{"id":"https://openalex.org/W3011402541","doi":"https://doi.org/10.1093/bioinformatics/btaa176","title":"Exploring high-dimensional biological data with sparse contrastive principal component analysis","display_name":"Exploring high-dimensional biological data with sparse contrastive principal component analysis","publication_year":2020,"publication_date":"2020-03-10","ids":{"openalex":"https://openalex.org/W3011402541","doi":"https://doi.org/10.1093/bioinformatics/btaa176","mag":"3011402541","pmid":"https://pubmed.ncbi.nlm.nih.gov/32176249"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa176","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa176","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056701920","display_name":"Philippe Boileau","orcid":"https://orcid.org/0000-0002-4850-2507"},"institutions":[{"id":"https://openalex.org/I4210101190","display_name":"Cancer Research And Biostatistics","ror":"https://ror.org/01575p865","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210101190"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Philippe Boileau","raw_affiliation_strings":["Graduate Group in Biostatistics"],"raw_orcid":"https://orcid.org/0000-0002-4850-2507","affiliations":[{"raw_affiliation_string":"Graduate Group in Biostatistics","institution_ids":["https://openalex.org/I4210101190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074787043","display_name":"Nima S. Hejazi","orcid":"https://orcid.org/0000-0002-7127-2789"},"institutions":[{"id":"https://openalex.org/I4210101190","display_name":"Cancer Research And Biostatistics","ror":"https://ror.org/01575p865","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210101190"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima S Hejazi","raw_affiliation_strings":["Center for Computational Biology","Graduate Group in Biostatistics"],"raw_orcid":"https://orcid.org/0000-0002-7127-2789","affiliations":[{"raw_affiliation_string":"Center for Computational Biology","institution_ids":[]},{"raw_affiliation_string":"Graduate Group in Biostatistics","institution_ids":["https://openalex.org/I4210101190"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018207168","display_name":"Sandrine Dudoit","orcid":"https://orcid.org/0000-0002-6069-8629"},"institutions":[{"id":"https://openalex.org/I4210120717","display_name":"Faculty of Public Health","ror":"https://ror.org/01zqv1s26","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210120717"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Sandrine Dudoit","raw_affiliation_strings":["Center for Computational Biology","Department of Statistics , University of California, Berkeley, CA 94720, USA","Division of Epidemiology and Biostatistics , School of Public Health"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Biology","institution_ids":[]},{"raw_affiliation_string":"Department of Statistics , University of California, Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Division of Epidemiology and Biostatistics , School of Public Health","institution_ids":["https://openalex.org/I4210120717"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056701920"],"corresponding_institution_ids":["https://openalex.org/I4210101190"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.8337,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.85562127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"36","issue":"11","first_page":"3422","last_page":"3430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.917900025844574,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.917900025844574,"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/T10885","display_name":"Gene expression and cancer classification","score":0.05079999938607216,"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":0.0031999999191612005,"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/principal-component-analysis","display_name":"Principal component analysis","score":0.7692859172821045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7580230236053467},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.7501379251480103},{"id":"https://openalex.org/keywords/bioconductor","display_name":"Bioconductor","score":0.6592386960983276},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5847700238227844},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5498341917991638},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5281702876091003},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.47954225540161133},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4469435214996338},{"id":"https://openalex.org/keywords/r-package","display_name":"R package","score":0.4372015595436096},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.43070682883262634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3665645122528076},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3297712504863739},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3247653543949127},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.17521080374717712},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11002081632614136}],"concepts":[{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.7692859172821045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580230236053467},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.7501379251480103},{"id":"https://openalex.org/C2779694297","wikidata":"https://www.wikidata.org/wiki/Q2888953","display_name":"Bioconductor","level":3,"score":0.6592386960983