{"id":"https://openalex.org/W2126155530","doi":"https://doi.org/10.1093/bioinformatics/btl049","title":"A novel sensitive method for the detection of user-defined compositional bias in biological sequences","display_name":"A novel sensitive method for the detection of user-defined compositional bias in biological sequences","publication_year":2006,"publication_date":"2006-02-24","ids":{"openalex":"https://openalex.org/W2126155530","doi":"https://doi.org/10.1093/bioinformatics/btl049","mag":"2126155530","pmid":"https://pubmed.ncbi.nlm.nih.gov/16500936"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btl049","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl049","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/9/1055/48840125/bioinformatics_22_9_1055.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/22/9/1055/48840125/bioinformatics_22_9_1055.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031363135","display_name":"Igor B. Kuznetsov","orcid":"https://orcid.org/0000-0003-3741-8964"},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Igor B. Kuznetsov","raw_affiliation_strings":["Gen*NY*sis Center for Excellence in Cancer Genomics, Department of Epidemiology and Biostatistics, University at Albany, State University of New York \u00a0 One Discovery Drive, Rensselaer, NY 12144, USA","Gen*NY*sis Center for Excellence in Cancer Genomics, Department of Epidemiology and Biostatistics, University at Albany, State University of New York One Discovery Drive, Rensselaer, NY 12144, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gen*NY*sis Center for Excellence in Cancer Genomics, Department of Epidemiology and Biostatistics, University at Albany, State University of New York \u00a0 One Discovery Drive, Rensselaer, NY 12144, USA","institution_ids":["https://openalex.org/I392282"]},{"raw_affiliation_string":"Gen*NY*sis Center for Excellence in Cancer Genomics, Department of Epidemiology and Biostatistics, University at Albany, State University of New York One Discovery Drive, Rensselaer, NY 12144, USA#TAB#","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035762390","display_name":"Seungwoo Hwang","orcid":"https://orcid.org/0000-0002-1523-8340"},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seungwoo Hwang","raw_affiliation_strings":["Gen*NY*sis Center for Excellence in Cancer Genomics, Department of Epidemiology and Biostatistics, University at Albany, State University of New York \u00a0 One Discovery Drive, Rensselaer, NY 12144, USA","Gen*NY*sis Center for Excellence in Cancer Genomics, Department of Epidemiology and Biostatistics, University at Albany, State University of New York One Discovery Drive, Rensselaer, NY 12144, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gen*NY*sis Center for Excellence in Cancer Genomics, Department of Epidemiology and Biostatistics, University at Albany, State University of New York \u00a0 One Discovery Drive, Rensselaer, NY 12144, USA","institution_ids":["https://openalex.org/I392282"]},{"raw_affiliation_string":"Gen*NY*sis Center for Excellence in Cancer Genomics, Department of Epidemiology and Biostatistics, University at Albany, State University of New York One Discovery Drive, Rensselaer, NY 12144, USA#TAB#","institution_ids":["https://openalex.org/I392282"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5031363135"],"corresponding_institution_ids":["https://openalex.org/I392282"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.8489,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.87620405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"22","issue":"9","first_page":"1055","last_page":"1063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.17479999363422394,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.17479999363422394,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.10909999907016754,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.06509999930858612,"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/computer-science","display_name":"Computer science","score":0.641838788986206},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48879238963127136},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4368932545185089},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4068514108657837},{"id":"https://openalex.org/keywords/biological-system","display_name":"Biological system","score":0.3833700716495514},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38291454315185547},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3691387176513672},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.32615721225738525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29277142882347107},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.26404786109924316},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.14359349012374878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.641838788986206},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48879238963127136},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4368932545185089},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4068514108657837},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3833700716495514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38291454315185547},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3691387176513672},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.32615721225738525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29277142882347107},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.26404786109924316},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.14359349012374878},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btl049","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl049","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/9/1055/48840125/bioinformatics_22_9_1055.