{"id":"https://openalex.org/W2170076955","doi":"https://doi.org/10.1093/bioinformatics/bth393","title":"DNA structure constraint is probably a fundamental factor inducing CpG deficiency in bacteria","display_name":"DNA structure constraint is probably a fundamental factor inducing CpG deficiency in bacteria","publication_year":2004,"publication_date":"2004-07-09","ids":{"openalex":"https://openalex.org/W2170076955","doi":"https://doi.org/10.1093/bioinformatics/bth393","mag":"2170076955","pmid":"https://pubmed.ncbi.nlm.nih.gov/15247101"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth393","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth393","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/18/3336/48906529/bioinformatics_20_18_3336.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/20/18/3336/48906529/bioinformatics_20_18_3336.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112009281","display_name":"Yong Wang","orcid":"https://orcid.org/0000-0003-3595-3867"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yong Wang","raw_affiliation_strings":["Department of Zoology, The University of Hong Kong, Pokfulam, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Zoology, The University of Hong Kong, Pokfulam, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110130288","display_name":"Frederick C. Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Frederick C. C. Leung","raw_affiliation_strings":["Department of Zoology, The University of Hong Kong, Pokfulam, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Zoology, The University of Hong Kong, Pokfulam, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112009281"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.1206,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.50195583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"20","issue":"18","first_page":"3336","last_page":"3345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10269","display_name":"Epigenetics and DNA Methylation","score":0.9984999895095825,"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/T10269","display_name":"Epigenetics and DNA Methylation","score":0.9984999895095825,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9829999804496765,"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/T10432","display_name":"DNA and Nucleic Acid Chemistry","score":0.9769999980926514,"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/cpg-site","display_name":"CpG site","score":0.8609521389007568},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.7423221468925476},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.6928815245628357},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.6632403135299683},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6257385015487671},{"id":"https://openalex.org/keywords/dna-methylation","display_name":"DNA methylation","score":0.6207578778266907},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.6149661540985107},{"id":"https://openalex.org/keywords/gc-content","display_name":"GC-content","score":0.5964287519454956},{"id":"https://openalex.org/keywords/bacterial-genome-size","display_name":"Bacterial genome size","score":0.5670679807662964},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.46682968735694885},{"id":"https://openalex.org/keywords/differentially-methylated-regions","display_name":"Differentially methylated regions","score":0.4302932322025299},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4195822477340698},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.418254554271698},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.21724116802215576},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09401834011077881}],"concepts":[{"id":"https://openalex.org/C140173407","wikidata":"https://www.wikidata.org/wiki/Q1138358","display_name":"CpG site","level":5,"score":0.8609521389007568},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7423221468925476},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6928815245628357},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.6632403135299683},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6257385015487671},{"id":"https://openalex.org/C190727270","wikidata":"https://www.wikidata.org/wiki/Q874745","display_name":"DNA methylation","level":4,"score":0.6207578778266907},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.6149661540985107},{"id":"https://openalex.org/C42251679","wikidata":"https://www.wikidata.org/wiki/Q933491","display_name":"GC-content","level":4,"score":0.5964287519454956},{"id":"https://openalex.org/C3742359","wikidata":"https://www.wikidata.org/wiki/Q4839988","display_name":"Bacterial genome size","level":4,"score":0.5670679807662964},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.46682968735694885},{"id":"https://openalex.org/C154253233","wikidata":"https://www.wikidata.org/wiki/Q14862240","display_name":"Differentially