{"id":"https://openalex.org/W4387641991","doi":"https://doi.org/10.1142/s0219720023500245","title":"CBDT-Oglyc: Prediction of O-glycosylation sites using ChiMIC-based balanced decision table and feature selection","display_name":"CBDT-Oglyc: Prediction of O-glycosylation sites using ChiMIC-based balanced decision table and feature selection","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4387641991","doi":"https://doi.org/10.1142/s0219720023500245","pmid":"https://pubmed.ncbi.nlm.nih.gov/37899352"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720023500245","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720023500245","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":"https://openalex.org/A5101612427","display_name":"Ying Zeng","orcid":"https://orcid.org/0000-0002-9358-8047"},"institutions":[{"id":"https://openalex.org/I27688046","display_name":"Hunan Institute of Engineering","ror":"https://ror.org/03zj2rn70","country_code":"CN","type":"education","lineage":["https://openalex.org/I27688046"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Zeng","raw_affiliation_strings":["School of Computer and Communication, Hunan Institute of Engineering, Xiangtan 411104, Hunan, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-9358-8047","affiliations":[{"raw_affiliation_string":"School of Computer and Communication, Hunan Institute of Engineering, Xiangtan 411104, Hunan, P. R. China","institution_ids":["https://openalex.org/I27688046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079474991","display_name":"Zheming Yuan","orcid":"https://orcid.org/0000-0002-7444-8743"},"institutions":[{"id":"https://openalex.org/I52180223","display_name":"Hunan Agricultural University","ror":"https://ror.org/01dzed356","country_code":"CN","type":"education","lineage":["https://openalex.org/I52180223"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheming Yuan","raw_affiliation_strings":["Hunan Engineering & Technology Research Center for Agricultural Big Data Analysis & Decision-Making, Hunan Agricultural University, Changsha 410128, Hunan, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-7444-8743","affiliations":[{"raw_affiliation_string":"Hunan Engineering & Technology Research Center for Agricultural Big Data Analysis & Decision-Making, Hunan Agricultural University, Changsha 410128, Hunan, P. R. China","institution_ids":["https://openalex.org/I52180223"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400884","display_name":"Yuan Chen","orcid":"https://orcid.org/0000-0001-9043-5240"},"institutions":[{"id":"https://openalex.org/I52180223","display_name":"Hunan Agricultural University","ror":"https://ror.org/01dzed356","country_code":"CN","type":"education","lineage":["https://openalex.org/I52180223"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Chen","raw_affiliation_strings":["Hunan Engineering & Technology Research Center for Agricultural Big Data Analysis & Decision-Making, Hunan Agricultural University, Changsha 410128, Hunan, P. R. China"],"raw_orcid":"https://orcid.org/0000-0001-9043-5240","affiliations":[{"raw_affiliation_string":"Hunan Engineering & Technology Research Center for Agricultural Big Data Analysis & Decision-Making, Hunan Agricultural University, Changsha 410128, Hunan, P. R. China","institution_ids":["https://openalex.org/I52180223"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102822284","display_name":"Ying Hu","orcid":"https://orcid.org/0009-0007-3772-2399"},"institutions":[{"id":"https://openalex.org/I27688046","display_name":"Hunan Institute of Engineering","ror":"https://ror.org/03zj2rn70","country_code":"CN","type":"education","lineage":["https://openalex.org/I27688046"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Hu","raw_affiliation_strings":["School of Computer and Communication, Hunan Institute of Engineering, Xiangtan 411104, Hunan, P. R. China"],"raw_orcid":"https://orcid.org/0009-0007-3772-2399","affiliations":[{"raw_affiliation_string":"School of Computer and Communication, Hunan Institute of Engineering, Xiangtan 411104, Hunan, P. R. China","institution_ids":["https://openalex.org/I27688046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101612427"],"corresponding_institution_ids":["https://openalex.org/I27688046"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30393975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"05","first_page":"2350024","last_page":"2350024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9972000122070312,"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":0.9948999881744385,"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":0.7437373399734497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.664170503616333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6614632606506348},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.591731071472168},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48196694254875183},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43866705894470215},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.41519755125045776},{"id":"https://openalex.org/keywords/glycosylation","display_name":"Glycosylation","score":0.41175127029418945},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37207552790641785},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0821397602558136}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7437373399734497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.664170503616333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6614632606506348},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.591731071472168},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48196694254875183},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43866705894470215},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.41519755125045776},{"id":"https://openalex.org/C2777313579","wikidata":"https://www.wikidata.org/wiki/Q898365","display_name":"Glycosylation","level":2,"score":0.41175127029418945},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37207552790641785},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0821397602558136},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720023500245","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720023500245","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:37899352","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37899352","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/G358409668","display_name":null,"funder_award_id":"21B0652","funder_id":"https://openalex.org/F4320333642","funder_display_name":"Scientific