{"id":"https://openalex.org/W4402901255","doi":"https://doi.org/10.1038/s41597-024-03841-9","title":"Dataset from a human-in-the-loop approach to identify functionally important protein residues from literature","display_name":"Dataset from a human-in-the-loop approach to identify functionally important protein residues from literature","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402901255","doi":"https://doi.org/10.1038/s41597-024-03841-9","pmid":"https://pubmed.ncbi.nlm.nih.gov/39333508","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/11436914"},"language":"en","primary_location":{"id":"doi:10.1038/s41597-024-03841-9","doi":"https://doi.org/10.1038/s41597-024-03841-9","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41597-024-03841-9","pdf_url":"https://www.nature.com/articles/s41597-024-03841-9.pdf","source":{"id":"https://openalex.org/S2607323502","display_name":"Scientific Data","issn_l":"2052-4463","issn":["2052-4463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-b","jufo-1","ki-jl-1","medline","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"Scientific Data","raw_type":"journal-article"},"volume":null,"type":"data-paper","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41597-024-03841-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126113637","display_name":"Melanie Vollmar","orcid":"https://orcid.org/0000-0002-9162-9159","observed_orcids":["https://orcid.org/0000-0002-9162-9159"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Melanie Vollmar","raw_affiliation_strings":["Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK. melaniev@ebi.ac.uk"],"raw_orcid":"https://orcid.org/0000-0002-9162-9159","affiliations":[{"raw_affiliation_string":"Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK. melaniev@ebi.ac.uk","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013246415","display_name":"Santosh Tirunagari","orcid":"https://orcid.org/0000-0002-9064-1965","observed_orcids":["https://orcid.org/0000-0002-9064-1965"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Santosh Tirunagari","raw_affiliation_strings":["Literature Services, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Literature Services, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074638543","display_name":"D\u00e9borah Harrus","orcid":"https://orcid.org/0000-0002-7651-672X","observed_orcids":["https://orcid.org/0000-0002-7651-672X"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Deborah Harrus","raw_affiliation_strings":["Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015459016","display_name":"David R. Armstrong","orcid":"https://orcid.org/0000-0002-4986-1229","observed_orcids":["https://orcid.org/0000-0002-4986-1229"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Armstrong","raw_affiliation_strings":["Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK"],"raw_orcid":"https://orcid.org/0000-0002-4986-1229","affiliations":[{"raw_affiliation_string":"Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049223954","display_name":"Romana G\u00e1borov\u00e1","orcid":"https://orcid.org/0009-0009-5900-9513","observed_orcids":["https://orcid.org/0009-0009-5900-9513"]},"institutions":[{"id":"https://openalex.org/I4210090417","display_name":"Central European Institute of Technology \u2013 Masaryk University","ror":"https://ror.org/009nz6031","country_code":"CZ","type":"education","lineage":["https://openalex.org/I1310815967","https://openalex.org/I21449261","https://openalex.org/I4210090417"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Romana G\u00e1borov\u00e1","raw_affiliation_strings":["CEITEC - Central European Institute of Technology, Masaryk University, Kamenice 5, 62500, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CEITEC - Central European Institute of Technology, Masaryk University, Kamenice 5, 62500, Brno, Czech Republic","institution_ids":["https://openalex.org/I4210090417"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072651997","display_name":"Deepti Sood Gupta","orcid":"https://orcid.org/0000-0001-9999-5607","observed_orcids":["https://orcid.org/0000-0001-9999-5607"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Deepti Gupta","raw_affiliation_strings":["Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057489258","display_name":"Marcelo Querino Lima Afonso","orcid":"https://orcid.org/0000-0002-9966-8187","observed_orcids":["https://orcid.org/0000-0002-9966-8187"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marcelo Querino Lima Afonso","raw_affiliation_strings":["Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003934048","display_name":"Genevieve L. Evans","orcid":"https://orcid.org/0000-0002-8612-9539","observed_orcids":["https://orcid.org/0000-0002-8612-9539"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Genevieve Evans","raw_affiliation_strings":["Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042460017","display_name":"Sameer S Velankar","orcid":"https://orcid.org/0000-0002-8439-5964","observed_orcids":["https://orcid.org/0000-0002-8439-5964"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sameer Velankar","raw_affiliation_strings":["Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK"],"raw_orcid":"https://orcid.org/0000-0002-8439-5964","affiliations":[{"raw_affiliation_string":"Protein Data Bank in