{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T15:08:45Z","timestamp":1789398525303,"version":"build-2803163510"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"content-version":"vor","delay-in-days":13,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01LM014087"],"award-info":[{"award-number":["R01LM014087"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Advances in sequencing technologies and the growing volume of single-cell data have created unprecedented opportunities for uncovering gene expression patterns causally induced by experimental perturbations or statistically associated, but not necessarily causal, with disease conditions. However, current analytical methods inadequately account for batch effects and data sparsity or fail to capture the inherent non-linearity in single-cell data, leading to biased estimation. To address these limitations, we developed NDreamer that combines neural discrete representation learning and matching to remove batch effects and estimate perturbation-induced or condition-associated signals at single-cell resolution. NDreamer outperformed existing methods by using mutual information loss on discrete latent variables to disentangle cells\u2019 intrinsic features from conditions or batch effects, while preserving both global and local variance within batches and conditions via triplet and local neighborhood loss. We applied NDreamer to multiple datasets across platforms, organs, and species and validated and benchmarked its performance in removing batch effects and estimating perturbation-induced or condition-associated signals. In particular, we applied NDreamer to an Alzheimer\u2019s disease cohort, revealing biologically relevant gene expression patterns that distinguish dementia patients from controls.<\/jats:p>","DOI":"10.1093\/bib\/bbag485","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T11:51:10Z","timestamp":1787140270000},"source":"Crossref","is-referenced-by-count":0,"title":["Single-cell-level perturbation-induced and condition-related signal estimation with batch effect removal using NDreamer"],"prefix":"10.1093","volume":"27","author":[{"given":"Xiao","family":"Xiao","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Yale University School of Public Health , 300 George Street, New Haven, CT 06511 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1195-9607","authenticated-orcid":false,"given":"Hongyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Yale University School of Public Health , 300 George Street, New Haven, CT 06511 ,","place":["United States"]},{"name":"Department of Genetics, Yale University School of Medicine , 333 Cedar Street, New Haven, CT 06520 ,","place":["United States"]},{"name":"Department of Statistics and Data Science, Yale University , 219 Prospect Street, New Haven, CT 06511 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-3687","authenticated-orcid":false,"given":"Zuoheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Yale University School of Public Health , 300 George Street, New Haven, CT 06511 ,","place":["United States"]},{"name":"Department of Biomedical Informatics & Data Science, Yale University School of Medicine , 101 College Street, New Haven, CT 06510 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"2026091410305860200_ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaz6063","article-title":"In vivo Perturb-Seq reveals neuronal and glial abnormalities associated with autism risk genes","volume":"370","author":"Jin","year":"2020","journal-title":"Science"},{"key":"2026091410305860200_ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-025-02909-7","article-title":"Pertpy: an end-to-end framework for perturbation analysis","volume-title":"Nat Methods","author":"Heumos"},{"key":"2026091410305860200_ref3","doi-asserted-by":"publisher","first-page":"1769","DOI":"10.1038\/s41592-023-02040-5","article-title":"Causal identification of single-cell experimental perturbation effects with CINEMA-OT","volume":"20","author":"Dong","year":"2023","journal-title":"Nat Methods"},{"key":"2026091410305860200_ref4","doi-asserted-by":"publisher","first-page":"1853","DOI":"10.1016\/j.cell.2016.11.038","article-title":"Perturb-Seq: dissecting molecular circuits with scalable single-cell RNA profiling of pooled genetic screens","volume":"167","author":"Dixit","year":"2016","journal-title":"Cell"},{"key":"2026091410305860200_ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3444944","article-title":"A survey on causal inference","volume-title":"ACM