Research Foundation of Hunan Provincial Education Department"},{"id":"https://openalex.org/G4866025149","display_name":null,"funder_award_id":"22B0735","funder_id":"https://openalex.org/F4320333642","funder_display_name":"Scientific Research Foundation of Hunan Provincial Education Department"},{"id":"https://openalex.org/G7414000644","display_name":null,"funder_award_id":"XJ2002","funder_id":"https://openalex.org/F4320328214","funder_display_name":"Hunan Institute of Engineering"}],"funders":[{"id":"https://openalex.org/F4320328214","display_name":"Hunan Institute of Engineering","ror":"https://ror.org/03zj2rn70"},{"id":"https://openalex.org/F4320333642","display_name":"Scientific Research Foundation of Hunan Provincial Education Department","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1966762385","https://openalex.org/W1978267297","https://openalex.org/W1990241987","https://openalex.org/W1992042749","https://openalex.org/W1996768014","https://openalex.org/W2008233728","https://openalex.org/W2014509414","https://openalex.org/W2024191848","https://openalex.org/W2063768466","https://openalex.org/W2072918899","https://openalex.org/W2076746539","https://openalex.org/W2077208244","https://openalex.org/W2087196100","https://openalex.org/W2090854439","https://openalex.org/W2092812720","https://openalex.org/W2103525038","https://openalex.org/W2106337298","https://openalex.org/W2107815233","https://openalex.org/W2133312664","https://openalex.org/W2141818629","https://openalex.org/W2150398411","https://openalex.org/W2154053567","https://openalex.org/W2157142295","https://openalex.org/W2158714788","https://openalex.org/W2165700458","https://openalex.org/W2166720212","https://openalex.org/W2263270445","https://openalex.org/W2465546685","https://openalex.org/W2621533740","https://openalex.org/W2939599083","https://openalex.org/W3031804055","https://openalex.org/W3119568991","https://openalex.org/W3124891265","https://openalex.org/W4220910624"],"related_works":["https://openalex.org/W1557094818","https://openalex.org/W2183246718","https://openalex.org/W2099261052","https://openalex.org/W3209204065","https://openalex.org/W2105707930","https://openalex.org/W1755711892","https://openalex.org/W2164205946","https://openalex.org/W2160907113","https://openalex.org/W2070813941","https://openalex.org/W4386317001"],"abstract_inverted_index":{"O-glycosylation":[0,66,75],"(Oglyc)":[1],"plays":[2],"an":[3,45],"important":[4],"role":[5],"in":[6,83,190,197],"various":[7],"biological":[8],"processes.":[9],"The":[10],"key":[11],"to":[12,79,144,204],"understanding":[13],"the":[14,20,34,119,162,174],"mechanisms":[15],"of":[16,36,54,97],"Oglyc":[17,41,81,199],"is":[18,68,77,87,112,136,142,202],"identifying":[19],"corresponding":[21],"glycosylation":[22],"sites.":[23,42],"Two":[24],"critical":[25],"steps,":[26],"feature":[27,47,115],"selection":[28,48],"and":[29,50,105,121,138,181,201],"classifier":[30,52,148,164],"design,":[31],"greatly":[32],"affect":[33],"accuracy":[35],"computational":[37,60],"methods":[38,189],"for":[39,74,114],"predicting":[40,198],"Based":[43,155],"on":[44,132,156,178,209],"efficient":[46],"algorithm":[49,111],"a":[51,58,128,146,157],"capable":[53],"handling":[55],"imbalanced":[56,126],"datasets,":[57],"new":[59],"method,":[61],"ChiMIC-based":[62,70,150],"balanced":[63,71,151],"decision":[64,72,152],"table":[65,73,153],"(CBDT-Oglyc),":[67,76],"proposed.":[69],"proposed":[78],"predict":[80],"sites":[82,200],"proteins.":[84],"Sequence":[85],"characterization":[86],"performed":[88],"by":[89],"combining":[90],"amino":[91,101],"acid":[92,102],"composition":[93,96],"(AAC),":[94],"undirected":[95],"[Formula:":[98],"see":[99],"text]-spaced":[100],"pairs":[103],"(undirected-CKSAAP)":[104],"pseudo-position-specific":[106],"scoring":[107],"matrix":[108],"(PsePSSM).":[109],"Chi-MIC-share":[110],"used":[113],"selection,":[116],"which":[117],"simplifies":[118],"model":[120],"improves":[122],"predictive":[123],"accuracy.":[124,192],"For":[125],"classification,":[127],"backtracking":[129],"method":[130],"based":[131],"local":[133],"chi-square":[134],"test":[135,176],"designed,":[137],"then":[139],"cost-sensitive":[140],"learning":[141],"incorporated":[143],"construct":[145],"novel":[147],"named":[149],"(CBDT).":[154],"1:49":[158],"(positives:negatives)":[159],"training":[160],"set,":[161],"CBDT":[163],"achieves":[165],"significantly":[166],"better":[167],"prediction":[168],"performance":[169],"than":[170],"traditional":[171],"classifiers.":[172],"Moreover,":[173],"independent":[175],"results":[177],"separate":[179],"human":[180],"mouse":[182],"glycoproteins":[183],"show":[184],"that":[185],"CBDT-Oglyc":[186,193],"outperforms":[187],"previous":[188],"global":[191],"shows":[194],"great":[195],"promise":[196],"expected":[203],"facilitate":[205],"further":[206],"experimental":[207],"studies":[208],"protein":[210],"glycosylation.":[211]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