methylated regions","level":5,"score":0.4302932322025299},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4195822477340698},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.418254554271698},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.21724116802215576},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09401834011077881},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D018899","descriptor_name":"CpG Islands","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018899","descriptor_name":"CpG Islands","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018899","descriptor_name":"CpG Islands","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/bth393","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth393","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/18/3336/48906529/bioinformatics_20_18_3336.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:15247101","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15247101","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.331.4674","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.331.4674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/20/18/3336.full.pdf","raw_type":"text"},{"id":"pmh:oai:hub.hku.hk:10722/84624","is_oa":false,"landing_page_url":"http://hdl.handle.net/10722/84624","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bth393","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth393","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/18/3336/48906529/bioinformatics_20_18_3336.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2170076955.pdf","grobid_xml":"https://content.openalex.org/works/W2170076955.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1964360556","https://openalex.org/W1976190891","https://openalex.org/W1977396924","https://openalex.org/W1986167448","https://openalex.org/W2000026908","https://openalex.org/W2012564126","https://openalex.org/W2025166640","https://openalex.org/W2027762791","https://openalex.org/W2034105248","https://openalex.org/W2035923243","https://openalex.org/W2038399775","https://openalex.org/W2044719651","https://openalex.org/W2050598518","https://openalex.org/W2059301943","https://openalex.org/W2060418270","https://openalex.org/W2061425738","https://openalex.org/W2062909955","https://openalex.org/W2088156872","https://openalex.org/W2092464006","https://openalex.org/W2099533874","https://openalex.org/W2118011548","https://openalex.org/W2121417064","https://openalex.org/W2129201414","https://openalex.org/W2140211206","https://openalex.org/W2147839609","https://openalex.org/W2149272138","https://openalex.org/W2155578142","https://openalex.org/W2161167739","https://openalex.org/W2163408209","https://openalex.org/W4251549090","https://openalex.org/W6811477456"],"related_works":["https://openalex.org/W4233664389","https://openalex.org/W2127540087","https://openalex.org/W2057635072","https://openalex.org/W4286742095","https://openalex.org/W4319927080","https://openalex.org/W2116754984","https://openalex.org/W2963862309","https://openalex.org/W3111025641","https://openalex.org/W3165014476","https://openalex.org/W2170076955"],"abstract_inverted_index":{"By":[0],"comparing":[1],"real":[2],"bacterial":[3,33],"genomes":[4,8,34],"and":[5,79,98],"Markov":[6],"artificial":[7],"in":[9,29,42,77,82,129],"the":[10,16,23,45,50,92,109,122,136],"second":[11],"order,":[12],"we":[13,133],"found":[14],"that":[15,49,60,108,135],"core":[17],"structure":[18,69],"of":[19,36,66,74,103,111,124,138,151],"a":[20,152],"restricted":[21,142],"pattern,":[22,25,47],"TTCGAA":[24],"was":[26],"under":[27],"represented":[28],"low":[30],"GC":[31,96,117,149],"content":[32,97,150],"regardless":[35],"CpG":[37,99,125],"dinucleotide":[38],"level.":[39],"This":[40],"is":[41,52,88],"contrast":[43],"to":[44,63],"AACGTT":[46],"indicating":[48],"counterselection":[51],"context-dependent.":[53],"Further":[54],"study":[55],"discovered":[56],"nine":[57],"underrepresented":[58],"patterns":[59,81,113,143],"were":[61,114],"supposed":[62],"be":[64,145],"capable":[65],"inducing":[67],"DNA":[68,84],"constraint.":[70],"In":[71],"summary,":[72],"most":[73],"them":[75],"are":[76],"TTCGNA":[78],"TTCGAN":[80],"both":[83],"strands.":[85],"An":[86],"explanation":[87],"also":[89],"proposed":[90],"for":[91],"strong":[93],"correlation":[94],"between":[95],"deficiency.":[100],"The":[101],"result":[102],"random":[104],"sequence":[105],"simulation":[106],"showed":[107],"occurrences":[110],"these":[112,130,141],"correlated":[115],"with":[116],"content,":[118],"as":[119,121],"well":[120],"percentage":[123],"dinucleotides":[126],"being":[127],"trapped":[128],"patterns.":[131],"Finally,":[132],"suggest":[134],"degree":[137],"counter-selection":[139],"against":[140],"could":[144],"influenced":[146],"by":[147],"global":[148],"genome.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
