{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T02:45:51Z","timestamp":1777949151252,"version":"3.51.4"},"reference-count":52,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:00:00Z","timestamp":1775692800000},"content-version":"vor","delay-in-days":8,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003569","name":"Ministry of Food and Drug Safety","doi-asserted-by":"publisher","award":["RS-2025-02215961"],"award-info":[{"award-number":["RS-2025-02215961"]}],"id":[{"id":"10.13039\/501100003569","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003569","name":"Ministry of Food and Drug Safety","doi-asserted-by":"publisher","award":["RS-2024-00332003"],"award-info":[{"award-number":["RS-2024-00332003"]}],"id":[{"id":"10.13039\/501100003569","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korea Health Technology R&D Project through the Korea Health Industry Development Institute"},{"name":"Ministry of Health & Welfare","award":["RS-2025-19252970"],"award-info":[{"award-number":["RS-2025-19252970"]}]},{"name":"Bio & Medical Technology Development Program of the National Research Foundation"},{"name":"Ministry of Science & ICT","award":["RS-2025-16063391"],"award-info":[{"award-number":["RS-2025-16063391"]}]},{"name":"Regional Innovation System & Education (RISE)\u201d through the Gwangju RISE Center"},{"name":"Ministry of Education (MOE) and the Gwangju Metropolitan Government","award":["2025-RISE-05-011"],"award-info":[{"award-number":["2025-RISE-05-011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Accurate prediction of condition-aware drug-induced transcriptional responses is essential for drug discovery and precision medicine. Current computational models, including encoder\u2013decoder architectures and generative adversarial network-based approaches, exhibit reasonable performance but frequently neglect biological characteristics and fail to generalize to unseen conditions. Thus, this study presents a latent diffusion model that combines a variational autoencoder (VAE) with a diffusion process.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The VAE compresses gene expression (GE) profiles into a low-dimensional latent space, where the diffusion process learns the joint probability distribution over latent GE representations and noisy intermediates, thereby enabling more effective capture of gene\u2013gene correlations. The model incorporates multiple perturbation conditions, including cell line, compound, dose, and time, to enhance prediction performance on unseen conditions. The reverse diffusion process predicts both the mean and variance of the posterior distribution, improving the fidelity of the generated GE profiles. The proposed model achieved the highest reconstruction performance in the unseen compound split with a Pearson correlation coefficient of 0.870\u2009\u00b1\u20090.001 and an R2 score of 0.739\u2009\u00b1\u20090.001, outperforming previous approaches. The model demonstrated superior preservation of gene\u2013gene correlations, as confirmed by heatmap analysis. To evaluate biological relevance, we predicted half-maximal inhibitory concentration using generated GE, outperforming baseline methods. Latent space analysis revealed that the model preserved cell line identity and continuous dose\u2013time variation. Gene set enrichment analysis confirmed that predicted GE reproduced known pathway-level responses to perturbation. These results demonstrate diffusion-based generative models as effective tools for modeling transcriptional responses in drug discovery and precision medicine.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Source code and dataset are available at https:\/\/doi.org\/10.5281\/zenodo.18871024.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag173","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T11:28:13Z","timestamp":1775561293000},"source":"Crossref","is-referenced-by-count":0,"title":["Predicting condition-aware drug-induced transcriptional responses via a latent diffusion model"],"prefix":"10.1093","volume":"42","author":[{"given":"Chaewon","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Intelligent Electronics and Computer Engineering, Chonnam National University , Gwangju,","place":["Republic of Korea"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0925-1853","authenticated-orcid":false,"given":"Sunyong","family":"Yoo","sequence":"additional","affiliation":[{"name":"Department of Intelligent Electronics and Computer Engineering, Chonnam National University , Gwangju,","place":["Republic of Korea"]},{"name":"R&D Center, MATILO AI Inc , Gwangju,","place":["Republic of Korea"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"key":"2026050308013624000_btag173-B2","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1186\/s12920-020-00829-3","article-title":"Network-based