{"id":"https://openalex.org/W4225275379","doi":"https://doi.org/10.1186/s12859-021-04504-x","title":"Large-scale protein-protein post-translational modification extraction with distant supervision and confidence calibrated BioBERT","display_name":"Large-scale protein-protein post-translational modification extraction with distant supervision and confidence calibrated BioBERT","publication_year":2022,"publication_date":"2022-01-04","ids":{"openalex":"https://openalex.org/W4225275379","doi":"https://doi.org/10.1186/s12859-021-04504-x","pmid":"https://pubmed.ncbi.nlm.nih.gov/34983371"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-021-04504-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04504-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-021-04504-x","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-021-04504-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040094977","display_name":"Aparna Elangovan","orcid":"https://orcid.org/0000-0003-3559-9917"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Aparna Elangovan","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409799","display_name":"Yuan Li","orcid":"https://orcid.org/0000-0002-2645-7119"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuan Li","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071950872","display_name":"Douglas E. V. Pires","orcid":"https://orcid.org/0000-0002-3004-2119"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Douglas E. V. Pires","raw_affiliation_strings":["School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018252802","display_name":"Melissa J. Davis","orcid":"https://orcid.org/0000-0003-4864-7033"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I196021976","display_name":"Walter and Eliza Hall Institute of Medical Research","ror":"https://ror.org/01b6kha49","country_code":"AU","type":"nonprofit","lineage":["https://openalex.org/I196021976"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Melissa J. Davis","raw_affiliation_strings":["Department of Clinical Pathology, Faculty of Medicine, Dentistry and Health Sciences, The University of Melbourne, Melbourne, Australia","The Walter and Eliza Hall Institute of Medical Research, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Clinical Pathology, Faculty of Medicine, Dentistry and Health Sciences, The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"The Walter and Eliza Hall Institute of Medical Research, Melbourne, Australia","institution_ids":["https://openalex.org/I196021976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067214173","display_name":"Karin Verspoor","orcid":"https://orcid.org/0000-0002-8661-1544"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","MK"],"is_corresponding":true,"raw_author_name":"Karin Verspoor","raw_affiliation_strings":["School of Computing Technologies, RMIT University, Melbourne, Australia. karin.verspoor@rmit.edu.au","School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia. karin.verspoor@rmit.edu.au","School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Technologies, RMIT University, Melbourne, Australia. karin.verspoor@rmit.edu.au","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]},{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia. karin.verspoor@rmit.edu.au","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]},{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067214173"],"corresponding_institution_ids":["https://openalex.org/I165779595","https://openalex.org/I4210095297","https://openalex.org/I82951845"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2790},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2790},"fwci":1.0185,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.73535767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"23","issue":"1","first_page":"4","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.6866999864578247,"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":0.6866999864578247,"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":0.2662999927997589,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.010499999858438969,"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/computer-science","display_name":"Computer science","score":0.6168190836906433},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5854368209838867},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.5814855098724365},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5439751744270325},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4737316370010376},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43800121545791626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41581499576568604},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41430607438087463},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.38785699009895325},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3863627314567566},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.32832837104797363},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22733613848686218},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14390361309051514},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1316635012626648},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11349251866340637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6168190836906433},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5854368209838867},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.5814855098724365},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5439751744270325},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4737316370010376},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43800121545791626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41581499576568604},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41430607438087463},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.38785699009895325},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3863627314567566},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.32832837104797363},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22733613848686218},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14390361309051514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1316635012626648},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11349251866340637},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"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":"D011499","descriptor_name":"Protein Processing, Post-Translational","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011499","descriptor_name":"Protein Processing, Post-Translational","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011499","descriptor_name":"Protein Processing, Post-Translational","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011499","descriptor_name":"Protein