{"id":"https://openalex.org/W2003853984","doi":"https://doi.org/10.1093/bib/bbs057","title":"Accounting for noise when clustering biological data","display_name":"Accounting for noise when clustering biological data","publication_year":2012,"publication_date":"2012-10-14","ids":{"openalex":"https://openalex.org/W2003853984","doi":"https://doi.org/10.1093/bib/bbs057","mag":"2003853984","pmid":"https://pubmed.ncbi.nlm.nih.gov/23063929"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbs057","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbs057","pdf_url":"https://academic.oup.com/bib/article-pdf/14/4/423/478640/bbs057.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/14/4/423/478640/bbs057.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086551415","display_name":"Roman Sloutsky","orcid":"https://orcid.org/0000-0002-0794-1255"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Sloutsky","raw_affiliation_strings":["Division of Biology and Biomedical Sciences, Washington University in St. Louis, One Brookings Drive, Brauer 2004, St. Louis, MO 63130, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biology and Biomedical Sciences, Washington University in St. Louis, One Brookings Drive, Brauer 2004, St. Louis, MO 63130, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044043250","display_name":"Nelson Jim\u00e9nez","orcid":"https://orcid.org/0009-0000-2922-1657"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210140143","display_name":"Dynamic Systems (United States)","ror":"https://ror.org/043vm9914","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140143"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Jimenez","raw_affiliation_strings":["Nicolas Jimenez obtained a Bachelor\u2019s in Physics with a minor in Mathematics from Johns Hopkins University. His current work involves using dynamical systems theory to characterize a hybrid dynamical system currently used to model single neurons. His previous work includes graph-based approaches to consensus clustering and software engineering for closed-loop treatment of Type I diabetes","Johns Hopkins University ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nicolas Jimenez obtained a Bachelor\u2019s in Physics with a minor in Mathematics from Johns Hopkins University. His current work involves using dynamical systems theory to characterize a hybrid dynamical system currently used to model single neurons. His previous work includes graph-based approaches to consensus clustering and software engineering for closed-loop treatment of Type I diabetes","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I4210140143"]},{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086610385","display_name":"S. Joshua Swamidass","orcid":"https://orcid.org/0000-0003-2191-0778"},"institutions":[{"id":"https://openalex.org/I4210151238","display_name":"Center for Genomic Science","ror":"https://ror.org/04xbkmk86","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210151238"]},{"id":"https://openalex.org/I4210151837","display_name":"High Throughput Biology (United States)","ror":"https://ror.org/05h1bjp83","country_code":"US","type":"company","lineage":["https://openalex.org/I4210151837"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"S. J. Swamidass","raw_affiliation_strings":["S. Joshua Swamidass is a faculty member in the Division of Laboratory and Genomic Medicine of the Department of Pathology and Immunology of Washington University in St. Louis. Using statistics and machine learning, his research focuses on predicting the properties of molecules based on their structure and new methods of high-throughput screening analysis","Laboratory and Genomic Medicine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S. Joshua Swamidass is a faculty member in the Division of Laboratory and Genomic Medicine of the Department of Pathology and Immunology of Washington University in St. Louis. Using statistics and machine learning, his research focuses on predicting the properties of molecules based on their structure and new methods of high-throughput screening analysis","institution_ids":["https://openalex.org/I4210151837"]},{"raw_affiliation_string":"Laboratory and Genomic Medicine","institution_ids":["https://openalex.org/I4210151238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055984455","display_name":"Kristen M. Naegle","orcid":"https://orcid.org/0000-0001-7146-9592"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]},{"id":"https://openalex.org/I4210146172","display_name":"Cellular Therapeutics (United Kingdom)","ror":"https://ror.org/04ea9m912","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210146172"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"K. M. Naegle","raw_affiliation_strings":["Kristen M. Naegle is an Assistant Professor of Biomedical Engineering at Washington University in St. Louis. Her research involves the development of algorithms and information to make predictions regarding the function of post-translational modifications in cellular signaling networks and validation of those predictions using molecular and cellular experimental techniques","Washington University \u2013 St Louis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kristen M. Naegle is an Assistant Professor of Biomedical Engineering at Washington University in St. Louis. Her research involves the development of algorithms and information to make predictions regarding the function of post-translational modifications in cellular signaling networks and validation of those predictions using molecular and cellular experimental techniques","institution_ids":["https://openalex.org/I4210146172"]},{"raw_affiliation_string":"Washington University \u2013 St