{"id":"https://openalex.org/W7117358510","doi":"https://doi.org/10.1093/bioinformatics/btaf685","title":"Integrating curation into scientific publishing to train AI models","display_name":"Integrating curation into scientific publishing to train AI models","publication_year":2025,"publication_date":"2025-12-27","ids":{"openalex":"https://openalex.org/W7117358510","doi":"https://doi.org/10.1093/bioinformatics/btaf685","pmid":"https://pubmed.ncbi.nlm.nih.gov/41455082"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf685","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf685","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf685/66140480/btaf685.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/btaf685/66140480/btaf685.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058921480","display_name":"J. Abreu-Vicente","orcid":"https://orcid.org/0000-0002-0211-6416"},"institutions":[{"id":"https://openalex.org/I1303691731","display_name":"European Molecular Biology Organization","ror":"https://ror.org/04wfr2810","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I1303691731"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jorge Abreu-Vicente","raw_affiliation_strings":["EMBO , Heidelberg 69117,"],"affiliations":[{"raw_affiliation_string":"EMBO , Heidelberg 69117,","institution_ids":["https://openalex.org/I1303691731"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029119505","display_name":"Hannah Sonntag","orcid":"https://orcid.org/0000-0001-5461-3265"},"institutions":[{"id":"https://openalex.org/I1303691731","display_name":"European Molecular Biology Organization","ror":"https://ror.org/04wfr2810","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I1303691731"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hannah Sonntag","raw_affiliation_strings":["EMBO , Heidelberg 69117,"],"affiliations":[{"raw_affiliation_string":"EMBO , Heidelberg 69117,","institution_ids":["https://openalex.org/I1303691731"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121401202","display_name":"Thomas Eidens","orcid":null},"institutions":[{"id":"https://openalex.org/I1303691731","display_name":"European Molecular Biology Organization","ror":"https://ror.org/04wfr2810","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I1303691731"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Eidens","raw_affiliation_strings":["EMBO , Heidelberg 69117,"],"affiliations":[{"raw_affiliation_string":"EMBO , Heidelberg 69117,","institution_ids":["https://openalex.org/I1303691731"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011455956","display_name":"Cassie S. Mitchell","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cassie S Mitchell","raw_affiliation_strings":["Department of Biomedical Engineering, Georgia Institute of Technology and Emory University School of Medicine , Atlanta, GA 30332,"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, Georgia Institute of Technology and Emory University School of Medicine , Atlanta, GA 30332,","institution_ids":["https://openalex.org/I150468666","https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020988596","display_name":"Thomas Lemberger","orcid":"https://orcid.org/0000-0002-2499-4025"},"institutions":[{"id":"https://openalex.org/I1303691731","display_name":"European Molecular Biology Organization","ror":"https://ror.org/04wfr2810","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I1303691731"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Lemberger","raw_affiliation_strings":["EMBO , Heidelberg 69117,"],"affiliations":[{"raw_affiliation_string":"EMBO , Heidelberg 69117,","institution_ids":["https://openalex.org/I1303691731"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058921480"],"corresponding_institution_ids":["https://openalex.org/I1303691731"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65084944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"1","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":0.6025999784469604,"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":0.6025999784469604,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.16769999265670776,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.02539999969303608,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5263000130653381},{"id":"https://openalex.org/keywords/publishing","display_name":"Publishing","score":0.4422999918460846},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.43639999628067017},{"id":"https://openalex.org/keywords/scientific-publishing","display_name":"Scientific publishing","score":0.39430001378059387},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7026000022888184},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5263000130653381},{"id":"https://openalex.org/C151719136","wikidata":"https://www.wikidata.org/wiki/Q3972943","display_name":"Publishing","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4187000095844269},{"id":"https://openalex.org/C2984423262","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific publishing","level":3,"score":0.39430001378059387},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33239999413490295},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2840999960899353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C2988963302","wikidata":"https://www.wikidata.org/wiki/Q629206","display_name":"Program code","level":2,"score":0.26339998841285706}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011643","descriptor_name":"Publishing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011643","descriptor_name":"Publishing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011643","descriptor_name":"Publishing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011643","descriptor_name":"Publishing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011643","descriptor_name":"Publishing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011643","descriptor_name":"Publishing","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":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaf685","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf685","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf685/66140480/btaf685.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:41455082","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41455082","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:12836429","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12836429/","pdf_url":null,"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"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaf685","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf685","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf685/66140480/btaf685.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/4","display_name":"Quality Education","score":0.6676077842712402}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7117358510.pdf","grobid_xml":"https://content.openalex.org/works/W7117358510.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1984293430","https://openalex.org/W2071038402","https://openalex.org/W2113142309","https://openalex.org/W2123579157","https://openalex.org/W2149069010","https://openalex.org/W2162965868","https://openalex.org/W2163918411","https://openalex.org/W2302501749","https://openalex.org/W2346452181","https://openalex.org/W2946690328","https://openalex.org/W2952465807","https://openalex.org/W2973059055","https://openalex.org/W3028004046","https://openalex.org/W3034917217","https://openalex.org/W3046375318","https://openalex.org/W3082330004","https://openalex.org/W3109524385","https://openalex.org/W3179500067","https://openalex.org/W4226154421","https://openalex.org/W4283318325","https://openalex.org/W4387780829"],"related_works":[],"abstract_inverted_index":{"Trained":[0],"models":[1],"are":[2,11],"available":[3,12],"at":[4,13],"https://huggingface.co/EMBO.":[5],"The":[6],"SourceData-NLP":[7],"dataset":[8],"and":[9,16],"code":[10],"https://github.com/source-data/soda-data,":[14],"https://github.com/source-data/soda-model,":[15],"https://github.com/source-data/soda_image_segmentation.":[17]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-12-27T00:00:00"}
