{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T19:27:02Z","timestamp":1787081222286,"version":"build-2736575974"},"posted":{"date-parts":[[2026,8,14]]},"group-title":"Bioinformatics","reference-count":47,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"award":["1R01HG014487-01"],"award-info":[{"award-number":["1R01HG014487-01"]}],"id":[{"id":"https:\/\/ror.org\/01cwqze88","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,8,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Spatial omics datasets are increasing in size and complexity, exceeding the memory of standard computers and thereby limiting data analysis. Here we present dbverse, a framework for larger-than-memory matrix, spatial and genomic data analysis in embedded analytical databases. Benchmarks show dbverse provides orders of magnitude runtime improvements relative to established in-memory and file-backed methods for core operations in single-cell and spatial omics analysis. We integrated dbverse with Giotto Suite, scaling end-to-end preprocessing of millions of cells and enabling spatial alternative polyadenylation analysis as demonstrated on a Visium HD 3\u2032 ovarian clear cell carcinoma sample. The dbverse framework provides an interoperable database foundation for larger-than-memory spatial omics analysis on ordinary computers.<\/jats:p>","DOI":"10.64898\/2026.08.09.743742","type":"posted-content","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T22:05:11Z","timestamp":1786745111000},"source":"Crossref","is-referenced-by-count":0,"title":["dbverse scales spatial omics analysis with embedded analytical databases"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9174-5387","authenticated-orcid":false,"given":"Edward C.","family":"Ruiz","sequence":"first","affiliation":[{"name":"Section of Hematology and Medical Oncology, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0043-8598","authenticated-orcid":false,"given":"Veronica","family":"Jarzabek","sequence":"additional","affiliation":[{"name":"Section of Hematology and Medical Oncology, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4565-832X","authenticated-orcid":false,"given":"Jiaji","family":"Chen","sequence":"additional","affiliation":[{"name":"Section of Hematology and Medical Oncology, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timur","family":"Rizvanov","sequence":"additional","affiliation":[{"name":"Section of Hematology and Medical Oncology, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iqra","family":"Amin","sequence":"additional","affiliation":[{"name":"Section of Hematology and Medical Oncology, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7650-7754","authenticated-orcid":false,"given":"Ruben","family":"Dries","sequence":"additional","affiliation":[{"name":"Section of Hematology and Medical Oncology, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, MA, USA"},{"name":"Section of Computational Biomedicine, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026081811551375000_2026.08.09.743742v1.1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-021-01249-6"},{"key":"2026081811551375000_2026.08.09.743742v1.2","doi-asserted-by":"crossref","unstructured":"Moses, L. & Pachter, L. Museum of spatial transcriptomics. Nat. Methods 1\u201313 (2022).","DOI":"10.1101\/2021.05.11.443152"},{"key":"2026081811551375000_2026.08.09.743742v1.3","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02565-3"},{"key":"2026081811551375000_2026.08.09.743742v1.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2022.04.003"},{"key":"2026081811551375000_2026.08.09.743742v1.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2022.10.021"},{"key":"2026081811551375000_2026.08.09.743742v1.6","doi-asserted-by":"publisher","DOI":"10.1038\/S41587-022-01483-Z"},{"key":"2026081811551375000_2026.08.09.743742v1.7","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa6090"},{"key":"2026081811551375000_2026.08.09.743742v1.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2021.05.010"},{"key":"2026081811551375000_2026.08.09.743742v1.9","doi-asserted-by":"publisher","DOI":"10.1101\/2024.06.04.597233"},{"key":"2026081811551375000_2026.08.09.743742v1.10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-43458-x"},{"key":"2026081811551375000_2026.08.09.743742v1.11","doi-asserted-by":"crossref","unstructured":"Kishi, J. Y. et al. Light-Seq: light-directed in situ barcoding of biomolecules in fixed cells and tissues for spatially indexed sequencing. Nat. Methods 1\u201310 (2022).","DOI":"10.1038\/s41592-022-01604-1"},{"key":"2026081811551375000_2026.08.09.743742v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2024.05.055"},{"key":"2026081811551375000_2026.08.09.743742v1.13","doi-asserted-by":"crossref","first-page":"4987","DOI":"10.1038\/s41467-024-49174-4","article-title":"Optimizing the design of spatial genomic studies","volume":"15","year":"2024","journal-title":"Nat. Commun"},{"key":"2026081811551375000_2026.08.09.743742v1.14","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1038\/d41586-023-02559-9","article-title":"The quest to map the mouse brain","volume":"620","year":"2023","journal-title":"Nature"},{"key":"2026081811551375000_2026.08.09.743742v1.15","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-023-01766-6"},{"key":"2026081811551375000_2026.08.09.743742v1.16","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1146\/annurev-biodatasci-102523-103640","article-title":"Spatially resolved single-cell omics: Methods, challenges, and future perspectives","volume":"7","year":"2024","journal-title":"Annu. Rev. Biomed. Data Sci"},{"key":"2026081811551375000_2026.08.09.743742v1.17","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25557-9"},{"key":"2026081811551375000_2026.08.09.743742v1.