drug sensitivity prediction","volume":"13","author":"Ahmed","year":"2020","journal-title":"BMC Med Genomics"},{"key":"2026050308013624000_btag173-B3","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1186\/s12967-020-02350-8","article-title":"Differential responsiveness to BRAF inhibitors of melanoma cell lines BRAF V600E-mutated","volume":"18","author":"Al Hashmi","year":"2020","journal-title":"J Transl Med"},{"key":"2026050308013624000_btag173-B4","doi-asserted-by":"crossref","first-page":"i130","DOI":"10.1093\/bioinformatics\/btae249","article-title":"Transfer learning of condition-specific perturbation in gene interactions improves drug response prediction","volume":"40","author":"Bang","year":"2024","journal-title":"Bioinformatics"},{"key":"2026050308013624000_btag173-B5","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1038\/nature09454","article-title":"Clinical efficacy of a RAF inhibitor needs broad target blockade in BRAF-mutant melanoma","volume":"467","author":"Bollag","year":"2010","journal-title":"Nature"},{"key":"2026050308013624000_btag173-B6","doi-asserted-by":"crossref","first-page":"29887","DOI":"10.1074\/jbc.M112.371682","article-title":"Aurora B is regulated by the mitogen-activated protein kinase\/extracellular signal-regulated kinase (MAPK\/ERK) signaling pathway and is a valuable potential target in melanoma cells","volume":"287","author":"Bonet","year":"2012","journal-title":"J Biol Chem"},{"key":"2026050308013624000_btag173-B7","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1007\/s00204-020-02656-y","article-title":"Prospects and challenges of multi-omics data integration in toxicology","volume":"94","author":"Canzler","year":"2020","journal-title":"Arch Toxicol"},{"key":"2026050308013624000_btag173-B8","doi-asserted-by":"crossref","first-page":"840","DOI":"10.2174\/0115748936355418250114104026","article-title":"A graphlet-based explanation generator for graph neural networks over biological datasets","volume":"20","author":"Cetin","year":"2025","journal-title":"CBIO"},{"key":"2026050308013624000_btag173-B9","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.1056\/NEJMoa1103782","article-title":"Improved survival with vemurafenib in melanoma with BRAF V600E mutation","volume":"364","author":"Chapman","year":"2011","journal-title":"New Engl J Med"},{"key":"2026050308013624000_btag173-B10","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1158\/0008-5472.CAN-09-1491","article-title":"Oncogenic B-Raf(V600E) induces spindle abnormalities, supernumerary centrosomes, and aneuploidy in human melanocytic cells","volume":"70","author":"Cui","year":"2010","journal-title":"Cancer Res"},{"key":"2026050308013624000_btag173-B11","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.semcancer.2006.07.014","article-title":"The c-myc target gene network","volume":"16","author":"Dang","year":"2006","journal-title":"Semin Cancer Biol"},{"key":"2026050308013624000_btag173-B12","first-page":"34","article-title":"Diffusion models beat GANs on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026050308013624000_btag173-B13","doi-asserted-by":"crossref","first-page":"1950","DOI":"10.1002\/ijc.32611","article-title":"HO-1 downregulation favors BRAF(V600) melanoma cell death induced by vemurafenib\/PLX4032 and increases NK recognition","volume":"146","author":"Furfaro","year":"2020","journal-title":"Int J Cancer"},{"key":"2026050308013624000_btag173-B14","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1038\/s41592-025-02877-y","article-title":"Squidiff: predicting cellular development and responses to perturbations using a diffusion model","volume":"23","author":"He","year":"2026","journal-title":"Nat Methods"},{"key":"2026050308013624000_btag173-B15","doi-asserted-by":"crossref","first-page":"465","DOI":"10.31887\/DCNS.2014.16.4\/rherwig","article-title":"Computational modeling of drug response with applications to neuroscience","volume":"16","author":"Herwig","year":"2014","journal-title":"Dialogues Clin Neurosci"},{"key":"2026050308013624000_btag173-B16","first-page":"26711","article-title":"Predicting cellular responses to novel drug perturbations at a single-cell resolution","volume":"35","author":"Hetzel","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026050308013624000_btag173-B17","first-page":"6840","volume-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020"},{"key":"2026050308013624000_btag173-B18","doi-asserted-by":"crossref","first-page":"e70016","DOI":"10.1002\/qub2.70016","article-title":"Predicting drug-perturbed transcriptional responses using multi-conditional diffusion transformer","volume":"14","author":"Hu","year":"2026","journal-title":"Quantitative Biology"},{"key":"2026050308013624000_btag173-B19","doi-asserted-by":"crossref","first-page":"4383","DOI":"10.1158\/1078-0432.CCR-13-0074","article-title":"Vemurafenib