{"id":"https://openalex.org/W3138718357","doi":"https://doi.org/10.1021/acs.jcim.0c01054","title":"Extraction of Data on Parent Compounds and Their Metabolites from Texts of Scientific Abstracts","display_name":"Extraction of Data on Parent Compounds and Their Metabolites from Texts of Scientific Abstracts","publication_year":2021,"publication_date":"2021-03-16","ids":{"openalex":"https://openalex.org/W3138718357","doi":"https://doi.org/10.1021/acs.jcim.0c01054","mag":"3138718357","pmid":"https://pubmed.ncbi.nlm.nih.gov/33724829"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.0c01054","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c01054","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/A5078075050","display_name":"Olga Tarasova","orcid":"https://orcid.org/0000-0002-3723-7832"},"institutions":[{"id":"https://openalex.org/I4210152028","display_name":"Institute of Biomedical Chemistry","ror":"https://ror.org/040wrkp27","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210110862","https://openalex.org/I4210152028"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Olga A. Tarasova","raw_affiliation_strings":["Institute of Biomedical Chemistry, Pogodinskaya Str., 10/8, Moscow 119121, Russia"],"raw_orcid":"https://orcid.org/0000-0002-3723-7832","affiliations":[{"raw_affiliation_string":"Institute of Biomedical Chemistry, Pogodinskaya Str., 10/8, Moscow 119121, Russia","institution_ids":["https://openalex.org/I4210152028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045408104","display_name":"Nadezhda Biziukova","orcid":"https://orcid.org/0000-0002-2044-1327"},"institutions":[{"id":"https://openalex.org/I4210152028","display_name":"Institute of Biomedical Chemistry","ror":"https://ror.org/040wrkp27","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210110862","https://openalex.org/I4210152028"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Nadezhda Yu. Biziukova","raw_affiliation_strings":["Institute of Biomedical Chemistry, Pogodinskaya Str., 10/8, Moscow 119121, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Biomedical Chemistry, Pogodinskaya Str., 10/8, Moscow 119121, Russia","institution_ids":["https://openalex.org/I4210152028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036658657","display_name":"Anastasia V. Rudik","orcid":"https://orcid.org/0000-0002-8916-9675"},"institutions":[{"id":"https://openalex.org/I4210152028","display_name":"Institute of Biomedical Chemistry","ror":"https://ror.org/040wrkp27","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210110862","https://openalex.org/I4210152028"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Anastassia V. Rudik","raw_affiliation_strings":["Institute of Biomedical Chemistry, Pogodinskaya Str., 10/8, Moscow 119121, Russia"],"raw_orcid":"https://orcid.org/0000-0002-8916-9675","affiliations":[{"raw_affiliation_string":"Institute of Biomedical Chemistry, Pogodinskaya Str., 10/8, Moscow 119121, Russia","institution_ids":["https://openalex.org/I4210152028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021812000","display_name":"Alexander V. Dmitriev","orcid":"https://orcid.org/0000-0002-2431-3429"},"institutions":[{"id":"https://openalex.org/I4210152028","display_name":"Institute of Biomedical Chemistry","ror":"https://ror.org/040wrkp27","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210110862","https://openalex.org/I4210152028"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexander V. Dmitriev","raw_affiliation_strings":["Institute of Biomedical Chemistry, Pogodinskaya Str., 10/8, Moscow 119121, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Biomedical Chemistry, Pogodinskaya Str., 10/8, Moscow 119121, Russia","institution_ids":["https://openalex.org/I4210152028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050528382","display_name":"Dmitry Filimonov","orcid":"https://orcid.org/0000-0002-0339-8478"},"institutions":[{"id":"https://openalex.org/I4210152028","display_name":"Institute of Biomedical Chemistry","ror":"https://ror.org/040wrkp27","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210110862","https://openalex.org/I4210152028"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitry A. Filimonov","raw_affiliation_strings":["Institute of Biomedical Chemistry, Pogodinskaya Str., 10/8, Moscow 119121, Russia"],"raw_orcid":"https://orcid.org/0000-0002-0339-8478","affiliations":[{"raw_affiliation_string":"Institute