{"id":"https://openalex.org/W2101800045","doi":"https://doi.org/10.1093/bioinformatics/bth077","title":"Correction of sequence-based artifacts in serial analysis of gene expression","display_name":"Correction of sequence-based artifacts in serial analysis of gene expression","publication_year":2004,"publication_date":"2004-02-10","ids":{"openalex":"https://openalex.org/W2101800045","doi":"https://doi.org/10.1093/bioinformatics/bth077","mag":"2101800045","pmid":"https://pubmed.ncbi.nlm.nih.gov/14871862"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth077","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth077","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/8/1254/48905393/bioinformatics_20_8_1254.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":"erratum","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/20/8/1254/48905393/bioinformatics_20_8_1254.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088280452","display_name":"Viatcheslav R. Akmaev","orcid":"https://orcid.org/0000-0001-8361-7708"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Viatcheslav R. Akmaev","raw_affiliation_strings":["Genzyme Corporation, Framingham, MA 01701-9322, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genzyme Corporation, Framingham, MA 01701-9322, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007632632","display_name":"Clarence J. Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clarence J. Wang","raw_affiliation_strings":["Genzyme Corporation, Framingham, MA 01701-9322, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genzyme Corporation, Framingham, MA 01701-9322, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5088280452"],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":"8","first_page":"1254","last_page":"1263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9146999716758728,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9146999716758728,"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/T11970","display_name":"Molecular Biology Techniques and Applications","score":0.03319999948143959,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.009600000455975533,"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":0.6417990922927856},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6066033840179443},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5513399839401245},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.525162398815155},{"id":"https://openalex.org/keywords/sequence-analysis","display_name":"Sequence analysis","score":0.5029842257499695},{"id":"https://openalex.org/keywords/serial-analysis-of-gene-expression","display_name":"Serial analysis of gene expression","score":0.48647376894950867},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.3446189761161804},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.32615742087364197},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.26287567615509033},{"id":"https://openalex.org/keywords/gene-expression-profiling","display_name":"Gene expression profiling","score":0.2533140778541565},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24562638998031616},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23703566193580627}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6417990922927856},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6066033840179443},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5513399839401245},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.525162398815155},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.5029842257499695},{"id":"https://openalex.org/C20032557","wikidata":"https://www.wikidata.org/wiki/Q286721","display_name":"Serial analysis of gene expression","level":5,"score":0.48647376894950867},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.3446189761161804},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.32615742087364197},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.26287567615509033},{"id":"https://openalex.org/C18431079","wikidata":"https://www.wikidata.org/wiki/Q1502169","display_name":"Gene expression profiling","level":4,"score":0.2533140778541565},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24562638998031616},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23703566193580627}],"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":"D001932","descriptor_name":"Brain Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001932","descriptor_name":"Brain Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001932","descriptor_name":"Brain Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005910","descriptor_name":"Glioma","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005910","descriptor_name":"Glioma","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005910","descriptor_name":"Glioma","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","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":"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":"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":"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":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016133","descriptor_name":"Polymerase Chain