{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T05:28:58Z","timestamp":1786771738185,"version":"build-2736575974"},"posted":{"date-parts":[[2026,8,12]]},"group-title":"Bioinformatics","reference-count":64,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,8,12]]},"abstract":"<jats:title>SUMMARY<\/jats:title>\n                <jats:p>Single-cell RNA technologies enable the routine acquisition of transcriptomic atlases. However, these molecular profiles are influenced by overlapping sources of variation. Since these covariates confound comparisons, data integration is the first step in most analyses.<\/jats:p>\n                <jats:p>Three challenges remain: correcting strong batch effects, scaling to millions of cells, and modeling how covariates influence gene expression. To address these challenges, we developed PIANO: Probabilistic Inference Autoencoder Networks for multi-Omics, a deep learning framework whose central feature is a generative model of gene expression data. Additionally, PIANO achieves robust integrations and trains 10x faster than previous methods.<\/jats:p>\n                <jats:p>PIANO accurately integrates single-cell data across species and across single-cell and spatial transcriptomics modalities. As practical applications, PIANO models spatially-resolved gene expression during Alzheimer\u2019s disease progression in human brains and integrates over 100 million cancer cells to model drug perturbations. In summary, PIANO\u2019s integration and generative modeling capabilities will empower novel insights for countless future studies.<\/jats:p>","DOI":"10.64898\/2026.08.06.743394","type":"posted-content","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:50:30Z","timestamp":1786582230000},"source":"Crossref","is-referenced-by-count":0,"title":["PIANO: Probabilistic Inference Autoencoder Networks for multi-Omics enables robust generative modeling of gene expression and scales single-cell integration to 100 million cells"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3073-7911","authenticated-orcid":false,"given":"Ning","family":"Wang","sequence":"first","affiliation":[{"name":"Princeton Neuroscience Institute (PNI)"},{"name":"Allen Institute, Brain Science (AIBS)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4986-1019","authenticated-orcid":false,"given":"Christopher","family":"Cardenas","sequence":"additional","affiliation":[{"name":"Princeton Neuroscience Institute (PNI)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victor E.","family":"Nieto-Caballero","sequence":"additional","affiliation":[{"name":"Princeton Neuroscience Institute (PNI)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Turner","sequence":"additional","affiliation":[{"name":"Princeton Neuroscience Institute (PNI)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hannah","family":"Feinberg","sequence":"additional","affiliation":[{"name":"Princeton Neuroscience Institute (PNI)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Yuan","sequence":"additional","affiliation":[{"name":"Allen Institute, Brain Science (AIBS)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathaniel","family":"Scott","sequence":"additional","affiliation":[{"name":"Princeton Neuroscience Institute (PNI)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5220-0341","authenticated-orcid":false,"given":"Michael","family":"DeBerardine","sequence":"additional","affiliation":[{"name":"Princeton Neuroscience Institute (PNI)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8442-5999","authenticated-orcid":false,"given":"Shu","family":"Dan","sequence":"additional","affiliation":[{"name":"Princeton Neuroscience Institute (PNI)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2019-0505","authenticated-orcid":false,"given":"Lakme","family":"Caceres","sequence":"additional","affiliation":[{"name":"Princeton Neuroscience Institute (PNI)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jessica","family":"Schembri","sequence":"additional","affiliation":[{"name":"Princeton Neuroscience Institute (PNI)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9361-5607","authenticated-orcid":false,"given":"Zizhen","family":"Yao","sequence":"additional","affiliation":[{"name":"Allen Institute, Brain Science (AIBS)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6146-0404","authenticated-orcid":false,"given":"Changkyu","family":"Lee","sequence":"additional","affiliation":[{"name":"Allen