of Biomedical Chemistry, Pogodinskaya Str., 10/8, Moscow 119121, Russia","institution_ids":["https://openalex.org/I4210152028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029121475","display_name":"Vladimir Poroikov","orcid":"https://orcid.org/0000-0001-7937-2621"},"institutions":[{"id":"https://openalex.org/I4210152028","display_name":"Institute of Biomedical Chemistry","ror":"https://ror.org/040wrkp27","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210110862","https://openalex.org/I4210152028"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Vladimir V. Poroikov","raw_affiliation_strings":["Institute of Biomedical Chemistry, Pogodinskaya Str., 10/8, Moscow 119121, Russia"],"raw_orcid":"https://orcid.org/0000-0001-7937-2621","affiliations":[{"raw_affiliation_string":"Institute of Biomedical Chemistry, Pogodinskaya Str., 10/8, Moscow 119121, Russia","institution_ids":["https://openalex.org/I4210152028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5078075050"],"corresponding_institution_ids":["https://openalex.org/I4210152028"],"apc_list":null,"apc_paid":null,"fwci":0.6508,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.66278667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"61","issue":"4","first_page":"1683","last_page":"1690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9986000061035156,"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":0.9986000061035156,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9919999837875366,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9690999984741211,"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":0.5975693464279175},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.563330352306366},{"id":"https://openalex.org/keywords/chemical-nomenclature","display_name":"Chemical nomenclature","score":0.5306341052055359},{"id":"https://openalex.org/keywords/chemical-similarity","display_name":"Chemical similarity","score":0.5038718581199646},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4780074656009674},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47585245966911316},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3619083762168884},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3418843746185303},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.33038511872291565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23198089003562927},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1650385856628418},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.10736051201820374},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.10084441304206848}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5975693464279175},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.563330352306366},{"id":"https://openalex.org/C125832229","wikidata":"https://www.wikidata.org/wiki/Q6503924","display_name":"Chemical nomenclature","level":2,"score":0.5306341052055359},{"id":"https://openalex.org/C24259465","wikidata":"https://www.wikidata.org/wiki/Q2272153","display_name":"Chemical similarity","level":3,"score":0.5038718581199646},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4780074656009674},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47585245966911316},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3619083762168884},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3418843746185303},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.33038511872291565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23198089003562927},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1650385856628418},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.10736051201820374},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.10084441304206848},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","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":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.0c01054","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c01054","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:33724829","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33724829","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":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G549206480","display_name":null,"funder_award_id":"19 15 00396","funder_id":"https://openalex.org/F4320324099","funder_display_name":"Russian Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320324099","display_name":"Russian