Reaction","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016133","descriptor_name":"Polymerase Chain Reaction","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016133","descriptor_name":"Polymerase Chain Reaction","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":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","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":"D020224","descriptor_name":"Expressed Sequence Tags","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020224","descriptor_name":"Expressed Sequence Tags","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020224","descriptor_name":"Expressed Sequence Tags","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bth077","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth077","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/8/1254/48905393/bioinformatics_20_8_1254.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:14871862","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/14871862","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:10.1.1.332.2869","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.2869","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/20/8/1254.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bth077","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth077","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/8/1254/48905393/bioinformatics_20_8_1254.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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1981926627","https://openalex.org/W2002982210","https://openalex.org/W2010888033","https://openalex.org/W2022257958","https://openalex.org/W2031928161","https://openalex.org/W2059797405","https://openalex.org/W2064504648","https://openalex.org/W2066574980","https://openalex.org/W2079851474","https://openalex.org/W2119464179","https://openalex.org/W2119923823","https://openalex.org/W2121016876","https://openalex.org/W2125558666","https://openalex.org/W2150815784"],"related_works":["https://openalex.org/W2400451280","https://openalex.org/W2381424852","https://openalex.org/W2355911084","https://openalex.org/W1977473994","https://openalex.org/W2953897862","https://openalex.org/W2098357168","https://openalex.org/W2070775287","https://openalex.org/W3030245994","https://openalex.org/W2038353697","https://openalex.org/W2052655934"],"abstract_inverted_index":{"MOTIVATION:":[0],"Serial":[1],"Analysis":[2],"of":[3,19,22,45,65,70,83,92,112,133,174,183,189,217,225],"Gene":[4],"Expression":[5],"(SAGE)":[6],"is":[7,79,118,165,232],"a":[8,148,166],"powerful":[9],"technology":[10],"for":[11,122,131,203,234],"measuring":[12],"global":[13],"gene":[14,31,53],"expression,":[15],"through":[16],"rapid":[17],"generation":[18],"large":[20,113],"numbers":[21],"transcript":[23],"tags.":[24,227],"Beyond":[25],"their":[26,93],"intrinsic":[27],"value":[28,111],"in":[29],"differential":[30,103],"expression":[32,104],"analysis,":[33],"SAGE":[34,57,75,78,114,197],"tag":[35,97,115,125,134,210,219],"collections":[36,211],"afford":[37],"abundant":[38,180],"information":[39],"on":[40,102,147],"the":[41,46,62,80,110,153,223,238],"size":[42],"and":[43,49,76,123,136,157,186,199,221],"shape":[44],"sample":[47],"transcriptome":[48],"can":[50],"accelerate":[51],"novel":[52],"discovery.":[54],"These":[55],"latter":[56],"applications":[58],"are":[59,145],"facilitated":[60],"by":[61],"enhanced":[63],"method":[64],"Long":[66,77,196],"SAGE.":[67],"A":[68],"characteristic":[69],"sequencing-based":[71],"methods,":[72],"such":[73,96],"as":[74],"unavoidable":[81],"occurrence":[82],"artifact":[84],"sequences":[85],"resulting":[86],"from":[87,178,237],"sequencing":[88,158],"errors.":[89],"By":[90],"virtue":[91],"low-random":[94],"incidence,":[95],"errors":[98,220],"have":[99],"minimal":[100],"impact":[101],"analysis.":[105],"However,":[106],"to":[107,120,195],"fully":[108],"exploit":[109],"datasets,":[116],"it":[117],"desirable":[119],"account":[121],"correct":[124],"artifacts.":[126],"RESULTS:":[127],"We":[128,192],"present":[129],"estimates":[130,144],"occurrences":[132,224],"errors,":[135],"an":[137],"efficient":[138],"error":[139,159,176,201],"correction":[140,162],"algorithm.":[141],"Error":[142],"rate":[143],"based":[146],"stochastic":[149],"model":[150],"that":[151,169,213],"includes":[152],"Polymerase":[154],"chain":[155],"reaction":[156],"contributions.":[160],"The":[161,229],"algorithm,":[163],"SAGEScreen,":[164],"multi-step":[167],"procedure":[168],"addresses":[170],"ditag":[171],"processing,":[172],"estimation":[173],"empirical":[175],"rates":[177,202],"highly":[179],"tags,":[181],"grouping":[182],"similar-sequence":[184],"tags":[185],"statistical":[187],"testing":[188],"observed":[190],"counts.":[191],"apply":[193],"SAGEScreen":[194,214,230],"libraries":[198],"compare":[200],"several":[204],"processing":[205],"scenarios.":[206],"Results":[207],"with":[208],"simulated":[209],"indicate":[212],"corrects":[215],"78%":[216],"recoverable":[218],"reduces":[222],"singleton":[226],"AVAILABILITY:":[228],"software":[231],"available":[233],"academic":[235],"users":[236],"first":[239],"author.":[240]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