synergizes with nutlin-3 to deplete survivin and suppresses melanoma viability and tumor growth","volume":"19","author":"Ji","year":"2013","journal-title":"Clin Cancer Res"},{"key":"2026050308013624000_btag173-B20","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1038\/nature12688","article-title":"A melanocyte lineage program confers resistance to MAP kinase pathway inhibition","volume":"504","author":"Johannessen","year":"2013","journal-title":"Nature"},{"key":"2026050308013624000_btag173-B21","first-page":"772","article-title":"Graph convolutional network for drug response prediction using gene expression data","volume":"9","author":"Kim","year":"2021","journal-title":"Mathematics-Basel"},{"key":"2026050308013624000_btag173-B22","author":"Kingma","year":"2013"},{"key":"2026050308013624000_btag173-B23","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.ejca.2015.12.002","article-title":"p53 reactivation by PRIMA-1(met) (APR-246) sensitises (V600E\/K)BRAF melanoma to vemurafenib","volume":"55","author":"Krayem","year":"2016","journal-title":"Eur J Cancer"},{"key":"2026050308013624000_btag173-B24","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"Ann Math Statist"},{"key":"2026050308013624000_btag173-B25","doi-asserted-by":"crossref","first-page":"794216","DOI":"10.3389\/fonc.2022.794216","article-title":"Dimethyl fumarate combined with vemurafenib enhances anti-melanoma efficacy via inhibiting the hippo\/YAP, NRF2-ARE, and AKT\/mTOR\/ERK pathways in A375 melanoma cells","volume":"12","author":"Li","year":"2022","journal-title":"Front Oncol"},{"key":"2026050308013624000_btag173-B26","doi-asserted-by":"crossref","first-page":"btae518","DOI":"10.1093\/bioinformatics\/btae518","article-title":"scDiffusion: conditional generation of high-quality single-cell data using diffusion model","volume":"40","author":"Luo","year":"2024","journal-title":"Bioinformatics"},{"key":"2026050308013624000_btag173-B27","doi-asserted-by":"crossref","first-page":"4583","DOI":"10.1158\/1078-0432.CCR-06-0290","article-title":"Predicting cancer drug response by proteomic profiling","volume":"12","author":"Ma","year":"2006","journal-title":"Clin Cancer Res"},{"key":"2026050308013624000_btag173-B28","doi-asserted-by":"crossref","first-page":"e31770","DOI":"10.7554\/eLife.31770","article-title":"Activation of G protein-coupled estrogen receptor signaling inhibits melanoma and improves response to immune checkpoint blockade","volume":"7","author":"Natale","year":"2018","journal-title":"Elife"},{"key":"2026050308013624000_btag173-B29","volume-title":"International conference on machine learning. PMLR","author":"Nichol"},{"key":"2026050308013624000_btag173-B30","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbad034","article-title":"Improved drug response prediction by drug target data integration via network-based profiling","volume":"24","author":"Pak","year":"2023","journal-title":"Brief Bioinform"},{"key":"2026050308013624000_btag173-B31","doi-asserted-by":"crossref","first-page":"e17714","DOI":"10.1016\/j.heliyon.2023.e17714","article-title":"Vemurafenib induces a noncanonical senescence-associated secretory phenotype in melanoma cells which promotes vemurafenib resistance","volume":"9","author":"Peng","year":"2023","journal-title":"Heliyon"},{"key":"2026050308013624000_btag173-B32","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1038\/sj.bjp.0707373","article-title":"Origin and evolution of high throughput screening","volume":"152","author":"Pereira","year":"2007","journal-title":"Br J Pharmacol"},{"key":"2026050308013624000_btag173-B33","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1038\/s42256-020-00285-9","article-title":"A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing","volume":"3","author":"Pham","year":"2021","journal-title":"Nat Mach Intell"},{"key":"2026050308013624000_btag173-B34","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1038\/nrendo.2011.122","article-title":"The G-protein-coupled estrogen receptor GPER in health and disease","volume":"7","author":"Prossnitz","year":"2011","journal-title":"Nat Rev Endocrinol"},{"key":"2026050308013624000_btag173-B35","doi-asserted-by":"crossref","first-page":"9256","DOI":"10.1038\/s41467-024-53457-1","article-title":"Predicting transcriptional responses to novel chemical perturbations using deep generative model for drug discovery","volume":"15","author":"Qi","year":"2024","journal-title":"Nat Commun"},{"key":"2026050308013624000_btag173-B36","author":"Razavi","year":"2019"},{"key":"2026050308013624000_btag173-B1","year":"2023"},{"key":"2026050308013624000_btag173-B37","author":"Rombach R, Blattmann A, Lorenz D","year":"2022","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"2026050308013624000_btag173-B38","first-page":"1256","author":"Ross","year":"2022"},{"key":"2026050308013624000_btag173-B39","doi-asserted-by":"crossref","first-page":"5076","DOI":"10.1093\/bioinformatics\/btaa624","article-title":"Style