{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:34:17Z","timestamp":1772138057927,"version":"3.50.1"},"reference-count":7,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T00:00:00Z","timestamp":1671753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"publisher","award":["PZ00P3_186101"],"award-info":[{"award-number":["PZ00P3_186101"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Summary<\/jats:title>\n                    <jats:p>In many modern bioinformatics applications, such as statistical genetics, or single-cell analysis, one frequently encounters datasets which are orders of magnitude too large for conventional in-memory analysis. To tackle this challenge, we introduce SIMBSIG (SIMmilarity Batched Search Integrated GPU), a highly scalable Python package which provides a scikit-learn-like interface for out-of-core, GPU-enabled similarity searches, principal component analysis and clustering. Due to the PyTorch backend, it is highly modular and particularly tailored to many data types with a particular focus on biobank data analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>SIMBSIG is freely available from PyPI and its source code and documentation can be found on GitHub (https:\/\/github.com\/BorgwardtLab\/simbsig) under a BSD-3 license.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac829","type":"journal-article","created":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T08:11:58Z","timestamp":1671783118000},"source":"Crossref","is-referenced-by-count":0,"title":["SIMBSIG: similarity search and clustering for biobank-scale data"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8996-7167","authenticated-orcid":false,"given":"Michael F","family":"Adamer","sequence":"first","affiliation":[{"name":"Department of Biosystems Science and Engineering, ETH Zurich , 4058 Basel, Switzerland"},{"name":"Swiss Institute for Bioinformatics (SIB) , 1015 Lausanne, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eljas","family":"Roellin","sequence":"additional","affiliation":[{"name":"Department of Biosystems Science and Engineering, ETH Zurich , 4058 Basel, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lucie","family":"Bourguignon","sequence":"additional","affiliation":[{"name":"Department of Health Sciences and Technology, ETH Zurich , 8008 Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7221-2393","authenticated-orcid":false,"given":"Karsten","family":"Borgwardt","sequence":"additional","affiliation":[{"name":"Department of Biosystems Science and Engineering, ETH Zurich , 4058 Basel, Switzerland"},{"name":"Swiss Institute for Bioinformatics (SIB) , 1015 Lausanne, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2022,12,23]]},"reference":[{"key":"2023010801253554200_btac829-B1","first-page":"420","author":"Aggarwal","year":"2001"},{"key":"2023010801253554200_btac829-B2","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41586-018-0579-z","article-title":"The UK biobank resource with deep phenotyping and genomic data","volume":"562","author":"Bycroft","year":"2018","journal-title":"Nature"},{"key":"2023010801253554200_btac829-B3","doi-asserted-by":"crossref","first-page":"2580","DOI":"10.1137\/100804139","article-title":"An algorithm for the principal component analysis of large data sets","volume":"33","author":"Halko","year":"2011","journal-title":"SIAM J. Sci. Comput"},{"key":"2023010801253554200_btac829-B4","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","article-title":"Billion-scale similarity search with GPUs","volume":"7","author":"Johnson","year":"2021","journal-title":"IEEE Trans. Big Data"},{"key":"2023010801253554200_btac829-B5","author":"Raschka","year":"2020"},{"key":"2023010801253554200_btac829-B6","first-page":"1177","author":"Sculley","year":"2010"},{"key":"2023010801253554200_btac829-B7","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1093\/bib\/bbu024","article-title":"Kernel methods for large-scale genomic data analysis","volume":"16","author":"Wang","year":"2015","journal-title":"Brief. Bioinform"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac829\/48362078\/btac829.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac829\/48494113\/btac829.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac829\/48494113\/btac829.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T20:25:48Z","timestamp":1673123148000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btac829\/6958553"}},"subtitle":[],"editor":[{"given":"Russell","family":"Schwartz","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2022,12,23]]},"references-count":7,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac829","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.09.22.509063","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,1,1]]},"published":{"date-parts":[[2022,12,23]]},"article-number":"btac829"}}