Trans Knowl Discov Data","author":"Yao","year":"2021"},{"key":"2026091410305860200_ref6","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1006\/clim.2000.4902","article-title":"Response differences between human CD4+ and CD8+ T-cells during CD28 costimulation: implications for immune cell-based therapies and studies related to the expansion of double-positive T-cells during aging","volume":"96","author":"Laux","year":"2000","journal-title":"Clin Immunol"},{"key":"2026091410305860200_ref7","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1038\/s41592-019-0494-8","article-title":"scGen predicts single-cell perturbation responses","volume":"16","author":"Lotfollahi","year":"2019","journal-title":"Nat Methods"},{"key":"2026091410305860200_ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2025.101443","article-title":"scCausalVI disentangles single-cell perturbation responses with causality-aware generative model","volume-title":"Cell Syst","author":"An"},{"key":"2026091410305860200_ref9","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1038\/s41588-021-00778-2","article-title":"Characterizing the molecular regulation of inhibitory immune checkpoints with multimodal single-cell screens","volume":"53","author":"Papalexi","year":"2021","journal-title":"Nat Genet"},{"key":"2026091410305860200_ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.09786","article-title":"Examining pathological bias in a generative adversarial network discriminator: a case study on a StyleGAN3 model","author":"Grissom","year":"2024"},{"key":"2026091410305860200_ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.02726","article-title":"Bias in generative AI","author":"Zhou","year":"2024"},{"key":"2026091410305860200_ref12","doi-asserted-by":"publisher","first-page":"1861","DOI":"10.1038\/s41587-024-02463-1","article-title":"Recovery of biological signals lost in single-cell batch integration with CellANOVA","volume":"43","author":"Zhang","year":"2024","journal-title":"Nat Biotechnol"},{"key":"2026091410305860200_ref13","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41592-021-01336-8","article-title":"Benchmarking atlas-level data integration in single-cell genomics","volume":"19","author":"Luecken","year":"2022","journal-title":"Nat Methods"},{"key":"2026091410305860200_ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.00937","article-title":"Neural discrete representation learning","volume-title":"NeurIPS","author":"Oord","year":"2017"},{"key":"2026091410305860200_ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.00446","article-title":"Generating diverse high-Fidelity images with VQ-VAE-2","volume-title":"NeurIPS","author":"Razavi","year":"2019"},{"key":"2026091410305860200_ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114","article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma","year":"2014"},{"key":"2026091410305860200_ref17","doi-asserted-by":"publisher","first-page":"2024.05.28.596224","DOI":"10.1101\/2024.05.28.596224","article-title":"Inference of heterogeneous effects in single-cell genetic perturbation screens","author":"Fu","year":"2024"},{"key":"2026091410305860200_ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-025-07988-y","article-title":"Partially characterized topology guides reliable anchor-free scRNA-integration","volume-title":"Commun Biol","author":"He"},{"key":"2026091410305860200_ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1611.01144","article-title":"Categorical reparameterization with Gumbel-Softmax","volume-title":"ICLR","author":"Jang","year":"2017"},{"key":"2026091410305860200_ref20","doi-asserted-by":"publisher","first-page":"3942","DOI":"10.1093\/bioinformatics\/btac427","article-title":"ResPAN: a powerful batch correction model for scRNA-seq data through residual adversarial networks","volume":"38","author":"Wang","year":"2022","journal-title":"Bioinformatics"},{"key":"2026091410305860200_ref21","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1038\/s41592-018-0254-1","article-title":"A test metric for assessing single-cell RNA-seq batch correction","volume":"16","author":"Buttner","year":"2019","journal-title":"Nat Methods"},{"key":"2026091410305860200_ref22","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1038\/s41592-019-0619-0","article-title":"Fast, sensitive and accurate integration of single-cell data with harmony","volume":"16","author":"Korsunsky","year":"2019","journal-title":"Nat Methods"},{"key":"2026091410305860200_ref23","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1186\/s13059-021-02280-8","article-title":"iMAP: integration of multiple single-cell datasets by adversarial paired transfer networks","volume":"22","author":"Wang","year":"2021","journal-title":"Genome Biol"},{"key":"2026091410305860200_ref24","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1038\/nbt.4042","article-title":"Multiplexed droplet single-cell RNA-sequencing using natural genetic variation","volume":"36","author":"Kang","year":"2018","journal-title":"Nat Biotechnol"},{"key":"2026091410305860200_ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.03426","article-title":"UMAP: uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018"},{"key":"2026091410305860200_ref26","doi-asserted-by":"publisher","first-page":"912","DOI":"10.1038\/s41467-024-45227-w","article-title":"scDisInFact: disentangled learning for integration and prediction of multi-batch multi-condition single-cell RNA-sequencing data","volume":"15","author":"Zhang","year":"2024","journal-title":"Nat Commun"},{"key":"2026091410305860200_ref27","doi-asserted-by":"publisher","first-page":"e1011880","DOI":"10.1371\/journal.pcbi.1011880","article-title":"A novel batch-effect correction method for scRNA-seq data based on adversarial information factorization","volume":"20","author":"Monnier","year":"2024","journal-title":"PLoS Comput Biol"},{"key":"2026091410305860200_ref28","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1038\/s41467-023-36635-5","article-title":"Batch alignment of single-cell transcriptomics data using deep metric learning","volume":"14","author":"Yu","year":"2023","journal-title":"Nat Commun"},{"key":"2026091410305860200_ref29","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1038\/s42255-022-00531-x","article-title":"Single-cell multi-omics analysis of human pancreatic islets reveals novel cellular states in type 1 diabetes","volume":"4","author":"Fasolino","year":"2022","journal-title":"Nat Metab"},{"key":"2026091410305860200_ref30","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1038\/s41467-024-45295-y","article-title":"Unraveling the epigenetic code: human kidney DNA methylation and chromatin dynamics in renal disease development","volume":"15","author":"Yan","year":"2024","journal-title":"Nat Commun"},{"key":"2026091410305860200_ref31","doi-asserted-by":"publisher","first-page":"2611","DOI":"10.1038\/s41467-019-10500-w","article-title":"Simulating multiple faceted variability in single cell RNA sequencing","volume":"10","author":"Zhang","year":"2019","journal-title":"Nat Commun"},{"key":"2026091410305860200_ref32","doi-asserted-by":"publisher","first-page":"2366","DOI":"10.1038\/s41593-024-01774-5","article-title":"Integrated multimodal cell atlas of Alzheimer's disease","volume":"27","author":"Gabitto","year":"2024","journal-title":"Nat Neurosci"},{"key":"2026091410305860200_ref33","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.neurobiolaging.2016.12.029","article-title":"Mitochondrial genes are altered in blood early in Alzheimer's disease","volume":"53","author":"Lunnon","year":"2017","journal-title":"Neurobiol Aging"},{"key":"2026091410305860200_ref34","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/s13577-018-0205-2","article-title":"Mitochondrial mRNA expression in fibroblasts of down syndrome subjects","volume":"31","author":"Salemi","year":"2018","journal-title":"Hum Cell"},{"key":"2026091410305860200_ref35","doi-asserted-by":"publisher","first-page":"193","DOI":"10.3233\/JAD-170799","article-title":"A selection of important genes and their correlated behavior in Alzheimer's disease","volume":"65","author":"Cruz-Rivera","year":"2018","journal-title":"J Alzheimer's Dis"},{"key":"2026091410305860200_ref36","doi-asserted-by":"publisher","first-page":"5702","DOI":"10.1038\/s41380-021-01068-3","article-title":"Brain cells derived from Alzheimer's disease patients have multiple specific innate abnormalities in energy metabolism","volume":"26","author":"Ryu","year":"2021","journal-title":"Mol Psychiatry"},{"key":"2026091410305860200_ref37","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1007\/s10571-009-9398-y","article-title":"Amyloid-beta leads to impaired cellular respiration, energy production and mitochondrial electron chain complex activities in human neuroblastoma cells","volume":"29","author":"Rhein","year":"2009","journal-title":"Cell Mol Neurobiol"},{"key":"2026091410305860200_ref38","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s13024-024-00788-8","article-title":"SIRT2 and ALDH1A1 as critical enzymes for astrocytic GABA