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.gpb.2022.10.001"},{"key":"2026081811551375000_2026.08.09.743742v1.19","doi-asserted-by":"crossref","unstructured":"Aihara, G. et al. SEraster: a rasterization preprocessing framework for scalable spatial omics data analysis. Bioinformatics 40, (2024).","DOI":"10.1093\/bioinformatics\/btae412"},{"key":"2026081811551375000_2026.08.09.743742v1.20","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae546"},{"key":"2026081811551375000_2026.08.09.743742v1.21","doi-asserted-by":"crossref","unstructured":"Raasveldt, M. & M\u00fchleisen, H. DuckDB: an Embeddable Analytical Database. in Proceedings of the 2019 International Conference on Management of Data 1981\u20131984 (Association for Computing Machinery, New York, NY, USA, 2019).","DOI":"10.1145\/3299869.3320212"},{"key":"2026081811551375000_2026.08.09.743742v1.22","doi-asserted-by":"publisher","DOI":"10.1145\/3626246.3653368"},{"key":"2026081811551375000_2026.08.09.743742v1.23","unstructured":"Kuiper, L. , Raasveldt, M. & M\u00fchleisen, H. Efficient External Sorting in DuckDB. https:\/\/ir.cwi.nl\/pub\/31877 (2022)."},{"key":"2026081811551375000_2026.08.09.743742v1.24","doi-asserted-by":"publisher","DOI":"10.1109\/icde.2006.150"},{"key":"2026081811551375000_2026.08.09.743742v1.25","first-page":"1","article-title":"Decoding billions of integers per second through vectorization","volume":"45","year":"2015","journal-title":"Softw. Pract. Exp"},{"key":"2026081811551375000_2026.08.09.743742v1.26","first-page":"1","article-title":"ALP: Adaptive lossless floating-point compression","volume":"1","year":"2023","journal-title":"Proc. ACM Manag. Data"},{"key":"2026081811551375000_2026.08.09.743742v1.27","unstructured":"Arrow: Apache Arrow Is the Universal Columnar Format and Multi-Language Toolbox for Fast Data Interchange and in-Memory Analytics. (Github)."},{"key":"2026081811551375000_2026.08.09.743742v1.28","doi-asserted-by":"publisher","DOI":"10.1101\/2025.03.27.645853"},{"key":"2026081811551375000_2026.08.09.743742v1.29","unstructured":"Bates, D. , Maechler, M. & Jagan, M. Matrix: Sparse and Dense Matrix Classes and Methods. Preprint at https:\/\/CRAN.R-project.org\/package=Matrix (2024)."},{"key":"2026081811551375000_2026.08.09.743742v1.30","unstructured":"Goswami, R. Ropensci\/fastMatMR: High-Performance Matrix Market File Operations. (2026)."},{"key":"2026081811551375000_2026.08.09.743742v1.31","doi-asserted-by":"publisher","DOI":"10.32614\/RJ-2018-009"},{"key":"2026081811551375000_2026.08.09.743742v1.32","doi-asserted-by":"publisher","DOI":"10.1201\/9780429459016"},{"key":"2026081811551375000_2026.08.09.743742v1.33","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btp328"},{"key":"2026081811551375000_2026.08.09.743742v1.34","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003118"},{"key":"2026081811551375000_2026.08.09.743742v1.35","unstructured":"Pag\u00e8s, H. , Hickey, P. & Lun, A. DelayedArray: A unified framework for working transparently with on-disk and in-memory array-like datasets. R package version 0.20. 0."},{"key":"2026081811551375000_2026.08.09.743742v1.36","doi-asserted-by":"publisher","DOI":"10.18129\/B9.BIOC.HDF5ARRAY"},{"key":"2026081811551375000_2026.08.09.743742v1.37","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-018-1597-8"},{"key":"2026081811551375000_2026.08.09.743742v1.38","doi-asserted-by":"crossref","first-page":"2052","DOI":"10.1038\/s41592-025-02817-w","article-title":"Giotto Suite: a multiscale and technology-agnostic spatial multiomics analysis ecosystem","volume":"22","year":"2025","journal-title":"Nat. Methods"},{"key":"2026081811551375000_2026.08.09.743742v1.39","doi-asserted-by":"crossref","unstructured":"Wu, X. , Liu, T. , Ye, C. , Ye, W. & Ji, G. scAPAtrap: identification and quantification of alternative polyadenylation sites from single-cell RNA-seq data. Brief. Bioinform. 22, (2021).","DOI":"10.1093\/bib\/bbaa273"},{"key":"2026081811551375000_2026.08.09.743742v1.40","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa997"},{"key":"2026081811551375000_2026.08.09.743742v1.41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2009.06.016"},{"key":"2026081811551375000_2026.08.09.743742v1.42","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-32305-0"},{"key":"2026081811551375000_2026.08.09.743742v1.43","unstructured":"Simple Feature Access - Part 1: Common Architecture. Open Geospatial Consortium https:\/\/www.ogc.org\/publications\/standard\/sfa\/ (2023)."},{"key":"2026081811551375000_2026.08.09.743742v1.44","unstructured":"Hijmans, R. J. terra: Spatial Data Analysis. Preprint at https:\/\/github.com\/rspatial\/terra (2024)."},{"key":"2026081811551375000_2026.08.09.743742v1.45","unstructured":"Exon: Exon Is an OLAP Query Engine Specifically for Biology and Life Science Applications. (Github)."},{"key":"2026081811551375000_2026.08.09.743742v1.46","unstructured":"Silge, J. , Wickham, H. & Luraschi, J. pins: Pin, Discover, and Share Resources. Preprint at https:\/\/pins.rstudio.com\/ (2025)."},{"key":"2026081811551375000_2026.08.09.743742v1.47","doi-asserted-by":"publisher","DOI":"10.1101\/2023.11.26.568752"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.08.09.743742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T18:55:21Z","timestamp":1787079321000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.08.09.743742"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,14]]},"references-count":47,"URL":"https:\/\/doi.org\/10.64898\/2026.08.09.743742","relation":{},"subject":[],"published":{"date-parts":[[2026,8,14]]},"subtype":"preprint"}}