Science Foundation","ror":"https://ror.org/03y2gwe85"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2009660063","https://openalex.org/W2033237963","https://openalex.org/W2092489937","https://openalex.org/W2147469877","https://openalex.org/W2149369282","https://openalex.org/W2160022416","https://openalex.org/W2165671627","https://openalex.org/W2482589566","https://openalex.org/W2523785361","https://openalex.org/W2557491692","https://openalex.org/W2610394652","https://openalex.org/W2619954869","https://openalex.org/W2737498716","https://openalex.org/W2769387903","https://openalex.org/W2771333655","https://openalex.org/W2781993106","https://openalex.org/W2800079696","https://openalex.org/W2911871734","https://openalex.org/W2912105929","https://openalex.org/W2964864162","https://openalex.org/W2969999569","https://openalex.org/W2995830828","https://openalex.org/W3006948250","https://openalex.org/W3020388671","https://openalex.org/W3034826648","https://openalex.org/W3038818907","https://openalex.org/W3042438073","https://openalex.org/W3083145286","https://openalex.org/W3090556797","https://openalex.org/W4313371821"],"related_works":["https://openalex.org/W4292296636","https://openalex.org/W1987966112","https://openalex.org/W2384995271","https://openalex.org/W2412446857","https://openalex.org/W2090768198","https://openalex.org/W1576126133","https://openalex.org/W4249871115","https://openalex.org/W22579956","https://openalex.org/W630734576","https://openalex.org/W2482675266"],"abstract_inverted_index":{"The":[0,33],"growing":[1],"amount":[2],"of":[3,11,15,17,27,29,43,61,65,74,83,89,104,118,121,148,153,161,168,178,185,189,203,207,218,240,253,263,274,276,279,288],"experimental":[4],"data":[5,34,52,75,85],"on":[6,53,76,86,165,211,250],"chemical":[7,66,90,179,224],"objects":[8],"includes":[9],"properties":[10,56,78],"small":[12],"molecules,":[13],"results":[14],"studies":[16],"their":[18,77,95,108,125,157,194,244],"interaction":[19],"with":[20,267],"human":[21],"and":[22,25,50,57,107,124,156,193,221,243,286],"animal":[23],"proteins,":[24],"methods":[26],"synthesis":[28],"organic":[30],"compounds":[31,67,91,106,123,155,220,242],"(OCs).":[32],"obtained":[35],"can":[36,98],"be":[37],"used":[38,232],"to":[39,70,236,282],"identify":[40],"the":[41,54,72,84,87,101,119,128,146,149,166,169,176,197,201,205,228,238,247,251,272,277,283],"names":[42,64,88,120,206,217,239,278],"OCs":[44],"automatically,":[45],"including":[46],"all":[47,222],"possible":[48,96],"synonyms":[49],"relevant":[51],"molecular":[55],"biological":[58,102],"activity.":[59],"Utilization":[60],"different":[62],"synonymic":[63],"allows":[68],"researchers":[69],"increase":[71,271],"completeness":[73],"available":[79],"from":[80,127,159,246],"publications.":[81,163],"Enrichment":[82],"by":[92],"information":[93],"about":[94],"metabolites":[97,109,126,158,195,209,245,280],"help":[99],"estimate":[100],"effects":[103],"parent":[105,122,154,190,219,241],"more":[110],"thoroughly.":[111],"Therefore,":[112],"an":[113],"attempt":[114],"at":[115,140],"automated":[116],"extraction":[117,147],"texts":[129,248,254],"is":[130],"a":[131,142,183,289],"rather":[132],"important":[133],"task.":[134],"In":[135],"our":[136],"study,":[137],"we":[138,174,231],"aimed":[139],"developing":[141],"method":[143],"that":[144,261],"provides":[145],"named":[150],"entities":[151],"(NEs)":[152],"abstracts":[160],"scientific":[162],"Based":[164],"application":[167,287],"conditional":[170,233],"random":[171,234,293],"fields'":[172],"algorithm,":[173],"extracted":[175],"NEs":[177,192,225],"compounds.":[180],"We":[181,199],"developed":[182],"set":[184],"rules":[186,264],"allowing":[187],"identification":[188],"compound":[191],"in":[196,227,265],"texts.":[198],"evaluated":[200],"possibility":[202],"extracting":[204],"potential":[208],"based":[210,249],"cosine":[212,268],"similarity":[213,269],"between":[214],"strings":[215],"representing":[216],"other":[223],"found":[226],"text.":[229],"Additionally,":[230],"fields":[235],"fetch":[237],"corpus":[252],"labeled":[255],"manually.":[256],"Our":[257],"computational":[258],"experiments":[259],"showed":[260],"usage":[262],"combination":[266],"could":[270],"accuracy":[273],"recognition":[275],"compared":[281],"rule-based":[284],"algorithm":[285,291],"machine-learning":[290],"(conditional":[292],"fields).":[294]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}