{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T12:51:08Z","timestamp":1765198268525,"version":"3.46.0"},"posted":{"date-parts":[[2025,12,2]]},"group-title":"Genomics","reference-count":26,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NIGMS Maximizing Investigators\u2019 Research Award","award":["R35","GM146960"],"award-info":[{"award-number":["R35","GM146960"]}]},{"name":"Vanderbilt Seeding Success Grant","award":["FF_300627"],"award-info":[{"award-number":["FF_300627"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,12,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  Spatial transcriptomics (ST) provides high-dimensional gene expression profiles together with spatial coordinates, enabling the reconstruction of tissue architecture at cellular resolution. While recent graph-based deep learning methods have advanced spatial clustering in ST, many rely on complex architectures that obscure interpretability and rarely integrate biological priors such as marker gene information. We introduce BioLACE, a scalable framework that unifies spatial structure, transcriptomic variation, and curated marker gene profiles within a shared Variational Autoencoder (VAE) latent space. BioLACEjointly optimizes three complementary objectives: (1) a VAE reconstruction loss to preserve transcriptional structure, (2) a graph Laplacian regularizer to enforce spatial smoothness, and (3) a temperature-scaled InfoNCE contrastive loss guided by marker-informed similarities. Applied to MERFISH hypothalamus, mouse spinal cord, and Slide-seq mouse cerebellum datasets, BioLACE achieves superior cell type clustering accuracy, well-defined biologically consistent boundaries, and interpretable latent representations, highlighting its generality and scalability for modern ST analysis. The source code and tutorials for BioLACE are publicly available at\n                  <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/maiziezhoulab\/BioLACE\">https:\/\/github.com\/maiziezhoulab\/BioLACE<\/jats:ext-link>\n                  .\n                <\/jats:p>","DOI":"10.64898\/2025.12.01.691603","type":"posted-content","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T12:47:52Z","timestamp":1765198072000},"source":"Crossref","is-referenced-by-count":0,"title":["BioLACE: unifying spatial geometry and marker priors for cohesive cell-type clustering in spatial transcriptomics"],"prefix":"10.64898","author":[{"given":"Haoran","family":"Qin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuling","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jihoon","family":"Baek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiman","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4015-4787","authenticated-orcid":false,"given":"Shan","family":"Meltzer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin Maizie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025120800563741000_2025.12.01.691603v1.1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaf2403"},{"key":"2025120800563741000_2025.12.01.691603v1.2","doi-asserted-by":"crossref","unstructured":"Yunfei Hu , Manfei Xie , Yikang Li , Mingxing Rao , Wenjun Shen , Can Luo , Haoran Qin , Jihoon Baek , and Xin Zhou . Benchmarking clustering, alignment, and integration methods for spatial transcriptomics. Genome Biology, 25, 08 2024.","DOI":"10.1186\/s13059-024-03361-0"},{"key":"2025120800563741000_2025.12.01.691603v1.3","doi-asserted-by":"crossref","unstructured":"Edward Zhao , Matthew Stone , Xing Ren , Thomas Pulliam , Paul Nghiem , Jason Bielas , and Raphael Gottardo . Bayesspace enables the robust characterization of spatial gene expression architecture in tissue sections at in-creased resolution. 09 2020.","DOI":"10.1101\/2020.09.04.283812"},{"key":"2025120800563741000_2025.12.01.691603v1.4","first-page":"1","article-title":"Banksy unifies cell typing and tissue domain segmentation for scalable spatial omics data analysis","volume":"56","year":"2024","journal-title":"Nature Genetics"},{"key":"2025120800563741000_2025.12.01.691603v1.5","doi-asserted-by":"crossref","unstructured":"Jian Hu , Xiangjie Li , Kyle Coleman , Amelia Schroeder , Nan Ma , David Irwin , Edward Lee , Russell Shinohara , and Mingyao Li . Spagcn: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network. Nature Methods, 18, 11 2021.","DOI":"10.1038\/s41592-021-01255-8"},{"key":"2025120800563741000_2025.12.01.691603v1.6","doi-asserted-by":"crossref","unstructured":"Hang Xu , Huazhu Fu , Yahui Long , Kok Siong Ang , Raman Sethi , Kelvin Chong , Mengwei Li , Rom Uddam-vathanak , Hong Lee , Jingjing Ling , Ao Chen , Ling Shao , Longqi Liu , and Jinmiao Chen . Unsupervised spatially embedded deep representation of spatial transcriptomics. Genome Medicine, 16, 01 2024.","DOI":"10.1186\/s13073-024-01283-x"},{"key":"2025120800563741000_2025.12.01.691603v1.7","doi-asserted-by":"crossref","first-page":"106792","DOI":"10.1016\/j.isci.2023.106792","article-title":"Adept: Autoencoder