{"id":"https://openalex.org/W4384500356","doi":"https://doi.org/10.1021/acs.jcim.3c00269","title":"Improving Compound\u2013Protein Interaction Prediction by Self-Training with Augmenting Negative Samples","display_name":"Improving Compound\u2013Protein Interaction Prediction by Self-Training with Augmenting Negative Samples","publication_year":2023,"publication_date":"2023-07-17","ids":{"openalex":"https://openalex.org/W4384500356","doi":"https://doi.org/10.1021/acs.jcim.3c00269","pmid":"https://pubmed.ncbi.nlm.nih.gov/37460105"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.3c00269","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00269","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.3c00269","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.3c00269","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027799892","display_name":"Takuto Koyama","orcid":"https://orcid.org/0000-0002-9569-8370"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuto Koyama","raw_affiliation_strings":["Graduate School of Medicine, Kyoto University, Sakyo-ku 606-8507 Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9569-8370","affiliations":[{"raw_affiliation_string":"Graduate School of Medicine, Kyoto University, Sakyo-ku 606-8507 Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053913367","display_name":"Shigeyuki Matsumoto","orcid":"https://orcid.org/0000-0001-9329-6362"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shigeyuki Matsumoto","raw_affiliation_strings":["Graduate School of Medicine, Kyoto University, Sakyo-ku 606-8507 Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9329-6362","affiliations":[{"raw_affiliation_string":"Graduate School of Medicine, Kyoto University, Sakyo-ku 606-8507 Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043360512","display_name":"Hiroaki Iwata","orcid":"https://orcid.org/0000-0001-9791-0008"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroaki Iwata","raw_affiliation_strings":["Graduate School of Medicine, Kyoto University, Sakyo-ku 606-8507 Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9791-0008","affiliations":[{"raw_affiliation_string":"Graduate School of Medicine, Kyoto University, Sakyo-ku 606-8507 Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013489463","display_name":"Ryosuke Kojima","orcid":"https://orcid.org/0000-0003-1095-8864"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryosuke Kojima","raw_affiliation_strings":["Graduate School of Medicine, Kyoto University, Sakyo-ku 606-8507 Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Medicine, Kyoto University, Sakyo-ku 606-8507 Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046211758","display_name":"Yasushi Okuno","orcid":"https://orcid.org/0000-0003-3596-4208"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yasushi Okuno","raw_affiliation_strings":["Graduate School of Medicine, Kyoto University, Sakyo-ku 606-8507 Kyoto, Japan","HPC- and AI-driven Drug Development Platform Division, RIKEN Center for Computational Science, Kobe 650-0047, Hyogo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Medicine, Kyoto University, Sakyo-ku 606-8507 Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"HPC- and AI-driven Drug Development Platform Division, RIKEN Center for Computational Science, Kobe 650-0047, Hyogo, Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046211758","https://openalex.org/A5053913367"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129730"],"apc_list":null,"apc_paid":null,"fwci":0.9263,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78442536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"63","issue":"15","first_page":"4552","last_page":"4559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9623000025749207,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9574999809265137,"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/generalizability-theory","display_name":"Generalizability theory","score":0.9704927206039429},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6981731057167053},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5285598039627075},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5199219584465027},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5107033848762512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.498260498046875},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39573997259140015},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1456383466720581},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08560770750045776}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.9704927206039429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6981731057167053},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5285598039627075},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5199219584465027},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5107033848762512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.498260498046875},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39573997259140015},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1456383466720581},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08560770750045776},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"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":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.3c00269","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00269","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.3c00269","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:37460105","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37460105","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of chemical information and modeling","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10428206","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10428206","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10428206/pdf/ci3c00269.