{"id":"https://openalex.org/W2980318882","doi":"https://doi.org/10.1093/bib/bbz083","title":"Beware the Jaccard: the choice of <b>similarity measure</b> is important and non-trivial in genomic colocalisation analysis","display_name":"Beware the Jaccard: the choice of <b>similarity measure</b> is important and non-trivial in genomic colocalisation analysis","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2980318882","doi":"https://doi.org/10.1093/bib/bbz083","mag":"2980318882","pmid":"https://pubmed.ncbi.nlm.nih.gov/31624847"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbz083","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbz083","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"review","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028258664","display_name":"Stefania Salvatore","orcid":"https://orcid.org/0000-0003-1724-6181"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Stefania Salvatore","raw_affiliation_strings":["Department of Informatics, University of Oslo, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035654730","display_name":"Knut Dagestad Rand","orcid":"https://orcid.org/0000-0003-3359-7619"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Knut Dagestad Rand","raw_affiliation_strings":["Department of Mathematics, University of Oslo, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055428069","display_name":"Ivar Grytten","orcid":"https://orcid.org/0000-0001-8941-942X"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Ivar Grytten","raw_affiliation_strings":["Department of Informatics, University of Oslo, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066037133","display_name":"Egil Ferkingstad","orcid":"https://orcid.org/0000-0001-8090-7988"},"institutions":[{"id":"https://openalex.org/I165368041","display_name":"University of Iceland","ror":"https://ror.org/01db6h964","country_code":"IS","type":"education","lineage":["https://openalex.org/I165368041"]}],"countries":["IS"],"is_corresponding":false,"raw_author_name":"Egil Ferkingstad","raw_affiliation_strings":["Science Institute, University of Iceland, Reykjavik, Iceland"],"affiliations":[{"raw_affiliation_string":"Science Institute, University of Iceland, Reykjavik, Iceland","institution_ids":["https://openalex.org/I165368041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088348797","display_name":"Diana Doma\u0144ska","orcid":"https://orcid.org/0000-0002-6051-1289"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Diana Domanska","raw_affiliation_strings":["Department of Informatics, University of Oslo, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030811512","display_name":"Lars Holden","orcid":"https://orcid.org/0000-0002-9475-5206"},"institutions":[{"id":"https://openalex.org/I144648426","display_name":"Norwegian Computing Center","ror":"https://ror.org/02gm7te43","country_code":"NO","type":"nonprofit","lineage":["https://openalex.org/I144648426"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Lars Holden","raw_affiliation_strings":["Statistics For Innovation, Norwegian Computing Center, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Statistics For Innovation, Norwegian Computing Center, Oslo, Norway","institution_ids":["https://openalex.org/I144648426"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023268296","display_name":"Marius Gheorghe","orcid":"https://orcid.org/0000-0002-9666-0809"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Marius Gheorghe","raw_affiliation_strings":["Centre for Molecular Medicine Norway (NCMM), Nordic EMBL Partnership, University of Oslo, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Centre for Molecular Medicine Norway (NCMM), Nordic EMBL Partnership, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087735169","display_name":"Anthony Mathelier","orcid":"https://orcid.org/0000-0001-5127-5459"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]},{"id":"https://openalex.org/I1281400175","display_name":"Oslo University Hospital","ror":"https://ror.org/00j9c2840","country_code":"NO","type":"healthcare","lineage":["https://openalex.org/I1281400175"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Anthony Mathelier","raw_affiliation_strings":["Centre for Molecular Medicine Norway (NCMM), Nordic EMBL Partnership, University of Oslo, Oslo, Norway","Department of Cancer Genetics, Institute for Cancer Research, Oslo University Hospital Radiumhospitalet, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Centre for Molecular Medicine Norway (NCMM), Nordic EMBL Partnership, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"Department of Cancer Genetics, Institute for Cancer Research, Oslo University Hospital Radiumhospitalet, Oslo, Norway","institution_ids":["https://openalex.org/I1281400175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077821870","display_name":"Ingrid K. Glad","orcid":"https://orcid.org/0000-0002-5156-7109"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Ingrid Glad","raw_affiliation_strings":["Department of Mathematics, University of Oslo, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054500587","display_name":"Geir Kjetil Sandve","orcid":"https://orcid.org/0000-0002-4959-1409"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Geir Kjetil Sandve","raw_affiliation_strings":["Department of Informatics, University of