{"id":"https://openalex.org/W4306696320","doi":"https://doi.org/10.1186/s13040-022-00311-z","title":"Expanding a database-derived biomedical knowledge graph via multi-relation extraction from biomedical abstracts","display_name":"Expanding a database-derived biomedical knowledge graph via multi-relation extraction from biomedical abstracts","publication_year":2022,"publication_date":"2022-10-18","ids":{"openalex":"https://openalex.org/W4306696320","doi":"https://doi.org/10.1186/s13040-022-00311-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/36258252"},"language":"en","primary_location":{"id":"doi:10.1186/s13040-022-00311-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-022-00311-z","pdf_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-022-00311-z","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-022-00311-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085139756","display_name":"David N. Nicholson","orcid":"https://orcid.org/0000-0003-0002-5761"},"institutions":[{"id":"https://openalex.org/I4210125521","display_name":"Translational Therapeutics (United States)","ror":"https://ror.org/02z3rcy16","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125521"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David N. Nicholson","raw_affiliation_strings":["Department of Systems Pharmacology and Translational Therapeutics, University of Pennsylvania, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0002-5761","affiliations":[{"raw_affiliation_string":"Department of Systems Pharmacology and Translational Therapeutics, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I4210125521","https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043439179","display_name":"Daniel Himmelstein","orcid":"https://orcid.org/0000-0002-3012-7446"},"institutions":[{"id":"https://openalex.org/I4210125521","display_name":"Translational Therapeutics (United States)","ror":"https://ror.org/02z3rcy16","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125521"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel S. Himmelstein","raw_affiliation_strings":["Department of Systems Pharmacology and Translational Therapeutics, University of Pennsylvania, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3012-7446","affiliations":[{"raw_affiliation_string":"Department of Systems Pharmacology and Translational Therapeutics, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I4210125521","https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050692257","display_name":"Casey S. Greene","orcid":"https://orcid.org/0000-0001-8713-9213"},"institutions":[{"id":"https://openalex.org/I51713134","display_name":"University of Colorado Anschutz Medical Campus","ror":"https://ror.org/03wmf1y16","country_code":"US","type":"education","lineage":["https://openalex.org/I51713134"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Casey S. Greene","raw_affiliation_strings":["Department of Biomedical Informatics, University of Colorado School of Medicine and Center for Health Artificial Intellegence (CHAI), University of Colorado School of Medicine, Aurora, USA. casey.s.greene@cuanschutz.edu","Department of Biomedical Informatics, University of Colorado School of Medicine and Center for Health Artificial Intellegence (CHAI), University of Colorado School of Medicine, Aurora, USA"],"raw_orcid":"https://orcid.org/0000-0001-8713-9213","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, University of Colorado School of Medicine and Center for Health Artificial Intellegence (CHAI), University of Colorado School of Medicine, Aurora, USA. casey.s.greene@cuanschutz.edu","institution_ids":["https://openalex.org/I51713134"]},{"raw_affiliation_string":"Department of Biomedical Informatics, University of Colorado School of Medicine and Center for Health Artificial Intellegence (CHAI), University of Colorado School of Medicine, Aurora, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050692257"],"corresponding_institution_ids":["https://openalex.org/I51713134"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.8662,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.71628437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"15","issue":"1","first_page":"26","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9733999967575073,"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":0.9733999967575073,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.007899999618530273,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.004100000020116568,"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/computer-science","display_name":"Computer