{"id":"https://openalex.org/W4379878431","doi":"https://doi.org/10.1093/bioinformatics/btad369","title":"S1000: a better taxonomic name corpus for biomedical information extraction","display_name":"S1000: a better taxonomic name corpus for biomedical information extraction","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4379878431","doi":"https://doi.org/10.1093/bioinformatics/btad369","pmid":"https://pubmed.ncbi.nlm.nih.gov/37289518"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad369","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad369","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad369/50540439/btad369.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad369/50540439/btad369.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018656314","display_name":"Jouni Luoma","orcid":"https://orcid.org/0000-0001-9286-1868"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Jouni Luoma","raw_affiliation_strings":["TurkuNLP Group, Department of Computing, University of Turku , Turku 20014, Finland"],"affiliations":[{"raw_affiliation_string":"TurkuNLP Group, Department of Computing, University of Turku , Turku 20014, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026049213","display_name":"Katerina Nastou","orcid":"https://orcid.org/0000-0003-3611-5726"},"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":false,"raw_author_name":"Katerina Nastou","raw_affiliation_strings":["Novo Nordisk Foundation Center for Protein Research, University of Copenhagen , Blegdamsvej 3 , Copenhagen 2200, Denmark"],"affiliations":[{"raw_affiliation_string":"Novo Nordisk Foundation Center for Protein Research, University of Copenhagen , Blegdamsvej 3 , Copenhagen 2200, Denmark","institution_ids":["https://openalex.org/I2801134892","https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007825608","display_name":"Tomoko Ohta","orcid":"https://orcid.org/0000-0002-9418-8352"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoko Ohta","raw_affiliation_strings":["Textimi , Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Textimi , Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037344342","display_name":"Harttu Toivonen","orcid":null},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Harttu Toivonen","raw_affiliation_strings":["TurkuNLP Group, Department of Computing, University of Turku , Turku 20014, Finland"],"affiliations":[{"raw_affiliation_string":"TurkuNLP Group, Department of Computing, University of Turku , Turku 20014, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025850900","display_name":"Evangelos Pafilis","orcid":"https://orcid.org/0000-0001-5079-0125"},"institutions":[{"id":"https://openalex.org/I4210131924","display_name":"Hellenic Centre for Marine Research","ror":"https://ror.org/038kffh84","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210131924"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Evangelos Pafilis","raw_affiliation_strings":["Hellenic Centre for Marine Research, Institute of Marine Biology, Biotechnology and Aquaculture , Heraklion 71003, Greece","Institute of Marine Biology, Biotechnology and Aquaculture, Hellenic Centre for Marine Research, Heraklion, Crete, Greece"],"affiliations":[{"raw_affiliation_string":"Hellenic Centre for Marine Research, Institute of Marine Biology, Biotechnology and Aquaculture , Heraklion 71003, Greece","institution_ids":["https://openalex.org/I4210131924"]},{"raw_affiliation_string":"Institute of Marine Biology, Biotechnology and Aquaculture, Hellenic Centre for Marine Research, Heraklion, Crete, Greece","institution_ids":["https://openalex.org/I4210131924"]}]},{"author_position":"middle","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":false,"raw_author_name":"Lars Juhl Jensen","raw_affiliation_strings":["Novo Nordisk Foundation Center for Protein Research, University of Copenhagen , Blegdamsvej 3 , Copenhagen 2200, Denmark"],"affiliations":[{"raw_affiliation_string":"Novo Nordisk Foundation Center for Protein Research, University of Copenhagen , Blegdamsvej 3 , Copenhagen 2200, Denmark","institution_ids":["https://openalex.org/I2801134892","https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066925770","display_name":"Sampo Pyysalo","orcid":"https://orcid.org/0000-0002-6279-5000"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sampo Pyysalo","raw_affiliation_strings":["TurkuNLP Group, Department of Computing, University of Turku , Turku 20014, Finland"],"affiliations":[{"raw_affiliation_string":"TurkuNLP Group, Department of Computing, University of Turku , Turku 20014, Finland","institution_ids":["https://openalex.org/I155660961"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5018656314"],"corresponding_institution_ids":["https://openalex.org/I155660961"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3888,"currency":"EUR","value_usd":4193},"fwci":2.2695,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8811961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"39","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9997000098228455,"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":0.9997000098228455,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9923999905586243,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9505000114440918,"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":0.6951606273651123},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5515678524971008},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.49821925163269043},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4731667637825012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