{"id":"https://openalex.org/W2170037754","doi":"https://doi.org/10.1186/1471-2105-11-s1-s66","title":"BayesMotif: de novo protein sorting motif discovery from impure datasets","display_name":"BayesMotif: de novo protein sorting motif discovery from impure datasets","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2170037754","doi":"https://doi.org/10.1186/1471-2105-11-s1-s66","mag":"2170037754","pmid":"https://pubmed.ncbi.nlm.nih.gov/20122242"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-11-s1-s66","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-s1-s66","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-S1-S66","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-S1-S66","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060537711","display_name":"Jianjun Hu","orcid":"https://orcid.org/0000-0002-8725-6660"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jianjun Hu","raw_affiliation_strings":["Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA. jianjunh@cse.sc.edu","Department of Computer Science and Engineering, University of South Carolina, Columbia, SC, 29208, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA. jianjunh@cse.sc.edu","institution_ids":["https://openalex.org/I155781252"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of South Carolina, Columbia, SC, 29208, USA","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403556","display_name":"Fan Zhang","orcid":"https://orcid.org/0000-0003-2176-3835"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of South Carolina, Columbia, SC, 29208, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of South Carolina, Columbia, SC, 29208, USA","institution_ids":["https://openalex.org/I155781252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5060537711"],"corresponding_institution_ids":["https://openalex.org/I155781252"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.1245,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52255146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"11","issue":"S1","first_page":"S66","last_page":"S66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.738099992275238,"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":0.738099992275238,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.042899999767541885,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.03020000085234642,"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/computational-biology","display_name":"Computational biology","score":0.6817296743392944},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.6683576703071594},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.562507688999176},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.4486885964870453},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.41658246517181396},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3967477083206177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3656402826309204},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.33797216415405273},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.28801456093788147},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.19168692827224731},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.08819013833999634},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06361603736877441}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6817296743392944},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.6683576703071594},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.562507688999176},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.4486885964870453},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.41658246517181396},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3967477083206177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3656402826309204},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.33797216415405273},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.28801456093788147},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.19168692827224731},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.08819013833999634},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06361603736877441},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056510","descriptor_name":"Position-Specific Scoring Matrices","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056510","descriptor_name":"Position-Specific Scoring Matrices","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056510","descriptor_name":"Position-Specific Scoring Matrices","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-11-s1-s66","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-s1-s66","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-S1-S66","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:20122242","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20122242","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:scholarcommons.sc.edu:csce_facpub-1110","is_oa":true,"landing_page_url":"https://scholarcommons.sc.edu/csce_facpub/119","pdf_url":null,"source":{"id":"https://openalex.org/S4377196354","display_name":"Scholar