{"id":"https://openalex.org/W2028578434","doi":"https://doi.org/10.1021/ci800332w","title":"Extraction of CYP Chemical Interactions from Biomedical Literature Using Natural Language Processing Methods","display_name":"Extraction of CYP Chemical Interactions from Biomedical Literature Using Natural Language Processing Methods","publication_year":2009,"publication_date":"2009-01-21","ids":{"openalex":"https://openalex.org/W2028578434","doi":"https://doi.org/10.1021/ci800332w","mag":"2028578434","pmid":"https://pubmed.ncbi.nlm.nih.gov/19434828"},"language":"en","primary_location":{"id":"doi:10.1021/ci800332w","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci800332w","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","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/A5009869574","display_name":"Dazhi Jiao","orcid":"https://orcid.org/0000-0001-5052-3836"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dazhi Jiao","raw_affiliation_strings":["Indiana University School of Informatics, Bloomington, Indiana, 47408","Indiana University School of Informatics, Bloomington, Indiana 47408, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University School of Informatics, Bloomington, Indiana, 47408","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Indiana University School of Informatics, Bloomington, Indiana 47408, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002092202","display_name":"David Wild","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David J. Wild","raw_affiliation_strings":["Indiana University School of Informatics, Bloomington, Indiana, 47408"],"affiliations":[{"raw_affiliation_string":"Indiana University School of Informatics, Bloomington, Indiana, 47408","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009869574"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":1.4435,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.80610811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"49","issue":"2","first_page":"263","last_page":"269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9782999753952026,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9710000157356262,"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":0.8715194463729858},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7491157054901123},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6993927955627441},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6980772018432617},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.6926397085189819},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5638377070426941},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5622342228889465},{"id":"https://openalex.org/keywords/dependency-grammar","display_name":"Dependency grammar","score":0.560228705406189},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.52793288230896},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5091411471366882},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48503464460372925},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4752887487411499},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11190852522850037},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.09757179021835327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8715194463729858},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7491157054901123},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6993927955627441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6980772018432617},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.6926397085189819},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5638377070426941},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5622342228889465},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.560228705406189},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.52793288230896},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5091411471366882},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48503464460372925},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4752887487411499},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11190852522850037},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.09757179021835327},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D003577","descriptor_name":"Cytochrome P-450 Enzyme System","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D003577","descriptor_name":"Cytochrome P-450 Enzyme System","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D003577","descriptor_name":"Cytochrome P-450 Enzyme System","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci800332w","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci800332w","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:19434828","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19434828","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":"Journal of chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1524134026","https://openalex.org/W1568793342","https://openalex.org/W1574901103","https://openalex.org/W1648311451","https://openalex.org/W1773803948","https://openalex.org/W1850865022","https://openalex.org/W2005058680","https://openalex.org/W2010241890","https://openalex.org/W2027903554","https://openalex.org/W2048140075","https://openalex.org/W2096765155","https://openalex.org/W2097100227","https://openalex.org/W2109070394","https://openalex.org/W2109711517","https://openalex.org/W2112670696","https://openalex.org/W2117488115","https://openalex.org/W2120433106","https://openalex.org/W2120814856","https://openalex.org/W2141274067","https://openalex.org/W2149803936","https://openalex.org/W2156697464","https://openalex.org/W2158425599","https://openalex.org/W2158796363","https://openalex.org/W3135507221"],"related_works":["https://openalex.org/W4385484560","https://openalex.org/W2334378031","https://openalex.org/W842810586","https://openalex.org/W2916255597","https://openalex.org/W3095980030","https://openalex.org/W4319940250","https://openalex.org/W2352298027","https://openalex.org/W2092919065","https://openalex.org/W3138801416","https://openalex.org/W4379379356"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,31,117],"system":[4,51,95,114,151],"that":[5],"automatically":[6],"extracts":[7],"CYP":[8],"protein":[9],"and":[10,22,42,53,66,88,109,132,135,145,147,154],"chemical":[11],"interactions":[12],"from":[13,39,128],"journal":[14],"article":[15],"abstracts,":[16],"using":[17,37],"natural":[18],"language":[19],"processing":[20],"(NLP)":[21],"text":[23],"mining":[24],"methods.":[25],"In":[26],"our":[27,50,61,73,113],"system,":[28,74],"we":[29],"employ":[30],"maximum":[32],"entropy":[33],"based":[34,64],"learning":[35,63],"method,":[36],"results":[38],"syntactic,":[40],"semantic,":[41],"lexical":[43],"analysis":[44],"of":[45,78,93,121,138],"texts.":[46],"We":[47],"first":[48],"present":[49],"architecture":[52],"then":[54],"discuss":[55],"the":[56,67,94,99,133,136,139,149],"data":[57],"set":[58],"for":[59,148],"training":[60],"machine":[62],"models":[65],"methods":[68],"in":[69,72,112],"building":[70],"components":[71,111],"such":[75],"as":[76,123],"part":[77],"speech":[79],"(POS)":[80],"tagging,":[81],"Named":[82],"Entity":[83],"Recognition":[84],"(NER),":[85],"dependency":[86,107],"parsing,":[87,108],"relation":[89],"extraction.":[90],"An":[91],"evaluation":[92],"is":[96],"conducted":[97],"at":[98],"end,":[100],"yielding":[101],"very":[102,118],"promising":[103],"results:":[104],"The":[105],"POS,":[106],"NER":[110],"have":[115],"achieved":[116],"high":[119],"level":[120],"accuracy":[122],"measured":[124],"by":[125],"precision,":[126],"ranging":[127],"85.9%":[129],"to":[130],"98.5%,":[131],"precision":[134],"recall":[137],"interaction":[140],"extraction":[141],"component":[142],"are":[143,152],"76.0%":[144],"82.6%,":[146],"overall":[150],"68.4%":[153],"72.2%,":[155],"respectively.":[156]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}