{"id":"https://openalex.org/W2915025660","doi":"https://doi.org/10.1142/s0219720019500100","title":"Is there codon usage bias for poly-Q stretches in the human proteome?","display_name":"Is there codon usage bias for poly-Q stretches in the human proteome?","publication_year":2019,"publication_date":"2019-01-25","ids":{"openalex":"https://openalex.org/W2915025660","doi":"https://doi.org/10.1142/s0219720019500100","mag":"2915025660","pmid":"https://pubmed.ncbi.nlm.nih.gov/30866735"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720019500100","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720019500100","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/A5023828983","display_name":"Oxana V. Galzitskaya","orcid":"https://orcid.org/0000-0002-3962-1520"},"institutions":[{"id":"https://openalex.org/I4210137602","display_name":"Institute of Protein Research","ror":"https://ror.org/0489f0s93","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210129690","https://openalex.org/I4210137602"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Oxana V. Galzitskaya","raw_affiliation_strings":["Institute of Protein Research, Russian Academy of Sciences, Institutskaya Str., 4, Pushchino, Moscow Region 142290, Russia"],"raw_orcid":"https://orcid.org/0000-0002-3962-1520","affiliations":[{"raw_affiliation_string":"Institute of Protein Research, Russian Academy of Sciences, Institutskaya Str., 4, Pushchino, Moscow Region 142290, Russia","institution_ids":["https://openalex.org/I4210137602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009627524","display_name":"Georgii Novikov","orcid":"https://orcid.org/0000-0002-3558-6676"},"institutions":[{"id":"https://openalex.org/I1328943360","display_name":"Saint Petersburg Academic University","ror":"https://ror.org/05ne3s142","country_code":"RU","type":"education","lineage":["https://openalex.org/I1313323035","https://openalex.org/I1328943360","https://openalex.org/I4210096333"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Georgii S. Novikov","raw_affiliation_strings":["St. Petersburg Academic University, Nanotechnology Research and Education Centre of the Russian Academy of Sciences, St. Petersburg, Khlopina Str., 8/3, 194021, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"St. Petersburg Academic University, Nanotechnology Research and Education Centre of the Russian Academy of Sciences, St. Petersburg, Khlopina Str., 8/3, 194021, Russia","institution_ids":["https://openalex.org/I1328943360"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045067748","display_name":"Nikita V. Dovidchenko","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137602","display_name":"Institute of Protein Research","ror":"https://ror.org/0489f0s93","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210129690","https://openalex.org/I4210137602"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Nikita V. Dovidchenko","raw_affiliation_strings":["Institute of Protein Research, Russian Academy of Sciences, Institutskaya Str., 4, Pushchino, Moscow Region 142290, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Protein Research, Russian Academy of Sciences, Institutskaya Str., 4, Pushchino, Moscow Region 142290, Russia","institution_ids":["https://openalex.org/I4210137602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103474857","display_name":"M. Yu. Lobanov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137602","display_name":"Institute of Protein Research","ror":"https://ror.org/0489f0s93","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210129690","https://openalex.org/I4210137602"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Mikhail Yu. Lobanov","raw_affiliation_strings":["Institute of Protein Research, Russian Academy of Sciences, Institutskaya Str., 4, Pushchino, Moscow Region 142290, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Protein Research, Russian Academy of Sciences, Institutskaya Str., 4, Pushchino, Moscow Region 142290, Russia","institution_ids":["https://openalex.org/I4210137602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023828983"],"corresponding_institution_ids":["https://openalex.org/I4210137602"],"apc_list":null,"apc_paid":null,"fwci":0.171,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.51363952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"17","issue":"01","first_page":"1950010","last_page":"1950010"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","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/T10521","display_name":"RNA and protein synthesis mechanisms","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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9986000061035156,"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/proteome","display_name":"Proteome","score":0.8326462507247925},{"id":"https://openalex.org/keywords/human-proteome-project","display_name":"Human proteome project","score":0.8100125193595886},{"id":"https://openalex.org/keywords/codon-usage-bias","display_name":"Codon usage bias","score":0.6297997236251831},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5680805444717407},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.5427982211112976},{"id":"https://openalex.org/keywords/glutamine","display_name":"Glutamine","score":0.5339625477790833},{"id":"https://openalex.org/keywords/alternative-splicing","display_name":"Alternative splicing","score":0.513508141040802},{"id":"https://openalex.org/keywords/rna-splicing","display_name":"RNA splicing","score":0.49304720759391785},{"id":"https://openalex.org/keywords/protein-data-bank","display_name":"Protein Data Bank (RCSB PDB)","score":0.4906562864780426},{"id":"https://openalex.org/keywords/human-proteins","display_name":"Human proteins","score":0.4853188395500183},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.48516207933425903},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.45365631580352783},{"id":"https://openalex.org/keywords/stop-codon","display_name":"Stop codon","score":0.4353669285774231},{"id":"https://openalex.org/keywords/amino-acid","display_name":"Amino