Europe, European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5126113637"],"corresponding_institution_ids":["https://openalex.org/I1303153112"],"apc_list":{"value":2290,"currency":"USD","value_usd":2290},"apc_paid":{"value":2290,"currency":"USD","value_usd":2290},"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"1","first_page":"1032","last_page":"1032"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9940999746322632,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9940999746322632,"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"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.003800000064074993,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/protein-function-annotation","display_name":"protein annotation","score":0.6079999804496765},{"id":"https://openalex.org/keywords/human-in-the-loop-annotation","display_name":"human-in-the-loop annotation","score":0.8980000019073486},{"id":"https://openalex.org/keywords/literature-curation","display_name":"literature curation","score":0.7039999961853027},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.8989999890327454},{"id":"https://openalex.org/keywords/protein-structure-features","display_name":"protein structure features","score":0.847000002861023},{"id":"https://openalex.org/keywords/pubmedbert","display_name":"PubMedBERT","score":0.6840000152587891},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"protein function prediction","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.771309494972229},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7588962912559509},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.7041996717453003},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.662025511264801},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4687654674053192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4612921476364136},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4555146098136902},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41005223989486694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3710985779762268},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08390972018241882},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[{"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1038/s41597-024-03841-9","doi":"https://doi.org/10.1038/s41597-024-03841-9","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41597-024-03841-9","pdf_url":"https://www.nature.com/articles/s41597-024-03841-9.pdf","source":{"id":"https://openalex.org/S2607323502","display_name":"Scientific Data","issn_l":"2052-4463","issn":["2052-4463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-b","jufo-1","ki-jl-1","medline","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"Scientific Data","raw_type":"journal-article"},{"id":"doi:10.1101/2024.03.09.583700","doi":"https://doi.org/10.1101/2024.03.09.583700","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1101/2024.03.09.583700","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2024/03/13/2024.03.09.583700.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:11436914","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11436914","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11436914/pdf/41597_2024_Article_3841.pdf","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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sci Data","raw_type":"Text"},{"id":"pmid:39333508","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39333508","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,"listed_in":[],"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":"Scientific data","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:f80bdb22b3a741edbcfa948b5d5090f0","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/f80bdb22b3a741edbcfa948b5d5090f0","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,"listed_in":[],"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":"Scientific Data, Vol 11, Iss 1, Pp 1-18 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1038/s41597-024-03841-9","doi":"https://doi.org/10.1038/s41597-024-03841-9","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41597-024-03841-9","pdf_url":"https://www.nature.com/articles/s41597-024-03841-9.pdf","source":{"id":"https://openalex.org/S2607323502","display_name":"Scientific Data","issn_l":"2052-4463","issn":["2052-4463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-b","jufo-1","ki-jl-1","medline","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"Scientific Data","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4178066241","display_name":"Czech National Infrastructure for Biological Data","funder_award_id":"LM2023055","funder_id":"https://openalex.org/F4320321005","funder_display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4843104021","display_name":null,"funder_award_id":"LM2023055","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7660536142","display_name":null,"funder_award_id":"LM2023055","funder_id":"https://openalex.org/F4320323870","funder_display_name":"Central European Institute of Technology"},{"id":"https://openalex.org/G7804282757","display_name":"Career Accelerator for Research Infrastructure Scientists","funder_award_id":"945405","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321005","display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy","ror":"https://ror.org/037n8p820"},{"id":"https://openalex.org/F4320323870","display_name":"Central European Institute of Technology","ror":"https://ror.org/01p7k1986"},{"id":"https://openalex.org/F4320326548","display_name":"Masarykova