{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T10:20:02Z","timestamp":1783074002783,"version":"3.54.6"},"posted":{"date-parts":[[2025,11,19]]},"group-title":"Genomics","reference-count":51,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T00:00:00Z","timestamp":1763510400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"crossref","award":["R35GM162089"],"award-info":[{"award-number":["R35GM162089"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"crossref"}]},{"name":"University of Washington's Alzheimer's Disease Research Center","award":["Development Project"],"award-info":[{"award-number":["Development Project"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,6,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Cellular morphological transitions are observed across many diseases, yet their functional role remains unclear because few technologies profile form and function in the same cell. Linking single-cell morphology to transcriptomics is difficult: the two modalities share no feature correspondence and are typically measured in different cells.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>We present GeoAdvAE, a geometry-aware adversarial autoencoder for diagonal (unpaired) integration of single-cell morphology and single-cell RNA sequencing. GeoAdvAE couples modality-specific variational autoencoders with a Gromov-Wasserstein regularizer and an adversarial discriminator to embed unpaired morphologies and transcriptomes into a shared latent space that preserves both reconstruction fidelity and cross-modal geometry.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>\n                    Using patch-seq neurons with joint morphology-RNA measurements as ground truth, GeoAdvAE attains the best cross-modal cell-type matching accuracy among diagonal integration methods, outperforming optimal-transport, latent-alignment, and adversarial baselines. Applied to 98 CAJAL-quantified microglial morphologies and 31,948 single-cell transcriptomes from the 5xFAD Alzheimer\u2019s disease model, GeoAdvAE recovers a one-dimensional axis that aligns the two modalities. Integrated-gradient attribution highlights transcriptomic shifts (DNA repair in ramified microglia; cell killing in amoeboid microglia), nominates gene markers (\n                    <jats:italic>Ms4a6b<\/jats:italic>\n                    ;\n                    <jats:italic>Ftl1<\/jats:italic>\n                    \/\n                    <jats:italic>Fth1<\/jats:italic>\n                    ), and reveals disease-associated microglia signatures that are decoupled from morphology.\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>\n                    GeoAd-vAE provides a scalable and interpretable approach to connecting cellular \u201cform\u201d and \u201cfunction\u201d when joint profiling of morphology and transcriptomics is impractical. Our method is publicly available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/turbodu222\/GeoAdVAE\">https:\/\/github.com\/turbodu222\/GeoAdVAE<\/jats:ext-link>\n                    .\n                  <\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2025.11.19.689368","type":"posted-content","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T05:45:23Z","timestamp":1763617523000},"source":"Crossref","is-referenced-by-count":1,"title":["Integrating morphology and gene expression of neural cells in unpaired single-cell data using GeoAdvAE"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2323-6448","authenticated-orcid":false,"given":"Jinqiu Turbo","family":"Du","sequence":"first","affiliation":[{"name":"Department of Biostatistics, University of Washington, Seattle WA 98195, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7093-8681","authenticated-orcid":false,"given":"Tom","family":"Chartrand","sequence":"additional","affiliation":[{"name":"Allen Institute, Seattle WA 98109, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suman","family":"Jayadev","sequence":"additional","affiliation":[{"name":"Department of Neurology, University of Washington, Seattle WA 98107, USA"},{"name":"Department of Medicine, Division of Medical Genetics, University of Washington, Seattle WA 98195, USA"},{"name":"Institute for Stem Cell and Regenerative Medicine, University of Washington, Seattle WA 98195, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katherine E.","family":"Prater","sequence":"additional","affiliation":[{"name":"Department of Neurology, University of Washington, Seattle WA 98107, USA"},{"name":"Institute for Stem Cell and Regenerative Medicine, University of Washington, Seattle WA 