4663248360157013},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4216597378253937},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.06331214308738708},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06056571006774902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6951606273651123},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5515678524971008},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.49821925163269043},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4731667637825012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4663248360157013},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4216597378253937},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.06331214308738708},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06056571006774902}],"mesh":[{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/btad369","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad369","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad369/50540439/btad369.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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:37289518","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37289518","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:pubmedcentral.nih.gov:10281857","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10281857","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10281857/pdf/btad369.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/ed4bbda4-eee6-4505-b272-0e7cbf0f4151","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/ed4bbda4-eee6-4505-b272-0e7cbf0f4151","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Luoma , J , Nastou , K , Ohta , T , Toivonen , H , Pafilis , E , Jensen , L J & Pyysalo , S 2023 , ' S1000 : a better taxonomic name corpus for biomedical information extraction ' , Bioinformatics , vol. 39 , no. 6 , btad369 . https://doi.org/10.1093/bioinformatics/btad369","raw_type":"article"},{"id":"pmh:oai:www.utupub.fi:10024/186590","is_oa":false,"landing_page_url":"https://www.utupub.fi/handle/10024/186590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad369","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad369","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad369/50540439/btad369.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":[{"id":"https://metadata.un.org/sdg/15","score":0.6100000143051147,"display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G1244917469","display_name":"Deep learning for next-generation biomedical text mining","funder_award_id":"332844","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G1426318481","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G251831730","display_name":null,"funder_award_id":"332844","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G2689612763","display_name":null,"funder_award_id":"Marie","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3609107129","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G3948645045","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"},{"id":"https://openalex.org/G4282887365","display_name":null,"funder_award_id":"NNF14CC0001","funder_id":"https://openalex.org/F4320322436","funder_display_name":"Novo Nordisk"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6662978750","display_name":null,"funder_award_id":"NNF14CC0001","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"},{"id":"https://openalex.org/G7031468586","display_name":null,"funder_award_id":"NNF14CC000","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8441515038","display_name":"Deep learning-based text mining for interpretation of omics data","funder_award_id":"101023676","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G996161988","display_name":null,"funder_award_id":"14CC0001","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320322436","display_name":"Novo Nordisk","ror":"https://ror.org/0435rc536"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320325957","display_name":"Novo Nordisk Fonden","ror":"https://ror.org/04txyc737"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4379878431.pdf"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2054187786","https://openalex.org/W2071879021","https://openalex.org/W2100627415","https://openalex.org/W2120754707","https://openalex.org/W2145870108","https://openalex.org/W2149369282","https://openalex.org/W2154142897","https://openalex.org/W2163107094","https://openalex.org/W2169099542","https://openalex.org/W2346452181","https://openalex.org/W2911489562","https://openalex.org/W2949176808","https://openalex.org/W3048090444","https://openalex.org/W3112376646","https://openalex.org/W3133665323","https://openalex.org/W3173561451","https://openalex.org/W4308834893"],"related_works":["https://openalex.org/W2377297411","https://openalex.org/W3148217948","https://openalex.org/W2375788636","https://openalex.org/W2358561207","https://openalex.org/W2975617233","https://openalex.org/W2388704129","https://openalex.org/W2392827053","https://openalex.org/W3188962172","https://openalex.org/W3204019825","https://openalex.org/W2368651715"],"abstract_inverted_index":{"All":[0],"resources":[1],"introduced":[2],"in":[3],"this":[4],"study":[5],"are":[6],"available":[7],"under":[8],"open":[9],"licenses":[10],"from":[11],"https://jensenlab.org/resources/s1000/.":[12],"The":[13],"webpage":[14],"contains":[15],"links":[16],"to":[17],"a":[18],"Zenodo":[19],"project":[20],"and":[21],"three":[22],"GitHub":[23],"repositories":[24],"associated":[25],"with":[26],"the":[27],"study.":[28]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
