{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T17:54:54Z","timestamp":1791222894427,"version":"4.1.0"},"posted":{"date-parts":[[2026,9,30]]},"group-title":"Bioinformatics","reference-count":43,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"id":[{"id":"https:\/\/ror.org\/001d55x84","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  Spatial transcriptomics reveals cellular organization within intact tissues, whereas dissociated single-cell RNA sequencing provides broad transcriptomic coverage but loses information about cellular proximity and neighborhood structure. Here, we developed\n                  <jats:bold>ProxiNet<\/jats:bold>\n                  , a spatially supervised framework that learns transcriptomic signatures of pairwise cellular proximity from spatial reference datasets and transfers these relationships to dissociated single-cell transcriptomes. ProxiNet predicted cellular proximity across brain regions and spatial technologies, including zero-shot cross-technology transfer, and gradient-based attribution identified genes and broader transcriptional programs associated with proximity predictions. In spatial datasets with known coordinates, ProxiNet-derived cellular neighborhoods recovered reproducible tissue organization and anatomical structure, providing independent spatial validation of the inferred proximity relationships. Applying the spatially calibrated model to dissociated scRNA-seq revealed heterogeneous cellular neighborhoods with distinct cell-type compositions and candidate communication programs. In an Alzheimer\u2019s disease dataset, ProxiNet further identified age-associated remodeling of inferred neighborhoods, including an AD-associated neighborhood at 8 months characterized by distinct astrocyte and neuronal transcriptional states and candidate intercellular communication programs. Together, these results establish pairwise cellular proximity as an interpretable and transferable representation for extending spatially learned tissue organization to dissociated single-cell transcriptomes.\n                <\/jats:p>","DOI":"10.64898\/2026.09.25.754372","type":"posted-content","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T22:05:16Z","timestamp":1790805916000},"source":"Crossref","is-referenced-by-count":0,"title":["ProxiNet transfers spatially learned cellular proximity to dissociated single-cell transcriptomes"],"prefix":"10.64898","author":[{"given":"Yuxiang","family":"Zhan","sequence":"first","affiliation":[{"name":"Whitehead Institute for Biomedical Research, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binwei","family":"Yan","sequence":"additional","affiliation":[{"name":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Health Informatics, King\u2019s College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manolis","family":"Kellis","sequence":"additional","affiliation":[{"name":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"},{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Sun","sequence":"additional","affiliation":[{"name":"Whitehead Institute for Biomedical Research, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026100510200924000_2026.09.25.754372v1.1","doi-asserted-by":"crossref","unstructured":"Nesari, A. M. , MotieGhader, H. & Ghorbian, AS . Advances and challenges in single-cell RNA sequencing data analysis: a comprehensive review. Brief Bioinform 27, (2026).","DOI":"10.1093\/bib\/bbaf723"},{"key":"2026100510200924000_2026.09.25.754372v1.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.07.005"},{"key":"2026100510200924000_2026.09.25.754372v1.3","doi-asserted-by":"publisher","DOI":"10.1038\/s41576-021-00370-8"},{"key":"2026100510200924000_2026.09.25.754372v1.4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1773-3"},{"key":"2026100510200924000_2026.09.25.754372v1.5","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-021-01264-7"},{"key":"2026100510200924000_2026.09.25.754372v1.6","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-39895-3"},{"key":"2026100510200924000_2026.09.25.754372v1.7","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-023-01697-9"},{"key":"2026100510200924000_2026.09.25.754372v1.8","doi-asserted-by":"crossref","first-page":"101022","DOI":"10.1016\/j.patter.2024.101022","article-title":"CellContrast: Reconstructing spatial relationships in single-cell RNA sequencing data via deep contrastive learning","volume":"5","year":"2024","journal-title":"Patterns (N Y)"},{"key":"2026100510200924000_2026.09.25.754372v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-024-02193-4"},{"key":"2026100510200924000_2026.09.25.754372v1.10","doi-asserted-by":"crossref","first-page":"2525","DOI":"10.1038\/s41592-025-02814-z","article-title":"Nicheformer: a foundation model for single-cell and spatial omics","volume":"22","year":"2025","journal-title":"Nat Methods"},{"key":"2026100510200924000_2026.09.25.754372v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06808-9"},{"key":"2026100510200924000_2026.09.25.754372v1.