{"id":"https://openalex.org/W1978759257","doi":"https://doi.org/10.1109/bigdata.2013.6691723","title":"A scalable data analysis platform for metagenomics","display_name":"A scalable data analysis platform for metagenomics","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W1978759257","doi":"https://doi.org/10.1109/bigdata.2013.6691723","mag":"1978759257"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2013.6691723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","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/A5101741249","display_name":"Wei Tang","orcid":"https://orcid.org/0000-0002-3020-7817"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Tang","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL, USA","[Argonne Nat. Lab., Argonne, IL, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"[Argonne Nat. Lab., Argonne, IL, USA]","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050332036","display_name":"Jared Wilkening","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jared Wilkening","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL, USA","[Argonne Nat. Lab., Argonne, IL, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"[Argonne Nat. Lab., Argonne, IL, USA]","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113516752","display_name":"Narayan Desai","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Narayan Desai","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL, USA","[Argonne Nat. Lab., Argonne, IL, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"[Argonne Nat. Lab., Argonne, IL, USA]","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054085463","display_name":"Wolfgang Gerlach","orcid":"https://orcid.org/0000-0002-1480-1242"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wolfgang Gerlach","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL, USA","University of Chicago , Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"University of Chicago , Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027887614","display_name":"Andreas Wilke","orcid":"https://orcid.org/0000-0002-7699-2267"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Wilke","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL, USA","[Argonne Nat. Lab., Argonne, IL, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"[Argonne Nat. Lab., Argonne, IL, USA]","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086419862","display_name":"Folker Meyer","orcid":"https://orcid.org/0000-0003-1112-2284"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Folker Meyer","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL, USA","[Argonne Nat. Lab., Argonne, IL, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"[Argonne Nat. Lab., Argonne, IL, USA]","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.2094,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.98519623,"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":"21","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998000264167786,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991999864578247,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.989300012588501,"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/bottleneck","display_name":"Bottleneck","score":0.8022955060005188},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7908608317375183},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7466029524803162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743360161781311},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.6199185252189636},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.6119192838668823},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5255547761917114},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4735504686832428},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4498825669288635},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4410162568092346},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4341857433319092},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.4253045320510864},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38348594307899475},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3016665577888489},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.1448715627193451}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8022955060005188},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7908608317375183},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7466029524803162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743360161781311},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.6199185252189636},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.6119192838668823},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5255547761917114},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4735504686832428},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4498825669288635},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4410162568092346},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4341857433319092},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.4253045320510864},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38348594307899475},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3016665577888489},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.1448715627193451},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"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/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2013.6691723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1480333175","https://openalex.org/W1931807685","https://openalex.org/W1966952999","https://openalex.org/W1983833794","https://openalex.org/W1989348205","https://openalex.org/W2001291669","https://openalex.org/W2030692069","https://openalex.org/W2036880373","https://openalex.org/W2040890279","https://openalex.org/W2047585229","https://openalex.org/W2077579791","https://openalex.org/W2117608012","https://openalex.org/W2119180969","https://openalex.org/W2129666400","https://openalex.org/W2136145671","https://openalex.org/W2136482257","https://openalex.org/W2141322436","https://openalex.org/W2148317584","https://openalex.org/W2155545841","https://openalex.org/W2173213060","https://openalex.org/W2794396950","https://openalex.org/W2913513779","https://openalex.org/W6749789004"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W2748922771","https://openalex.org/W1830081926","https://openalex.org/W3021715857"],"abstract_inverted_index":{"With":[0],"the":[1,8,13,61],"advent":[2],"of":[3,12,16],"high-throughput":[4],"DNA":[5],"sequencing":[6],"technology,":[7],"analysis":[9,73,111,117],"and":[10,52,85,95,99,108],"management":[11,78,88],"increasing":[14],"amount":[15],"biological":[17,82,115],"sequence":[18,83],"data":[19,47,72,77,84,110,116],"has":[20,40],"become":[21],"a":[22,30,35,42,70,76,86,106],"bottleneck":[23],"for":[24,49,81,113],"scientific":[25,37],"progress.":[26],"For":[27],"example,":[28],"MG-RAST,":[29],"metagenome":[31],"annotation":[32],"system":[33,79,89],"serving":[34],"large":[36],"community":[38],"worldwide,":[39],"experienced":[41],"sustained,":[43],"exponential":[44],"growth":[45],"in":[46],"submissions":[48],"several":[50],"years;":[51],"this":[53,66],"trend":[54],"is":[55],"expected":[56],"to":[57,104],"continue.":[58],"To":[59],"address":[60],"computational":[62],"challenges":[63],"posed":[64],"by":[65],"workload,":[67],"we":[68],"developed":[69],"new":[71],"platform,":[74],"including":[75],"(Shock)":[80],"workflow":[87],"(AWE)":[90],"supporting":[91],"scalable,":[92],"fault-tolerant":[93],"task":[94],"resource":[96],"management.":[97],"Shock":[98],"AWE":[100],"can":[101],"be":[102],"used":[103],"build":[105],"scalable":[107],"reproducible":[109],"infrastructure":[112],"upper-level":[114],"services.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