acid","score":0.33195754885673523},{"id":"https://openalex.org/keywords/exon","display_name":"Exon","score":0.30032098293304443},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.2796046733856201},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.22908082604408264},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.22575202584266663},{"id":"https://openalex.org/keywords/proteomics","display_name":"Proteomics","score":0.18233337998390198},{"id":"https://openalex.org/keywords/rna","display_name":"RNA","score":0.07366403937339783}],"concepts":[{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.8326462507247925},{"id":"https://openalex.org/C94795543","wikidata":"https://www.wikidata.org/wiki/Q3813754","display_name":"Human proteome project","level":4,"score":0.8100125193595886},{"id":"https://openalex.org/C87253356","wikidata":"https://www.wikidata.org/wiki/Q1106472","display_name":"Codon usage bias","level":4,"score":0.6297997236251831},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5680805444717407},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5427982211112976},{"id":"https://openalex.org/C2779349466","wikidata":"https://www.wikidata.org/wiki/Q181619","display_name":"Glutamine","level":3,"score":0.5339625477790833},{"id":"https://openalex.org/C194583182","wikidata":"https://www.wikidata.org/wiki/Q21114084","display_name":"Alternative splicing","level":4,"score":0.513508141040802},{"id":"https://openalex.org/C54458228","wikidata":"https://www.wikidata.org/wiki/Q237218","display_name":"RNA splicing","level":4,"score":0.49304720759391785},{"id":"https://openalex.org/C65556437","wikidata":"https://www.wikidata.org/wiki/Q766195","display_name":"Protein Data Bank (RCSB PDB)","level":2,"score":0.4906562864780426},{"id":"https://openalex.org/C2911029443","wikidata":"https://www.wikidata.org/wiki/Q21296145","display_name":"Human proteins","level":3,"score":0.4853188395500183},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.48516207933425903},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.45365631580352783},{"id":"https://openalex.org/C20580545","wikidata":"https://www.wikidata.org/wiki/Q28354","display_name":"Stop codon","level":3,"score":0.4353669285774231},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.33195754885673523},{"id":"https://openalex.org/C36823959","wikidata":"https://www.wikidata.org/wiki/Q373027","display_name":"Exon","level":3,"score":0.30032098293304443},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2796046733856201},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.22908082604408264},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.22575202584266663},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.18233337998390198},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.07366403937339783}],"mesh":[{"descriptor_ui":"D000081183","descriptor_name":"Codon Usage","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000081183","descriptor_name":"Codon Usage","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000081183","descriptor_name":"Codon Usage","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020449","descriptor_name":"Repetitive Sequences, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020449","descriptor_name":"Repetitive Sequences, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020449","descriptor_name":"Repetitive Sequences, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D064267","descriptor_name":"Intrinsically Disordered Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720019500100","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720019500100","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:30866735","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30866735","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/G1816318948","display_name":null,"funder_award_id":"18-14-00321","funder_id":"https://openalex.org/F4320324099","funder_display_name":"Russian Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320324099","display_name":"Russian Science Foundation","ror":"https://ror.org/03y2gwe85"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W978290998","https://openalex.org/W1553492626","https://openalex.org/W1789686293","https://openalex.org/W1994402808","https://openalex.org/W1995385480","https://openalex.org/W2030853720","https://openalex.org/W2040271470","https://openalex.org/W2043750605","https://openalex.org/W2044341390","https://openalex.org/W2053780937","https://openalex.org/W2059704674","https://openalex.org/W2080457513","https://openalex.org/W2126877059","https://openalex.org/W2137373119","https://openalex.org/W2166131777","https://openalex.org/W2324199163","https://openalex.org/W2327743356","https://openalex.org/W2410790038","https://openalex.org/W2609055977","https://openalex.org/W2768477255","https://openalex.org/W2792064435","https://openalex.org/W2883034802","https://openalex.org/W4252232449"],"related_works":["https://openalex.org/W2591608042","https://openalex.org/W2580329791","https://openalex.org/W2137401535","https://openalex.org/W2167973314","https://openalex.org/W2299447828","https://openalex.org/W4389024253","https://openalex.org/W2730490632","https://openalex.org/W3199390947","https://openalex.org/W2293189348","https://openalex.org/W2386962198"],"abstract_inverted_index":{"We":[0,115],"have":[1,17,36,116],"analyzed":[2],"codon":[3,41,56,98],"usage":[4,42],"for":[5,11,40,43,59,71,81,94,101,108,118],"poly-Q":[6,22,60,119],"stretches":[7,23,61,120],"of":[8,92,150],"different":[9],"lengths":[10],"the":[12,31,38,47,51,54,87,90,96,111,122,130,135,145,151],"human":[13,48,72,112,123],"proteome.":[14,49],"First,":[15],"we":[16,35],"obtained":[18,70],"that":[19,125],"all":[20],"long":[21],"in":[24,46,121,126,138],"Protein":[25],"Data":[26],"Bank":[27],"(PDB)":[28],"belong":[29],"to":[30,134],"disordered":[32],"regions.":[33],"Second,":[34],"found":[37],"bias":[39],"glutamine":[44,75,102],"homo-repeats":[45,76,103,136,152],"In":[50],"cases":[52,128],"when":[53],"same":[55,97],"is":[57,99,104],"used":[58,100],"only":[62],"CAG":[63],"triplets":[64],"are":[65,69],"found.":[66],"Similar":[67],"results":[68],"proteins":[73,82,93,109],"with":[74,78,84,153],"associated":[77,83],"diseases.":[79],"Moreover,":[80],"diseases":[85],"(from":[86],"HraDis":[88],"database),":[89],"fraction":[91],"which":[95],"less":[105],"(22%)":[106],"than":[107],"from":[110],"proteome":[113,124],"(26%).":[114],"demonstrated":[117],"some":[127],"(28)":[129],"splicing":[131],"sites":[132,142],"correspond":[133],"and":[137],"11":[139],"cases,":[140],"these":[141],"appear":[143],"at":[144],"[Formula:":[146],"see":[147,157],"text]-terminal":[148],"part":[149],"statistical":[154],"significance":[155],"10[Formula:":[156],"text].":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}