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:16500936","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16500936","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}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btl049","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl049","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/9/1055/48840125/bioinformatics_22_9_1055.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":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2126155530.pdf","grobid_xml":"https://content.openalex.org/works/W2126155530.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W68124440","https://openalex.org/W91742334","https://openalex.org/W1017703714","https://openalex.org/W1513332069","https://openalex.org/W1591864042","https://openalex.org/W1972097354","https://openalex.org/W1980841561","https://openalex.org/W1986769472","https://openalex.org/W1995864101","https://openalex.org/W2003144438","https://openalex.org/W2008399824","https://openalex.org/W2021800656","https://openalex.org/W2030736691","https://openalex.org/W2037958165","https://openalex.org/W2042968613","https://openalex.org/W2049156449","https://openalex.org/W2096950454","https://openalex.org/W2098822637","https://openalex.org/W2103017472","https://openalex.org/W2104412724","https://openalex.org/W2108428298","https://openalex.org/W2126625758","https://openalex.org/W2130479394","https://openalex.org/W2132129663","https://openalex.org/W2135083016","https://openalex.org/W2158714788","https://openalex.org/W2160011199","https://openalex.org/W2161409639","https://openalex.org/W2165890129","https://openalex.org/W2165999027","https://openalex.org/W2169009914","https://openalex.org/W2324660492","https://openalex.org/W4213149192","https://openalex.org/W4255690077"],"related_works":["https://openalex.org/W1921169094","https://openalex.org/W366410996","https://openalex.org/W4239902399","https://openalex.org/W2002243093","https://openalex.org/W2146076056","https://openalex.org/W2971191913","https://openalex.org/W2144092555","https://openalex.org/W2731939565","https://openalex.org/W1528058524","https://openalex.org/W2800590509"],"abstract_inverted_index":{"MOTIVATION:":[0],"Most":[1],"biological":[2,193],"sequences":[3],"contain":[4,56],"compositionally":[5,32,87,114,149,202],"biased":[6,33,53,88,115,150,203],"segments":[7,24,34,54,89,116],"in":[8,65],"which":[9],"one":[10],"or":[11],"more":[12],"residue":[13,123],"types":[14,30,98,200],"are":[15,25,35,63,195],"significantly":[16,196],"overrepresented.":[17],"The":[18,152],"function":[19,194],"and":[20,37,71,82,177],"evolution":[21],"of":[22,31,50,68,78,85,95,99,113,118,122,144,147,165,168,188,201],"these":[23],"poorly":[26],"understood.":[27],"Usually,":[28],"all":[29],"masked":[36],"ignored":[38],"during":[39],"sequence":[40],"analysis.":[41],"However,":[42],"it":[43],"has":[44],"been":[45],"shown":[46],"for":[47,110,137],"a":[48,66,91,106,119,133],"number":[49],"proteins":[51,189],"that":[52,55,131,186],"amino":[57],"acids":[58],"with":[59,190,198],"similar":[60],"chemical":[61],"properties":[62],"involved":[64],"variety":[67],"molecular":[69],"functions":[70],"human":[72],"diseases.":[73],"A":[74],"detailed":[75],"large-scale":[76],"analysis":[77],"the":[79,111,127,145,166,191],"functional":[80],"implications":[81],"evolutionary":[83],"conservation":[84],"different":[86],"requires":[90],"sensitive":[92,108],"method":[93,109,153],"capable":[94],"detecting":[96],"user-specified":[97,120],"compositional":[100,159],"bias.":[101],"RESULTS:":[102],"We":[103,180],"present":[104],"BIAS,":[105],"novel":[107],"detection":[112],"composed":[117],"set":[121],"types.":[124],"BIAS":[125,171,183],"uses":[126],"discrete":[128],"scan":[129],"statistics":[130],"provides":[132],"highly":[134],"accurate":[135],"correction":[136],"multiple":[138],"tests":[139],"to":[140,184],"compute":[141],"analytical":[142,163],"estimates":[143,164],"significance":[146,167],"each":[148],"segment.":[151],"can":[154],"take":[155],"into":[156],"account":[157],"global":[158],"bias":[160],"when":[161],"computing":[162],"local":[169],"clusters.":[170],"is":[172],"benchmarked":[173],"against":[174],"SEG,":[175],"SAPS":[176],"CAST":[178],"programs.":[179],"also":[181],"use":[182],"show":[185],"groups":[187],"same":[192],"associated":[197],"particular":[199],"segments.":[204]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-23T06:36:01.041984","created_date":"2025-10-10T00:00:00"}
