{"id":"https://openalex.org/W1123913732","doi":"https://doi.org/10.1109/globalsip.2015.7418173","title":"Big data proteogenomics and high performance computing: Challenges and opportunities","display_name":"Big data proteogenomics and high performance computing: Challenges and opportunities","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W1123913732","doi":"https://doi.org/10.1109/globalsip.2015.7418173","mag":"1123913732"},"language":"en","primary_location":{"id":"doi:10.1109/globalsip.2015.7418173","doi":"https://doi.org/10.1109/globalsip.2015.7418173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2015.7418173","pdf_url":null,"source":{"id":"https://openalex.org/S4306418625","display_name":"IEEE Global Conference on Signal and Information Processing","issn_l":"2376-4066","issn":["2376-4066"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5102729196","display_name":"Fahad Saeed","orcid":"https://orcid.org/0000-0002-3410-9552","observed_orcids":["https://orcid.org/0000-0002-3410-9552"]},"institutions":[{"id":"https://openalex.org/I141649380","display_name":"Western Michigan University","ror":"https://ror.org/04j198w64","country_code":"US","type":"education","lineage":["https://openalex.org/I141649380"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fahad Saeed","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Western Michigan University, Kalamazoo, MI","Department of Electrical and Computer Engineering, Department of Computer Science, Western Michigan University, Kalamazoo, MI 49008-5466"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Western Michigan University, Kalamazoo, MI","institution_ids":["https://openalex.org/I141649380"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Department of Computer Science, Western Michigan University, Kalamazoo, MI 49008-5466","institution_ids":["https://openalex.org/I141649380"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5102729196"],"corresponding_institution_ids":["https://openalex.org/I141649380"],"apc_list":null,"apc_paid":null,"fwci":6.9783,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.95323981,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"141","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9110999703407288,"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"}},"topics":[{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9110999703407288,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.04280000180006027,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.013100000098347664,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/proteogenomics","display_name":"proteogenomics","score":1.0},{"id":"https://openalex.org/keywords/big-data","display_name":"big data","score":0.9589999914169312},{"id":"https://openalex.org/keywords/high-performance-computing","display_name":"high-performance computing","score":0.9810000061988831},{"id":"https://openalex.org/keywords/mass-spectrometry","display_name":"mass spectrometry","score":0.8859999775886536},{"id":"https://openalex.org/keywords/next-generation-sequencing","display_name":"next-generation sequencing","score":0.996999979019165},{"id":"https://openalex.org/keywords/data-integration","display_name":"data integration","score":0.8420000076293945},{"id":"https://openalex.org/keywords/data-storage","display_name":"data storage","score":0.8330000042915344},{"id":"https://openalex.org/keywords/data-transmission","display_name":"data transmission","score":0.9610000252723694},{"id":"https://openalex.org/keywords/data-analysis","display_name":"data analysis","score":0.4480000138282776},{"id":"https://openalex.org/keywords/systems-biology","display_name":"systems biology","score":0.609000027179718},{"id":"https://openalex.org/keywords/computational-challenges","display_name":"computational challenges","score":0.5289999842643738}],"concepts":[{"id":"https://openalex.org/C145741570","wikidata":"https://www.wikidata.org/wiki/Q7251534","display_name":"Proteogenomics","level":5,"score":0.9232296347618103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7618049383163452},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7098732590675354},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44884854555130005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.13380283117294312},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.10345876216888428},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08317422866821289},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/globalsip.2015.7418173","doi":"https://doi.org/10.1109/globalsip.2015.7418173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2015.7418173","pdf_url":null,"source":{"id":"https://openalex.org/S4306418625","display_name":"IEEE