{"id":"https://openalex.org/W4406458194","doi":"https://doi.org/10.1109/bigdata62323.2024.10825091","title":"Value-Compressed Sparse Column (VCSC): Sparse Matrix Storage for Single-cell Omics Data","display_name":"Value-Compressed Sparse Column (VCSC): Sparse Matrix Storage for Single-cell Omics Data","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458194","doi":"https://doi.org/10.1109/bigdata62323.2024.10825091"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5092849691","display_name":"Seth Wolfgang","orcid":"https://orcid.org/0009-0002-4356-5186"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Seth Wolfgang","raw_affiliation_strings":["University of Indiana,Department of Intelligent Systems Engineering,Bloomington,IN,USA"],"affiliations":[{"raw_affiliation_string":"University of Indiana,Department of Intelligent Systems Engineering,Bloomington,IN,USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092849690","display_name":"Skyler Ruiter","orcid":"https://orcid.org/0009-0008-5978-9866"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Skyler Ruiter","raw_affiliation_strings":["University of Indiana,Department of Intelligent Systems Engineering,Bloomington,IN,USA"],"affiliations":[{"raw_affiliation_string":"University of Indiana,Department of Intelligent Systems Engineering,Bloomington,IN,USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004132685","display_name":"Marc Tunnell","orcid":"https://orcid.org/0000-0001-5281-4012"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc Tunnell","raw_affiliation_strings":["Purdue University,Department of Computer Science,West Lafayette,IN,USA"],"affiliations":[{"raw_affiliation_string":"Purdue University,Department of Computer Science,West Lafayette,IN,USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041929142","display_name":"Timothy J. Triche","orcid":"https://orcid.org/0000-0001-5665-946X"},"institutions":[{"id":"https://openalex.org/I1317189400","display_name":"Van Andel Institute","ror":"https://ror.org/00wm07d60","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1317189400"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy Triche","raw_affiliation_strings":["Van Andel Institute,Department of Epigenetics,Grand Rapids,MI,USA"],"affiliations":[{"raw_affiliation_string":"Van Andel Institute,Department of Epigenetics,Grand Rapids,MI,USA","institution_ids":["https://openalex.org/I1317189400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015859325","display_name":"Erin Carrier","orcid":"https://orcid.org/0000-0002-2254-2957"},"institutions":[{"id":"https://openalex.org/I8606887","display_name":"Grand Valley State University","ror":"https://ror.org/001m1hv61","country_code":"US","type":"education","lineage":["https://openalex.org/I8606887"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erin Carrier","raw_affiliation_strings":["Grand Valley State University,College of Computing,Allendale,MI,USA"],"affiliations":[{"raw_affiliation_string":"Grand Valley State University,College of Computing,Allendale,MI,USA","institution_ids":["https://openalex.org/I8606887"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038529544","display_name":"Zachary J. DeBruine","orcid":"https://orcid.org/0000-0003-2234-4827"},"institutions":[{"id":"https://openalex.org/I8606887","display_name":"Grand Valley State University","ror":"https://ror.org/001m1hv61","country_code":"US","type":"education","lineage":["https://openalex.org/I8606887"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary DeBruine","raw_affiliation_strings":["Grand Valley State University,College of Computing,Allendale,MI,USA"],"affiliations":[{"raw_affiliation_string":"Grand Valley State University,College of Computing,Allendale,MI,USA","institution_ids":["https://openalex.org/I8606887"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5092849691"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":0.2501,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61205232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4952","last_page":"4958"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9930999875068665,"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":0.9923999905586243,"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/sparse-matrix","display_name":"Sparse matrix","score":0.6579943895339966},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.6267834305763245},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5864668488502502},{"id":"https://openalex.org/keywords/compressed-sensing","display_name":"Compressed