{"id":"https://openalex.org/W4410953566","doi":"https://doi.org/10.1186/s12859-025-06171-8","title":"Class-balanced negative training sets for improving classifier model predictions of enhancer-promoter interactions","display_name":"Class-balanced negative training sets for improving classifier model predictions of enhancer-promoter interactions","publication_year":2025,"publication_date":"2025-06-02","ids":{"openalex":"https://openalex.org/W4410953566","doi":"https://doi.org/10.1186/s12859-025-06171-8","pmid":"https://pubmed.ncbi.nlm.nih.gov/40457173"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-025-06171-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06171-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06171-8","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06171-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035228232","display_name":"Osamu Maruyama","orcid":"https://orcid.org/0000-0002-5760-1507"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]},{"id":"https://openalex.org/I155853523","display_name":"Minami Kyushu University","ror":"https://ror.org/05aymst21","country_code":"JP","type":"education","lineage":["https://openalex.org/I155853523"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Osamu Maruyama","raw_affiliation_strings":["Faculty of Design, Kyushu University, 4 Chome-9-1, Shiobaru, Minami Ward, Fukuoka, 8158540, Japan. maruyama.osamu.158@m.kyushu-u.ac.jp","Faculty of Design, Kyushu University, 4 Chome-9-1, Shiobaru, Minami Ward, Fukuoka, 8158540, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Design, Kyushu University, 4 Chome-9-1, Shiobaru, Minami Ward, Fukuoka, 8158540, Japan. maruyama.osamu.158@m.kyushu-u.ac.jp","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"Faculty of Design, Kyushu University, 4 Chome-9-1, Shiobaru, Minami Ward, Fukuoka, 8158540, Japan","institution_ids":["https://openalex.org/I155853523"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088377873","display_name":"Tsukasa Koga","orcid":"https://orcid.org/0009-0005-7963-7200"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsukasa Koga","raw_affiliation_strings":["Graduate School of Design, Kyushu University, 4 Chome-9-1, Shiobaru, Minami Ward, Fukuoka, 8158540, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Design, Kyushu University, 4 Chome-9-1, Shiobaru, Minami Ward, Fukuoka, 8158540, Japan","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035228232"],"corresponding_institution_ids":["https://openalex.org/I135598925","https://openalex.org/I155853523"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07475432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"1","first_page":"145","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.6032999753952026,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.6032999753952026,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.3443000018596649,"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/T10885","display_name":"Gene expression and cancer classification","score":0.014299999922513962,"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/enhancer","display_name":"Enhancer","score":0.62371826171875},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.544590175151825},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5348101854324341},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47894197702407837},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.4602600038051605},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.42950063943862915},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.37896016240119934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3456980288028717},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34527385234832764},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3431228995323181},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3247099220752716},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.2067837417125702},{"id":"https://openalex.org/keywords/transcription-factor","display_name":"Transcription factor","score":0.1600741147994995},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.14423534274101257}],"concepts":[{"id":"https://openalex.org/C111936080","wikidata":"https://www.wikidata.org/wiki/Q913367","display_name":"Enhancer","level":4,"score":0.62371826171875},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.544590175151825},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5348101854324341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47894197702407837},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.4602600038051605},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.42950063943862915},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.37896016240119934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3456980288028717},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34527385234832764},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3431228995323181},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3247099220752716},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2067837417125702},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.1600741147994995},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.14423534274101257}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004742","descriptor_name":"Enhancer Elements, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004742","descriptor_name":"Enhancer Elements, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004742","descriptor_name":"Enhancer