science","score":0.7291488647460938},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5638599395751953},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5361383557319641},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.5235737562179565},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5114694833755493},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5023937225341797},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49788665771484375},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.44695836305618286},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33358845114707947},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1893487274646759}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7291488647460938},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5638599395751953},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5361383557319641},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.5235737562179565},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5114694833755493},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5023937225341797},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49788665771484375},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.44695836305618286},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33358845114707947},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1893487274646759}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13040-022-00311-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-022-00311-z","pdf_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-022-00311-z","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},{"id":"pmid:36258252","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36258252","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":"BioData mining","raw_type":null},{"id":"pmh:oai:doaj.org/article:f823aa1e03e042cdb425499dfda9e19d","is_oa":true,"landing_page_url":"https://doaj.org/article/f823aa1e03e042cdb425499dfda9e19d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Mining, Vol 15, Iss 1, Pp 1-15 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9578183","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9578183","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":"BioData Min","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13040-022-00311-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-022-00311-z","pdf_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-022-00311-z","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1729374867","display_name":null,"funder_award_id":"R01 HG010067","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G2769988617","display_name":null,"funder_award_id":"GBMF 4552","funder_id":"https://openalex.org/F4320306202","funder_display_name":"Gordon and Betty Moore Foundation"},{"id":"https://openalex.org/G3616542314","display_name":null,"funder_award_id":"HG010067","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G7614424270","display_name":null,"funder_award_id":"GBMF4552","funder_id":"https://openalex.org/F4320306202","funder_display_name":"Gordon and Betty Moore Foundation"}],"funders":[{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306696320.pdf","grobid_xml":"https://content.openalex.org/works/W4306696320.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1473718842","https://openalex.org/W1610821757","https://openalex.org/W1700570096","https://openalex.org/W1850865022","https://openalex.org/W1907286193","https://openalex.org/W1986657538","https://openalex.org/W1988428986","https://openalex.org/W2022484638","https://openalex.org/W2029017735","https://openalex.org/W2030531674","https://openalex.org/W2033853342","https://openalex.org/W2041053370","https://openalex.org/W2052217781","https://openalex.org/W2053039860","https://openalex.org/W2076063813","https://openalex.org/W2081375228","https://openalex.org/W2097960255","https://openalex.org/W2098679902","https://openalex.org/W2104070133","https://openalex.org/W2107598941","https://openalex.org/W2115746733","https://openalex.org/W2116702276","https://openalex.org/W2121570534","https://openalex.org/W2121844933","https://openalex.org/W2136437513","https://openalex.org/W2148130205","https://openalex.org/W2166474856","https://openalex.org/W2208994311","https://openalex.org/W2346452181","https://openalex.org/W2395579298","https://openalex.org/W2414378847","https://openalex.org/W2512727383","https://openalex.org/W2559028527","https://openalex.org/W2619954869","https://openalex.org/W2752636837","https://openalex.org/W2766208765","https://openalex.org/W2767891136","https://openalex.org/W2786693834","https://openalex.org/W2790711259","https://openalex.org/W2804236178","https://openalex.org/W2809349863","https://openalex.org/W2884668708","https://openalex.org/W2885403013","https://openalex.org/W2895889524","https://openalex.org/W2897752557","https://openalex.org/W2901653629","https://openalex.org/W2911489562","https://openalex.org/W2919939141","https://openalex.org/W2946690328","https://openalex.org/W2947858052","https://openalex.org/W2949311246","https