{"id":"https://openalex.org/W2950342274","doi":"https://doi.org/10.1093/bioinformatics/btz490","title":"CoCoScore: context-aware co-occurrence scoring for text mining applications using distant supervision","display_name":"CoCoScore: context-aware co-occurrence scoring for text mining applications using distant supervision","publication_year":2019,"publication_date":"2019-06-10","ids":{"openalex":"https://openalex.org/W2950342274","doi":"https://doi.org/10.1093/bioinformatics/btz490","mag":"2950342274","pmid":"https://pubmed.ncbi.nlm.nih.gov/31199464"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz490","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz490","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/1/264/48981379/bioinformatics_36_1_264.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/36/1/264/48981379/bioinformatics_36_1_264.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006363776","display_name":"Alexander Junge","orcid":"https://orcid.org/0000-0002-2410-9671"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]},{"id":"https://openalex.org/I2801134892","display_name":"Novo Nordisk Foundation","ror":"https://ror.org/04txyc737","country_code":"DK","type":"facility","lineage":["https://openalex.org/I2801134892"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Alexander Junge","raw_affiliation_strings":["Disease Systems Biology Program, Novo Nordisk Foundation Center for Protein Research, University of Copenhagen , Copenhagen N 2200, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-2410-9671","affiliations":[{"raw_affiliation_string":"Disease Systems Biology Program, Novo Nordisk Foundation Center for Protein Research, University of Copenhagen , Copenhagen N 2200, Denmark","institution_ids":["https://openalex.org/I124055696","https://openalex.org/I2801134892"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005772961","display_name":"Lars Juhl Jensen","orcid":"https://orcid.org/0000-0001-7885-715X"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]},{"id":"https://openalex.org/I2801134892","display_name":"Novo Nordisk Foundation","ror":"https://ror.org/04txyc737","country_code":"DK","type":"facility","lineage":["https://openalex.org/I2801134892"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Lars Juhl Jensen","raw_affiliation_strings":["Disease Systems Biology Program, Novo Nordisk Foundation Center for Protein Research, University of Copenhagen , Copenhagen N 2200, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-7885-715X","affiliations":[{"raw_affiliation_string":"Disease Systems Biology Program, Novo Nordisk Foundation Center for Protein Research, University of Copenhagen , Copenhagen N 2200, Denmark","institution_ids":["https://openalex.org/I124055696","https://openalex.org/I2801134892"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005772961","https://openalex.org/A5006363776"],"corresponding_institution_ids":["https://openalex.org/I124055696","https://openalex.org/I2801134892"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.5957,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.83673469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"36","issue":"1","first_page":"264","last_page":"271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9882000088691711,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9882000088691711,"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":0.004999999888241291,"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/T10028","display_name":"Topic Modeling","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7504393458366394},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7276565432548523},{"id":"https://openalex.org/keywords/co-occurrence","display_name":"Co-occurrence","score":0.6086958050727844},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4309406876564026},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.41921693086624146},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41492295265197754},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.2761955261230469},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13795867562294006},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09020507335662842},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.06542882323265076}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7504393458366394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7276565432548523},{"id":"https://openalex.org/C154290570","wikidata":"https://www.wikidata.org/wiki/Q1756768","display_name":"Co-occurrence","level":2,"score":0.6086958050727844},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4309406876564026},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41921693086624146},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41492295265197754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2761955261230469},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13795867562294006},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09020507335662842},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.06542882323265076}],"mesh":[{"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btz490","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz490","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/1/264/48981379/bioinformatics_36_1_264.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:31199464","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31199464","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:pure.atira.dk:openaire_cris_publications/eb7bccc4-2974-4c10-897b-ca2590bbe4b0","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/eb7bccc4-2974-4c10-897b-ca2590bbe4b0","pdf_url":"https://curis.ku.dk/ws/files/231245051/btz490.