Elements, Genetic","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":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","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":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-025-06171-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06171-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06171-8","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40457173","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40457173","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:doaj.org/article:b31e2dabf48647e6a320cc3c6437bbce","is_oa":true,"landing_page_url":"https://doaj.org/article/b31e2dabf48647e6a320cc3c6437bbce","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 26, Iss 1, Pp 1-18 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:10945376","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12131720","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-025-06171-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06171-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06171-8","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1564504789","display_name":null,"funder_award_id":"JP23-K21718","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6431621577","display_name":null,"funder_award_id":"JP23\u2013K21718","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410953566.pdf","grobid_xml":"https://content.openalex.org/works/W4410953566.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W1977855308","https://openalex.org/W1985621639","https://openalex.org/W2090037139","https://openalex.org/W2333286569","https://openalex.org/W2735099323","https://openalex.org/W2752211734","https://openalex.org/W2768844315","https://openalex.org/W2800857888","https://openalex.org/W2911079020","https://openalex.org/W2945038365","https://openalex.org/W2949423586","https://openalex.org/W2951218167","https://openalex.org/W2971769670","https://openalex.org/W2993022331","https://openalex.org/W3002247544","https://openalex.org/W3113809900","https://openalex.org/W3147833596","https://openalex.org/W3197375931","https://openalex.org/W4205731547","https://openalex.org/W4213060883","https://openalex.org/W4282028407","https://openalex.org/W4387346562","https://openalex.org/W4399783809","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2113330652","https://openalex.org/W2061914098","https://openalex.org/W4393004084","https://openalex.org/W2118646732","https://openalex.org/W4309683845","https://openalex.org/W4387565139","https://openalex.org/W4389440207","https://openalex.org/W4378781551","https://openalex.org/W2054923215","https://openalex.org/W4230529346"],"abstract_inverted_index":{"BACKGROUND:":[0],"Enhancers":[1],"regulate":[2],"gene":[3,18,43],"expression":[4],"by":[5],"forming":[6],"DNA":[7],"loops,":[8],"thereby":[9],"bringing":[10],"themselves":[11],"in":[12,42,223],"close":[13],"proximity":[14],"to":[15,51,85,133],"the":[16,36,67,102,123,148,158,187,199,215],"target":[17],"promoter.":[19],"The":[20,170,232],"human":[21],"genome":[22],"contains":[23],"hundreds":[24],"of":[25,27,38,69,125,217],"thousands":[26],"enhancers,":[28],"vastly":[29],"outnumbering":[30],"its":[31],"20,000-25,000":[32],"protein-coding":[33],"genes,":[34],"highlighting":[35],"importance":[37],"enhancer-promoter":[39,59],"interactions":[40],"(EPIs)":[41],"regulation.":[44],"Supervised":[45],"learning":[46,110],"models":[47,172],"have":[48],"been":[49],"developed":[50,130],"predict":[52],"EPIs,":[53],"often":[54],"using":[55,175],"experimentally":[56],"validated":[57],"interacting":[58],"pairs":[60,80],"and":[61,88,96,104,147,160,165,196],"artificially":[62],"generated":[63],"negative":[64,71,105,117,136,178,182,211,225],"samples.":[65],"However,":[66],"lack":[68],"reliable":[70,116],"samples":[72,118,212],"presents":[73],"a":[74,176],"challenge.":[75],"Current":[76],"methods":[77,132,156,222],"randomly":[78],"select":[79],"from":[81,109],"unlabeled":[82],"data,":[83],"leading":[84],"class":[86],"imbalance":[87],"reduced":[89],"predictive":[90],"performance.":[91],"This":[92],"imbalance,":[93],"where":[94],"enhancers":[95],"promoters":[97],"are":[98],"unevenly":[99],"distributed":[100],"between":[101],"positive":[103],"sets,":[106],"hinders":[107],"classifiers":[108,162],"meaningful":[111],"patterns.":[112],"Therefore,":[113],"constructing":[114],"more":[115],"is":[119,235],"crucial":[120],"for":[121,139],"improving":[122],"accuracy":[124],"EPI":[126,140,218],"predictions.":[127],"RESULTS:":[128],"We":[129,153],"two":[131],"generate":[134],"class-balanced":[135],"training":[137,183],"sets":[138,184],"classifiers:":[141],"one":[142],"based":[143],"on":[144,150],"maximum":[145],"flow":[146],"other":[149],"Gibbs":[151],"sampling.":[152],"evaluated":[154],"these":[155],"with":[157],"TargetFinder":[159],"TransEPI":[161],"across":[163,190],"five":[164],"six":[166],"cell":[167],"lines,":[168],"respectively.":[169],"trained":[171],"were":[173],"tested":[174],"common":[177],"test":[179],"set.":[180],"Our":[181,205],"significantly":[185],"improved":[186],"prediction":[188,230],"performance":[189,216],"several":[191],"metrics,":[192],"including":[193],"precision,":[194],"recall,":[195],"area":[197],"under":[198],"receiver":[200],"operating":[201],"characteristic":[202],"curve.":[203],"CONCLUSIONS:":[204],"findings":[206],"demonstrate":[207],"that":[208],"carefully":[209],"designed":[210],"can":[213],"enhance":[214],"classifiers.":[219],"Further":[220],"advanced":[221],"generating":[224],"EPIs":[226],"should":[227],"further":[228],"improve":[229],"accuracy.":[231],"source":[233],"code":[234],"available":[236],"at":[237],"https://github.com/maruyama-lab-design/CBOEP2":[238],".":[239]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}