{"id":"https://openalex.org/W2874035062","doi":"https://doi.org/10.1145/3219104.3229278","title":"Searching the Sequence Read Archive using Jetstream and Wrangler","display_name":"Searching the Sequence Read Archive using Jetstream and Wrangler","publication_year":2018,"publication_date":"2018-07-12","ids":{"openalex":"https://openalex.org/W2874035062","doi":"https://doi.org/10.1145/3219104.3229278","mag":"2874035062"},"language":"en","primary_location":{"id":"doi:10.1145/3219104.3229278","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219104.3229278","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219104.3229278","source":{"id":"https://openalex.org/S4306524298","display_name":"Proceedings of the Practice and Experience on Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"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 Practice and Experience on Advanced Research Computing","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/10.1145/3219104.3229278","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025670930","display_name":"Kyle Levi","orcid":"https://orcid.org/0000-0002-5611-0685"},"institutions":[{"id":"https://openalex.org/I26538001","display_name":"San Diego State University","ror":"https://ror.org/0264fdx42","country_code":"US","type":"education","lineage":["https://openalex.org/I26538001"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kyle Levi","raw_affiliation_strings":["San Diego State University - Biological and Medical Informatics Program, San Diego, California, United States of America"],"affiliations":[{"raw_affiliation_string":"San Diego State University - Biological and Medical Informatics Program, San Diego, California, United States of America","institution_ids":["https://openalex.org/I26538001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079942660","display_name":"Mats Rynge","orcid":"https://orcid.org/0000-0002-1779-7189"},"institutions":[{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mats Rynge","raw_affiliation_strings":["USC Information Sciences Institute, Marina del Rey, California, United States of America"],"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute, Marina del Rey, California, United States of America","institution_ids":["https://openalex.org/I2801204180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075415797","display_name":"Eroma Abeysinghe","orcid":"https://orcid.org/0000-0002-1801-2515"},"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":"Eroma Abeysinghe","raw_affiliation_strings":["Indiana University - Science Gateways Research Center, Bloomington, Indiana, United States of America"],"affiliations":[{"raw_affiliation_string":"Indiana University - Science Gateways Research Center, Bloomington, Indiana, United States of America","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036802114","display_name":"Robert A. Edwards","orcid":"https://orcid.org/0000-0001-8383-8949"},"institutions":[{"id":"https://openalex.org/I26538001","display_name":"San Diego State University","ror":"https://ror.org/0264fdx42","country_code":"US","type":"education","lineage":["https://openalex.org/I26538001"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert A. Edwards","raw_affiliation_strings":["San Diego State University - Department of Computer Science, San Diego, California, United States of America"],"affiliations":[{"raw_affiliation_string":"San Diego State University - Department of Computer Science, San Diego, California, United States of America","institution_ids":["https://openalex.org/I26538001"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025670930"],"corresponding_institution_ids":["https://openalex.org/I26538001"],"apc_list":null,"apc_paid":null,"fwci":2.9525,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91854574,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9969000220298767,"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"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9969000220298767,"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"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.995199978351593,"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/pipeline","display_name":"Pipeline (software)","score":0.7076740264892578},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6982582807540894},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.6729140281677246},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6141465902328491},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6026691794395447},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5172103643417358},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49667245149612427},{"id":"https://openalex.org/keywords/gateway","display_name":"Gateway (web page)","score":0.48994773626327515},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45607832074165344},{"id":"https://openalex.org/keywords/citizen-science","display_name":"Citizen science","score":0.4530961811542511},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4329816699028015},{"id":"https://openalex.org/keywords/cyberinfrastructure","display_name":"Cyberinfrastructure","score":0.4274926483631134},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4132637083530426},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34494858980178833},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34359851479530334},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3232526183128357},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09405097365379333},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08731949329376221},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08464580774307251}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7076740264892578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6982582807540894},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.6729140281677246},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6141465902328491},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6026691794395447},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5172103643417358},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49667245149612427},{"id":"https://openalex.org/C2777710495","wikidata":"https://www.wikidata.org/wiki/Q5527195","display_name":"Gateway (web page)","level":2,"score":0.48994773626327515},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45607832074165344},{"id":"https://openalex.org/C197352329","wikidata":"https://www.wikidata.org/wiki/Q1093434","display_name":"Citizen science","level":2,"score":0.4530961811542511},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4329816699028015},{"id":"https://openalex.org/C2776397876","wikidata":"https://www.wikidata.org/wiki/Q1450531","display_name":"Cyberinfrastructure","level":2,"score":0.4274926483631134},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4132637083530426},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34494858980178833},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34359851479530334},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3232526183128357},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09405097365379333},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08731949329376221},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08464580774307251},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3219104.3229278","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219104.3229278","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219104.3229278","source":{"id":"https://openalex.org/S4306524298","display_name":"Proceedings of the Practice and Experience on Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"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 Practice and Experience on Advanced Research Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3219104.3229278","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3219104.3229278","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3219104.3229278","source":{"id":"https://openalex.org/S4306524298","display_name":"Proceedings of the Practice and Experience on Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"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 Practice and Experience on Advanced Research Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2874035062.pdf","grobid_xml":"https://content.openalex.org/works/W2874035062.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1795725","https://openalex.org/W1557515632","https://openalex.org/W1966912927","https://openalex.org/W2001818158","https://openalex.org/W2043701535","https://openalex.org/W2089375051","https://openalex.org/W2094373869","https://openalex.org/W2100643889","https://openalex.org/W2122210493","https://openalex.org/W2129154270","https://openalex.org/W2148317584","https://openalex.org/W2233923532","https://openalex.org/W2725432521","https://openalex.org/W3011856351","https://openalex.org/W4239871258","https://openalex.org/W4242424635","https://openalex.org/W4391092847","https://openalex.org/W4402673998"],"related_works":["https://openalex.org/W273500195","https://openalex.org/W2043019925","https://openalex.org/W4236056781","https://openalex.org/W4293768956","https://openalex.org/W2773781927","https://openalex.org/W2184477657","https://openalex.org/W90628286","https://openalex.org/W1696735061","https://openalex.org/W4361794984","https://openalex.org/W2792198850"],"abstract_inverted_index":{"The":[0],"Sequence":[1],"Read":[2],"Archive":[3],"(SRA),":[4],"the":[5,24,45,56,105,108,111,127,130,144],"world's":[6],"largest":[7],"database":[8],"of":[9,17,27,36,58,98,129,148],"sequences,":[10],"hosts":[11],"approximately":[12],"10":[13,28],"petabases":[14],"(1016":[15],"bp)":[16],"sequence":[18,66],"data":[19,37,67,88],"and":[20,50,74,117,152],"is":[21,38,166],"growing":[22],"at":[23],"alarming":[25],"rate":[26],"TB":[29],"per":[30],"day.":[31],"Yet":[32],"this":[33,78],"rich":[34],"trove":[35],"inaccessible":[39],"to":[40,63,100,103,125,138,142,155,168],"most":[41,59],"researchers:":[42],"searching":[43],"through":[44],"SRA":[46,109,145],"requires":[47],"large":[48],"storage":[49],"computing":[51,114],"facilities":[52],"that":[53,165],"are":[54,94,133,153],"beyond":[55],"capacity":[57],"laboratories.":[60],"Enabling":[61],"scientists":[62,141],"analyze":[64],"existing":[65,136],"will":[68],"provide":[69],"insight":[70],"into":[71],"ecology,":[72],"medicine,":[73],"industrial":[75],"applications.":[76],"In":[77],"project":[79],"we":[80],"specifically":[81],"focus":[82],"on":[83],"metagenomic":[84],"sequences":[85],"(whole":[86],"community":[87],"sets":[89],"from":[90],"different":[91],"environments).":[92],"We":[93,119,132],"developing":[95],"a":[96,122,157,161],"set":[97],"tools":[99],"enable":[101,139],"biologists":[102],"mine":[104],"metagenomes":[106,146],"in":[107],"using":[110],"NSF-funded":[112],"cloud":[113],"resources,":[115],"Jetstream":[116],"Wrangler.":[118],"have":[120],"developed":[121],"proof-of-principle":[123],"pipeline":[124,159],"demonstrate":[126],"feasibility":[128],"approach.":[131],"leveraging":[134],"our":[135],"infrastructure":[137],"all":[140,169],"access":[143],"regardless":[147],"their":[149],"computational":[150],"ability":[151],"working":[154],"create":[156],"stable":[158],"with":[160],"science":[162],"gateway":[163],"portal":[164],"accessible":[167],"researchers.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
