{"id":"https://openalex.org/W3216679652","doi":"https://doi.org/10.1142/s0219720021500293","title":"O-glycosylation site prediction for <i>Homo sapiens</i> by combining properties and sequence features with support vector machine","display_name":"O-glycosylation site prediction for <i>Homo sapiens</i> by combining properties and sequence features with support vector machine","publication_year":2021,"publication_date":"2021-11-19","ids":{"openalex":"https://openalex.org/W3216679652","doi":"https://doi.org/10.1142/s0219720021500293","mag":"3216679652","pmid":"https://pubmed.ncbi.nlm.nih.gov/34806952"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720021500293","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720021500293","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yan Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhu","raw_affiliation_strings":["School of Science, Dalian Maritime University, Dalian 116026, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science, Dalian Maritime University, Dalian 116026, P. R. China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuwan Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuwan Yin","raw_affiliation_strings":["School of Science, Dalian Maritime University, Dalian 116026, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science, Dalian Maritime University, Dalian 116026, P. R. China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jia Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Zheng","raw_affiliation_strings":["School of Science, Dalian Maritime University, Dalian 116026, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science, Dalian Maritime University, Dalian 116026, P. R. China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yixia Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I154833797","display_name":"Lingnan Normal University","ror":"https://ror.org/01h6ecw13","country_code":"CN","type":"education","lineage":["https://openalex.org/I154833797"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixia Shi","raw_affiliation_strings":["School of Mathematics and Statistics, Lingnan Normal University, Zhanjiang 524048, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Lingnan Normal University, Zhanjiang 524048, P. R. China","institution_ids":["https://openalex.org/I154833797"]}]},{"author_position":"last","author":{"id":null,"display_name":"Cangzhi Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cangzhi Jia","raw_affiliation_strings":["School of Science, Dalian Maritime University, Dalian 116026, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science, Dalian Maritime University, Dalian 116026, P. R. China","institution_ids":["https://openalex.org/I43313876"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4071,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60276876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"20","issue":"01","first_page":"2150029","last_page":"2150029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.7328000068664551,"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":0.7328000068664551,"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/T10602","display_name":"Glycosylation and Glycoproteins Research","score":0.18610000610351562,"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":0.021700000390410423,"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/undersampling","display_name":"Undersampling","score":0.7878000140190125},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.6718000173568726},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6553999781608582},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5608000159263611},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5303000211715698},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49079999327659607},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4684999883174896},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.46619999408721924}],"concepts":[{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.7878000140190125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461000084877014},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.6718000173568726},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6553999781608582},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6312999725341797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6294999718666077},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5608000159263611},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4447000026702881},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43720000982284546},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3833000063896179},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.26980000734329224}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006031","descriptor_name":"Glycosylation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006031","descriptor_name":"Glycosylation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006031","descriptor_name":"Glycosylation","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720021500293","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720021500293","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:34806952","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34806952","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 bioinformatics and computational biology","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6108461235","display_name":null,"funder_award_id":"62071079","funder_id":"https://openalex.org/F4320315254","funder_display_name":"Innovative Research Group Project of the National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320315254","display_name":"Innovative Research Group Project of the National Natural Science Foundation of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W44721752","https://openalex.org/W1680640252","https://openalex.org/W1911726212","https://openalex.org/W1963545514","https://openalex.org/W2063768466","https://openalex.org/W2072918899","https://openalex.org/W2088456241","https://openalex.org/W2097606916","https://openalex.org/W2103525038","https://openalex.org/W2209329607","https://openalex.org/W2397556949","https://openalex.org/W2742750032","https://openalex.org/W2810614960","https://openalex.org/W2894436452","https://openalex.org/W2894566366","https://openalex.org/W2903703585","https://openalex.org/W2906946803","https://openalex.org/W2908351833","https://openalex.org/W2910591656","https://openalex.org/W2922210059","https://openalex.org/W2946682182","https://openalex.org/W2963791543","https://openalex.org/W2967960129","https://openalex.org/W2977291005","https://openalex.org/W2993510908","https://openalex.org/W2999829553","https://openalex.org/W3123058709","https://openalex.org/W3127515140","https://openalex.org/W3135678255","https://openalex.org/W3155214885","https://openalex.org/W3189075232","https://openalex.org/W4213345021"],"related_works":[],"abstract_inverted_index":{"O-glycosylation":[0,25,54,143],"is":[1,13,27],"a":[2,16,45,69,120],"protein":[3,37],"posttranslational":[4,38],"modification":[5],"important":[6],"in":[7,126],"regulating":[8],"almost":[9],"all":[10],"cells.":[11],"It":[12],"related":[14],"to":[15,30,43,76,89,105,111],"large":[17],"number":[18],"of":[19,36,97,123],"physiological":[20],"and":[21,51,68,93,113,131,162],"pathological":[22],"phenomena.":[23],"Recognizing":[24],"sites":[26],"the":[28,33,83,95,98,115,135,141],"key":[29],"further":[31,154],"investigating":[32],"molecular":[34],"mechanism":[35],"modification.":[39],"This":[40],"study":[41],"aimed":[42],"collect":[44],"reliable":[46],"dataset":[47],"on":[48,157],"Homo":[49,57],"sapiens":[50],"develop":[52],"an":[53],"predictor":[55],"for":[56,153],"sapiens,":[58],"named":[59],"Captor,":[60],"through":[61],"multiple":[62],"features.":[63],"A":[64,100],"random":[65],"undersampling":[66],"method":[67],"synthetic":[70],"minority":[71],"oversampling":[72],"technique":[73],"were":[74],"employed":[75],"deal":[77],"with":[78],"imbalanced":[79],"data.":[80],"In":[81],"addition,":[82],"Kruskal\u2013Wallis":[84],"(K\u2013W)":[85],"test":[86,137],"was":[87,109],"adopted":[88],"optimize":[90,114],"feature":[91],"vectors":[92],"improve":[94],"performance":[96],"model.":[99],"support":[101],"vector":[102],"machine,":[103],"due":[104],"its":[106],"optimal":[107],"performance,":[108],"used":[110],"train":[112],"final":[116],"prediction":[117],"model":[118],"after":[119],"comprehensive":[121],"comparison":[122],"various":[124],"classifiers":[125],"traditional":[127],"machine":[128],"learning":[129],"methods":[130],"deep":[132],"learning.":[133],"On":[134],"independent":[136],"set,":[138],"Captor":[139,147],"outperformed":[140],"existing":[142],"tool,":[144],"suggesting":[145],"that":[146],"could":[148],"provide":[149],"more":[150],"instructive":[151],"guidance":[152],"experimental":[155],"research":[156],"O-glycosylation.":[158],"The":[159],"source":[160],"code":[161],"datasets":[163],"are":[164],"available":[165],"at":[166],"https://github.com/YanZhu06/Captor/":[167],".":[168]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2021-12-06T00:00:00"}