://openalex.org/W2950342274","https://openalex.org/W2959716049","https://openalex.org/W2962915384","https://openalex.org/W2964242047","https://openalex.org/W2979826702","https://openalex.org/W3098012550","https://openalex.org/W4235216760"],"related_works":["https://openalex.org/W2976808399","https://openalex.org/W2609844752","https://openalex.org/W4392969631","https://openalex.org/W4285246823","https://openalex.org/W4226278302","https://openalex.org/W4221160509","https://openalex.org/W2547211086","https://openalex.org/W2538200646","https://openalex.org/W1968988659","https://openalex.org/W2888033806"],"abstract_inverted_index":{"BACKGROUND:":[0],"Knowledge":[1],"graphs":[2,352],"support":[3],"biomedical":[4,12,155,209,350],"research":[5],"efforts":[6],"by":[7,52,119],"providing":[8],"contextual":[9],"information":[10],"for":[11,282],"entities,":[13],"constructing":[14],"networks,":[15],"and":[16,58,83,104,136,145,176,211,223,253,260],"supporting":[17],"the":[18,114,214,266,278,337],"interpretation":[19],"of":[20,153,216,263,291,340],"high-throughput":[21],"analyses.":[22],"These":[23],"databases":[24,54],"are":[25,65],"populated":[26],"via":[27],"manual":[28,50],"curation,":[29],"which":[30,64,255],"is":[31,43,84],"challenging":[32],"to":[33,68,112,140,182,203,225,249,289,348],"scale":[34],"with":[35,55,101,315,353],"an":[36],"exponentially":[37],"rising":[38],"publication":[39],"rate.":[40],"Data":[41],"programming":[42],"a":[44,75,85,98,159,168,179,200,208],"paradigm":[45],"that":[46,88,171,206,219,230,301,336,356],"circumvents":[47],"this":[48,250,302,341],"arduous":[49],"process":[51,118],"combining":[53],"simple":[56],"rules":[57],"heuristics":[59],"written":[60],"as":[61],"label":[62,77,115,122,174,190,233,242,316,322],"functions,":[63],"programs":[66],"designed":[67],"annotate":[69],"textual":[70],"data":[71],"automatically.":[72],"Unfortunately,":[73],"writing":[74],"useful":[76],"function":[78,116,191,317],"requires":[79],"substantial":[80],"error":[81],"analysis":[82],"nontrivial":[86],"task":[87],"takes":[89],"multiple":[90,102,128],"days":[91],"per":[92],"function.":[93],"This":[94],"bottleneck":[95],"makes":[96],"populating":[97,349],"knowledge":[99,162,311,351],"graph":[100],"nodes":[103],"edge":[105,129,217,284,327],"types":[106,218,328],"practically":[107],"infeasible.":[108],"Thus,":[109],"we":[110,198,286],"sought":[111],"accelerate":[113],"creation":[117],"evaluating":[120],"how":[121,184],"functions":[123,175,234,243,323],"can":[124,304],"be":[125,221],"re-used":[126],"across":[127],"types.":[130],"RESULTS:":[131],"We":[132,148,166,228,334],"obtained":[133],"entity-tagged":[134],"abstracts":[135],"subsetted":[137],"these":[138,357],"entities":[139,156],"only":[141],"contain":[142],"compounds,":[143],"genes,":[144],"disease":[146],"mentions.":[147],"extracted":[149],"sentences":[150,205],"containing":[151],"co-mentions":[152],"certain":[154],"contained":[157],"in":[158],"previously":[160],"described":[161],"graph,":[163],"Hetionet":[164,226,295],"v1.":[165,227,296],"trained":[167,199],"baseline":[169],"model":[170,202,270,281],"used":[172,178],"database-only":[173],"then":[177,212],"sampling":[180],"approach":[181],"measure":[183],"well":[185],"adding":[186,231],"edge-specific":[187,241],"or":[188],"edge-mismatch":[189,232],"combinations":[192],"improved":[193,236,330],"over":[194],"our":[195,309],"baseline.":[196],"Next,":[197],"discriminator":[201],"detect":[204],"indicated":[207,257],"relationship":[210,237],"estimated":[213],"number":[215],"could":[220],"recalled":[222,287],"added":[224],"found":[229],"rarely":[235],"extraction,":[238],"while":[239],"control":[240],"did.":[244],"There":[245],"were":[246,319],"two":[247],"exceptions":[248],"trend,":[251],"Compound-binds-Gene":[252],"Gene-interacts-Gene,":[254],"both":[256],"physical":[258],"relationships":[259],"showed":[261],"signs":[262],"transferability.":[264],"Across":[265],"scenarios":[267],"tested,":[268],"discriminative":[269,280],"performance":[271,331],"strongly":[272],"depends":[273],"on":[274],"generated":[275],"annotations.":[276],"Using":[277],"best":[279],"each":[283],"type,":[285],"close":[288],"30%":[290],"established":[292],"edges":[293,307],"within":[294],"CONCLUSIONS:":[297],"Our":[298],"results":[299,314],"show":[300],"framework":[303],"incorporate":[305],"novel":[306],"into":[308],"source":[310],"graph.":[312],"However,":[313],"transfer":[318],"mixed.":[320],"Only":[321],"describing":[324],"very":[325],"similar":[326],"supported":[329],"when":[332],"transferred.":[333],"expect":[335],"continued":[338],"development":[339],"strategy":[342],"may":[343],"provide":[344],"essential":[345],"building":[346],"blocks":[347],"discoveries,":[354],"ensuring":[355],"resources":[358],"include":[359],"cutting-edge":[360],"results.":[361]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}