production in Alzheimer's disease","volume":"20","author":"Bhalla","year":"2025","journal-title":"Mol Neurodegener"},{"key":"2026091410305860200_ref39","doi-asserted-by":"publisher","first-page":"14954","DOI":"10.1038\/s41598-024-65010-7","article-title":"Changes in expression of VGF, SPECC1L, HLA-DRA and RANBP3L act with APOE E4 to alter risk for late onset Alzheimer's disease","volume":"14","author":"Branciamore","year":"2024","journal-title":"Sci Rep"},{"key":"2026091410305860200_ref40","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1016\/j.neurobiolaging.2019.06.008","article-title":"Association of PPP2R1A with Alzheimer's disease and specific cognitive domains","volume":"81","author":"Miron","year":"2019","journal-title":"Neurobiol Aging"},{"key":"2026091410305860200_ref41","doi-asserted-by":"publisher","first-page":"7611","DOI":"10.1073\/pnas.86.19.7611","article-title":"Brain interleukin 1 and S-100 immunoreactivity are elevated in down syndrome and Alzheimer disease","volume":"86","author":"Griffin","year":"1989","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026091410305860200_ref42","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1002\/glia.24624","article-title":"Endogenous histidine peptides are physiological antioxidants that prevent oligodendrocyte cell death and myelin loss in vivo","volume":"73","author":"Sajrawi","year":"2025","journal-title":"Glia"},{"key":"2026091410305860200_ref43","doi-asserted-by":"publisher","first-page":"1422","DOI":"10.2353\/ajpath.2010.100087","article-title":"Early oligodendrocyte\/myelin pathology in Alzheimer's disease mice constitutes a novel therapeutic target","volume":"177","author":"Desai","year":"2010","journal-title":"Am J Pathol"},{"key":"2026091410305860200_ref44","doi-asserted-by":"publisher","first-page":"e105603","DOI":"10.15252\/embj.2020105603","article-title":"PIP2 depletion and altered endocytosis caused by expression of Alzheimer's disease-protective variant PLCgamma2 R522","volume":"40","author":"Maguire","year":"2021","journal-title":"EMBO J"},{"key":"2026091410305860200_ref45","doi-asserted-by":"publisher","first-page":"2087","DOI":"10.1038\/s41593-019-0539-4","article-title":"A single-cell atlas of entorhinal cortex from individuals with Alzheimer's disease reveals cell-type-specific gene expression regulation","volume":"22","author":"Grubman","year":"2019","journal-title":"Nat Neurosci"},{"key":"2026091410305860200_ref46","doi-asserted-by":"publisher","first-page":"849","DOI":"10.17219\/acem\/68846","article-title":"CXCL9, CXCL10, CXCL11, and their receptor (CXCR3) in neuroinflammation and neurodegeneration","volume":"27","author":"Koper","year":"2018","journal-title":"Adv Clin Exp Med"},{"key":"2026091410305860200_ref47","doi-asserted-by":"publisher","DOI":"10.3390\/jpm12050827","article-title":"Altered TIMP-3 levels in the cerebrospinal fluid and plasma of patients with Alzheimer's disease","volume":"12","author":"Park","year":"2022","journal-title":"J Pers Med"},{"key":"2026091410305860200_ref48","doi-asserted-by":"publisher","first-page":"e59554","DOI":"10.1371\/journal.pone.0059554","article-title":"Prion protein is decreased in Alzheimer's brain and inversely correlates with BACE1 activity, amyloid-beta levels and Braak stage","volume":"8","author":"Whitehouse","year":"2013","journal-title":"PLoS One"},{"key":"2026091410305860200_ref49","doi-asserted-by":"publisher","first-page":"10895","DOI":"10.1523\/JNEUROSCI.3135-07.2007","article-title":"The metalloprotease inhibitor TIMP-3 regulates amyloid precursor protein and apolipoprotein E receptor proteolysis","volume":"27","author":"Hoe","year":"2007","journal-title":"J Neurosci"},{"key":"2026091410305860200_ref50","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1093\/brain\/awv056","article-title":"HS3ST2 expression is critical for the abnormal phosphorylation of tau in Alzheimer's disease-related tau pathology","volume":"138","author":"Sepulveda-Diaz","year":"2015","journal-title":"Brain"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag485\/71074815\/bbag485.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag485\/71074815\/bbag485.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T14:31:11Z","timestamp":1789396271000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag485\/8793688"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,1]]},"references-count":50,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag485","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,9,1]]},"article-number":"bbag485"}}