Institute, Brain Science (AIBS)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3638-8831","authenticated-orcid":false,"given":"Jonathan W.","family":"Pillow","sequence":"additional","affiliation":[{"name":"Princeton Neuroscience Institute (PNI)"},{"name":"Princeton Center for Statistics and Machine Learning (CSML)"},{"name":"Princeton Program in Applied and Computational Mathematics (PACM)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1400-6820","authenticated-orcid":false,"given":"Fenna M.","family":"Krienen","sequence":"additional","affiliation":[{"name":"Princeton Neuroscience Institute (PNI)"},{"name":"Princeton Program in Quantitative and Computational Biology (QCB)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026081422101803000_2026.08.06.743394v1.1","doi-asserted-by":"publisher","DOI":"10.1126\/science.add7046"},{"key":"2026081422101803000_2026.08.06.743394v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06812-z"},{"key":"2026081422101803000_2026.08.06.743394v1.3","unstructured":"The Human Cell Atlas: towards a first draft atlas (2024). Nature. https:\/\/www.nature.com\/collections\/jccbbdahji."},{"key":"2026081422101803000_2026.08.06.743394v1.4","unstructured":"Brain Initiative Cell Census Network 2.0 (2023). Nature. https:\/\/www.nature.com\/collections\/fgihbeccbd."},{"key":"2026081422101803000_2026.08.06.743394v1.5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06818-7"},{"key":"2026081422101803000_2026.08.06.743394v1.6","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adk3986"},{"key":"2026081422101803000_2026.08.06.743394v1.7","doi-asserted-by":"crossref","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","year":"2019","journal-title":"Nature Methods"},{"key":"2026081422101803000_2026.08.06.743394v1.8","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.4096"},{"key":"2026081422101803000_2026.08.06.743394v1.9","unstructured":"Kingma, D.P. , and Welling, M. (2013). Auto-Encoding Variational Bayes."},{"key":"2026081422101803000_2026.08.06.743394v1.10","unstructured":"Ganin, Y. , and Lempitsky, V. (2014). Unsupervised Domain Adaptation by Backpropagation."},{"key":"2026081422101803000_2026.08.06.743394v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/S41591-019-0468-5"},{"key":"2026081422101803000_2026.08.06.743394v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.stem.2016.05.010"},{"key":"2026081422101803000_2026.08.06.743394v1.13","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1016\/j.cels.2016.09.002","article-title":"A Single-Cell Transcriptome Atlas of the Human Pancreas","volume":"3","year":"2016","journal-title":"Cell Syst"},{"key":"2026081422101803000_2026.08.06.743394v1.14","doi-asserted-by":"publisher","DOI":"10.1101\/gr.212720.116"},{"key":"2026081422101803000_2026.08.06.743394v1.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmet.2016.08.020"},{"key":"2026081422101803000_2026.08.06.743394v1.16","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06311-1"},{"key":"2026081422101803000_2026.08.06.743394v1.17","doi-asserted-by":"publisher","DOI":"10.1172\/jci.insight.124928"},{"key":"2026081422101803000_2026.08.06.743394v1.18","unstructured":"Datasets-Single Cell Gene Expression - Official 10x Genomics Support https:\/\/support.10xgenomics.com\/single-cell-gene-expression\/datasets\/3.0.0\/pbmc_10k_v3."},{"key":"2026081422101803000_2026.08.06.743394v1.19","doi-asserted-by":"publisher","DOI":"10.12688\/f1000research.15809.2"},{"key":"2026081422101803000_2026.08.06.743394v1.20","first-page":"1","article-title":"A Bayesian mixture model for clustering droplet-based single-cell transcriptomic data from population studies","volume":"10","year":"2019","journal-title":"Nature Communications"},{"key":"2026081422101803000_2026.08.06.743394v1.21","doi-asserted-by":"publisher","DOI":"10.1126\/science.aah4573"},{"key":"2026081422101803000_2026.08.06.743394v1.