{"id":"https://openalex.org/W2611234392","doi":"https://doi.org/10.1142/s0218001417500409","title":"Enhanced Prediction for Observed Peptide Count in Protein Mass Spectrometry Data by Optimally Balancing the Training Dataset","display_name":"Enhanced Prediction for Observed Peptide Count in Protein Mass Spectrometry Data by Optimally Balancing the Training Dataset","publication_year":2017,"publication_date":"2017-05-02","ids":{"openalex":"https://openalex.org/W2611234392","doi":"https://doi.org/10.1142/s0218001417500409","mag":"2611234392"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001417500409","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001417500409","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"},"type":"article","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/A5100628406","display_name":"Anoop Kumar Tiwari","orcid":"https://orcid.org/0000-0002-8241-6186"},"institutions":[{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anoop Kumar Tiwari","raw_affiliation_strings":["Department of Computer Science, Banaras Hindu University, Varanasi, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Banaras Hindu University, Varanasi, India","institution_ids":["https://openalex.org/I91357014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004453727","display_name":"Abhigyan Nath","orcid":"https://orcid.org/0000-0003-1253-7115"},"institutions":[{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhigyan Nath","raw_affiliation_strings":["Department of Computer Science, Banaras Hindu University, Varanasi, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Banaras Hindu University, Varanasi, India","institution_ids":["https://openalex.org/I91357014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673463","display_name":"Karthikeyan Subbiah","orcid":"https://orcid.org/0000-0001-9614-9827"},"institutions":[{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Karthikeyan Subbiah","raw_affiliation_strings":["Department of Computer Science, Banaras Hindu University, Varanasi, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Banaras Hindu University, Varanasi, India","institution_ids":["https://openalex.org/I91357014"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046454544","display_name":"K.K. Shukla","orcid":"https://orcid.org/0000-0002-8756-6474"},"institutions":[{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]},{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kaushal Kumar Shukla","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100628406"],"corresponding_institution_ids":["https://openalex.org/I91357014"],"apc_list":null,"apc_paid":null,"fwci":0.319,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.57123485,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"31","issue":"12","first_page":"1750040","last_page":"1750040"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12388","display_name":"Identification and Quantification in Food","score":0.9904000163078308,"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/oversampling","display_name":"Oversampling","score":0.8323370218276978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7581748962402344},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.7115755677223206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6995275020599365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6717036366462708},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.559367835521698},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.5234260559082031},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4402593970298767},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39452531933784485},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39203083515167236}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.8323370218276978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581748962402344},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7115755677223206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6995275020599365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6717036366462708},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.559367835521698},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.5234260559082031},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4402593970298767},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39452531933784485},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39203083515167236},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001417500409","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001417500409","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W101663867","https://openalex.org/W978357671","https://openalex.org/W1544435011","https://openalex.org/W1583700199","https://openalex.org/W1766594731","https://openalex.org/W1873256004","https://openalex.org/W1941659294","https://openalex.org/W1965975293","https://openalex.org/W1968512230","https://openalex.org/W1991181258","https://openalex.org/W2005228904","https://openalex.org/W2008056655","https://openalex.org/W2013947447","https://openalex.org/W2032685209","https://openalex.org/W2038058994","https://openalex.org/W2039809330","https://openalex.org/W2060240123","https://openalex.org/W2068362550","https://openalex.org/W2082238959","https://openalex.org/W2087240369","https://openalex.org/W2096347263","https://openalex.org/W2097169398","https://openalex.org/W2109509105","https://openalex.org/W2114968414","https://openalex.org/W2115625429","https://openalex.org/W2118790811","https://openalex.org/W2118978333","https://openalex.org/W2132791018","https://openalex.org/W2133990480","https://openalex.org/W2140494000","https://openalex.org/W2143635696","https://openalex.org/W2148143831","https://openalex.org/W2148342439","https://openalex.org/W2150566147","https://openalex.org/W2152923973","https://openalex.org/W2153030642","https://openalex.org/W2161267827","https://openalex.org/W2171913440","https://openalex.org/W2183183828","https://openalex.org/W2246109554","https://openalex.org/W2557824881","https://openalex.org/W2911964244","https://openalex.org/W4212883601","https://openalex.org/W4230683138","https://openalex.org/W4250258832","https://openalex.org/W4302081184"],"related_works":["https://openalex.org/W3008199583","https://openalex.org/W3184937791","https://openalex.org/W4319718059","https://openalex.org/W3021503072","https://openalex.org/W3176807344","https://openalex.org/W4316469706","https://openalex.org/W4293261997","https://openalex.org/W4291692947","https://openalex.org/W4297107051","https://openalex.org/W4283010365"],"abstract_inverted_index":{"Imbalanced":[0],"dataset":[1,28],"affects":[2],"the":[3,20,26,35,40,48,55,60,70,79,86,108,140,146,151,161,168,187],"learning":[4,36,63,165],"of":[5,19,43,47,114,118,122,125,129,153,163],"classifiers.":[6],"This":[7,136],"imbalance":[8],"problem":[9],"is":[10,17],"almost":[11],"ubiquitous":[12],"in":[13,54],"biological":[14],"datasets.":[15],"Resampling":[16],"one":[18],"common":[21],"methods":[22],"to":[23,90],"deal":[24],"with":[25,131],"imbalanced":[27,80],"problem.":[29],"In":[30],"this":[31],"study,":[32],"we":[33,106],"explore":[34],"performance":[37,77,162],"by":[38,111,144,174,184],"varying":[39],"balancing":[41,72,104],"ratios":[42],"training":[44,178],"datasets,":[45],"consisting":[46],"observed":[49,68],"peptides":[50,53],"and":[51,127],"absent":[52],"Mass":[56],"Spectrometry":[57],"experiment":[58],"on":[59],"different":[61,103],"machine":[62,164],"algorithms.":[64],"It":[65],"has":[66,74],"been":[67],"that":[69,160],"ideal":[71],"ratio":[73],"yielded":[75],"better":[76],"than":[78],"dataset,":[81,179],"but":[82],"it":[83,156],"was":[84],"not":[85],"best":[87,109],"as":[88],"compared":[89],"some":[91],"intermediate":[92],"ratio.":[93],"By":[94],"experimenting":[95],"using":[96],"Synthetic":[97],"Minority":[98],"Oversampling":[99],"Technique":[100],"(SMOTE)":[101],"at":[102],"ratios,":[105],"obtained":[107,183],"results":[110,152],"achieving":[112],"sensitivity":[113],"92.1%,":[115],"specificity":[116],"value":[117],"94.7%,":[119],"overall":[120],"accuracy":[121],"93.4%,":[123],"MCC":[124],"0.869,":[126],"AUC":[128],"0.982":[130],"boosted":[132],"random":[133],"forest":[134],"algorithm.":[135,149],"study":[137],"also":[138],"identifies":[139],"most":[141],"discriminating":[142],"features":[143],"applying":[145],"feature":[147],"ranking":[148],"From":[150],"current":[154],"experiments,":[155],"can":[157,171,181],"be":[158,172,182],"inferred":[159],"algorithms":[166],"for":[167],"classification":[169],"tasks":[170],"enhanced":[173],"selecting":[175],"optimally":[176],"balanced":[177],"which":[180],"suitably":[185],"modifying":[186],"class":[188],"distribution.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}