276},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5847700238227844},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5498341917991638},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5281702876091003},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.47954225540161133},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4469435214996338},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.4372015595436096},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.43070682883262634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3665645122528076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3297712504863739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3247653543949127},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.17521080374717712},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11002081632614136},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"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":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btaa176","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa176","pdf_url":null,"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:32176249","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32176249","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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4099999964237213,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1533335653","https://openalex.org/W1965448327","https://openalex.org/W1973094248","https://openalex.org/W1975852576","https://openalex.org/W1975900269","https://openalex.org/W1982729887","https://openalex.org/W2007820457","https://openalex.org/W2017746705","https://openalex.org/W2030548544","https://openalex.org/W2034400748","https://openalex.org/W2039521726","https://openalex.org/W2094754409","https://openalex.org/W2097714737","https://openalex.org/W2109048721","https://openalex.org/W2116528446","https://openalex.org/W2116650193","https://openalex.org/W2137499573","https://openalex.org/W2150593711","https://openalex.org/W2160697532","https://openalex.org/W2165207521","https://openalex.org/W2491460411","https://openalex.org/W2593403760","https://openalex.org/W2783644856","https://openalex.org/W2805695370","https://openalex.org/W2883439616","https://openalex.org/W2884552970","https://openalex.org/W2901677030","https://openalex.org/W2902652978","https://openalex.org/W2943864384","https://openalex.org/W2949067670","https://openalex.org/W2950336271","https://openalex.org/W2951506174","https://openalex.org/W2953251392","https://openalex.org/W2963093613","https://openalex.org/W4230605228","https://openalex.org/W6747689705","https://openalex.org/W6755955226"],"related_works":["https://openalex.org/W3110687914","https://openalex.org/W2082691086","https://openalex.org/W3130603810","https://openalex.org/W4384695349","https://openalex.org/W1836423264","https://openalex.org/W2548999290","https://openalex.org/W2144569930","https://openalex.org/W2010514871","https://openalex.org/W1510604416","https://openalex.org/W2112504441"],"abstract_inverted_index":{"MOTIVATION:":[0],"Statistical":[1],"analyses":[2,120,161],"of":[3,14,34,59,74,80,87,121,144],"high-throughput":[4],"sequencing":[5,133],"data":[6,22,76,176],"have":[7,47],"re-shaped":[8],"the":[9,56,78,145,147,155],"biological":[10,19,102],"sciences.":[11],"In":[12],"spite":[13],"myriad":[15],"advances,":[16],"recovering":[17,60],"interpretable":[18,99],"signal":[20],"from":[21],"corrupted":[23],"by":[24,68],"technical":[25],"noise":[26],"remains":[27],"a":[28,85,115],"prevalent":[29],"open":[30],"problem.":[31],"Several":[32],"classes":[33],"procedures,":[35],"among":[36],"them":[37],"classical":[38],"dimensionality":[39,111],"reduction":[40,112],"techniques":[41],"and":[42,62,100,118,130,140],"others":[43],"incorporating":[44],"subject-matter":[45],"knowledge,":[46],"provided":[48],"effective":[49],"advances.":[50],"However,":[51],"no":[52],"procedure":[53],"currently":[54],"satisfies":[55],"dual":[57],"objectives":[58],"stable":[61],"relevant":[63,101],"features":[64],"simultaneously.":[65],"RESULTS:":[66],"Inspired":[67],"recent":[69],"proposals":[70],"for":[71,159],"making":[72],"use":[73],"control":[75],"in":[77,163],"removal":[79],"unwanted":[81],"variation,":[82],"we":[83],"propose":[84],"variant":[86],"principal":[88],"component":[89],"analysis":[90],"(PCA),":[91],"sparse":[92],"contrastive":[93],"PCA":[94],"that":[95],"extracts":[96],"sparse,":[97],"stable,":[98],"signal.":[103],"The":[104],"new":[105],"methodology":[106],"is":[107,151,166],"compared":[108],"to":[109],"competing":[110],"approaches":[113],"through":[114],"simulation":[116],"study":[117],"via":[119,154,169],"several":[122],"publicly":[123],"available":[124,153,168,178],"protein":[125],"expression,":[126],"microarray":[127],"gene":[128],"expression":[129],"single-cell":[131],"transcriptome":[132],"datasets.":[134],"AVAILABILITY":[135],"AND":[136],"IMPLEMENTATION:":[137],"A":[138],"free":[139],"open-source":[141],"software":[142],"implementation":[143],"methodology,":[146],"scPCA":[148],"R":[149],"package,":[150],"made":[152],"Bioconductor":[156],"Project.":[157],"Code":[158],"all":[160],"presented":[162],"this":[164],"article":[165],"also":[167],"GitHub.":[170],"CONTACT:":[171],"philippe_boileau@berkeley.edu.":[172],"SUPPLEMENTARY":[173],"INFORMATION:":[174],"Supplementary":[175],"are":[177],"at":[179],"Bioinformatics":[180],"online.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}