Louis","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":0.8063,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.70637254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"14","issue":"4","first_page":"423","last_page":"436"},"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":0.9965999722480774,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.982200026512146,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8433003425598145},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6957342624664307},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6589157581329346},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6320515275001526},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.5771656036376953},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4138014316558838},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29582101106643677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29292407631874084},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.21699121594429016},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.14696621894836426}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8433003425598145},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6957342624664307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6589157581329346},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6320515275001526},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.5771656036376953},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4138014316558838},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29582101106643677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29292407631874084},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.21699121594429016},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14696621894836426},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":"D010766","descriptor_name":"Phosphorylation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010766","descriptor_name":"Phosphorylation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010766","descriptor_name":"Phosphorylation","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":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbs057","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbs057","pdf_url":"https://academic.oup.com/bib/article-pdf/14/4/423/478640/bbs057.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:23063929","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23063929","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/bbs057","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbs057","pdf_url":"https://academic.oup.com/bib/article-pdf/14/4/423/478640/bbs057.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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1547480755","https://openalex.org/W1548779692","https://openalex.org/W1651215666","https://openalex.org/W1940737455","https://openalex.org/W1992242907","https://openalex.org/W1992419399","https://openalex.org/W1999223659","https://openalex.org/W2012712694","https://openalex.org/W2047051739","https://openalex.org/W2064757259","https://openalex.org/W2065912508","https://openalex.org/W2081535641","https://openalex.org/W2093290031","https://openalex.org/W2098216772","https://openalex.org/W2104303958","https://openalex.org/W2104313063","https://openalex.org/W2106294446","https://openalex.org/W2108343180","https://openalex.org/W2109363337","https://openalex.org/W2113413055","https://openalex.org/W2115137285","https://openalex.org/W2115346774","https://openalex.org/W2121149195","https://openalex.org/W2130851950","https://openalex.org/W2134338931","https://openalex.org/W2135000328","https://openalex.org/W2137132755","https://openalex.org/W2137784044","https://openalex.org/W2143508593","https://openalex.org/W2144227498","https://openalex.org/W2147126535","https://openalex.org/W2151566419","https://openalex.org/W2151808499","https://openalex.org/W2156842451","https://openalex.org/W2158787958","https://openalex.org/W2160310631","https://openalex.org/W2164628006","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W3125814499","https://openalex.org/W2090827041","https://openalex.org/W187246281","https://openalex.org/W2565703248","https://openalex.org/W2143548620"],"abstract_inverted_index":{"Clustering":[0,17],"is":[1],"a":[2,33,93,135],"powerful":[3],"and":[4,10,23,63,97,103,146],"commonly":[5],"used":[6,123],"technique":[7],"that":[8],"organizes":[9],"elucidates":[11],"the":[12,39,107,140,144],"structure":[13],"of":[14,35,44,52,81,109,116,137,143],"biological":[15,53,64,87,154],"data.":[16],"data":[18,88,95,155],"from":[19,60],"gene":[20],"expression,":[21],"metabolomics":[22],"proteomics":[24],"experiments":[25],"has":[26],"proven":[27],"to":[28,57,71,112,124,151],"be":[29,122,130,149],"useful":[30],"at":[31],"deriving":[32],"variety":[34],"insights,":[36],"such":[37],"as":[38],"shared":[40],"regulation":[41],"or":[42],"function":[43],"biochemical":[45],"components":[46],"within":[47],"networks.":[48],"However,":[49],"experimental":[50],"measurements":[51],"processes":[54],"are":[55,69],"subject":[56],"substantial":[58],"noise-stemming":[59],"both":[61],"technical":[62],"variability-and":[65],"most":[66],"clustering":[67,110,127],"algorithms":[68,111],"sensitive":[70],"this":[72,75,119],"noise.":[73,113],"In":[74],"article,":[76],"we":[77],"explore":[78],"several":[79],"methods":[80,115,133],"accounting":[82,117],"for":[83,118],"noise":[84,120,145],"when":[85,126],"analyzing":[86],"sets":[89],"through":[90],"clustering.":[91],"Using":[92],"toy":[94],"set":[96],"two":[98],"different":[99],"case":[100],"studies-gene":[101],"expression":[102],"protein":[104],"phosphorylation-we":[105],"demonstrate":[106],"sensitivity":[108],"Several":[114],"can":[121,129,147],"establish":[125],"results":[128],"trusted.":[131],"These":[132],"span":[134],"range":[136],"assumptions":[138],"about":[139],"statistical":[141],"properties":[142],"therefore":[148],"applied":[150],"virtually":[152],"any":[153],"source.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}