98195, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1236-9847","authenticated-orcid":false,"given":"Kevin Z.","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of Washington, Seattle WA 98195, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026070302400732000_2025.11.19.689368v3.1","first-page":"1357","article-title":"Supervised principal component analysis: Visualization, classification and regression on subspaces and submanifolds","volume":"7","year":"2011","journal-title":"Pattern Recognition 44"},{"key":"2026070302400732000_2025.11.19.689368v3.2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa443"},{"key":"2026070302400732000_2025.11.19.689368v3.3","first-page":"eadf0805","article-title":"Morphoelectric and transcriptomic divergence of the layer 1 interneuron repertoire in human versus mouse neocortex","volume":"6667","year":"2023","journal-title":"Science 382"},{"key":"2026070302400732000_2025.11.19.689368v3.4","article-title":"What makes for good morphology representations for spatial omics?","year":"2024","journal-title":"arXiv preprint"},{"key":"2026070302400732000_2025.11.19.689368v3.5","first-page":"1096","article-title":"Integration of spatial and single-cell data across modalities with weakly linked features","volume":"7","year":"2024","journal-title":"Nature Biotechnology 42"},{"key":"2026070302400732000_2025.11.19.689368v3.6","first-page":"1379","article-title":"A tool for mapping microglial morphology, mor-phOMICs, reveals brain-region and sex-dependent phenotypes","volume":"10","year":"2022","journal-title":"Nature Neuroscience 25"},{"key":"2026070302400732000_2025.11.19.689368v3.7","doi-asserted-by":"crossref","unstructured":"Daniels, R. H. , Hall, P. S. , and Bokoch, G. M. Membrane targeting of p21-activated kinase 1 (PAK1) induces neurite outgrowth from PC12 cells. The EMBO journal (1998).","DOI":"10.1093\/emboj\/17.3.754"},{"key":"2026070302400732000_2025.11.19.689368v3.8","first-page":"33","article-title":"The concept of resilience to Alzheimer\u2019s disease: Current definitions and cellular and molecular mechanisms","volume":"1","year":"2024","journal-title":"Molecular neurodegeneration 19"},{"key":"2026070302400732000_2025.11.19.689368v3.9","first-page":"3","article-title":"SCOT: Single-cell multi-omics alignment with optimal transport","volume":"1","year":"2022","journal-title":"Journal of Computational Biology 29"},{"key":"2026070302400732000_2025.11.19.689368v3.10","doi-asserted-by":"crossref","first-page":"790","DOI":"10.3389\/fimmu.2019.00790","article-title":"Phagocytosis in the brain: Homeostasis and disease","volume":"10","year":"2019","journal-title":"Frontiers in Immunology"},{"key":"2026070302400732000_2025.11.19.689368v3.11","doi-asserted-by":"crossref","unstructured":"Gomez-Arboledas, A. , Acharya, M. M. , and Tenner, A. J. The role of complement in synaptic pruning and neurodegeneration. ImmunoTargets and Therapy (2021), 373\u2013386.","DOI":"10.2147\/ITT.S305420"},{"key":"2026070302400732000_2025.11.19.689368v3.12","first-page":"935","article-title":"Integrated morphoelectric and transcriptomic classification of cortical GABAergic cells","volume":"4","year":"2020","journal-title":"Cell 183"},{"key":"2026070302400732000_2025.11.19.689368v3.13","first-page":"3672","article-title":"CAJAL enables analysis and integration of single-cell morphological data using metric geometry","volume":"1","year":"2023","journal-title":"Nature Communications 14"},{"key":"2026070302400732000_2025.11.19.689368v3.14","first-page":"221","article-title":"Quantifying microglial morphology: An insight into function","volume":"3","year":"2024","journal-title":"Clinical and Experimental Immunology 216"},{"key":"2026070302400732000_2025.11.19.689368v3.15","first-page":"105","article-title":"Ferritin is a component of the neuritic (senile) plaque in Alzheimer dementia","volume":"2","year":"1990","journal-title":"Acta Neuropathologica 81"},{"key":"2026070302400732000_2025.11.19.689368v3.16","doi-asserted-by":"crossref","first-page":"815347","DOI":"10.3389\/fnagi.2022.815347","article-title":"Microglia polarization from M1 to M2 in neurodegenerative diseases","volume":"14","year":"2022","journal-title":"Frontiers in Aging Neuroscience"},{"key":"2026070302400732000_2025.11.19.689368v3.17","first-page":"459","article-title":"Microglia in Alzheimer\u2019s disease","volume":"2","year":"2018","journal-title":"Journal of Cell Biology 217"},{"key":"2026070302400732000_2025.11.19.689368v3.18","first-page":"712","article-title":"Complement and microglia mediate early synapse loss in Alzheimer mouse models","volume":"6286","year":"2016","journal-title":"Science 