{"id":"https://openalex.org/W4317911177","doi":"https://doi.org/10.1142/s021969132250045x","title":"Calibrating the classifier for protein family prediction with protein sequence using machine learning techniques: An empirical investigation","display_name":"Calibrating the classifier for protein family prediction with protein sequence using machine learning techniques: An empirical investigation","publication_year":2023,"publication_date":"2023-01-25","ids":{"openalex":"https://openalex.org/W4317911177","doi":"https://doi.org/10.1142/s021969132250045x"},"language":"en","primary_location":{"id":"doi:10.1142/s021969132250045x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021969132250045x","pdf_url":null,"source":{"id":"https://openalex.org/S56986848","display_name":"International Journal of Wavelets Multiresolution and Information Processing","issn_l":"0219-6913","issn":["0219-6913","1793-690X"],"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 Wavelets, Multiresolution and Information Processing","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/A5030394668","display_name":"T. Idhaya","orcid":null},"institutions":[{"id":"https://openalex.org/I182997119","display_name":"Manonmaniam Sundaranar University","ror":"https://ror.org/02qgw5c67","country_code":"IN","type":"education","lineage":["https://openalex.org/I182997119"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"T. Idhaya","raw_affiliation_strings":["Department of Computer Science and Engineering, Manonmaniam Sundaranar University, Abhishekapatti, Tirunelveli, Tamil Nadu, India"],"raw_orcid":"https://orcid.org/0000-0001-6339-8165","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Manonmaniam Sundaranar University, Abhishekapatti, Tirunelveli, Tamil Nadu, India","institution_ids":["https://openalex.org/I182997119"]}]},{"author_position":"middle","author":{"id":null,"display_name":"A. Suruliandi","orcid":null},"institutions":[{"id":"https://openalex.org/I182997119","display_name":"Manonmaniam Sundaranar University","ror":"https://ror.org/02qgw5c67","country_code":"IN","type":"education","lineage":["https://openalex.org/I182997119"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"A. Suruliandi","raw_affiliation_strings":["Department of Computer Science and Engineering, Manonmaniam Sundaranar University, Abhishekapatti, Tirunelveli, Tamil Nadu, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Manonmaniam Sundaranar University, Abhishekapatti, Tirunelveli, Tamil Nadu, India","institution_ids":["https://openalex.org/I182997119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009621447","display_name":"Dragos Calitoiu","orcid":"https://orcid.org/0000-0003-0173-9846"},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dragos Calitoiu","raw_affiliation_strings":["School of Mathematics and Statistics, Carleton University, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Carleton University, Canada","institution_ids":["https://openalex.org/I67031392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068883308","display_name":"S. P. Raja","orcid":null},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. P. Raja","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Vellore 632014, Tamil Nadu, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Vellore 632014, Tamil Nadu, India","institution_ids":["https://openalex.org/I876193797"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030394668"],"corresponding_institution_ids":["https://openalex.org/I182997119"],"apc_list":null,"apc_paid":null,"fwci":0.2999,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61614692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"21","issue":"03","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.994700014591217,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9944999814033508,"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/classifier","display_name":"Classifier (UML)","score":0.7102280855178833},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.674627423286438},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6210896372795105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6033746004104614},{"id":"https://openalex.org/keywords/protein-family","display_name":"Protein family","score":0.5870838165283203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5797570943832397},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.5513857007026672},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5029208064079285},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47675785422325134},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.43497827649116516},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.36356037855148315},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3467657268047333},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.340410053730011},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.26359719038009644},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.20976564288139343},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.19918188452720642},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1832490861415863}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7102280855178833},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.674627423286438},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6210896372795105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6033746004104614},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.5870838165283203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5797570943832397},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.5513857007026672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5029208064079285