{"id":"https://openalex.org/W4293024107","doi":"https://doi.org/10.1145/3489517.3530449","title":"A near-storage framework for boosted data preprocessing of mass spectrum clustering","display_name":"A near-storage framework for boosted data preprocessing of mass spectrum clustering","publication_year":2022,"publication_date":"2022-07-10","ids":{"openalex":"https://openalex.org/W4293024107","doi":"https://doi.org/10.1145/3489517.3530449"},"language":"en","primary_location":{"id":"doi:10.1145/3489517.3530449","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3489517.3530449","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3489517.3530449","source":{"id":"https://openalex.org/S4363608816","display_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3489517.3530449","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100407819","display_name":"Weihong Xu","orcid":"https://orcid.org/0000-0001-8521-7644"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weihong Xu","raw_affiliation_strings":["University of California"],"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072579616","display_name":"Jaeyoung Kang","orcid":"https://orcid.org/0000-0003-1048-1285"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaeyoung Kang","raw_affiliation_strings":["University of California"],"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112841571","display_name":"Tajana Rosing","orcid":null},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tajana Rosing","raw_affiliation_strings":["University of California"],"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100407819"],"corresponding_institution_ids":["https://openalex.org/I2803209242"],"apc_list":null,"apc_paid":null,"fwci":3.9626,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.95200629,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"313","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9969000220298767,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9969000220298767,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.7730574607849121},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7041764259338379},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7003657221794128},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5433517098426819},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4562349319458008},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4260948896408081},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.41277819871902466},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37330782413482666},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32861968874931335},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14332568645477295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1407683789730072},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1035502552986145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730574607849121},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7041764259338379},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7003657221794128},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5433517098426819},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4562349319458008},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4260948896408081},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.41277819871902466},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37330782413482666},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32861968874931335},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14332568645477295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1407683789730072},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1035502552986145}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3489517.3530449","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3489517.3530449","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3489517.3530449","source":{"id":"https://openalex.org/S4363608816","display_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3489517.3530449","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3489517.3530449","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3489517.3530449","source":{"id":"https://openalex.org/S4363608816","display_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1213656504","display_name":null,"funder_award_id":"#1826967","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2032484114","display_name":null,"funder_award_id":"#2052809","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G317115702","display_name":null,"funder_award_id":"1911095","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3287241332","display_name":null,"funder_award_id":"#2100237","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3839026591","display_name":null,"funder_award_id":"#1911095","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4678109426","display_name":null,"funder_award_id":"#2112167","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G502606643","display_name":null,"funder_award_id":"1826967","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5454659100","display_name":null,"funder_award_id":"#2112665","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5665456810","display_name":null,"funder_award_id":"2100237","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6026952011","display_name":null,"funder_award_id":"2052809","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7406030291","display_name":null,"funder_award_id":"CRISP","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7906245503","display_name":null,"funder_award_id":"211266","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8732482030","display_name":null,"funder_award_id":"SRC program","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293024107.pdf","grobid_xml":"https://content.openalex.org/works/W4293024107.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1480858518","https://openalex.org/W1981593008","https://openalex.org/W1984566266","https://openalex.org/W2023010129","https://openalex.org/W2056499061","https://openalex.org/W2057761395","https://openalex.org/W2105102111","https://openalex.org/W2159046366","https://openalex.org/W2186821278","https://openalex.org/W2212342797","https://openalex.org/W2252860746","https://openalex.org/W2322680505","https://openalex.org/W2352208637","https://openalex.org/W2465480251","https://openalex.org/W2562753754","https://openalex.org/W2593489870","https://openalex.org/W2792589388","https://openalex.org/W2952261448","https://openalex.org/W2979937837","https://openalex.org/W2991491873","https://openalex.org/W3017149008","https://openalex.org/W3176745572","https://openalex.org/W4252466366"],"related_works":["https://openalex.org/W2965443650","https://openalex.org/W62276109","https://openalex.org/W2288882656","https://openalex.org/W2566086483","https://openalex.org/W2801924399","https://openalex.org/W2106322795","https://openalex.org/W2234560492","https://openalex.org/W2094936398","https://openalex.org/W2953374787","https://openalex.org/W2080529643"],"abstract_inverted_index":{"Mass":[0,46],"spectrometry":[1],"(MS)":[2],"has":[3],"been":[4],"a":[5,89],"key":[6],"to":[7,12,16,70,93,141,171,205,209],"proteomics":[8],"and":[9,18,59,76,83,105,135,173,179],"metabolomics":[10],"due":[11],"its":[13],"unique":[14],"ability":[15],"identify":[17],"analyze":[19],"protein":[20,61],"structures.":[21],"Modern":[22],"MS":[23,65,193],"equipment":[24],"generates":[25],"massive":[26],"amount":[27],"of":[28,43,99,117,124,203],"tandem":[29],"mass":[30],"spectra":[31,109],"with":[32,150,207],"high":[33],"redundancy,":[34],"making":[35],"spectral":[36],"analysis":[37],"the":[38,114,143,157,161,177,180],"major":[39],"bottleneck":[40],"in":[41,201],"design":[42,159],"new":[44],"medicines.":[45],"spectrum":[47,72,96],"clustering":[48,194],"is":[49,169],"one":[50],"promising":[51],"solution":[52],"as":[53],"it":[54,168],"greatly":[55],"reduces":[56],"data":[57,101,118,144],"redundancy":[58],"boosts":[60],"identification.":[62],"However,":[63],"state-of-the-art":[64,181],"tools":[66],"take":[67],"many":[68],"hours":[69],"run":[71],"clustering.":[73,86],"Spectra":[74],"loading":[75,100],"preprocessing":[77,166],"consumes":[78],"average":[79],"82%":[80],"execution":[81],"time":[82],"energy":[84,212],"during":[85],"We":[87,120],"propose":[88],"near-storage":[90],"framework,":[91],"MSAS,":[92],"speed":[94,202],"up":[95,170],"preprocessing.":[97],"Instead":[98],"into":[102,191],"host":[103],"memory":[104],"CPU,":[106],"MSAS":[107,190],"processes":[108],"near":[110],"storage,":[111],"thus":[112],"reducing":[113],"expensive":[115],"cost":[116],"movement.":[119],"present":[121],"two":[122,131],"types":[123],"accelerators":[125,138],"that":[126,156],"leverage":[127],"internal":[128],"bandwidth":[129],"at":[130,146],"storage":[132,148],"levels:":[133],"SSD":[134],"channel.":[136],"The":[137],"are":[139],"optimized":[140],"match":[142],"rate":[145],"each":[147],"level":[149,199],"negligible":[151],"overhead.":[152],"Our":[153],"results":[154],"demonstrate":[155],"channel-level":[158,189],"yields":[160],"best":[162],"performance":[163],"improvement":[164],"for":[165],"-":[167],"187X":[172],"1.8X":[174],"faster":[175],"than":[176],"CPU":[178],"in-storage":[182],"computing":[183],"solution,":[184],"INSIDER,":[185],"respectively.":[186],"After":[187],"integrating":[188],"existing":[192],"tools,":[195],"we":[196],"measure":[197],"system":[198],"improvements":[200],"3.5X":[204],"9.8X":[206],"2.8X":[208],"11.9X":[210],"better":[211],"efficiency.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}