Processing, Post-Translational","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":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","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":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":8,"locations":[{"id":"doi:10.1186/s12859-021-04504-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04504-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-021-04504-x","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34983371","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34983371","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:arXiv.org:2201.02229","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.02229","pdf_url":"https://arxiv.org/pdf/2201.02229","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:alma61RMIT.INST:11294180740001341","is_oa":true,"landing_page_url":"http://purl.org/au-research/grants/arc/LP160101469","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"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":"","raw_type":"text"},{"id":"pmh:oai:digital.library.adelaide.edu.au:2440/137237","is_oa":true,"landing_page_url":"https://hdl.handle.net/2440/137237","pdf_url":null,"source":{"id":"https://openalex.org/S4306401835","display_name":"Adelaide Research & Scholarship (AR&S) (University of Adelaide)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5681781","host_organization_name":"The University of Adelaide","host_organization_lineage":["https://openalex.org/I5681781"],"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":"http://dx.doi.org/10.1186/s12859-021-04504-x","raw_type":"Journal article"},{"id":"pmh:oai:doaj.org/article:38e7c141a7094506ad1a87c2f9ad4512","is_oa":true,"landing_page_url":"https://doaj.org/article/38e7c141a7094506ad1a87c2f9ad4512","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,"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":"BMC Bioinformatics, Vol 23, Iss 1, Pp 1-23 (2022)","raw_type":"article"},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/296012","is_oa":true,"landing_page_url":"http://hdl.handle.net/11343/296012","pdf_url":null,"source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"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":"","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8729035","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8729035","pdf_url":null,"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,"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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-021-04504-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04504-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-021-04504-x","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225275379.pdf","grobid_xml":"https://content.openalex.org/works/W4225275379.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1610821757","https://openalex.org/W1850865022","https://openalex.org/W1954715867","https://openalex.org/W1995683190","https://openalex.org/W2041053370","https://openalex.org/W2043274355","https://openalex.org/W2043764521","https://openalex.org/W2052250375","https://openalex.org/W2071925258","https://openalex.org/W2105924489","https://openalex.org/W2107598941","https://openalex.org/W2124450377","https://openalex.org/W2166474856","https://openalex.org/W2732651590","https://openalex.org/W2740401597","https://openalex.org/W2768826694","https://openalex.org/W2781804600","https://openalex.org/W2900569176","https://openalex.org/W2904726360","https://openalex.org/W2908698522","https://openalex.org/W2911489562","https://openalex.org/W2913223193","https://openalex.org/W2916288174","https://openalex.org/W2945813221","https://openalex.org/W2960293113","https://openalex.org/W2963341956","https://openalex.org/W2964348125","https://openalex.org/W3014596384","https://openalex.org/W3080627676","https://openalex.org/W3099624838","https://openalex.org/W3134774296","https://openalex.org/W3136918052","https://openalex.org/W3154151289"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W2358755282","https://openalex.org/W2949152769","https://openalex.org/W4372354731"],"abstract_inverted_index":{"MOTIVATION:":[0],"Protein-protein":[1],"interactions":[2,28],"(PPIs)":[3],"are":[4,11,22,38],"critical":[5],"to":[6,13,63,86,97,142,149,185,249,283,310],"normal":[7],"cellular":[8],"function":[9],"and":[10,24,112,182,213,223,254,292,301],"related":[12],"many":[14],"disease":[15],"pathways.":[16],"A":[17],"range":[18],"of":[19,36,123,134,146,198,258,294],"protein":[20,27,106],"functions":[21],"mediated":[23],"regulated":[25],"by":[26,66,77,178,272],"through":[29,51],"post-translational":[30],"modifications":[31],"(PTM).":[32],"However,":[33,177],"only":[34,273],"4%":[35],"PPIs":[37,68],"annotated":[39,103],"with":[40,70,104,139,202,265,277],"PTMs":[41],"in":[42,166,299],"biological":[43],"knowledge":[44],"databases":[45],"such":[46],"as":[47],"IntAct,":[48],"mainly":[49],"performed":[50],"manual":[52],"curation,":[53],"which":[54],"is":[55],"neither":[56],"time-":[57],"nor":[58],"cost-effective.":[59],"Here":[60],"we":[61,195,288],"aim":[62],"facilitate":[64,311],"annotation":[65],"extracting":[67],"along":[69],"their":[71,108],"pairwise":[72],"PTM":[73,110],"from":[74,115],"the":[75,93,116,132,144,162,191,199,234,246,256,261,270,281,290,302],"literature":[76],"using":[78,83],"distantly":[79],"supervised":[80,101],"training":[81],"data":[82],"deep":[84,295],"learning":[85],"aid":[87],"human":[88,236,312],"curation.":[89],"METHOD:":[90],"We":[91,119,130,205,268],"use":[92,133],"IntAct":[94],"PPI":[95],"database":[96],"create":[98],"a":[99,167,239],"distant":[100],"dataset":[102],"interacting":[105],"pairs,":[107],"corresponding":[109],"type,":[111],"associated":[113,276],"abstracts":[114,212],"PubMed":[117,211],"database.":[118],"train":[120],"an":[121],"ensemble":[122,135],"BioBERT":[124],"models-dubbed":[125],"PPI-BioBERT-x10-to":[126],"improve":[127],"confidence":[128,137,140,152,181,231,252,266,308],"calibration.":[129,267],"extend":[131],"average":[136],"approach":[138],"variation":[141,184],"counteract":[143],"effects":[145],"class":[147],"imbalance":[148],"extract":[150],"high":[151,180,187,230],"predictions.":[153,232],"RESULTS":[154],"AND":[155],"CONCLUSION:":[156],"The":[157],"PPI-BioBERT-x10":[158,207],"model":[159],"evaluated":[160,206],"on":[161,208,238,307],"test":[163,200,262],"set":[164,263],"resulted":[165],"modest":[168],"F1-micro":[169],"41.3":[170],"(P":[171],"=5":[172],"8.1,":[173],"R":[174],"=":[175],"32.1).":[176],"combining":[179],"low":[183],"identify":[186],"quality":[188],"predictions,":[189,222],"tuning":[190],"predictions":[192,201,275],"for":[193,304],"precision,":[194],"retained":[196],"19%":[197],"100%":[203],"precision.":[204],"18":[209],"million":[210,216],"extracted":[214],"1.6":[215],"(546507":[217],"unique":[218],"PTM-PPI":[219,221],"triplets)":[220],"filter":[224],"[Formula:":[225],"see":[226],"text]":[227],"(4584":[228],"unique)":[229],"Of":[233],"5700,":[235],"evaluation":[237],"small":[240],"randomly":[241],"sampled":[242],"subset":[243],"shows":[244],"that":[245],"precision":[247,282],"drops":[248],"33.7%":[250],"despite":[251],"calibration":[253,309],"highlights":[255],"challenges":[257,293],"generalisability":[259],"beyond":[260],"even":[264],"circumvent":[269],"problem":[271],"including":[274],"multiple":[278],"papers,":[279],"improving":[280],"58.8%.":[284],"In":[285],"this":[286],"work,":[287],"highlight":[289],"benefits":[291],"learning-based":[296],"text":[297],"mining":[298],"practice,":[300],"need":[303],"increased":[305],"emphasis":[306],"curation":[313],"efforts.":[314]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2022-05-04T00:00:00"}