{"id":"https://openalex.org/W2103727721","doi":"https://doi.org/10.1093/bioinformatics/bti617","title":"Accounting for probe-level noise in principal component analysis of microarray data","display_name":"Accounting for probe-level noise in principal component analysis of microarray data","publication_year":2005,"publication_date":"2005-08-09","ids":{"openalex":"https://openalex.org/W2103727721","doi":"https://doi.org/10.1093/bioinformatics/bti617","mag":"2103727721","pmid":"https://pubmed.ncbi.nlm.nih.gov/16091409"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti617","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti617","pdf_url":null,"source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"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","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017674487","display_name":"Guido Sanguinetti","orcid":"https://orcid.org/0000-0002-6663-8336"},"institutions":[{"id":"https://openalex.org/I3131424716","display_name":"Portobello High School","ror":"https://ror.org/0045cz905","country_code":"GB","type":"education","lineage":["https://openalex.org/I3131424716"]},{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"G. Sanguinetti","raw_affiliation_strings":["Department of Computer Science, Regent Court 211 Portobello Road, Sheffield S1 4DP, UK","Department of Computer Science, Regent Court, 211 Portobello Road, Sheffield, S1 4DP, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Regent Court 211 Portobello Road, Sheffield S1 4DP, UK","institution_ids":["https://openalex.org/I3131424716"]},{"raw_affiliation_string":"Department of Computer Science, Regent Court, 211 Portobello Road, Sheffield, S1 4DP, UK#TAB#","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030562190","display_name":"Marta Milo","orcid":"https://orcid.org/0000-0002-6996-6431"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"M. Milo","raw_affiliation_strings":["Department of Computer Science, Regent Court, 211 Portobello Road, Sheffield, S1 4DP, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Regent Court, 211 Portobello Road, Sheffield, S1 4DP, UK#TAB#","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023995814","display_name":"Magnus Rattray","orcid":"https://orcid.org/0000-0001-8196-5565"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"M. Rattray","raw_affiliation_strings":["School Of Computer Science, University of Manchester, Oxford Road, Manchester M13 9PL, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School Of Computer Science, University of Manchester, Oxford Road, Manchester M13 9PL, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023849469","display_name":"Neil D. Lawrence","orcid":"https://orcid.org/0000-0001-9258-1030"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"N. D. Lawrence","raw_affiliation_strings":["Department of Computer Science, Regent Court, 211 Portobello Road, Sheffield, S1 4DP, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Regent Court, 211 Portobello Road, Sheffield, S1 4DP, UK#TAB#","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017674487"],"corresponding_institution_ids":["https://openalex.org/I3131424716","https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":2.6373,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.89817004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"21","issue":"19","first_page":"3748","last_page":"3754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9743000268936157,"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":0.9743000268936157,"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/T12867","display_name":"Advanced Biosensing Techniques and Applications","score":0.00279999990016222,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.8118230700492859},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5822973847389221},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5466362833976746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5292118191719055},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4349881410598755},{"id":"https://openalex.org/keywords/accounting","display_name":"Accounting","score":0.4098206162452698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19076067209243774},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.1033291220664978}],"concepts":[{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.8118230700492859},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5822973847389221},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5466362833976746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5292118191719055},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4349881410598755},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.4098206162452698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19076067209243774},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.1033291220664978},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","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":"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":"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013269","descriptor_name":"Stochastic Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013269","descriptor_name":"Stochastic Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013269","descriptor_name":"Stochastic