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,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Chem Inf Model","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.3c00269","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00269","pdf_url":"https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.3c00269","source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2570330558","display_name":null,"funder_award_id":"JP20K12063","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5680769591","display_name":null,"funder_award_id":"JP22nk0101111","funder_id":"https://openalex.org/F4320311405","funder_display_name":"Japan Agency for Medical Research and Development"}],"funders":[{"id":"https://openalex.org/F4320311405","display_name":"Japan Agency for Medical Research and Development","ror":"https://ror.org/004rtk039"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384500356.pdf","grobid_xml":"https://content.openalex.org/works/W4384500356.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1966716734","https://openalex.org/W1988037271","https://openalex.org/W2031441006","https://openalex.org/W2086286404","https://openalex.org/W2092285329","https://openalex.org/W2096541451","https://openalex.org/W2100672820","https://openalex.org/W2103994532","https://openalex.org/W2134967712","https://openalex.org/W2138512826","https://openalex.org/W2139736926","https://openalex.org/W2148145769","https://openalex.org/W2148853951","https://openalex.org/W2152630148","https://openalex.org/W2153838454","https://openalex.org/W2166410137","https://openalex.org/W2204695023","https://openalex.org/W2259538443","https://openalex.org/W2513544049","https://openalex.org/W2612690371","https://openalex.org/W2767891136","https://openalex.org/W2785947426","https://openalex.org/W2860192827","https://openalex.org/W2889326414","https://openalex.org/W2899070097","https://openalex.org/W2899788782","https://openalex.org/W3018980093","https://openalex.org/W3028589594","https://openalex.org/W3030071125","https://openalex.org/W3039465695","https://openalex.org/W3096561213","https://openalex.org/W3107621688","https://openalex.org/W3202143517","https://openalex.org/W3210331473","https://openalex.org/W4200019701","https://openalex.org/W4296774836","https://openalex.org/W6605118383"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W410723623","https://openalex.org/W2413243053","https://openalex.org/W2015341305","https://openalex.org/W4225593417","https://openalex.org/W2035068594","https://openalex.org/W2059783833","https://openalex.org/W2573498121","https://openalex.org/W3160494304","https://openalex.org/W1549477351"],"abstract_inverted_index":{"Identifying":[0],"compound-protein":[1],"interactions":[2],"(CPIs)":[3],"is":[4,13,139],"crucial":[5],"for":[6,40,76,107,116,126,141,153],"drug":[7,162],"discovery.":[8,163],"Since":[9],"experimentally":[10,63],"validating":[11],"CPIs":[12],"often":[14,52],"time-consuming":[15],"and":[16,80,111],"costly,":[17],"computational":[18],"approaches":[19],"are":[20],"expected":[21],"to":[22,59,84],"facilitate":[23],"the":[24,34,60,86,112,122,133],"process.":[25],"Rapid":[26],"growths":[27],"of":[28,36,62,88,121],"available":[29],"CPI":[30,41,155],"databases":[31],"have":[32],"accelerated":[33],"development":[35],"many":[37],"machine-learning":[38],"methods":[39,106],"predictions.":[42],"However,":[43],"their":[44,47],"performance,":[45],"particularly":[46],"generalizability":[48],"against":[49],"external":[50,117],"data,":[51,159],"suffers":[53],"from":[54],"a":[55,73,143],"data":[56,92,109],"imbalance":[57],"attributed":[58],"lack":[61],"validated":[64],"inactive":[65],"(negative)":[66],"samples.":[67],"In":[68],"this":[69],"study,":[70],"we":[71],"developed":[72],"self-training":[74,129],"method":[75],"augmenting":[77,132],"both":[78],"credible":[79],"informative":[81],"negative":[82],"samples":[83,134],"improve":[85],"performance":[87,99],"models":[89],"impaired":[90],"by":[91],"imbalances.":[93],"The":[94,148],"constructed":[95,102],"model":[96,144],"demonstrated":[97],"higher":[98],"than":[100],"those":[101],"with":[103,135,145],"other":[104],"conventional":[105],"solving":[108],"imbalances,":[110],"improvement":[113],"was":[114],"prominent":[115],"datasets.":[118],"Moreover,":[119],"examination":[120],"prediction":[123,137],"score":[124],"thresholds":[125],"pseudo-labeling":[127],"during":[128],"revealed":[130],"that":[131],"ambiguous":[136],"scores":[138],"beneficial":[140],"constructing":[142],"high":[146],"generalizability.":[147],"present":[149],"study":[150],"provides":[151],"guidelines":[152],"improving":[154],"predictions":[156],"on":[157],"real-world":[158],"thus":[160],"facilitating":[161]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}