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0590-4"},{"key":"2026081422101803000_2026.08.06.743394v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.3192"},{"key":"2026081422101803000_2026.08.06.743394v1.24","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1038\/s41592-018-0229-2","article-title":"Deep generative modeling for single-cell transcriptomics","volume":"15","year":"2018","journal-title":"Nature Methods"},{"key":"2026081422101803000_2026.08.06.743394v1.25","doi-asserted-by":"publisher","DOI":"10.1101\/2023.11.03.565463"},{"key":"2026081422101803000_2026.08.06.743394v1.26","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-43590-8"},{"key":"2026081422101803000_2026.08.06.743394v1.27","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-021-01336-8"},{"key":"2026081422101803000_2026.08.06.743394v1.28","doi-asserted-by":"publisher","DOI":"10.1101\/2025.02.20.639398"},{"key":"2026081422101803000_2026.08.06.743394v1.29","doi-asserted-by":"publisher","DOI":"10.64898\/2025.12.15.694496"},{"key":"2026081422101803000_2026.08.06.743394v1.30","doi-asserted-by":"publisher","DOI":"10.1101\/2025.11.22.689869"},{"key":"2026081422101803000_2026.08.06.743394v1.31","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-017-1381-1"},{"key":"2026081422101803000_2026.08.06.743394v1.32","doi-asserted-by":"publisher","DOI":"10.1016\/j.gde.2025.102397"},{"key":"2026081422101803000_2026.08.06.743394v1.33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2025.09.011"},{"key":"2026081422101803000_2026.08.06.743394v1.34","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade9516"},{"key":"2026081422101803000_2026.08.06.743394v1.35","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05547-7"},{"key":"2026081422101803000_2026.08.06.743394v1.36","doi-asserted-by":"crossref","first-page":"3017","DOI":"10.1038\/s41467-026-69696-3","article-title":"Multi-species integration, alignment and annotation of single-cell RNA-seq data with CAMEX","volume":"17","year":"2026","journal-title":"Nature Communications"},{"key":"2026081422101803000_2026.08.06.743394v1.37","doi-asserted-by":"crossref","first-page":"102449","DOI":"10.1016\/j.stemcr.2025.102449","article-title":"Single-cell multiomic comparison of mouse and rat spermatogenesis reveals gene regulatory networks conserved for over 20 million years","volume":"20","year":"2025","journal-title":"Stem Cell Reports"},{"key":"2026081422101803000_2026.08.06.743394v1.38","doi-asserted-by":"publisher","DOI":"10.1111\/jcmm.14149"},{"key":"2026081422101803000_2026.08.06.743394v1.39","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa6090"},{"key":"2026081422101803000_2026.08.06.743394v1.40","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06808-9"},{"key":"2026081422101803000_2026.08.06.743394v1.41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2019.05.031"},{"key":"2026081422101803000_2026.08.06.743394v1.42","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-2921860\/v1"},{"key":"2026081422101803000_2026.08.06.743394v1.43","doi-asserted-by":"crossref","unstructured":"Travaglini, K. J. , Gabitto, M. I. , Ding, Y. , Agrawal, A. , Postupna, N. , Mahoney, J. T. , Kaplan, E. S. , Melief, E. J. , Goldy, J. , Chakka, A. B. , Xiao, M. , Bajwa, T. S. , Tj\u00e4rnberg, A. , Ariza, J. , Ding, S.-L. , Gelfand, E. , Kana, O. Z. , Lai, H.-Y. , Long, B. , Rachleff, V. M. , Saldi, G. A. , Schultz, C. P. , Alfiler, L. , Ayala, A. , Barta, S. , Bertagnolli, D. , Cardenas, T. , Casper, T. , Chakrabarty, R. , Clark, M. , Cuevas, N. V. , Cuoco, M. S. , Dalley, R. , Dee, N. , Duncan, L. , Esposito, L. , Ferrer, R. , Fleckenstein, L. E. , Gloe, J. , Guilford, N. , Guzman, J. , Hammond, M. , Hastings, S. , Haynor, D. R. , Hulsey-Vincent, H. , Ho, W. , James, K. , Juneau, Z. , Kalmbach, B. , Kannan, M. , Khedr, M. , Kim, C. , Lee, B. , Martin, N. X. , McCue, R. , McMillen, D. , Milchsack, L. M. , Moramarco, F. , Nguy, B. , Nyhus, J. , Olsen, P. , Oyaizu, S. L. , Oyama, A. , Phillips, E. , Rocha, D. , Ruiz, A. , Senturk, H. , Sunkin, S. M. , Tieu, M. , Torkelson, A. , Tran, A. , Close, J. L. , Crane, P. K. , Ganjam, K. , Gatto, N. M. , Grabowski, T. J. , Jayadev, S. , Larson, E. B. , Latimer, C. S. , Levi, B. P. , Mukherjee, S. , Smith, K. A. , Waters, J. , Miller, J. A. , Hodge, R. D. , Hawrylycz, M. , Keene, C. D. , Lein, E. S. (2026). Multiregional single-cell profiling reveals shared and specialized cellular vulnerability in Alzheimer\u2019s disease. bioRxiv.","DOI":"10.64898\/2026.07.01.734821"},{"key":"2026081422101803000_2026.08.06.743394v1.44","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccr.2014.03.011"},{"key":"2026081422101803000_2026.08.06.743394v1.45","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1038\/s41392-023-01705-z","article-title":"Targeting the RAS\/RAF\/MAPK pathway for cancer therapy: from mechanism to clinical studies","volume":"8","year":"2023","journal-title":"Signal Transduction and Targeted