{"id":"https://openalex.org/W2150028022","doi":"https://doi.org/10.1093/bioinformatics/btn089","title":"Biological sequence classification utilizing positive and unlabeled data","display_name":"Biological sequence classification utilizing positive and unlabeled data","publication_year":2008,"publication_date":"2008-03-14","ids":{"openalex":"https://openalex.org/W2150028022","doi":"https://doi.org/10.1093/bioinformatics/btn089","mag":"2150028022","pmid":"https://pubmed.ncbi.nlm.nih.gov/18344247"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btn089","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn089","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/9/1198/49046088/bioinformatics_24_9_1198.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/24/9/1198/49046088/bioinformatics_24_9_1198.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101505354","display_name":"Yuanyuan Xiao","orcid":"https://orcid.org/0000-0003-0908-1364"},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanyuan Xiao","raw_affiliation_strings":["Department of Epidemiology and Biostatistics, Center for Bioinformatics and Molecular Biostatistics, University of California, San Francisco, CA 94107, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Epidemiology and Biostatistics, Center for Bioinformatics and Molecular Biostatistics, University of California, San Francisco, CA 94107, USA","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013969270","display_name":"Mark R. Segal","orcid":"https://orcid.org/0000-0003-4213-3138"},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mark R. Segal","raw_affiliation_strings":["Department of Epidemiology and Biostatistics, Center for Bioinformatics and Molecular Biostatistics, University of California, San Francisco, CA 94107, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Epidemiology and Biostatistics, Center for Bioinformatics and Molecular Biostatistics, University of California, San Francisco, CA 94107, USA","institution_ids":["https://openalex.org/I180670191"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5013969270"],"corresponding_institution_ids":["https://openalex.org/I180670191"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":null,"fwci":0.3897,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.62830197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"24","issue":"9","first_page":"1198","last_page":"1205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.9983999729156494,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.9983999729156494,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9980000257492065,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.996399998664856,"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":0.6593413352966309},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6196990013122559},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5789124965667725},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5426159501075745},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5347883105278015},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5183888077735901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.513484537601471},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.49291348457336426},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4884559214115143},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.48826050758361816},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.43996962904930115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4296048879623413},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4177979826927185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6593413352966309},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6196990013122559},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5789124965667725},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5426159501075745},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5347883105278015},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5183888077735901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.513484537601471},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.49291348457336426},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4884559214115143},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.48826050758361816},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.43996962904930115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4296048879623413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4177979826927185},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"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":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":"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":"D005819","descriptor_name":"Genetic Markers","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005819","descriptor_name":"Genetic Markers","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005819","descriptor_name":"Genetic Markers","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"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":"D013194","descriptor_name":"Staining and Labeling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013194","descriptor_name":"Staining and Labeling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013194","descriptor_name":"Staining and Labeling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btn089","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn089","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/9/1198/49046088/bioinformatics_24_9_1198.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:18344247","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18344247","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/btn089","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn089","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/9/1198/49046088/bioinformatics_24_9_1198.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":[{"id":"https://metadata.un.org/sdg/15","score":0.6800000071525574,"display_name":"Life in Land"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332622","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2150028022.pdf","grobid_xml":"https://content.openalex.org/works/W2150028022.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W22461475","https://openalex.org/W1550206324","https://openalex.org/W1596981350","https://openalex.org/W1861993554","https://openalex.org/W1971158461","https://openalex.org/W1980801609","https://openalex.org/W1998563096","https://openalex.org/W2012908927","https://openalex.org/W2021945571","https://openalex.org/W2024046085","https://openalex.org/W2038553416","https://openalex.org/W2071949631","https://openalex.org/W2085742009","https://openalex.org/W2120682057","https://openalex.org/W2132870739","https://openalex.org/W2134510195","https://openalex.org/W2144166466","https://openalex.org/W2147658756","https://openalex.org/W2166831581","https://openalex.org/W2171338658","https://openalex.org/W2400705412","https://openalex.org/W2916255248","https://openalex.org/W6632865047","https://openalex.org/W6639315830","https://openalex.org/W6650010582"],"related_works":["https://openalex.org/W2340181363","https://openalex.org/W2963778518","https://openalex.org/W4298073324","https://openalex.org/W157554648","https://openalex.org/W2251988637","https://openalex.org/W2353489492","https://openalex.org/W2913145454","https://openalex.org/W2366051640","https://openalex.org/W2003538433","https://openalex.org/W2991126413"],"abstract_inverted_index":{"MOTIVATION:":[0],"In":[1],"the":[2,66,78,101,141,149],"genomics":[3],"setting,":[4],"an":[5,84],"increasingly":[6],"common":[7],"data":[8],"configuration":[9],"consists":[10],"of":[11,15,27,71,109,148],"a":[12,18,24,51,90],"small":[13],"set":[14,26],"sequences":[16,28],"possessing":[17],"targeted":[19],"property":[20],"(positive":[21],"instances)":[22],"amongst":[23],"large":[25],"for":[29,58],"which":[30,72],"class":[31,91],"membership":[32],"is":[33],"unknown":[34],"(unlabeled":[35],"instances).":[36],"Traditional":[37],"two-class":[38],"classification":[39,56,80,86],"methods":[40],"do":[41],"not":[42],"effectively":[43],"handle":[44],"such":[45],"data.":[46,155],"RESULTS:":[47],"Here,":[48],"we":[49],"develop":[50],"novel":[52],"method,":[53],"likely":[54],"positive-iterative":[55],"(LP-IC)":[57],"this":[59],"problem,":[60],"and":[61,75,88,112,118,135,144],"contrast":[62],"its":[63],"performance":[64,125,147],"with":[65],"few":[67],"existing":[68,127],"methods,":[69],"most":[70],"were":[73],"devised":[74],"utilized":[76],"in":[77,129,137],"text":[79],"context.":[81],"LP-IC":[82,122],"employs":[83],"iterative":[85],"scheme":[87],"introduces":[89],"dispersion":[92],"measure,":[93],"adopted":[94],"from":[95,140],"unsupervised":[96],"clustering":[97],"approaches,":[98],"to":[99,126],"monitor":[100],"model":[102],"selection":[103],"process.":[104],"Using":[105],"two":[106],"case":[107],"studies--prediction":[108],"HLA":[110],"binding,":[111],"alternative":[113],"splicing":[114],"conservation":[115],"between":[116],"human":[117],"mouse--we":[119],"show":[120],"that":[121],"provides":[123],"superior":[124],"methodologies":[128],"terms":[130],"of:":[131],"(i)":[132],"combined":[133],"accuracy":[134],"precision":[136],"positive":[138],"identification":[139],"unlabeled":[142],"set;":[143],"(ii)":[145],"predictive":[146],"resultant":[150],"classifiers":[151],"on":[152],"independent":[153],"test":[154]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