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"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":"Junge , A & Jensen , L J 2019 , ' CoCoScore : Context-aware co-occurrence scoring for text mining applications using distant supervision ' , Bioinformatics . https://doi.org/10.1093/bioinformatics/btz490","raw_type":"article"},{"id":"pmh:oai:europepmc.org:5915575","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6956794","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btz490","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz490","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/1/264/48981379/bioinformatics_36_1_264.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":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1076064052","display_name":null,"funder_award_id":"NNF 14CC0001","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"},{"id":"https://openalex.org/G1434448165","display_name":null,"funder_award_id":"U54 CA189205","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G1610707847","display_name":null,"funder_award_id":"U24 224370","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2925704218","display_name":"Illuminating the Druggable Genome Knowledge Management Center (IDG KMC)","funder_award_id":"3u54ca189205-02s1","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4282887365","display_name":null,"funder_award_id":"NNF14CC0001","funder_id":"https://openalex.org/F4320322436","funder_display_name":"Novo Nordisk"}],"funders":[{"id":"https://openalex.org/F4320322436","display_name":"Novo Nordisk","ror":"https://ror.org/0435rc536"},{"id":"https://openalex.org/F4320325957","display_name":"Novo Nordisk Fonden","ror":"https://ror.org/04txyc737"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950342274.pdf","grobid_xml":"https://content.openalex.org/works/W2950342274.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1700570096","https://openalex.org/W1954715867","https://openalex.org/W2010604520","https://openalex.org/W2036935277","https://openalex.org/W2053039860","https://openalex.org/W2053673723","https://openalex.org/W2071879021","https://openalex.org/W2100627415","https://openalex.org/W2105924489","https://openalex.org/W2109093071","https://openalex.org/W2124045889","https://openalex.org/W2128386749","https://openalex.org/W2136437513","https://openalex.org/W2143892076","https://openalex.org/W2165671627","https://openalex.org/W2294516783","https://openalex.org/W2315579478","https://openalex.org/W2414378847","https://openalex.org/W2484065175","https://openalex.org/W2537623931","https://openalex.org/W2537679995","https://openalex.org/W2542446037","https://openalex.org/W2542946715","https://openalex.org/W2559588208","https://openalex.org/W2594818524","https://openalex.org/W2767691613","https://openalex.org/W2786738307","https://openalex.org/W2792450944","https://openalex.org/W2792864647","https://openalex.org/W2804425727","https://openalex.org/W2808473449","https://openalex.org/W2915895751","https://openalex.org/W6653109512","https://openalex.org/W6676135976"],"related_works":["https://openalex.org/W3184801418","https://openalex.org/W1995973042","https://openalex.org/W3127151603","https://openalex.org/W1956792114","https://openalex.org/W3082925012","https://openalex.org/W2381343884","https://openalex.org/W2371808321","https://openalex.org/W2375213056","https://openalex.org/W108429584","https://openalex.org/W2134031495"],"abstract_inverted_index":{"MOTIVATION:":[0],"Information":[1],"extraction":[2,60],"by":[3],"mining":[4,159],"the":[5,34,43,63,76,124],"scientific":[6],"literature":[7],"is":[8,90,155,177],"key":[9],"to":[10,58,120,161],"uncovering":[11],"relations":[12,25],"between":[13,102],"biomedical":[14,171],"entities.":[15,88],"Most":[16],"existing":[17],"approaches":[18,38,133],"based":[19,95],"on":[20,96],"natural":[21],"language":[22],"processing":[23],"extract":[24],"from":[26],"single":[27],"sentence-level":[28],"co-mentions,":[29],"ignoring":[30],"co-occurrence":[31,55,166],"statistics":[32],"over":[33],"whole":[35],"corpus.":[36],"Existing":[37],"counting":[39],"entity":[40],"co-occurrences":[41],"ignore":[42],"textual":[44,64],"context":[45,65],"of":[46,66,78,100,104,107],"each":[47,67,83],"co-occurrence.":[48],"RESULTS:":[49],"We":[50,127],"propose":[51],"a":[52,97,109,156],"novel":[53],"corpus-wide":[54],"scoring":[56],"approach":[57],"relation":[59],"that":[61,85,129],"takes":[62],"co-mention":[68],"into":[69],"account.":[70],"Our":[71],"method,":[72],"called":[73],"CoCoScore,":[74],"scores":[75],"certainty":[77],"stating":[79],"an":[80],"association":[81],"for":[82],"sentence":[84],"co-mentions":[86,114],"two":[87],"CoCoScore":[89,130,154,176],"trained":[91],"using":[92],"distant":[93],"supervision":[94],"gold-standard":[98],"set":[99],"associations":[101,140,150,164],"entities":[103],"interest.":[105],"Instead":[106],"requiring":[108],"manually":[110],"annotated":[111],"training":[112],"corpus,":[113],"are":[115,185],"labeled":[116],"as":[117,141,143],"positives/negatives":[118],"according":[119],"their":[121],"presence/absence":[122],"in":[123,134,144,151],"gold":[125],"standard.":[126],"show":[128],"outperforms":[131],"previous":[132],"identifying":[135,145],"human":[136],"disease-gene":[137],"and":[138,147,169],"tissue-gene":[139],"well":[142],"physical":[146],"functional":[148],"protein-protein":[149],"different":[152],"species.":[153],"versatile":[157],"text":[158],"tool":[160],"uncover":[162],"pairwise":[163],"via":[165],"mining,":[167],"within":[168],"beyond":[170],"applications.":[172],"AVAILABILITY":[173],"AND":[174],"IMPLEMENTATION:":[175],"available":[178,186],"at:":[179],"https://github.com/JungeAlexander/cocoscore.":[180],"SUPPLEMENTARY":[181],"INFORMATION:":[182],"Supplementary":[183],"data":[184],"at":[187],"Bioinformatics":[188],"online.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7}],"updated_date":"2026-08-10T07:06:39.071514","created_date":"2025-10-10T00:00:00"}