transfer with variational autoencoders is a promising approach to RNA-Seq data harmonization and analysis","volume":"36","author":"Russkikh","year":"2020","journal-title":"Bioinformatics"},{"key":"2026050308013624000_btag173-B40","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1186\/s13059-025-03519-4","article-title":"scVAEDer: integrating deep diffusion models and variational autoencoders for single-cell transcriptomics analysis","volume":"26","author":"Sadria","year":"2025","journal-title":"Genome Biol"},{"key":"2026050308013624000_btag173-B41","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1089\/cmb.2024.0807","article-title":"DRGAT: predicting drug responses via Diffusion-Based graph attention network","volume":"32","author":"Sefer","year":"2025","journal-title":"J Comput Biol"},{"key":"2026050308013624000_btag173-B42","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1007\/s10115-015-0904-x","article-title":"Diffusion archeology for diffusion progression history reconstruction","volume":"49","author":"Sefer","year":"2016","journal-title":"Knowl Inf Syst"},{"key":"2026050308013624000_btag173-B43","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1038\/s43588-021-00099-8","article-title":"Modeling gene regulatory networks using neural network architectures","volume":"1","author":"Shu","year":"2021","journal-title":"Nat Comput Sci"},{"key":"2026050308013624000_btag173-B44","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1126\/science.aax6234","article-title":"Massively multiplex chemical transcriptomics at single-cell resolution","volume":"367","author":"Srivatsan","year":"2020","journal-title":"Science"},{"key":"2026050308013624000_btag173-B45","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1016\/j.cell.2017.10.049","article-title":"A next generation connectivity map: l 1000 platform and the first 1,000,000 profiles","volume":"171","author":"Subramanian","year":"2017","journal-title":"Cell"},{"key":"2026050308013624000_btag173-B46","doi-asserted-by":"crossref","first-page":"1126044","DOI":"10.3389\/fsysb.2023.1126044","article-title":"Application of perturbation gene expression profiles in drug discovery-From mechanism of action to quantitative modelling","volume":"3","author":"Szalai","year":"2023","journal-title":"Front Syst Biol"},{"key":"2026050308013624000_btag173-B47","doi-asserted-by":"crossref","first-page":"100087","DOI":"10.1016\/j.patter.2020.100087","article-title":"Cellular state transformations using deep learning for precision medicine applications","volume":"1","author":"Targonski","year":"2020","journal-title":"Patterns"},{"key":"2026050308013624000_btag173-B48","doi-asserted-by":"crossref","first-page":"3377","DOI":"10.1093\/bioinformatics\/btac357","article-title":"scPreGAN, a deep generative model for predicting the response of single-cell expression to perturbation","volume":"38","author":"Wei","year":"2022","journal-title":"Bioinformatics"},{"key":"2026050308013624000_btag173-B49","author":"Xiao","year":"2021"},{"key":"2026050308013624000_btag173-B50","doi-asserted-by":"crossref","first-page":"5812","DOI":"10.1158\/0008-5472.CAN-19-0698","article-title":"MEK inhibition modulates cytokine response to mediate therapeutic efficacy in lung cancer","volume":"79","author":"Xie","year":"2019","journal-title":"Cancer Res"},{"key":"2026050308013624000_btag173-B51","first-page":"29620","article-title":"Subgdiff: a subgraph diffusion model to improve molecular representation learning","volume":"37","author":"Zhang","year":"2024","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026050308013624000_btag173-B52","doi-asserted-by":"crossref","first-page":"e102","DOI":"10.1038\/psp.2013.79","article-title":"Predicting cooperative drug effects through the quantitative cellular profiling of response to individual drugs","volume":"3","author":"Zhao","year":"2014","journal-title":"CPT Pharmacometrics Syst Pharmacol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag173\/67993206\/btag173.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/4\/btag173\/67993206\/btag173.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/4\/btag173\/67993206\/btag173.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T21:09:04Z","timestamp":1777842544000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag173\/8644339"}},"subtitle":[],"editor":[{"given":"Daisuke","family":"Kihara","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":52,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4,7]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag173","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,4]]},"published":{"date-parts":[[2026,4]]},"article-number":"btag173"}}