{"id":"https://openalex.org/W2147330307","doi":"https://doi.org/10.1093/bioinformatics/btn233","title":"ProBias: a web-server for the identification of user-specified types of compositionally biased segments in protein sequences","display_name":"ProBias: a web-server for the identification of user-specified types of compositionally biased segments in protein sequences","publication_year":2008,"publication_date":"2008-05-14","ids":{"openalex":"https://openalex.org/W2147330307","doi":"https://doi.org/10.1093/bioinformatics/btn233","mag":"2147330307","pmid":"https://pubmed.ncbi.nlm.nih.gov/18480099"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btn233","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn233","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/13/1534/49049974/bioinformatics_24_13_1534.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/24/13/1534/49049974/bioinformatics_24_13_1534.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"]},{"id":"https://openalex.org/I870398029","display_name":"Center for Excellence in Education","ror":"https://ror.org/03qhz4n98","country_code":"US","type":"education","lineage":["https://openalex.org/I870398029"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Igor B. Kuznetsov","raw_affiliation_strings":["Gen\u22c6NY\u22c6sis Center for Excellence in Cancer Genomics, Department of Epidemiology and Biostatistics, One Discovery Drive, University at Albany, Rensselaer, NY 12144, USA","Gen*NY*Sis Center for Excellence in Cancer Genomics, Department of Epidemiology and Biostatistics, One Discovery Drive, University at Albany, Rensselaer, NY 12144, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gen\u22c6NY\u22c6sis Center for Excellence in Cancer Genomics, Department of Epidemiology and Biostatistics, One Discovery Drive, University at Albany, 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, One Discovery Drive, University at Albany, Rensselaer, NY 12144, USA#TAB#","institution_ids":["https://openalex.org/I870398029"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031363135"],"corresponding_institution_ids":["https://openalex.org/I392282","https://openalex.org/I870398029"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":null,"fwci":0.1299,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.54032757,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"24","issue":"13","first_page":"1534","last_page":"1535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.19439999759197235,"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":0.19439999759197235,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.1111999973654747,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11162","display_name":"Enzyme Structure and Function","score":0.1071000024676323,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.7477319836616516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6496604084968567},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6401230096817017},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5511878132820129},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5366695523262024},{"id":"https://openalex.org/keywords/web-site","display_name":"Web site","score":0.47215843200683594},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.45769768953323364},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3287516236305237},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.30246251821517944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23214808106422424},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21960490942001343},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.17927375435829163},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.16468378901481628}],"concepts":[{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.7477319836616516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6496604084968567},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6401230096817017},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5511878132820129},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5366695523262024},{"id":"https://openalex.org/C2984519610","wikidata":"https://www.wikidata.org/wiki/Q35127","display_name":"Web site","level":3,"score":0.47215843200683594},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.45769768953323364},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3287516236305237},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30246251821517944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23214808106422424},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21960490942001343},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.17927375435829163},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.16468378901481628},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","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":"D008969","descriptor_name":"Molecular Sequence Data","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":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btn233","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn233","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/13/1534/49049974/bioinformatics_24_13_1534.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:18480099","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18480099","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":"Journal Article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btn233","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn233","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/13/1534/49049974/bioinformatics_24_13_1534.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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2147330307.pdf","grobid_xml":"https://content.openalex.org/works/W2147330307.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1491176290","https://openalex.org/W1497984091","https://openalex.org/W1513332069","https://openalex.org/W2008399824","https://openalex.org/W2032113351","https://openalex.org/W2064368562","https://openalex.org/W2089431713","https://openalex.org/W2096950454","https://openalex.org/W2104412724","https://openalex.org/W2108428298","https://openalex.org/W2111335223","https://openalex.org/W2123178347","https://openalex.org/W2126155530","https://openalex.org/W2154610073","https://openalex.org/W2160011199","https://openalex.org/W2161409639","https://openalex.org/W2614130212","https://openalex.org/W4255690077"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W1533177136","https://openalex.org/W4380994516","https://openalex.org/W2556260348"],"abstract_inverted_index":{"UNLABELLED:":[0],"Most":[1],"proteins":[2,96],"contain":[3,21],"compositionally":[4],"biased":[5],"segments":[6],"(CBS)":[7],"in":[8],"which":[9],"one":[10],"or":[11,119],"more":[12],"amino":[13,22,50],"acid":[14,51],"types":[15],"are":[16,130],"significantly":[17],"overrepresented.":[18],"CBS":[19,46,64,103],"that":[20,40,97],"acids":[23],"with":[24],"similar":[25],"chemical":[26],"properties":[27],"can":[28,107],"have":[29],"functional":[30,99],"and":[31,65],"structural":[32],"importance.":[33],"This":[34],"article":[35],"describes":[36],"ProBias,":[37],"a":[38,42],"web-server":[39,80],"searches":[41],"protein":[43],"sequence":[44],"for":[45,114],"composed":[47],"of":[48,63,87,94],"user-specified":[49],"types.":[52],"ProBias":[53,106],"utilizes":[54],"the":[55,75,83,88,92,112],"discrete":[56],"scan":[57],"statistics":[58],"to":[59,68,110],"estimate":[60],"statistical":[61],"significance":[62],"is":[66],"able":[67],"detect":[69],"even":[70],"subtle":[71],"local":[72],"deviations":[73],"from":[74],"random":[76],"independence":[77],"model.":[78],"The":[79],"also":[81],"analyzes":[82],"global":[84],"compositional":[85],"bias":[86],"input":[89],"sequence.":[90],"In":[91],"case":[93],"novel":[95],"lack":[98],"annotation,":[100],"statistically":[101],"significant":[102],"reported":[104],"by":[105],"be":[108],"used":[109],"guide":[111],"search":[113],"potential":[115],"functionally":[116],"important":[117],"sites":[118],"domains.":[120],"AVAILABILITY:":[121],"Freely":[122],"available":[123,131],"at":[124,132],"http://lcg.rit.albany.edu/ProBias.":[125],"SUPPLEMENTARY":[126],"INFORMATION:":[127],"Supplementary":[128],"data":[129],"Bioinformatics":[133],"online.":[134]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