Global Conference on Signal and Information Processing","issn_l":"2376-4066","issn":["2376-4066"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.848.6258","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.848.6258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://scholarworks.wmich.edu/cgi/viewcontent.cgi?article%3D1002%26context%3Dpcds_reports","raw_type":"text"},{"id":"pmh:oai:scholarworks.wmich.edu:pcds_reports-1002","doi":null,"is_oa":false,"landing_page_url":"https://scholarworks.wmich.edu/pcds_reports/3","pdf_url":null,"source":{"id":"https://openalex.org/S4377196527","display_name":"ScholarWorks - WMU (Western Michigan University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I141649380","host_organization_name":"Western Michigan University","host_organization_lineage":["https://openalex.org/I141649380"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Parallel Computing and Data Science Lab Technical Reports","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W53594632","https://openalex.org/W61452564","https://openalex.org/W1582081546","https://openalex.org/W1968044788","https://openalex.org/W1975798613","https://openalex.org/W1976797410","https://openalex.org/W1977790981","https://openalex.org/W1978275829","https://openalex.org/W1992388834","https://openalex.org/W1993158258","https://openalex.org/W2008752257","https://openalex.org/W2011354186","https://openalex.org/W2014344192","https://openalex.org/W2018774772","https://openalex.org/W2020101499","https://openalex.org/W2023655541","https://openalex.org/W2024569607","https://openalex.org/W2025191288","https://openalex.org/W2026433130","https://openalex.org/W2038668694","https://openalex.org/W2039997444","https://openalex.org/W2048593198","https://openalex.org/W2064676287","https://openalex.org/W2068016108","https://openalex.org/W2069542456","https://openalex.org/W2074426357","https://openalex.org/W2076852968","https://openalex.org/W2097420863","https://openalex.org/W2125043293","https://openalex.org/W2131806062","https://openalex.org/W2133703845","https://openalex.org/W2138196010","https://openalex.org/W2139518905","https://openalex.org/W2149548305","https://openalex.org/W2159683766","https://openalex.org/W2159725359","https://openalex.org/W2164372370","https://openalex.org/W2166588423","https://openalex.org/W2327886352","https://openalex.org/W2603513592","https://openalex.org/W3102187655","https://openalex.org/W4211208250","https://openalex.org/W4247320886","https://openalex.org/W4285719527","https://openalex.org/W6735922123"],"related_works":["https://openalex.org/W3114526652","https://openalex.org/W4392147084","https://openalex.org/W1973364049","https://openalex.org/W7064460745","https://openalex.org/W2179803057","https://openalex.org/W4294688275","https://openalex.org/W2216354124","https://openalex.org/W2760028537","https://openalex.org/W2524916633","https://openalex.org/W4392130777"],"abstract_inverted_index":{"Proteogenomics":[0],"is":[1,101],"an":[2],"emerging":[3],"field":[4],"of":[5,12,52,69,98,108],"systems":[6],"biology":[7],"research":[8,128],"at":[9],"the":[10,70,104,111],"intersection":[11],"proteomics":[13,23],"and":[14,24,41,56,87,110,117,132],"genomics.":[15],"Two":[16],"high-throughput":[17],"technologies,":[18],"Mass":[19],"Spectrometry":[20],"(MS)":[21],"for":[22,30,64,77,84,124],"Next":[25],"Generation":[26],"Sequencing":[27],"(NGS)":[28],"machines":[29],"genomics":[31],"are":[32,44,82,93,130,136],"required":[33],"to":[34,102],"conduct":[35],"proteogenomics":[36,65,79,109],"studies.":[37],"Independently":[38],"both":[39],"MS":[40],"NGS":[42],"technologies":[43],"inflicted":[45],"with":[46],"data":[47,61,86,106,120],"deluge":[48],"which":[49],"creates":[50],"problems":[51],"storage,":[53],"transfer,":[54],"analysis":[55,81],"visualization.":[57],"Integrating":[58],"these":[59,78,119],"big":[60,85,105],"sets":[62],"(NGS+MS)":[63],"studies":[66],"compounds":[67],"all":[68],"associated":[71,112],"computational":[72],"problems.":[73],"Existing":[74],"sequential":[75],"algorithms":[76],"datasets":[80],"inadequate":[83],"high":[88,125],"performance":[89,126],"computing":[90,127],"(HPC)":[91],"solutions":[92],"almost":[94],"non-existent.":[95],"The":[96],"purpose":[97],"this":[99],"paper":[100],"introduce":[103],"problem":[107],"challenges":[113],"in":[114],"analyzing,":[115],"storing":[116],"transferring":[118],"sets.":[121],"Further,":[122],"opportunities":[123],"community":[129],"identified":[131],"possible":[133],"future":[134],"directions":[135],"discussed.":[137]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}