with differentially expressed genes and imputation for a robust spatial transcriptomics clustering","volume":"26","year":"2023","journal-title":"iScience"},{"key":"2025120800563741000_2025.12.01.691603v1.8","doi-asserted-by":"crossref","unstructured":"Yahui Long , Kok Siong Ang , Mengwei Li , Kian Chong , Raman Sethi , Chengwei Zhong , Hang Xu , Zhiwei Ong , Karishma Sachaphibulkij , Ao Chen , Li Zeng , Huazhu Fu , Min Wu , Lina Lim , Longqi Liu , and Jinmiao Chen . Spatially informed clustering, integration, and deconvolution of spatial transcriptomics with graphst. Nature Communications, 14, 03 2023.","DOI":"10.1038\/s41467-023-36796-3"},{"key":"2025120800563741000_2025.12.01.691603v1.9","doi-asserted-by":"crossref","unstructured":"A.W. Zhang and others. Probabilistic cell-type assignment of single-cell rna-seq for tumor microenvironment profiling. Nature Methods, 2019.","DOI":"10.1038\/s41592-019-0529-1"},{"key":"2025120800563741000_2025.12.01.691603v1.10","doi-asserted-by":"crossref","unstructured":"Hannah Pliner , Jay Shendure , and Cole Trapnell . Supervised classification enables rapid annotation of cell atlases. Nature Methods, 16, 10 2019.","DOI":"10.1038\/s41592-019-0535-3"},{"key":"2025120800563741000_2025.12.01.691603v1.11","doi-asserted-by":"publisher","DOI":"10.3390\/genes10070531"},{"key":"2025120800563741000_2025.12.01.691603v1.12","unstructured":"Aaron van den Oord , Yazhe Li , and Oriol Vinyals . Representation learning with contrastive predictive coding, 2019."},{"key":"2025120800563741000_2025.12.01.691603v1.13","unstructured":"Ting Chen , Simon Kornblith , Mohammad Norouzi , and Geoffrey Hinton . A simple framework for contrastive learning of visual representations, 2020."},{"key":"2025120800563741000_2025.12.01.691603v1.14","unstructured":"Qimai Li , Zhichao Han , and Xiao-Ming Wu . Deeper insights into graph convolutional networks for semi-supervised learning, 2018."},{"key":"2025120800563741000_2025.12.01.691603v1.15","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaw1219"},{"key":"2025120800563741000_2025.12.01.691603v1.16","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-020-00801-7"},{"key":"2025120800563741000_2025.12.01.691603v1.17","doi-asserted-by":"crossref","unstructured":"V. A. Traag , L. Waltman , and N. J. van Eck . From louvain to leiden: guaranteeing well-connected communities. Scientific Reports, 9(1), March 2019.","DOI":"10.1038\/s41598-019-41695-z"},{"key":"2025120800563741000_2025.12.01.691603v1.18","unstructured":"Allen Institute for Brain Science. Allen reference atlas \u2013 mouse brain. https:\/\/atlas.brain-map.org, 2011. [Brain atlas]."},{"key":"2025120800563741000_2025.12.01.691603v1.19","unstructured":"Diederik P Kingma and Max Welling . Auto-encoding variational bayes, 2022."},{"key":"2025120800563741000_2025.12.01.691603v1.20","unstructured":"Christopher P. Burgess , Irina Higgins , Arka Pal , Loic Matthey , Nick Watters , Guillaume Desjardins , and Alexander Lerchner . Understanding disentangling in \u03b2-vae, 2018."},{"key":"2025120800563741000_2025.12.01.691603v1.21","unstructured":"Prannay Khosla , Piotr Teterwak , Chen Wang , Aaron Sarna , Yonglong Tian , Phillip Isola , Aaron Maschinot , Ce Liu , and Dilip Krishnan . Supervised contrastive learning, 2021."},{"key":"2025120800563741000_2025.12.01.691603v1.22","doi-asserted-by":"crossref","unstructured":"Yanguang Chen . Spatial autocorrelation equation based on moran\u2019s index, 2023.","DOI":"10.1038\/s41598-023-45947-x"},{"key":"2025120800563741000_2025.12.01.691603v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-021-01131-y"},{"key":"2025120800563741000_2025.12.01.691603v1.24","unstructured":"Shan Meltzer . https:\/\/github.com\/shanmeltzer\/Spinal_MERFISH, 2025."},{"key":"2025120800563741000_2025.12.01.691603v1.25","doi-asserted-by":"crossref","unstructured":"Giovanni Palla , Hannah Spitzer , Michal Klein , David Fischer , Anna Schaar , Louis Kuemmerle , Sergei Rybakov , Ignacio Ibarra , Olle Holmberg , Isaac Virshup , Mohammad Lotfollahi , Sabrina Richter , and Fabian Theis . Squidpy: a scalable framework for spatial omics analysis. Nature Methods, 19, 02 2022.","DOI":"10.1101\/2021.02.19.431994"},{"key":"2025120800563741000_2025.12.01.691603v1.26","doi-asserted-by":"crossref","first-page":"2216","DOI":"10.1016\/j.celrep.2018.02.003","article-title":"Massively parallel single nucleus transcriptional profiling defines spinal cord neurons and their activity during behavior","volume":"22","year":"2018","journal-title":"Cell Reports"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2025.12.01.691603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T12:47:56Z","timestamp":1765198076000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2025.12.01.691603"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":26,"URL":"https:\/\/doi.org\/10.64898\/2025.12.01.691603","relation":{},"subject":[],"published":{"date-parts":[[2025,12,2]]},"subtype":"preprint"}}