{"id":"https://openalex.org/W2615188342","doi":"https://doi.org/10.1093/bioinformatics/btx328","title":"Accelerating high-dimensional clustering with lossless data reduction","display_name":"Accelerating high-dimensional clustering with lossless data reduction","publication_year":2017,"publication_date":"2017-05-16","ids":{"openalex":"https://openalex.org/W2615188342","doi":"https://doi.org/10.1093/bioinformatics/btx328","mag":"2615188342","pmid":"https://pubmed.ncbi.nlm.nih.gov/28520900","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/5870568"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx328","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/18/2867/25164231/btx328.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/33/18/2867/25164231/btx328.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082974900","display_name":"Bahjat F. Qaqish","orcid":"https://orcid.org/0000-0002-5154-2059"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bahjat F Qaqish","raw_affiliation_strings":["Department of Biostatistics, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000939900","display_name":"Jonathon J. O\u2019Brien","orcid":"https://orcid.org/0000-0001-9660-4797"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jonathon J O\u2019Brien","raw_affiliation_strings":["Department of Cell Biology, Harvard Medical School, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Cell Biology, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004033972","display_name":"Jonathan Hibbard","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan C Hibbard","raw_affiliation_strings":["Department of Biostatistics, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042478590","display_name":"Katie J. Clowers","orcid":"https://orcid.org/0000-0001-8484-7118"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katie J Clowers","raw_affiliation_strings":["Department of Cell Biology, Harvard Medical School, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Cell Biology, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000939900"],"corresponding_institution_ids":["https://openalex.org/I136199984"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618,"provenance":"doaj"},"apc_paid":null,"fwci":0.306,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":6,"citation_normalized_percentile":{"value":0.483458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":81,"max":82},"biblio":{"volume":"33","issue":"18","first_page":"2867","last_page":"2872"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9985,"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":0.9985,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.998,"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"}},{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9963,"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/data-transformation","display_name":"Data transformation","score":0.4587948},{"id":"https://openalex.org/keywords/data-reduction","display_name":"Data Reduction","score":0.44059923},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4396677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189367},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.71678656},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6621932},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.64954865},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.63537335},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6223876},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.55552566},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4865026},{"id":"https://openalex.org/C2780365114","wikidata":"https://www.wikidata.org/wiki/Q169478","display_name":"MATLAB","level":2,"score":0.48552513},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.482221},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47829872},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4736696},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.4587948},{"id":"https://openalex.org/C153914771","wikidata":"https://www.wikidata.org/wiki/Q5227343","display_name":"Data reduction","level":2,"score":0.44059923},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4396677},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.43755195},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.216369},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17995262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15192446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12233794},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10688713},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.08865026},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019175","descriptor_name":"DNA Methylation","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005656","descriptor_name":"Fungal Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015966","descriptor_name":"Gene Expression Regulation, Fungal","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015003","descriptor_name":"Yeasts","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":4,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx328","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/18/2867/25164231/btx328.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://europepmc.org/articles/pmc5870568","pdf_url":"https://europepmc.org/articles/pmc5870568?pdf=render","source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":["European Bioinformatics Institute"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5870568","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28520900","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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx328","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/18/2867/25164231/btx328.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute","award_id":"5T32CA106209-07 (T32)"}],"datasets":[],"versions":[],"referenced_works_count":33,"referenced_works":["https://openalex.org/W1548779692","https://openalex.org/W1594031697","https://openalex.org/W1672197616","https://openalex.org/W1886306325","https://openalex.org/W1966701961","https://openalex.org/W1974542028","https://openalex.org/W1979921905","https://openalex.org/W1993436046","https://openalex.org/W2006495880","https://openalex.org/W2011430131","https://openalex.org/W2021039675","https://openalex.org/W2034400748","https://openalex.org/W2037184328","https://openalex.org/W2040814250","https://openalex.org/W2044702943","https://openalex.org/W2073149227","https://openalex.org/W2079707657","https://openalex.org/W2096283457","https://openalex.org/W2105860794","https://openalex.org/W2115462905","https://openalex.org/W2125310307","https://openalex.org/W2132549764","https://openalex.org/W2140736261","https://openalex.org/W2141951767","https://openalex.org/W2154699792","https://openalex.org/W2169694221","https://openalex.org/W2294644361","https://openalex.org/W2491691281","https://openalex.org/W2560367415","https://openalex.org/W4240959780","https://openalex.org/W4250657332","https://openalex.org/W4285719527","https://openalex.org/W96209122"],"related_works":["https://openalex.org/W62488488","https://openalex.org/W4233322082","https://openalex.org/W3165117444","https://openalex.org/W3106969033","https://openalex.org/W2370872739","https://openalex.org/W2357988910","https://openalex.org/W2186939576","https://openalex.org/W2170142494","https://openalex.org/W2072982484","https://openalex.org/W1993351602"],"abstract_inverted_index":{"For":[0,25],"cluster":[1],"analysis,":[2],"high-dimensional":[3],"data":[4,70],"are":[5,31],"associated":[6],"with":[7,42],"instability,":[8],"decreased":[9],"classification":[10],"accuracy":[11],"and":[12,61],"high-computational":[13],"burden.":[14],"The":[15,47],"latter":[16],"challenge":[17],"can":[18,49,62],"be":[19,50,63],"eliminated":[20],"as":[21],"a":[22,36],"serious":[23],"concern.":[24],"applications":[26],"where":[27],"dimension":[28],"reduction":[29],"techniques":[30],"not":[32],"implemented,":[33],"we":[34],"propose":[35],"temporary":[37],"transformation":[38],"which":[39],"accelerates":[40],"computations":[41],"no":[43],"loss":[44],"of":[45,69],"information.":[46],"algorithm":[48],"applied":[51],"for":[52],"any":[53],"statistical":[54],"procedure":[55],"depending":[56],"only":[57],"on":[58],"Euclidean":[59],"distances":[60],"implemented":[64],"sequentially":[65],"to":[66],"enable":[67],"analyses":[68],"that":[71],"would":[72],"otherwise":[73],"exceed":[74],"memory":[75],"limitations.":[76]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2615188342","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-01-16T01:46:55.049731","created_date":"2017-05-26"}