Processes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013269","descriptor_name":"Stochastic Processes","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":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"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":"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":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bti617","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti617","pdf_url":null,"source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"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:16091409","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16091409","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:pure.atira.dk:openaire_cris_publications/15bfae04-a221-4c60-bfe9-6567ba71aee7","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/15bfae04-a221-4c60-bfe9-6567ba71aee7","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sanguinetti, G, Milo, M, Rattray, M & Lawrence, N D 2005, 'Accounting for probe-level noise in principal component analysis of microarray data', Bioinformatics, vol. 21, no. 19, pp. 3748-3754. https://doi.org/10.1093/bioinformatics/bti617","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G2406845302","display_name":null,"funder_award_id":"BBS/B/0076X","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"},{"id":"https://openalex.org/F4320334629","display_name":"Biotechnology and Biological Sciences Research Council","ror":"https://ror.org/00cwqg982"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1498183065","https://openalex.org/W1577436787","https://openalex.org/W2049633694","https://openalex.org/W2050354343","https://openalex.org/W2060542838","https://openalex.org/W2063339587","https://openalex.org/W2102214238","https://openalex.org/W2122598723","https://openalex.org/W2125027820","https://openalex.org/W2146004021","https://openalex.org/W2146646206","https://openalex.org/W2148541040","https://openalex.org/W2159285593","https://openalex.org/W2163988673","https://openalex.org/W2171118759","https://openalex.org/W2542444350"],"related_works":["https://openalex.org/W1975632186","https://openalex.org/W3027745756","https://openalex.org/W3205213561","https://openalex.org/W2531880140","https://openalex.org/W2126145365","https://openalex.org/W2036609560","https://openalex.org/W346861917","https://openalex.org/W3024018414","https://openalex.org/W1542592062","https://openalex.org/W4380081032"],"abstract_inverted_index":{"MOTIVATION:":[0],"Principal":[1],"Component":[2],"Analysis":[3],"(PCA)":[4],"is":[5,189],"one":[6,48],"of":[7,17,49,80,135,178,186],"the":[8,15,36,77,117,133,155,179,183],"most":[9],"popular":[10],"dimensionality":[11],"reduction":[12],"techniques":[13],"for":[14,72],"analysis":[16,79],"high-dimensional":[18],"datasets.":[19],"However,":[20],"in":[21,123],"its":[22,50],"standard":[23,41,146],"form,":[24],"it":[25],"does":[26],"not":[27],"take":[28],"into":[29,115],"account":[30,116],"any":[31],"error":[32],"measures":[33],"associated":[34,119],"with":[35,58,67,120],"data":[37,57],"points":[38],"beyond":[39],"a":[40,107,162],"spherical":[42],"noise.":[43],"This":[44],"indiscriminate":[45],"nature":[46,177],"provides":[47,141],"main":[51],"weaknesses":[52],"when":[53],"applied":[54],"to":[55,111,131,160,166],"biological":[56],"inherently":[59],"large":[60],"variability,":[61],"such":[62],"as":[63],"expression":[64,168],"levels":[65],"measured":[66],"microarrays.":[68],"Methods":[69],"now":[70],"exist":[71],"extracting":[73],"credibility":[74,87],"intervals":[75,88],"from":[76],"probe-level":[78],"cDNA":[81],"and":[82,91,94,170],"oligonucleotide":[83],"microarray":[84,163],"experiments.":[85],"These":[86],"are":[89],"gene":[90,122],"experiment":[92],"specific,":[93],"can":[95,157],"be":[96,158],"propagated":[97],"through":[98],"an":[99,128],"appropriate":[100],"probabilistic":[101,176],"downstream":[102],"analysis.":[103],"RESULTS:":[104],"We":[105,126,152],"propose":[106],"new":[108,137],"model-based":[109],"approach":[110],"PCA":[112],"that":[113,182],"takes":[114],"variances":[118],"each":[121,124],"experiment.":[125],"develop":[127],"efficient":[129],"EM-algorithm":[130],"estimate":[132],"parameters":[134],"our":[136],"model.":[138],"The":[139,175],"model":[140,156,180],"significantly":[142],"better":[143],"results":[144],"than":[145],"PCA,":[147],"while":[148],"remaining":[149],"computationally":[150],"reasonable.":[151],"show":[153],"how":[154],"used":[159],"'denoise'":[161],"dataset":[164],"leading":[165],"improved":[167],"profiles":[169],"tighter":[171],"clustering":[172],"across":[173],"profiles.":[174],"means":[181],"correct":[184],"number":[185],"principal":[187],"components":[188],"automatically":[190],"obtained.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}