{"id":"https://openalex.org/W2106283722","doi":"https://doi.org/10.1093/bib/bbn054","title":"Potential Bias in GO::TermFinder","display_name":"Potential Bias in GO::TermFinder","publication_year":2008,"publication_date":"2008-12-06","ids":{"openalex":"https://openalex.org/W2106283722","doi":"https://doi.org/10.1093/bib/bbn054","mag":"2106283722","pmid":"https://pubmed.ncbi.nlm.nih.gov/19279157"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbn054","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbn054","pdf_url":"https://academic.oup.com/bib/article-pdf/10/3/289/556336/bbn054.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":"Briefings in 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/bib/article-pdf/10/3/289/556336/bbn054.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062202807","display_name":"Robert M Flight","orcid":"https://orcid.org/0000-0001-8141-7788"},"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"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"R. M. Flight","raw_affiliation_strings":["Department of Chemistry, Dalhousie University, Halifax, Nova Scotia B3H 4J3, Canada","Department of Chemistry, Dalhousie University, Halifax, Nova Scotia, B3H 4J3 (Canada)"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Dalhousie University, Halifax, Nova Scotia B3H 4J3, Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Department of Chemistry, Dalhousie University, Halifax, Nova Scotia, B3H 4J3 (Canada)","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059040456","display_name":"Peter D. Wentzell","orcid":"https://orcid.org/0000-0003-4389-801X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P. D. Wentzell","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062202807"],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":0.2693,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.59918638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"10","issue":"3","first_page":"289","last_page":"294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9997000098228455,"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":0.9997000098228455,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9947999715805054,"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/T11235","display_name":"Statistical Methods in Clinical Trials","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bonferroni-correction","display_name":"Bonferroni correction","score":0.8293853998184204},{"id":"https://openalex.org/keywords/false-discovery-rate","display_name":"False discovery rate","score":0.7758775353431702},{"id":"https://openalex.org/keywords/multiple-comparisons-problem","display_name":"Multiple comparisons problem","score":0.7101511359214783},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5951290726661682},{"id":"https://openalex.org/keywords/sampling-bias","display_name":"Sampling bias","score":0.5270997285842896},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.5113624930381775},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5077710747718811},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4590242803096771},{"id":"https://openalex.org/keywords/simple-random-sample","display_name":"Simple random sample","score":0.4473971128463745},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.43338632583618164},{"id":"https://openalex.org/keywords/random-permutation","display_name":"Random permutation","score":0.4220293164253235},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.41760915517807007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4143028259277344},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3730751872062683},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.2754168212413788},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.18494641780853271},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.16123613715171814},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.13853290677070618},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08212903141975403}],"concepts":[{"id":"https://openalex.org/C127808970","wikidata":"https://www.wikidata.org/wiki/Q385989","display_name":"Bonferroni correction","level":2,"score":0.8293853998184204},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.7758775353431702},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.7101511359214783},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5951290726661682},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.5270997285842896},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5113624930381775},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5077710747718811},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4590242803096771},{"id":"https://openalex.org/C20353970","wikidata":"https://www.wikidata.org/wiki/Q1056998","display_name":"Simple random sample","level":3,"score":0.4473971128463745},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.43338632583618164},{"id":"https://openalex.org/C200985842","wikidata":"https://www.wikidata.org/wiki/Q3375503","display_name":"Random permutation","level":3,"score":0.4220293164253235},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41760915517807007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4143028259277344},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3730751872062683},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2754168212413788},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.18494641780853271},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16123613715171814},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13853290677070618},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08212903141975403},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","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":"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":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","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},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbn054","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbn054","pdf_url":"https://academic.oup.com/bib/article-pdf/10/3/289/556336/bbn054.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:19279157","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19279157","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":"Briefings in bioinformatics","raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bib/bbn054","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbn054","pdf_url":"https://academic.oup.com/bib/article-pdf/10/3/289/556336/bbn054.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":"Briefings in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2106283722.pdf","grobid_xml":"https://content.openalex.org/works/W2106283722.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1604959358","https://openalex.org/W1985098050","https://openalex.org/W1990994334","https://openalex.org/W2103017472","https://openalex.org/W2110065044","https://openalex.org/W2112440119","https://openalex.org/W2127773177","https://openalex.org/W2139703939","https://openalex.org/W2157795344","https://openalex.org/W2166574880","https://openalex.org/W2169320928","https://openalex.org/W4294107304"],"related_works":["https://openalex.org/W2093104131","https://openalex.org/W2333750400","https://openalex.org/W2467227750","https://openalex.org/W4293336298","https://openalex.org/W2178204436","https://openalex.org/W4300887971","https://openalex.org/W2104806243","https://openalex.org/W3101083428","https://openalex.org/W4212966421","https://openalex.org/W1921844237"],"abstract_inverted_index":{"The":[0,35],"increased":[1],"need":[2],"for":[3,32,104],"multiple":[4],"statistical":[5],"comparisons":[6],"under":[7],"conditions":[8],"of":[9,25,37,51,108,115,118],"non-independence":[10],"in":[11,43,68,71,87],"bioinformatics":[12],"applications,":[13],"such":[14],"as":[15],"DNA":[16],"microarray":[17],"data":[18],"analysis,":[19],"has":[20,45],"led":[21],"to":[22,27,83,100,112,124,131],"the":[23,28,38,49,52,72,88,102,116,125,133],"development":[24],"alternatives":[26],"conventional":[29],"Bonferroni":[30],"correction":[31],"adjusting":[33],"P-values.":[34],"use":[36],"false":[39],"discovery":[40],"rate":[41],"(FDR),":[42],"particular,":[44],"grown":[46],"considerably.":[47],"However,":[48],"calculation":[50],"FDR":[53,117],"frequently":[54],"depends":[55],"on":[56],"drawing":[57],"random":[58,85,126],"samples":[59],"from":[60],"a":[61,69,80,105],"population,":[62],"and":[63,95],"inappropriate":[64],"sampling":[65,86,127],"will":[66],"result":[67],"bias":[70,81,103],"calculated":[73],"FDR.":[74],"In":[75],"this":[76],"work,":[77],"we":[78],"demonstrate":[79],"due":[82],"incorrect":[84],"widely":[89],"used":[90,99],"GO::TermFinder":[91],"package.":[92],"Both":[93],"T(2)":[94],"permutation":[96],"tests":[97],"are":[98],"confirm":[101],"test":[106],"set":[107],"data,":[109],"which":[110],"leads":[111],"an":[113],"overestimation":[114],"about":[119],"10%.":[120],"A":[121],"simple":[122],"fix":[123],"method":[128],"is":[129],"proposed":[130],"remove":[132],"bias.":[134]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
