse molecular design to modulate single cell transcriptomics. bioRxiv (2025). PMC: PMC11888154.","DOI":"10.1101\/2025.02.19.638723"},{"key":"2026091710051120000_2026.07.17.739269v2.21","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1038\/s42256-022-00534-z","article-title":"scbert as a large-scale pretrained deep language model for cell type annotation of single-cell rna-seq data","volume":"4","year":"2022","journal-title":"Nature machine intelligence"},{"key":"2026091710051120000_2026.07.17.739269v2.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06139-9"},{"key":"2026091710051120000_2026.07.17.739269v2.23","doi-asserted-by":"crossref","first-page":"1470","DOI":"10.1038\/s41592-024-02201-0","article-title":"scgpt: toward building a foundation model for single-cell multi-omics using generative ai","volume":"21","year":"2024","journal-title":"Nature methods"},{"key":"2026091710051120000_2026.07.17.739269v2.24","doi-asserted-by":"crossref","first-page":"1481","DOI":"10.1038\/s41592-024-02305-7","article-title":"Large-scale foundation model on single-cell transcriptomics","volume":"21","year":"2024","journal-title":"Nature methods"},{"key":"2026091710051120000_2026.07.17.739269v2.25","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1038\/s42256-024-00843-5","article-title":"Machine learning-aided generative molecular design","volume":"6","year":"2024","journal-title":"Nature Machine Intelligence"},{"key":"2026091710051120000_2026.07.17.739269v2.26","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","article-title":"Automatic chemical design using a data-driven continuous representation of molecules","volume":"4","year":"2018","journal-title":"ACS central science"},{"key":"2026091710051120000_2026.07.17.739269v2.27","unstructured":"De Cao, N. & Kipf, T. Molgan: An implicit generative model for small molecular graphs. arXiv preprint arXiv:1805.11973 (2018)."},{"key":"2026091710051120000_2026.07.17.739269v2.28","first-page":"2064","article-title":"Molgpt: molecular generation using a transformer-decoder model","volume":"62","year":"2021","journal-title":"Journal of chemical information and modeling"},{"key":"2026091710051120000_2026.07.17.739269v2.29","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1038\/s43588-024-00737-x","article-title":"Structure-based drug design with equivariant diffusion models","volume":"4","year":"2024","journal-title":"Nature Computational Science"},{"key":"2026091710051120000_2026.07.17.739269v2.30","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1038\/s41572-019-0137-5","article-title":"Opioid use disorder","volume":"6","year":"2020","journal-title":"Nature reviews Disease primers"},{"key":"2026091710051120000_2026.07.17.739269v2.31","doi-asserted-by":"publisher","DOI":"10.1111\/jcpt.13114"},{"key":"2026091710051120000_2026.07.17.739269v2.32","doi-asserted-by":"crossref","unstructured":"Lee, Y. K. et al. Opioid use disorder: current trends and potential treatments. Frontiers in public health 11, 1274719 (2024).","DOI":"10.3389\/fpubh.2023.1274719"},{"key":"2026091710051120000_2026.07.17.739269v2.33","doi-asserted-by":"crossref","unstructured":"Ochandarena, N. E. , Niehaus, J. K. , Tassou, A. & Scherrer, G . Cell-type specific molecular architecture for mu opioid receptor function in pain and addiction circuits. Neuropharmacology 238, 109597 (2023).","DOI":"10.1016\/j.neuropharm.2023.109597"},{"key":"2026091710051120000_2026.07.17.739269v2.34","doi-asserted-by":"publisher","DOI":"10.1038\/s41380-022-01837-8"},{"key":"2026091710051120000_2026.07.17.739269v2.35","doi-asserted-by":"crossref","first-page":"4296","DOI":"10.1038\/s41467-020-17440-w","article-title":"Multiplexed single-cell transcriptional response profiling to define cancer vulnerabilities and therapeutic mechanism of action","volume":"11","year":"2020","journal-title":"Nature communications"},{"key":"2026091710051120000_2026.07.17.739269v2.36","doi-asserted-by":"publisher","DOI":"10.1126\/science.aax6234"},{"key":"2026091710051120000_2026.07.17.739269v2.37","doi-asserted-by":"crossref","unstructured":"Sun, J. et al. Excape-db: an integrated large scale dataset facilitating big data analysis in chemogenomics. Journal of cheminformatics 9, 17 (2017).","DOI":"10.1186\/s13321-017-0203-5"},{"key":"2026091710051120000_2026.07.17.739269v2.38","doi-asserted-by":"crossref","unstructured":"Passaro, S. , et al. Boltz-2: Towards accurate and efficient binding affinity prediction. BioRxiv (2025).","DOI":"10.1101\/2025.06.14.659707"},{"key":"2026091710051120000_2026.07.17.739269v2.39","doi-asserted-by":"publisher","DOI":"10.1038\/nbt1284"},{"key":"2026091710051120000_2026.07.17.739269v2.40","doi-asserted-by":"crossref","first-page":"5610","DOI":"10.1038\/s41467-023-41455-8","article-title":"Single nucleus transcriptomics of ventral midbrain identifies glial activation associated with chronic opioid use disorder","volume":"14","year":"2023","journal-title":"Nature Communications"},{"key":"2026091710051120000_2026.07.17.739269v2.41","first-page":"236084","article-title":"Bi-directional acceleration of alcohol use and opioid use disorder","volume":"2019","year":"2019","journal-title":"Journal of drug and alcohol research"},{"key":"2026091710051120000_2026.07.17.739269v2.42","doi-asserted-by":"publisher","DOI":"10.1016\/j.biopsych.2021.06.007"},{"key":"2026091710051120000_2026.07.17.739269v2.43","doi-asserted-by":"crossref","unstructured":"Dai, Q. et al. Whole transcriptome sequencing of peripheral blood shows that immunity\/gnrh\/pi3k-akt pathways are associated with opioid use disorder. Frontiers in psychiatry 13, 893303 (2022).","DOI":"10.3389\/fpsyt.2022.893303"},{"key":"2026091710051120000_2026.07.17.739269v2.44","doi-asserted-by":"crossref","unstructured":"Nagamatsu, S. T. et al. Cph methylome analysis in human cortical neurons identifies novel gene pathways and drug targets for opioid use disorder. Frontiers in psychiatry 13, 1078894 (2023).","DOI":"10.3389\/fpsyt.2022.1078894"},{"key":"2026091710051120000_2026.07.17.739269v2.45","doi-asserted-by":"crossref","unstructured":"Gong, W.-K. et al. Prefrontal fgf1 signaling is required for accumbal deep brain stimulation treatment of addiction. Advanced Science 12, 2413370 (2025).","DOI":"10.1002\/advs.202413370"},{"key":"2026091710051120000_2026.07.17.739269v2.46","doi-asserted-by":"crossref","unstructured":"Gamble, M. C. et al. Mu-opioid receptor and receptor tyrosine kinase crosstalk: Implications in mechanisms of opioid tolerance, reduced analgesia to neuropathic pain, dependence, and reward. Frontiers in Systems Neuroscience 16, 1059089 (2022).","DOI":"10.3389\/fnsys.2022.1059089"},{"key":"2026091710051120000_2026.07.17.739269v2.47","unstructured":"Salehi, M. , MirKhalaf, A. , Barekateyn, M. , et al. Amitriptyline efficacy in control of acute opioid withdrawal syndrome (2005)."},{"key":"2026091710051120000_2026.07.17.739269v2.48","doi-asserted-by":"publisher","DOI":"10.1001\/archpsyc.55.2.153"},{"key":"2026091710051120000_2026.07.17.739269v2.49","doi-asserted-by":"publisher","DOI":"10.1176\/ajp.132.4.447"},{"key":"2026091710051120000_2026.07.17.739269v2.50","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1111\/ajad.12862","article-title":"Effective management of opioid withdrawal symptoms: A gateway to opioid dependence treatment","volume":"28","year":"2019","journal-title":"The American journal on addictions"},{"key":"2026091710051120000_2026.07.17.739269v2.51","unstructured":"Loshchilov, I. & Hutter, F. Decoupled weight decay regularization (2019)."},{"key":"2026091710051120000_2026.07.17.739269v2.52","unstructured":"Landrum, G. Rdkit: A software suite for cheminformatics, computational chemistry, and predictive modeling (2013)."},{"key":"2026091710051120000_2026.07.17.739269v2.53","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2017.10.049"},{"key":"2026091710051120000_2026.07.17.739269v2.54","doi-asserted-by":"crossref","unstructured":"Eraslan, G. , Simon, L. M. , Mircea, M. , Mueller, N. S. & Theis, F. J . Single-cell rna-seq denoising using a deep count autoencoder. Nature communications 10, 390 (2019).","DOI":"10.1038\/s41467-018-07931-2"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.07.17.739269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T17:05:28Z","timestamp":1789664728000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.07.17.739269"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":54,"URL":"https:\/\/doi.org\/10.64898\/2026.07.17.739269","relation":{},"subject":[],"published":{"date-parts":[[2026,7,22]]},"subtype":"preprint"}}