Therapy"},{"key":"2026081422101803000_2026.08.06.743394v1.46","doi-asserted-by":"publisher","DOI":"10.1038\/s41580-020-0255-7"},{"key":"2026081422101803000_2026.08.06.743394v1.47","doi-asserted-by":"crossref","unstructured":"Zhang, J. , Ubas, A. A. , de Borja, R. , Svensson, V. , Thomas, N. , Thakar, N. , Lai, I. , Winters, A. , Khan, U. , Jones, M. G. , Thompson, J. D. , Tran, V. , Pangallo, J. , Papalexi, E. , Sapre, A. , Nguyen, H. , Sanderson, O. , Nigos, M. , Kaplan, O. , Schroeder, S. , Hariadi, B. , Marrujo, S. , Salvino, C. C. A. , Olivares, G. G. , Koehler, R. , Geiss, G. , Rosenberg, A. , Roco, C. , Merico, D. , Alidoust, N. , Goodarzi, H. , Yu, J. (2025). Tahoe-100M: A Giga-Scale Single-Cell Perturbation Atlas for Context-Dependent Gene Function and Cellular Modeling. bioRxiv.","DOI":"10.1101\/2025.02.20.639398"},{"key":"2026081422101803000_2026.08.06.743394v1.48","doi-asserted-by":"publisher","DOI":"10.1021\/ac2000169"},{"key":"2026081422101803000_2026.08.06.743394v1.49","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaf394"},{"key":"2026081422101803000_2026.08.06.743394v1.50","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac907"},{"key":"2026081422101803000_2026.08.06.743394v1.51","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-022-02601-5"},{"key":"2026081422101803000_2026.08.06.743394v1.52","doi-asserted-by":"publisher","DOI":"10.15252\/msb.20209620"},{"key":"2026081422101803000_2026.08.06.743394v1.53","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-014-0550-8"},{"key":"2026081422101803000_2026.08.06.743394v1.54","doi-asserted-by":"crossref","first-page":"e1012881","DOI":"10.1371\/journal.pcbi.1012881","article-title":"SpaMask: Dual masking graph autoencoder with contrastive learning for spatial transcriptomics","volume":"21","year":"2025","journal-title":"PLoS Comput Biol"},{"key":"2026081422101803000_2026.08.06.743394v1.55","doi-asserted-by":"crossref","first-page":"1393","DOI":"10.1038\/s42003-025-08810-5","article-title":"SpaCross deciphers spatial structures and corrects batch effects in multi-slice spatially resolved transcriptomics","volume":"8","year":"2025","journal-title":"Commun Biol"},{"key":"2026081422101803000_2026.08.06.743394v1.56","doi-asserted-by":"crossref","first-page":"e09090","DOI":"10.1002\/advs.202509090","article-title":"SpaBatch: Deep Learning-Based Cross-Slice Integration and 3D Spatial Domain Identification in Spatial Transcriptomics","volume":"12","year":"2025","journal-title":"Adv Sci (Weinh)"},{"key":"2026081422101803000_2026.08.06.743394v1.57","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1038\/s43588-023-00543-x","volume":"3","author":"STAligner enables the integration and alignment of multiple spatial transcriptomics datasets","year":"2023","journal-title":"Nat Comput Sci"},{"key":"2026081422101803000_2026.08.06.743394v1.58","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-019-0379-5"},{"key":"2026081422101803000_2026.08.06.743394v1.59","unstructured":"Pillow, J. W. , Scott, J. (2012). Fully Bayesian inference for neural models with negative-binomial spiking. In (Advances in Neural Information Processing Systems)."},{"key":"2026081422101803000_2026.08.06.743394v1.60","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"2026081422101803000_2026.08.06.743394v1.61","unstructured":"Higgins, I. , Matthey, L. , Pal, A. , Burgess, C. , Glorot, X. , Botvinick, M. , Mohamed. S. , Lerchner, A. (2017). beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. In (International Conference on Learning Representations)."},{"key":"2026081422101803000_2026.08.06.743394v1.62","doi-asserted-by":"crossref","unstructured":"Fu, H. , Li, C. , Liu, X. , Gao, J. , Celikyilmaz, A. , and Carin, L. (2019). Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing.","DOI":"10.18653\/v1\/N19-1021"},{"key":"2026081422101803000_2026.08.06.743394v1.63","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1071"},{"key":"2026081422101803000_2026.08.06.743394v1.64","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1010"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.08.06.743394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T05:10:25Z","timestamp":1786770625000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.08.06.743394"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,12]]},"references-count":64,"URL":"https:\/\/doi.org\/10.64898\/2026.08.06.743394","relation":{},"subject":[],"published":{"date-parts":[[2026,8,12]]},"subtype":"preprint"}}