352"},{"key":"2026070302400732000_2025.11.19.689368v3.19","first-page":"5878","article-title":"Bridging cell morphological behaviors and molecular dynamics in multi-modal spatial omics with MorphLink","volume":"1","year":"2025","journal-title":"Nature Communications 16"},{"key":"2026070302400732000_2025.11.19.689368v3.20","first-page":"94","article-title":"MS4A6A\/Ms4a6d deficiency disrupts neuroprotective microglia functions and promotes inflammation in Alzheimer\u2019s disease model","volume":"1","year":"2025","journal-title":"Molecular Neurodegeneration 20"},{"key":"2026070302400732000_2025.11.19.689368v3.21","first-page":"27","article-title":"Iron loading is a prominent feature of activated microglia in Alzheimer\u2019s disease patients","volume":"1","year":"2021","journal-title":"Acta neuropathologica communications 9"},{"key":"2026070302400732000_2025.11.19.689368v3.22","doi-asserted-by":"crossref","unstructured":"Lee, D. , Vicari, J. M. , Porras, C. , Spencer, C. , Pjanic, M. , Wang, X. , Kinrot, S. , Weiler, P. , Kosoy, R. , Bendl, J. , et al. Plasticity of human microglia and brain perivascular macrophages in aging and Alzheimer\u2019s disease. medRxiv (2024), 2023\u201310.","DOI":"10.1101\/2023.10.25.23297558"},{"key":"2026070302400732000_2025.11.19.689368v3.23","doi-asserted-by":"crossref","unstructured":"Lee, H. , and Welch, J. D. MorphNet predicts cell morphology from single-cell gene expression. bioRxiv (2022), 2022\u201310.","DOI":"10.1101\/2022.10.21.513201"},{"key":"2026070302400732000_2025.11.19.689368v3.24","first-page":"6","article-title":"Cell-death pathways and tau-associated neuronal vulnerability in Alzheimer\u2019s disease","volume":"44","year":"2025","journal-title":"Cell Reports"},{"key":"2026070302400732000_2025.11.19.689368v3.25","first-page":"e2303647120","article-title":"Quantifying common and distinct information in single-cell multimodal data with Tilted Canonical Correlation Analysis","volume":"32","year":"2023","journal-title":"Proceedings of the National Academy of Sciences 120"},{"key":"2026070302400732000_2025.11.19.689368v3.26","first-page":"703","article-title":"scJoint integrates atlas-scale single-cell RNA-seq and ATAC-seq data with transfer learning","volume":"5","year":"2022","journal-title":"Nature Biotechnology 40"},{"key":"2026070302400732000_2025.11.19.689368v3.27","first-page":"10","article-title":"Jointly embedding multiple single-cell omics measurements","volume":"143","year":"2019","journal-title":"In Algorithms in Bioinformatics"},{"key":"2026070302400732000_2025.11.19.689368v3.28","first-page":"173","article-title":"Rho gtpases in neuronal morphogenesis","volume":"3","year":"2000","journal-title":"Nature Reviews Neuroscience 1"},{"key":"2026070302400732000_2025.11.19.689368v3.29","unstructured":"Qian, X. , Coleman, K. , Jiang, S. , Kriz, A. J. , Marciano, J. H. , Luo, C. , Cai, C. , Manam, M. D. , Caglayan, E. , Lai, A. , et al. Spatial transcriptomics reveals human cortical layer and area specification. Nature (2025), 1\u201311."},{"key":"2026070302400732000_2025.11.19.689368v3.30","doi-asserted-by":"crossref","first-page":"1211188","DOI":"10.3389\/fninf.2023.1211188","article-title":"Microglial morphometric analysis: So many options, so little consistency","volume":"17","year":"2023","journal-title":"Frontiers in Neuroinformatics"},{"key":"2026070302400732000_2025.11.19.689368v3.31","doi-asserted-by":"crossref","unstructured":"Rosner, D. , Sun, J. , Yee, A. , Wagh, C. , Rychkova, A. , Cacace, R. , Buonfiglioli, A. , Alwahagri, M. , Kong, P. , Roell, M. , et al. The Alzheimer\u2019s disease risk genes MS4A4A and MS4A6A cooperate to negatively regulate Trem2 and microglia states. bioRxiv (2024), 2024\u201311.","DOI":"10.1101\/2024.11.23.625001"},{"key":"2026070302400732000_2025.11.19.689368v3.32","first-page":"144","article-title":"Phenotypic variation of transcriptomic cell types in mouse motor cortex","volume":"7879","year":"2021","journal-title":"Nature 598"},{"key":"2026070302400732000_2025.11.19.689368v3.33","doi-asserted-by":"crossref","first-page":"194","DOI":"10.3389\/fnagi.2017.00194","article-title":"Aging microglia\u2014phenotypes, functions and implications for age-related neurodegenerative diseases","volume":"9","year":"2017","journal-title":"Frontiers in Aging Neuroscience"},{"key":"2026070302400732000_2025.11.19.689368v3.34","first-page":"13","article-title":"Alzheimer\u2019s patient microglia exhibit enhanced aging and unique transcriptional activation","volume":"31","year":"2020","journal-title":"Cell