{"id":"https://openalex.org/W4312113360","doi":"https://doi.org/10.1093/bioinformatics/btac829","title":"SIMBSIG: similarity search and clustering for biobank-scale data","display_name":"SIMBSIG: similarity search and clustering for biobank-scale data","publication_year":2022,"publication_date":"2022-12-23","ids":{"openalex":"https://openalex.org/W4312113360","doi":"https://doi.org/10.1093/bioinformatics/btac829","pmid":"https://pubmed.ncbi.nlm.nih.gov/36610707"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac829","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac829","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac829/48494113/btac829.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac829/48494113/btac829.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043820325","display_name":"Michael F. Adamer","orcid":"https://orcid.org/0000-0002-8996-7167"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Michael F Adamer","raw_affiliation_strings":["Department of Biosystems Science and Engineering, ETH Zurich , 4058 Basel, Switzerland","Swiss Institute for Bioinformatics (SIB) , 1015 Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-8996-7167","affiliations":[{"raw_affiliation_string":"Department of Biosystems Science and Engineering, ETH Zurich , 4058 Basel, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Swiss Institute for Bioinformatics (SIB) , 1015 Lausanne, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033297577","display_name":"Eljas Roellin","orcid":"https://orcid.org/0009-0002-4181-5516"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Eljas Roellin","raw_affiliation_strings":["Department of Biosystems Science and Engineering, ETH Zurich , 4058 Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biosystems Science and Engineering, ETH Zurich , 4058 Basel, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082294445","display_name":"Lucie Bourguignon","orcid":"https://orcid.org/0000-0001-8049-6461"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lucie Bourguignon","raw_affiliation_strings":["Department of Health Sciences and Technology, ETH Zurich , 8008 Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Health Sciences and Technology, ETH Zurich , 8008 Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074540538","display_name":"Karsten Borgwardt","orcid":"https://orcid.org/0000-0001-7221-2393"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Karsten Borgwardt","raw_affiliation_strings":["Department of Biosystems Science and Engineering, ETH Zurich , 4058 Basel, Switzerland","Swiss Institute for Bioinformatics (SIB) , 1015 Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-7221-2393","affiliations":[{"raw_affiliation_string":"Department of Biosystems Science and Engineering, ETH Zurich , 4058 Basel, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Swiss Institute for Bioinformatics (SIB) , 1015 Lausanne, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043820325"],"corresponding_institution_ids":["https://openalex.org/I12708293","https://openalex.org/I35440088"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12976442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.39559999108314514,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.39559999108314514,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.26010000705718994,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.10019999742507935,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/biobank","display_name":"Biobank","score":0.8548954129219055},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7129777073860168},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6528716683387756},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6173375844955444},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5431399345397949},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.459597647190094},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45825424790382385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18373960256576538},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.17544490098953247},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1702793538570404},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1618087887763977},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.11201995611190796}],"concepts":[{"id":"https://openalex.org/C116567970","wikidata":"https://www.wikidata.org/wiki/Q864217","display_name":"Biobank","level":2,"score":0.8548954129219055},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7129777073860168},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6528716683387756},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6173375844955444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5431399345397949},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.459597647190094},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45825424790382385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18373960256576538},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.17544490098953247},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1702793538570404},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1618087887763977},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.11201995611190796},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018070","descriptor_name":"Biological Specimen Banks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018070","descriptor_name":"Biological Specimen Banks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018070","descriptor_name":"Biological Specimen Banks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018070","descriptor_name":"Biological Specimen Banks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btac829","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac829","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac829/48494113/btac829.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36610707","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36610707","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9825260","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9825260","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac829","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac829","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btac829/48494113/btac829.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1636770102","display_name":null,"funder_award_id":"PZ00P3_186101","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G5431826769","display_name":"Precision-Medicine for Neurological Disorders: Harnessing the Power of Big Data and Machine Learning for Biomarker Discovery and Drug Repositioning Strategies","funder_award_id":"186101","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4312113360.pdf"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W1505090736","https://openalex.org/W2122617678","https://openalex.org/W2895486342","https://openalex.org/W2998702515"],"related_works":["https://openalex.org/W4285087457","https://openalex.org/W2105971613","https://openalex.org/W3113746618","https://openalex.org/W4226051228","https://openalex.org/W4226156868","https://openalex.org/W4244742767","https://openalex.org/W2024651825","https://openalex.org/W2323349009","https://openalex.org/W4248738672","https://openalex.org/W2470939431"],"abstract_inverted_index":{"SUMMARY:":[0],"In":[1],"many":[2,73],"modern":[3],"bioinformatics":[4],"applications,":[5],"such":[6],"as":[7],"statistical":[8],"genetics,":[9],"or":[10],"single-cell":[11],"analysis,":[12],"one":[13],"frequently":[14],"encounters":[15],"datasets":[16],"which":[17,45],"are":[18],"orders":[19],"of":[20],"magnitude":[21],"too":[22],"large":[23],"for":[24,50],"conventional":[25],"in-memory":[26],"analysis.":[27,83],"To":[28],"tackle":[29],"this":[30],"challenge,":[31],"we":[32],"introduce":[33],"SIMBSIG":[34,87],"(SIMmilarity":[35],"Batched":[36],"Search":[37],"Integrated":[38],"GPU),":[39],"a":[40,47,77,106],"highly":[41,67],"scalable":[42],"Python":[43],"package":[44],"provides":[46],"scikit-learn-like":[48],"interface":[49],"out-of-core,":[51],"GPU-enabled":[52],"similarity":[53],"searches,":[54],"principal":[55],"component":[56],"analysis":[57],"and":[58,69,93,97],"clustering.":[59],"Due":[60],"to":[61,72],"the":[62],"PyTorch":[63],"backend,":[64],"it":[65],"is":[66,88],"modular":[68],"particularly":[70],"tailored":[71],"data":[74,82],"types":[75],"with":[76],"particular":[78],"focus":[79],"on":[80,102],"biobank":[81],"AVAILABILITY":[84],"AND":[85],"IMPLEMENTATION:":[86],"freely":[89],"available":[90],"from":[91],"PyPI":[92],"its":[94],"source":[95],"code":[96],"documentation":[98],"can":[99],"be":[100],"found":[101],"GitHub":[103],"(https://github.com/BorgwardtLab/simbsig)":[104],"under":[105],"BSD-3":[107],"license.":[108]},"counts_by_year":[],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2025-10-10T00:00:00"}