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06569-5"},{"key":"2026100510200924000_2026.09.25.754372v1.13","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06818-7"},{"key":"2026100510200924000_2026.09.25.754372v1.14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"2026100510200924000_2026.09.25.754372v1.15","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"2026100510200924000_2026.09.25.754372v1.16","first-page":"273","volume":"20","year":"1995","journal-title":"Support-vector networks. Machine Learning"},{"key":"2026100510200924000_2026.09.25.754372v1.17","unstructured":"Kingma, D. P. & Welling, M. Auto-Encoding Variational Bayes. (2013)."},{"key":"2026100510200924000_2026.09.25.754372v1.18","unstructured":"Website. https:\/\/www.biorxiv.org\/content\/10.1101\/2025.02.13.638045v2."},{"key":"2026100510200924000_2026.09.25.754372v1.19","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736947"},{"key":"2026100510200924000_2026.09.25.754372v1.20","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30755-0"},{"key":"2026100510200924000_2026.09.25.754372v1.21","doi-asserted-by":"publisher","DOI":"10.1038\/s41596-020-0292-x"},{"key":"2026100510200924000_2026.09.25.754372v1.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06812-z"},{"key":"2026100510200924000_2026.09.25.754372v1.23","first-page":"26248","volume":"15","year":"2025","journal-title":"Analysis of changes in intercellular communications in Alzheimer\u2019s disease reveals conserved Sci Rep"},{"key":"2026100510200924000_2026.09.25.754372v1.24","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07606-7"},{"key":"2026100510200924000_2026.09.25.754372v1.25","doi-asserted-by":"crossref","first-page":"101175","DOI":"10.1016\/j.xcrm.2023.101175","article-title":"Human astrocytes and microglia show augmented ingestion of synapses in Alzheimer\u2019s disease via MFG-E8","volume":"4","year":"2023","journal-title":"Cell Rep Med"},{"key":"2026100510200924000_2026.09.25.754372v1.26","doi-asserted-by":"publisher","DOI":"10.3389\/fncel.2022.899251"},{"key":"2026100510200924000_2026.09.25.754372v1.27","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-020-0624-8"},{"key":"2026100510200924000_2026.09.25.754372v1.28","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1195-2"},{"key":"2026100510200924000_2026.09.25.754372v1.29","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-020-00764-7"},{"key":"2026100510200924000_2026.09.25.754372v1.30","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq466"},{"key":"2026100510200924000_2026.09.25.754372v1.31","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae909"},{"key":"2026100510200924000_2026.09.25.754372v1.32","unstructured":"Wang, M. et al. Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks. (2019)."},{"key":"2026100510200924000_2026.09.25.754372v1.33","unstructured":"Hamilton, W. L. , Ying, R. & Leskovec, AJ . Inductive Representation Learning on Large Graphs. (2017)."},{"key":"2026100510200924000_2026.09.25.754372v1.34","unstructured":"Kingma, D. P. & Ba, AJ . Adam: A Method for Stochastic Optimization. (2014)."},{"key":"2026100510200924000_2026.09.25.754372v1.35","unstructured":"Paszke, A. et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. (2019)."},{"key":"2026100510200924000_2026.09.25.754372v1.36","doi-asserted-by":"publisher","DOI":"10.1038\/s41596-021-00573-7"},{"key":"2026100510200924000_2026.09.25.754372v1.37","doi-asserted-by":"crossref","unstructured":"Nielsen, F. On the Jensen-Shannon Symmetrization of Distances Relying on Abstract Means. Entropy (Basel) 21, (2019).","DOI":"10.3390\/e21050485"},{"key":"2026100510200924000_2026.09.25.754372v1.38","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-66150-8"},{"key":"2026100510200924000_2026.09.25.754372v1.39","doi-asserted-by":"publisher","DOI":"10.1038\/s41596-024-01020-z"},{"key":"2026100510200924000_2026.09.25.754372v1.40","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"2026100510200924000_2026.09.25.754372v1.41","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-41695-z"},{"key":"2026100510200924000_2026.09.25.754372v1.42","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-017-1382-0"},{"key":"2026100510200924000_2026.09.25.754372v1.43","doi-asserted-by":"crossref","first-page":"vbad130","DOI":"10.1093\/bioadv\/vbad130","article-title":"CCPlotR: an R package for the visualization of cell-cell interactions","volume":"3","year":"2023","journal-title":"Bioinform Adv"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.25.754372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T17:20:22Z","timestamp":1791220822000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.09.25.754372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":43,"URL":"https:\/\/doi.org\/10.64898\/2026.09.25.754372","relation":{},"subject":[],"published":{"date-parts":[[2026,9,30]]},"subtype":"preprint"}}