{"id":"https://openalex.org/W2140048165","doi":"https://doi.org/10.1093/bioinformatics/bth239","title":"Estimating and comparing the rates of gene discovery and expressed sequence tag (EST) frequencies in EST surveys","display_name":"Estimating and comparing the rates of gene discovery and expressed sequence tag (EST) frequencies in EST surveys","publication_year":2004,"publication_date":"2004-04-01","ids":{"openalex":"https://openalex.org/W2140048165","doi":"https://doi.org/10.1093/bioinformatics/bth239","mag":"2140048165","pmid":"https://pubmed.ncbi.nlm.nih.gov/15059814"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth239","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth239","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/14/2279/48906190/bioinformatics_20_14_2279.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/20/14/2279/48906190/bioinformatics_20_14_2279.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021576212","display_name":"Edward Susko","orcid":"https://orcid.org/0000-0003-1122-8740"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]},{"id":"https://openalex.org/I4387156103","display_name":"Genome Atlantic","ror":"https://ror.org/0249g7f28","country_code":null,"type":"facility","lineage":["https://openalex.org/I4387156103"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Edward Susko","raw_affiliation_strings":["Genome Atlantic, Department of Mathematics and Statistics, Dahlhousie University, Nova Scotia, Canada. susko@mathstat.dal.ca","Genome Atlantic, Department of Mathematics and Statistics#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genome Atlantic, Department of Mathematics and Statistics, Dahlhousie University, Nova Scotia, Canada. susko@mathstat.dal.ca","institution_ids":["https://openalex.org/I129902397","https://openalex.org/I4387156103"]},{"raw_affiliation_string":"Genome Atlantic, Department of Mathematics and Statistics#TAB#","institution_ids":["https://openalex.org/I4387156103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053095410","display_name":"Andrew J. Roger","orcid":"https://orcid.org/0000-0003-1370-9820"},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Andrew J. Roger","raw_affiliation_strings":["Genome Atlantic, Canadian Institute for Advanced Research, Program in Evolutionary Biology, Department of Biochemistry and Molecular Biology, Dalhousie University, Halifax, Nova Scotia, Canada#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genome Atlantic, Canadian Institute for Advanced Research, Program in Evolutionary Biology, Department of Biochemistry and Molecular Biology, Dalhousie University, Halifax, Nova Scotia, Canada#TAB#","institution_ids":["https://openalex.org/I109736498","https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021576212"],"corresponding_institution_ids":["https://openalex.org/I129902397","https://openalex.org/I4387156103"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.8439,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.71162608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"20","issue":"14","first_page":"2279","last_page":"2287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.8790000081062317,"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":0.8790000081062317,"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/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.02319999970495701,"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":0.013700000010430813,"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/redundancy","display_name":"Redundancy (engineering)","score":0.525111973285675},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5244734287261963},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.48496341705322266},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4501981735229492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4305777847766876},{"id":"https://openalex.org/keywords/false-discovery-rate","display_name":"False discovery rate","score":0.42039069533348083},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.3809894621372223},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.35420989990234375},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.34563225507736206},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.27567344903945923},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17029765248298645}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.525111973285675},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5244734287261963},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.48496341705322266},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4501981735229492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4305777847766876},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.42039069533348083},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3809894621372223},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.35420989990234375},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.34563225507736206},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.27567344903945923},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17029765248298645},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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":"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":"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":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","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":true},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","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":"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":true},{"descriptor_ui":"D020224","descriptor_name":"Expressed Sequence Tags","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020224","descriptor_name":"Expressed Sequence Tags","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":2,"locations":[{"id":"doi:10.1093/bioinformatics/bth239","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth239","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/14/2279/48906190/bioinformatics_20_14_2279.