Commons (University of South Carolina)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I155781252","host_organization_name":"University of South Carolina","host_organization_lineage":["https://openalex.org/I155781252"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:3009540","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3009540","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-11-s1-s66","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-s1-s66","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-S1-S66","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6877852469","display_name":"CAREER:   Computational Analysis and Prediction of Genome-Wide Protein Targeting Signals and Localization","funder_award_id":"0845381","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310846","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2170037754.pdf","grobid_xml":"https://content.openalex.org/works/W2170037754.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1527927437","https://openalex.org/W1607784649","https://openalex.org/W2016076539","https://openalex.org/W2028903194","https://openalex.org/W2033976445","https://openalex.org/W2039290359","https://openalex.org/W2054163716","https://openalex.org/W2089047063","https://openalex.org/W2097727546","https://openalex.org/W2107751776","https://openalex.org/W2111127373","https://openalex.org/W2119309676","https://openalex.org/W2137933191","https://openalex.org/W2139042094","https://openalex.org/W2145091349","https://openalex.org/W2156125289","https://openalex.org/W2161746138","https://openalex.org/W2168514491","https://openalex.org/W2289232069"],"related_works":["https://openalex.org/W3170299350","https://openalex.org/W2368410102","https://openalex.org/W2368037387","https://openalex.org/W2073661767","https://openalex.org/W2380185347","https://openalex.org/W2370034659","https://openalex.org/W2159636084","https://openalex.org/W2117168988","https://openalex.org/W2103777723","https://openalex.org/W2610941444"],"abstract_inverted_index":{"BACKGROUND:":[0],"Protein":[1],"sorting":[2,29,38,59,75,85,92,118,183,242],"is":[3,24,61,77,126,140,210],"the":[4,20,47,81,90,155,176,196,214,271,286,293],"process":[5,23],"that":[6,146,154,175,195],"newly":[7],"synthesized":[8],"proteins":[9],"are":[10,40,147],"transported":[11],"to":[12,79,142,149,203,248,291],"their":[13],"target":[14],"locations":[15],"within":[16],"or":[17,49,187,283],"outside":[18],"of":[19,37,51,57,73,83,112,116,213,235,239,273,276,285,295],"cell.":[21],"This":[22],"precisely":[25],"regulated":[26],"by":[27],"protein":[28,52,58,74,84,91,117,189,241],"signals":[30,39,60,76],"in":[31,120],"different":[32],"forms.":[33],"A":[34,135],"major":[35],"category":[36,238],"amino":[41],"acid":[42],"sub-sequences":[43],"usually":[44],"located":[45],"at":[46],"N-terminals":[48],"C-terminals":[50],"sequences.":[53,163],"Genome-wide":[54],"experimental":[55],"identification":[56,111],"extremely":[62],"time-consuming":[63],"and":[64,100,171],"costly.":[65],"Effective":[66],"computational":[67],"algorithms":[68,252],"for":[69,108,231],"de":[70,109,232],"novo":[71,110,233],"discovery":[72,94,234,251],"needed":[78],"improve":[80],"understanding":[82],"mechanisms.":[86],"METHODS:":[87],"We":[88,222],"formulated":[89],"motif":[93,133,169,219,250,300],"problem":[95,99],"as":[96,254,281],"a":[97,102,113,122,130,225,236],"classification":[98,228],"proposed":[101,223],"Bayesian":[103,227],"classifier":[104],"based":[105,229],"algorithm":[106,156,179,230,257,268],"(BayesMotif)":[107],"common":[114],"type":[115],"motifs":[119,152,159,184,206,243,261,287],"which":[121,288],"highly":[123,264],"conserved":[124,132,265],"anchor":[125],"present":[127],"along":[128],"with":[129,262],"less":[131],"regions.":[134],"false":[136,197],"positive":[137,198],"removal":[138,199],"procedure":[139,200],"developed":[141],"iteratively":[143],"remove":[144],"sequences":[145,216],"unlikely":[148],"contain":[150],"true":[151,205,218],"so":[153],"can":[157,180,201,258],"identify":[158,181,204],"from":[160,185,244],"impure":[161,188,245],"input":[162,215],"RESULTS:":[164],"Experiments":[165],"on":[166],"both":[167],"implanted":[168],"datasets":[170,173],"real-world":[172],"showed":[174],"enhanced":[177],"BayesMotif":[178],"anchored":[182,240],"pure":[186],"sequence":[190],"dataset.":[191],"It":[192],"also":[193,269],"shows":[194],"help":[202,290],"even":[207],"when":[208],"there":[209],"only":[211],"20%":[212],"containing":[217],"instances.":[220],"CONCLUSION:":[221],"BayesMotif,":[224],"novel":[226],"special":[237],"datasets.":[246],"Compared":[247],"conventional":[249],"such":[253,280],"MEME,":[255],"our":[256],"find":[259],"less-conserved":[260],"short":[263],"anchors.":[266],"Our":[267],"has":[270],"advantage":[272],"easy":[274],"incorporation":[275],"additional":[277],"meta-sequence":[278],"features":[279],"hydrophobicity":[282],"charge":[284],"may":[289],"overcome":[292],"limitations":[294],"PWM":[296],"(position":[297],"weight":[298],"matrix)":[299],"model.":[301]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}