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47675785422325134},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.43497827649116516},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.36356037855148315},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3467657268047333},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.340410053730011},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.26359719038009644},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.20976564288139343},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19918188452720642},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1832490861415863},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s021969132250045x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s021969132250045x","pdf_url":null,"source":{"id":"https://openalex.org/S56986848","display_name":"International Journal of Wavelets Multiresolution and Information Processing","issn_l":"0219-6913","issn":["0219-6913","1793-690X"],"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 Wavelets, Multiresolution and Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W86661845","https://openalex.org/W1496604422","https://openalex.org/W1516465541","https://openalex.org/W1821464114","https://openalex.org/W1853093403","https://openalex.org/W1967039216","https://openalex.org/W1967418149","https://openalex.org/W1985204165","https://openalex.org/W1993711987","https://openalex.org/W2005116846","https://openalex.org/W2009850217","https://openalex.org/W2014332260","https://openalex.org/W2035146707","https://openalex.org/W2042084565","https://openalex.org/W2044573154","https://openalex.org/W2045911289","https://openalex.org/W2046914949","https://openalex.org/W2047672715","https://openalex.org/W2054068479","https://openalex.org/W2060287713","https://openalex.org/W2069392850","https://openalex.org/W2075006095","https://openalex.org/W2094403468","https://openalex.org/W2111072639","https://openalex.org/W2114358087","https://openalex.org/W2119387367","https://openalex.org/W2120691371","https://openalex.org/W2140767933","https://openalex.org/W2141062474","https://openalex.org/W2154865259","https://openalex.org/W2155194485","https://openalex.org/W2160979370","https://openalex.org/W2166637863","https://openalex.org/W2167101736","https://openalex.org/W2183771695","https://openalex.org/W2518034873","https://openalex.org/W2969993699","https://openalex.org/W2977155845","https://openalex.org/W2983181663","https://openalex.org/W3048095951","https://openalex.org/W3131413015","https://openalex.org/W4213345021","https://openalex.org/W4236463097","https://openalex.org/W4294216483"],"related_works":["https://openalex.org/W2946599741","https://openalex.org/W2593264178","https://openalex.org/W2043066834","https://openalex.org/W3171039768","https://openalex.org/W2136856901","https://openalex.org/W2368468053","https://openalex.org/W2058542300","https://openalex.org/W1564749278","https://openalex.org/W4387310732","https://openalex.org/W4390971102"],"abstract_inverted_index":{"A":[0],"gene":[1],"is":[2,77,117,134,151,188,201],"a":[3,10,70,173,196],"basic":[4],"unit":[5],"of":[6,12,25,114,180,198,229],"congenital":[7],"traits":[8],"and":[9,29,47,49,60,100,110,150,210,236],"sequence":[11],"nucleotides":[13],"in":[14,34,41,84,191],"deoxyribonucleic":[15],"acid":[16,27],"that":[17,118,139],"encrypts":[18],"protein":[19,91,105,122,148,214],"synthesis.":[20],"Proteins":[21],"are":[22,30,58,108],"made":[23],"up":[24],"amino":[26],"residue":[28],"classified":[31],"for":[32,121,136,163,213,231],"use":[33],"protein-related":[35],"research,":[36],"which":[37],"includes":[38],"identifying":[39,50],"changes":[40],"genes,":[42],"finding":[43],"associations":[44],"with":[45],"diseases":[46],"phenotypes,":[48],"potential":[51],"drug":[52],"targets.":[53],"To":[54],"this":[55],"end,":[56],"proteins":[57],"studied":[59],"classified,":[61],"based":[62],"on":[63],"the":[64,81,85,115,130,147,156,159,177,193,205,218,220,225,237],"family.":[65],"For":[66],"family":[67,92,106,149,215],"prediction,":[68],"however,":[69],"computational":[71],"rather":[72],"than":[73,155],"an":[74],"experimental":[75],"approach":[76,133],"introduced,":[78],"owing":[79],"to":[80,90,104,145,168,175,184,203],"time":[82],"involved":[83],"latter":[86,131],"process.":[87],"Computational":[88],"approaches":[89,103,200],"prediction":[93,107],"involve":[94],"two":[95],"important":[96],"processes,":[97],"feature":[98,207,221,233],"selection":[99,208,234],"classification.":[101],"Existing":[102],"alignment-based":[109],"alignment-free.":[111],"The":[112],"drawback":[113],"former":[116],"it":[119,140],"searches":[120],"signatures":[123],"by":[124],"aligning":[125],"every":[126],"available":[127],"sequence.":[128],"Consequently,":[129],"alignment-free":[132],"taken":[135,162],"study,":[137,219],"given":[138],"only":[141],"needs":[142],"sequence-based":[143,160],"features":[144,167,179],"predict":[146],"far":[152],"more":[153],"efficient":[154],"former.":[157],"Nevertheless,":[158],"characteristics":[161],"study":[164],"have":[165],"additional":[166],"offer.":[169],"There":[170],"is,":[171],"thus,":[172],"need":[174],"select":[176],"best":[178,206,226],"all.":[181],"When":[182],"comes":[183],"classification":[185,211,227],"still":[186],"there":[187],"no":[189],"perfection":[190],"classifying":[192],"protein.":[194],"So,":[195],"comparison":[197],"different":[199],"done":[202],"find":[204],"technique":[209,212,235],"prediction.":[216],"From":[217],"subset":[222],"selected":[223],"provides":[224],"accuracy":[228],"96%":[230],"filter-based":[232],"random":[238],"forest":[239],"classifier.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}