{"id":"https://openalex.org/W3041336271","doi":"https://doi.org/10.1145/3405758.3405764","title":"Study of Data Imbalanced Problem in Protein-peptide Binding Prediction","display_name":"Study of Data Imbalanced Problem in Protein-peptide Binding Prediction","publication_year":2020,"publication_date":"2020-05-22","ids":{"openalex":"https://openalex.org/W3041336271","doi":"https://doi.org/10.1145/3405758.3405764","mag":"3041336271"},"language":"en","primary_location":{"id":"doi:10.1145/3405758.3405764","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3405758.3405764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 12th International Conference on Bioinformatics and Biomedical Technology","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101529294","display_name":"Lu Gao","orcid":"https://orcid.org/0009-0003-3417-0681"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Lu Gao","raw_affiliation_strings":["University of Macau, Macau, China, Avenida da Universidade, Taipa, Macau, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau, Macau, China, Avenida da Universidade, Taipa, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102848446","display_name":"Shirley W. I. Siu","orcid":"https://orcid.org/0000-0002-3695-7758"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Shirley W. I. Siu","raw_affiliation_strings":["University of Macau, Macau, China, Avenida da Universidade, Taipa, Macau, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau, Macau, China, Avenida da Universidade, Taipa, Macau, China","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204512498"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"197","issue":null,"first_page":"61","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9993000030517578,"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":0.9993000030517578,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.9958000183105469,"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/T13326","display_name":"Biochemical and Structural Characterization","score":0.9940999746322632,"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":0.5675914287567139},{"id":"https://openalex.org/keywords/peptide","display_name":"Peptide","score":0.48628103733062744},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.463348925113678},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4438021779060364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43490350246429443},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4211593270301819},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35789382457733154},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1994578242301941},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.10990804433822632}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5675914287567139},{"id":"https://openalex.org/C2779281246","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Peptide","level":2,"score":0.48628103733062744},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.463348925113678},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4438021779060364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43490350246429443},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4211593270301819},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35789382457733154},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1994578242301941},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.10990804433822632},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3405758.3405764","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3405758.3405764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 12th International Conference on Bioinformatics and Biomedical Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W759630152","https://openalex.org/W1980627844","https://openalex.org/W1983142511","https://openalex.org/W1984794455","https://openalex.org/W2002264084","https://openalex.org/W2047672715","https://openalex.org/W2092091950","https://openalex.org/W2104760790","https://openalex.org/W2108067237","https://openalex.org/W2109444605","https://openalex.org/W2131466679","https://openalex.org/W2147285856","https://openalex.org/W2264362083","https://openalex.org/W2315962322","https://openalex.org/W2548536600","https://openalex.org/W3093745921","https://openalex.org/W3155649056","https://openalex.org/W4233253307","https://openalex.org/W4240861547","https://openalex.org/W4244244707","https://openalex.org/W4255916494"],"related_works":["https://openalex.org/W1526195401","https://openalex.org/W4313385292","https://openalex.org/W1759461029","https://openalex.org/W2126989399","https://openalex.org/W2372019020","https://openalex.org/W2961085424","https://openalex.org/W2086851734","https://openalex.org/W2375446917","https://openalex.org/W3134906029","https://openalex.org/W2069603249"],"abstract_inverted_index":{"Peptide-binding":[0],"proteins":[1],"are":[2],"excessive":[3],"in":[4,27,39,115],"living":[5],"cells":[6],"and":[7,25,31,63,130],"proteinpeptide":[8],"interactions":[9],"mediate":[10],"a":[11,84,89,132],"wide":[12],"range":[13],"of":[14,18,60,65,72,92,113,135],"cellular":[15],"functions.":[16],"Prediction":[17],"protein-peptide":[19,136],"binding":[20,137],"residues":[21],"has":[22,47],"been":[23,49],"vital":[24],"popular":[26],"the":[28,43,58,78,101,111],"past":[29],"decades":[30],"machine":[32],"learning":[33],"methods":[34,62],"have":[35],"gained":[36],"more":[37],"attention":[38],"recent":[40],"years.":[41],"However,":[42],"data":[44,68,94,102,127],"imbalance":[45,66,118,128],"problem":[46,129],"not":[48],"dealt":[50],"with":[51,108],"effectively.":[52],"On":[53],"this":[54],"matter,":[55],"we":[56],"study":[57],"effects":[59],"sampling":[61],"degrees":[64],"on":[67,70,123,126],"classes":[69],"construction":[71],"prediction":[73,134],"model.":[74],"We":[75],"first":[76],"developed":[77],"NearMiss":[79],"under-sampling":[80],"method":[81],"(NMUS)":[82],"as":[83],"way":[85],"to":[86,99],"screen":[87],"out":[88],"given":[90],"number":[91],"quality":[93],"samples":[95],"from":[96],"majority":[97],"class":[98,117],"balance":[100],"sets.":[103],"The":[104],"remarkable":[105],"sensitivity":[106],"(SEN)":[107],"0.818":[109],"shows":[110],"advantage":[112],"NMUS":[114],"handling":[116],"problem.":[119],"This":[120],"research":[121],"carried":[122],"valuable":[124],"analysis":[125],"achieved":[131],"better":[133],"interaction.":[138]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}