Reports"},{"key":"2026070302400732000_2025.11.19.689368v3.35","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa843"},{"key":"2026070302400732000_2025.11.19.689368v3.36","first-page":"477","article-title":"Slingshot: Cell lineage and pseudotime inference for single-cell transcriptomics","volume":"1","year":"2018","journal-title":"BMC Genomics 19"},{"key":"2026070302400732000_2025.11.19.689368v3.37","first-page":"15545","article-title":"Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles","volume":"43","year":"2005","journal-title":"Proceedings of the National Academy of Sciences 102"},{"key":"2026070302400732000_2025.11.19.689368v3.38","unstructured":"Sundararajan, M. , Taly, A. , and Yan, Q. Axiomatic attribution for deep networks. In International conference on machine learning (2017), PMLR, pp. 3319\u20133328."},{"key":"2026070302400732000_2025.11.19.689368v3.39","doi-asserted-by":"crossref","first-page":"997786","DOI":"10.3389\/fimmu.2022.997786","article-title":"Microglia morphophysiological diversity and its implications for the CNS","volume":"13","year":"2022","journal-title":"Frontiers in Immunology"},{"key":"2026070302400732000_2025.11.19.689368v3.40","first-page":"e20200785","article-title":"Anti-human TREM2 induces microglia proliferation and reduces pathology in an Alzheimer\u2019s disease model","volume":"9","year":"2020","journal-title":"Journal of Experimental Medicine 217"},{"key":"2026070302400732000_2025.11.19.689368v3.41","first-page":"8210","article-title":"Prediction of cellular morphology changes under perturbations with a transcriptome-guided diffusion model","volume":"1","year":"2025","journal-title":"Nature Communications 16"},{"key":"2026070302400732000_2025.11.19.689368v3.42","first-page":"756","article-title":"EphA4-dependent axon guidance is mediated by the RacGAP \u03b12-chimaerin","volume":"5","year":"2007","journal-title":"Neuron 55"},{"key":"2026070302400732000_2025.11.19.689368v3.43","first-page":"1575","article-title":"Movers and shakers: Microglial dynamics and modulation of neural networks","volume":"7","year":"2023","journal-title":"Glia 71"},{"key":"2026070302400732000_2025.11.19.689368v3.44","first-page":"258","article-title":"The semantics of microglia activation: Neuroin-flammation, homeostasis, and stress","volume":"1","year":"2021","journal-title":"Journal of Neuroinflammation 18"},{"key":"2026070302400732000_2025.11.19.689368v3.45","first-page":"33","article-title":"sciCAN: Single-cell chromatin accessibility and gene expression data integration via cycle-consistent adversarial network","volume":"1","year":"2022","journal-title":"NPJ Systems Biology and Applications 8"},{"key":"2026070302400732000_2025.11.19.689368v3.46","first-page":"31","article-title":"Multi-domain translation between single-cell imaging and sequencing data using autoencoders","volume":"1","year":"2021","journal-title":"Nature Communications 12"},{"key":"2026070302400732000_2025.11.19.689368v3.47","first-page":"211","article-title":"Recent advances in Alzheimer\u2019s disease: Mechanisms, clinical trials and new drug development strategies","volume":"1","year":"2024","journal-title":"Signal transduction and targeted therapy 9"},{"key":"2026070302400732000_2025.11.19.689368v3.48","first-page":"729","article-title":"Intrinsic DNA damage repair deficiency results in progressive microglia loss and replacement","volume":"3","year":"2021","journal-title":"Glia 69"},{"key":"2026070302400732000_2025.11.19.689368v3.49","first-page":"7480","article-title":"Graph-based autoencoder integrates spatial transcriptomics with chromatin images and identifies joint biomarkers for Alzheimer\u2019s disease","volume":"1","year":"2022","journal-title":"Nature Communications 13"},{"key":"2026070302400732000_2025.11.19.689368v3.50","first-page":"139","article-title":"scDART: Integrating unmatched scRNA-seq and scATAC-seq data and learning cross-modality relationship simultaneously","volume":"1","year":"2022","journal-title":"Genome Biology 23"},{"key":"2026070302400732000_2025.11.19.689368v3.51","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y. , Park, T. , Isola, P. , and Efros, A. A. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision (2017), pp. 2223\u20132232.","DOI":"10.1109\/ICCV.2017.244"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.11.19.689368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T09:43:45Z","timestamp":1783071825000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.11.19.689368"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1101\/2025.11.19.689368","relation":{},"subject":[],"published":{"date-parts":[[2025,11,19]]},"subtype":"preprint"}}