Univerzita","ror":"https://ror.org/02j46qs45"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402901255.pdf","grobid_xml":"https://content.openalex.org/works/W4402901255.grobid-xml"},"referenced_works_count":91,"referenced_works":["https://openalex.org/W183866246","https://openalex.org/W1623072288","https://openalex.org/W1935434993","https://openalex.org/W2029017735","https://openalex.org/W2048679005","https://openalex.org/W2103017472","https://openalex.org/W2104148262","https://openalex.org/W2104848109","https://openalex.org/W2107580398","https://openalex.org/W2123171788","https://openalex.org/W2126276057","https://openalex.org/W2128484254","https://openalex.org/W2144578941","https://openalex.org/W2148488766","https://openalex.org/W2153081307","https://openalex.org/W2257876130","https://openalex.org/W2280030253","https://openalex.org/W2282857930","https://openalex.org/W2288303312","https://openalex.org/W2291204250","https://openalex.org/W2292303305","https://openalex.org/W2293057230","https://openalex.org/W2293211587","https://openalex.org/W2293600404","https://openalex.org/W2296709801","https://openalex.org/W2296998275","https://openalex.org/W2299138801","https://openalex.org/W2299491580","https://openalex.org/W2302501749","https://openalex.org/W2302542491","https://openalex.org/W2303511142","https://openalex.org/W2304646738","https://openalex.org/W2311213444","https://openalex.org/W2312883704","https://openalex.org/W2313088239","https://openalex.org/W2314026475","https://openalex.org/W2315721191","https://openalex.org/W2318173660","https://openalex.org/W2320456355","https://openalex.org/W2322888619","https://openalex.org/W2330964246","https://openalex.org/W2336014825","https://openalex.org/W2336546025","https://openalex.org/W2336984244","https://openalex.org/W2338139510","https://openalex.org/W2340759847","https://openalex.org/W2341613078","https://openalex.org/W2341662099","https://openalex.org/W2341709054","https://openalex.org/W2343308349","https://openalex.org/W2343412540","https://openalex.org/W2343701753","https://openalex.org/W2346206575","https://openalex.org/W2360792712","https://openalex.org/W2395813420","https://openalex.org/W2397565578","https://openalex.org/W2404674474","https://openalex.org/W2405114694","https://openalex.org/W2411304873","https://openalex.org/W2411867263","https://openalex.org/W2413557942","https://openalex.org/W2476390359","https://openalex.org/W2507500057","https://openalex.org/W2508915320","https://openalex.org/W2510321611","https://openalex.org/W2511106300","https://openalex.org/W2516516952","https://openalex.org/W2557399158","https://openalex.org/W2626778328","https://openalex.org/W2898210859","https://openalex.org/W2911489562","https://openalex.org/W2915895751","https://openalex.org/W2982977147","https://openalex.org/W3023249475","https://openalex.org/W3033916809","https://openalex.org/W3046375318","https://openalex.org/W3157132663","https://openalex.org/W3173727191","https://openalex.org/W3177828909","https://openalex.org/W3186179742","https://openalex.org/W3211795435","https://openalex.org/W4250800088","https://openalex.org/W4309506674","https://openalex.org/W4311287562","https://openalex.org/W4311288223","https://openalex.org/W4319323476","https://openalex.org/W4323036511","https://openalex.org/W4365137095","https://openalex.org/W4387780829","https://openalex.org/W6958423848","https://openalex.org/W7160249163"],"related_works":["https://openalex.org/W4392761558","https://openalex.org/W2064271409","https://openalex.org/W7116073155","https://openalex.org/W4417115741","https://openalex.org/W4413342662","https://openalex.org/W2977069059","https://openalex.org/W4412454282","https://openalex.org/W7125709762","https://openalex.org/W4319069621","https://openalex.org/W4415289724"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,13,80,87,116,128],"novel":[3],"system":[4,114],"that":[5],"leverages":[6],"curators":[7],"in":[8,59,126,146],"the":[9,33,60,94,141,150,158],"loop":[10],"to":[11,78],"develop":[12],"dataset":[14,129],"and":[15,21,44,52,54,108,123,134,157],"model":[16,83,96],"for":[17,72,103,106,110,130,143],"detecting":[18],"structure":[19,136],"features":[20],"functional":[22,132],"annotations":[23,133],"at":[24],"residue-level":[25,131],"from":[26,37,50,84],"standard":[27],"publication":[28],"text.":[29],"Our":[30,112],"approach":[31],"involves":[32],"integration":[34],"of":[35,65,101,119,161],"data":[36],"multiple":[38],"resources,":[39],"including":[40],"PDBe,":[41],"EuropePMC,":[42],"PubMedCentral,":[43],"PubMed,":[45],"combined":[46],"with":[47,97],"annotation":[48,61,89],"guidelines":[49],"UniProt,":[51],"LitSuggest":[53],"HuggingFace":[55],"models":[56,156],"as":[57],"tools":[58],"process.":[62],"A":[63],"team":[64],"seven":[66],"annotators":[67],"manually":[68],"curated":[69],"ten":[70],"articles":[71],"named":[73],"entities,":[74],"which":[75],"we":[76,91],"utilized":[77],"train":[79],"starting":[81],"PubmedBert":[82],"HuggingFace.":[85],"Using":[86],"human-in-the-loop":[88],"system,":[90],"iteratively":[92],"developed":[93],"best":[95],"commendable":[98],"performance":[99],"metrics":[100],"0.90":[102],"precision,":[104],"0.92":[105],"recall,":[107],"0.91":[109],"F1-measure.":[111],"proposed":[113],"showcases":[115],"successful":[117],"synergy":[118],"machine":[120,154],"learning":[121,155],"techniques":[122],"human":[124],"expertise":[125],"curating":[127],"protein":[135,147],"features.":[137],"The":[138],"results":[139],"demonstrate":[140],"potential":[142],"broader":[144],"applications":[145],"research,":[148],"bridging":[149],"gap":[151],"between":[152],"advanced":[153],"indispensable":[159],"insights":[160],"domain":[162],"experts.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2024-09-27T00:00:00"}