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:15059814","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15059814","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/bth239","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth239","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/14/2279/48906190/bioinformatics_20_14_2279.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":[{"display_name":"Life in Land","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"},{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320326645","display_name":"Genome Atlantic","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1587289137","https://openalex.org/W1980179247","https://openalex.org/W1981959724","https://openalex.org/W2045638068","https://openalex.org/W2045740840","https://openalex.org/W2047701135","https://openalex.org/W2072536072","https://openalex.org/W2082092506","https://openalex.org/W2095306947","https://openalex.org/W2110065044","https://openalex.org/W2119923823","https://openalex.org/W2121016876","https://openalex.org/W2146368895","https://openalex.org/W2146516445","https://openalex.org/W2148687138","https://openalex.org/W2164075646","https://openalex.org/W2323136350"],"related_works":["https://openalex.org/W2057598446","https://openalex.org/W2290081135","https://openalex.org/W3022782703","https://openalex.org/W2172032168","https://openalex.org/W1771779360","https://openalex.org/W871906761","https://openalex.org/W1993731342","https://openalex.org/W2119095362","https://openalex.org/W1988747059","https://openalex.org/W3210933308"],"abstract_inverted_index":{"MOTIVATION:":[0],"Expressed":[1],"sequence":[2],"tag":[3],"(EST)":[4],"surveys":[5],"are":[6,41,86,214,288,302,317,323],"an":[7,17,25,172],"efficient":[8],"way":[9],"to":[10,50,98,114,121,124,131,266,274,330,351],"characterize":[11],"large":[12],"numbers":[13,210,234],"of":[14,21,32,34,55,69,82,92,108,148,155,165,174,178,189,211,235,271,278,296,307,311,314,340],"genes":[15,78,101,180,213,237,287],"from":[16,38,58,116,199,227,245,269,344],"organism.":[18],"The":[19],"rate":[20,277],"gene":[22,279,334],"discovery":[23],"in":[24,80,88,102,119,141,161,185,220,293,333,337],"EST":[26,60,70,341],"survey":[27],"depends":[28],"on":[29],"the":[30,35,67,74,117,153,156,162,175,201,208,232,252,260,272,276,312,338],"degree":[31],"redundancy":[33],"cDNA":[36],"libraries":[37,57,71,94,118,229,247,261,273,342],"which":[39,77,90],"sequences":[40],"obtained.":[42],"However,":[43],"few":[44],"statistical":[45],"methods":[46,326],"have":[47,137],"been":[48,138],"developed":[49],"assess":[51],"and":[52,105,207,230,299,319],"compare":[53,132],"redundancies":[54],"various":[56],"preliminary":[59],"surveys.":[61],"RESULTS:":[62],"We":[63,191],"consider":[64,218],"statistics":[65,194,253],"for":[66,205,259,285,304],"comparison":[68],"based":[72,224],"upon":[73,225],"frequencies":[75],"with":[76,248],"occur":[79],"subsamples":[81],"reads.":[83,166,190],"These":[84,216,325],"measures":[85,135,217,258],"useful":[87,256],"determining":[89],"one":[91,111],"several":[93],"is":[95,130,159,171],"more":[96],"likely":[97,123],"yield":[99],"new":[100,126,187,212,236],"future":[103],"reads":[104,110,226,244],"what":[106],"proportion":[107,154],"additional":[109,179],"might":[112],"want":[113],"take":[115],"order":[120],"be":[122,183,240,264,328,358],"obtain":[125],"genes.":[127],"One":[128],"approach":[129],"single":[133,168,222],"sample":[134,164,188],"that":[136,158,181,195,238,262],"successfully":[139],"used":[140,265,329],"species":[142],"estimation":[143],"problems,":[144],"such":[145],"as":[146,152],"coverage":[147,206,219],"a":[149,186,221,294],"library,":[150],"defined":[151],"library":[157,169,223],"represented":[160,290],"given":[163],"Another":[167],"measure":[170],"estimate":[173],"expected":[176,209,233],"number":[177],"will":[182,239,357],"found":[184],"also":[192],"propose":[193],"jointly":[196],"use":[197],"data":[198],"all":[200,228,246],"libraries.":[202,297],"Analogous":[203],"formulas":[204],"presented.":[215],"similarly,":[231],"discovered":[241],"by":[242],"taking":[243],"fixed":[249],"proportions.":[250],"Together,":[251],"presented":[254,303,318],"provide":[255],"comparative":[257],"can":[263,327],"guide":[267],"sampling":[268],"each":[270],"maximize":[275],"discovery.":[280],"Finally,":[281],"we":[282],"present":[283],"tests":[284,301,310],"whether":[286],"equally":[289],"or":[291,348],"expressed":[292],"set":[295],"Binomial":[298],"chi2":[300],"gene-by-gene":[305],"comparisons":[306,321],"expression.":[308],"Overall":[309],"equality":[313],"proportional":[315],"representation":[316],"multiple":[320],"issues":[322],"addressed.":[324],"evaluate":[331],"changes":[332],"expression":[335],"reflected":[336],"composition":[339],"prepared":[343],"different":[345,352],"tissue":[346],"types":[347],"cells":[349],"exposed":[350],"environmental":[353],"conditions.":[354],"AVAILABILITY:":[355],"Software":[356],"made":[359],"available":[360],"at":[361],"http://www.mathstat.dal.ca/~tsusko":[362]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}