Oslo, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5028258664"],"corresponding_institution_ids":["https://openalex.org/I184942183"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":0.7643,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.66002961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"21","issue":"5","first_page":"1523","last_page":"1530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9872000217437744,"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/jaccard-index","display_name":"Jaccard index","score":0.9867033958435059},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5814146995544434},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5286042094230652},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5140074491500854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40068089962005615},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.31344687938690186},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24032840132713318},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.20759472250938416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19029662013053894}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.9867033958435059},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5814146995544434},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5286042094230652},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5140074491500854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40068089962005615},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.31344687938690186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24032840132713318},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.20759472250938416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19029662013053894},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005786","descriptor_name":"Gene Expression Regulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005786","descriptor_name":"Gene Expression Regulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005786","descriptor_name":"Gene Expression Regulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbz083","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbz083","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:31624847","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31624847","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":"Briefings in bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1987869189","https://openalex.org/W2018838463","https://openalex.org/W2078059415","https://openalex.org/W2084160423","https://openalex.org/W2101272820","https://openalex.org/W2106779017","https://openalex.org/W2128016314","https://openalex.org/W2136430672","https://openalex.org/W2146890600","https://openalex.org/W2152580867","https://openalex.org/W2259938310","https://openalex.org/W2323898614","https://openalex.org/W2327188017","https://openalex.org/W2580515272","https://openalex.org/W2582743722","https://openalex.org/W2611775752","https://openalex.org/W2745750801","https://openalex.org/W2767743008","https://openalex.org/W6732128741","https://openalex.org/W6762429248"],"related_works":["https://openalex.org/W1994775821","https://openalex.org/W2012019886","https://openalex.org/W2091133150","https://openalex.org/W4386507344","https://openalex.org/W2945869148","https://openalex.org/W2398781203","https://openalex.org/W2009279505","https://openalex.org/W4206503171","https://openalex.org/W4366711670","https://openalex.org/W2972216353"],"abstract_inverted_index":{"The":[0,147],"generation":[1],"and":[2,26,34,111,128,141,152,176,182],"systematic":[3],"collection":[4],"of":[5,13,24,54,56,62,79,104,166],"genome-wide":[6,57],"data":[7,14,178],"is":[8,135],"ever-increasing.":[9],"This":[10],"vast":[11],"amount":[12],"has":[15,95],"enabled":[16],"researchers":[17],"to":[18,50,121],"study":[19],"relations":[20,38],"between":[21],"a":[22],"variety":[23,61],"genomic":[25,45,87,93,130],"epigenomic":[27],"features,":[28],"including":[29],"genetic":[30],"variation,":[31],"gene":[32],"regulation":[33],"phenotypic":[35],"traits.":[36],"Such":[37],"are":[39,155],"typically":[40],"investigated":[41],"by":[42,138,158],"comparatively":[43],"assessing":[44,51,86],"co-occurrence.":[46],"Technically,":[47],"this":[48,69,123],"corresponds":[49],"the":[52,92,102,132],"similarity":[53,63,105],"pairs":[55],"binary":[58],"vectors.":[59],"A":[60],"measures":[64,81],"have":[65,82],"been":[66,83,97],"proposed":[67],"for":[68,85,91,169],"problem":[70],"in":[71],"other":[72],"fields":[73],"like":[74],"ecology.":[75],"However,":[76],"while":[77],"several":[78],"these":[80],"employed":[84],"co-occurrence,":[88],"their":[89],"appropriateness":[90],"setting":[94],"never":[96],"investigated.":[98],"We":[99],"show":[100],"that":[101,117],"choice":[103],"measure":[106],"may":[107],"strongly":[108,136],"influence":[109],"results":[110,173],"propose":[112],"two":[113],"alternative":[114],"modelling":[115],"assumptions":[116],"can":[118,179],"be":[119,143,164,180],"used":[120,144],"guide":[122],"choice.":[124],"On":[125],"both":[126],"simulated":[127,175],"real":[129,177],"data,":[131],"Jaccard":[133],"index":[134],"altered":[137],"dataset":[139,159],"size":[140],"should":[142,163],"with":[145],"caution.":[146],"Forbes":[148],"coefficient":[149],"(fold":[150],"change)":[151],"tetrachoric":[153],"correlation":[154],"less":[156],"influenced":[157],"size,":[160],"but":[161],"one":[162],"aware":[165],"increased":[167],"variance":[168],"small":[170],"datasets.":[171],"All":[172],"on":[174],"inspected":[181],"reproduced":[183],"at":[184],"https://hyperbrowser.uio.no/sim-measure.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-10-25T00:00:00"}