sensing","score":0.5712857246398926},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5280336141586304},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4787287414073944},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.273906946182251},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1486406922340393},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.1273420751094818},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.06990960240364075}],"concepts":[{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6579943895339966},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.6267834305763245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5864668488502502},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.5712857246398926},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5280336141586304},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4787287414073944},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.273906946182251},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1486406922340393},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.1273420751094818},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.06990960240364075},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315474","display_name":"Chan Zuckerberg Initiative","ror":"https://ror.org/02qenvm24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1965551736","https://openalex.org/W1988311079","https://openalex.org/W1990653637","https://openalex.org/W2022704179","https://openalex.org/W2035080386","https://openalex.org/W2060108852","https://openalex.org/W2080353445","https://openalex.org/W2089908605","https://openalex.org/W2114977680","https://openalex.org/W2126004407","https://openalex.org/W2219888463","https://openalex.org/W2997591727","https://openalex.org/W6750059447","https://openalex.org/W6929800938"],"related_works":["https://openalex.org/W3011821305","https://openalex.org/W2737338842","https://openalex.org/W3005946484","https://openalex.org/W4387560237","https://openalex.org/W4285148873","https://openalex.org/W2045476623","https://openalex.org/W4287713161","https://openalex.org/W2076468490","https://openalex.org/W2081219400","https://openalex.org/W2805810264"],"abstract_inverted_index":{"Genomics":[0,62],"datasets,":[1],"such":[2],"as":[3],"single-cell":[4,65],"transcriptomics,":[5],"are":[6],"often":[7,67],"very":[8],"large":[9],"and":[10,19,95,139,160,187],"highly":[11],"sparse,":[12],"posing":[13],"significant":[14,123],"challenges":[15],"for":[16,60,78],"both":[17],"storage":[18,186],"computation.":[20,80],"As":[21],"the":[22,38,181,190],"scale":[23],"of":[24,105,184,192],"data":[25,114,185],"generation":[26],"accelerates,":[27],"efficiently":[28],"compressing":[29,133],"these":[30],"datasets":[31],"becomes":[32],"crucial.":[33],"Current":[34],"compression":[35],"methods,":[36],"like":[37,53],"popular":[39],"Compressed":[40],"Sparse":[41,92,99],"Column":[42,93,100],"(CSC)":[43],"format,":[44],"capitalize":[45],"only":[46],"on":[47,119,152],"sparsity":[48],"but":[49],"overlook":[50],"other":[51],"properties":[52],"redundancy,":[54],"which":[55],"can":[56,162],"offer":[57],"additional":[58],"opportunities":[59],"compression.":[61],"data,":[63,121],"especially":[64],"assays,":[66],"exhibit":[68],"high":[69,106],"redundancy":[70,107],"within":[71,108],"columns,":[72],"making":[73],"traditional":[74],"sparse":[75],"formats":[76,174],"inefficient":[77],"in-core":[79],"In":[81],"this":[82],"paper,":[83],"we":[84],"present":[85],"two":[86],"extensions":[87],"to":[88,111,126,143],"CSC:":[89],"(1)":[90],"Value-Compressed":[91,98],"(VCSC)":[94],"(2)":[96],"Index-and":[97],"(IVCSC).":[101],"VCSC":[102,131,159],"takes":[103],"advantage":[104],"a":[109,144,176],"column":[110],"further":[112],"compress":[113],"up":[115,142],"1.9-fold":[116],"over":[117,150],"CSC":[118,151],"real":[120,153],"without":[122],"negative":[124],"impact":[125],"performance":[127],"characteristics.":[128],"IVCSC":[129,161],"extends":[130],"by":[132],"index":[134],"arrays":[135],"through":[136],"delta":[137],"encoding":[138],"byte-packing,":[140],"achieving":[141],"4.4-fold":[145],"decrease":[146],"in":[147,165,179,189],"memory":[148],"usage":[149],"data.":[154],"Our":[155],"benchmarks":[156],"show":[157],"that":[158],"be":[163],"used":[164],"compressed":[166],"form":[167],"with":[168],"little":[169],"added":[170],"computational":[171],"cost.":[172],"These":[173],"represent":[175],"step":[177],"forward":[178],"balancing":[180],"growing":[182],"demands":[183],"processing":[188],"era":[191],"large-scale":[193],"genomics.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-01-17T00:00:00"}