{"id":"https://openalex.org/W2207323202","doi":"https://doi.org/10.1109/bigdata.2015.7364117","title":"Big Data: Cloud computing in genomics applications","display_name":"Big Data: Cloud computing in genomics applications","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2207323202","doi":"https://doi.org/10.1109/bigdata.2015.7364117","mag":"2207323202"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7364117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (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/A5109225873","display_name":"Hangu Yeo","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hangu Yeo","raw_affiliation_strings":["Department of Next Generation Systems, IBM T. J. Watson Research Center, Yorktown Heights, NY, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Next Generation Systems, IBM T. J. Watson Research Center, Yorktown Heights, NY, U.S.A","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085993185","display_name":"Catherine H. Crawford","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Catherine H. Crawford","raw_affiliation_strings":["Department of Next Generation Systems, IBM T. J. Watson Research Center, Yorktown Heights, NY, U.S.A"],"affiliations":[{"raw_affiliation_string":"Department of Next Generation Systems, IBM T. J. Watson Research Center, Yorktown Heights, NY, U.S.A","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109225873"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":2.1572,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90334973,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2904","last_page":"2906"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9884999990463257,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9818999767303467,"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/computer-science","display_name":"Computer science","score":0.8428117632865906},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7717118263244629},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7693322896957397},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.759698212146759},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7587404251098633},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5341507196426392},{"id":"https://openalex.org/keywords/data-intensive-computing","display_name":"Data-intensive computing","score":0.4578482210636139},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43953683972358704},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.41619405150413513},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40753164887428284},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32872429490089417},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2657468616962433},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24716684222221375},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2219163179397583},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.0971621572971344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8428117632865906},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7717118263244629},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7693322896957397},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.759698212146759},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7587404251098633},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5341507196426392},{"id":"https://openalex.org/C76831024","wikidata":"https://www.wikidata.org/wiki/Q5227096","display_name":"Data-intensive computing","level":4,"score":0.4578482210636139},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43953683972358704},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41619405150413513},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40753164887428284},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32872429490089417},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2657468616962433},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24716684222221375},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2219163179397583},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.0971621572971344},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7364117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.550000011920929,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W50899556","https://openalex.org/W1597108197","https://openalex.org/W2055043387","https://openalex.org/W2103441770","https://openalex.org/W2161488606","https://openalex.org/W2170551349","https://openalex.org/W4236236547","https://openalex.org/W6602159766","https://openalex.org/W6683504902"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W2288337563","https://openalex.org/W2794953737","https://openalex.org/W2141724443"],"abstract_inverted_index":{"Healthcare":[0],"applications":[1,47,83],"typically":[2],"require":[3],"big":[4,53],"data":[5,54,100],"management":[6],"as":[7,9],"well":[8,50],"intensive":[10],"computation.":[11],"This":[12],"is":[13],"especially":[14],"true":[15],"with":[16,132],"recently":[17],"developed":[18],"next":[19],"generation":[20],"sequencing":[21],"technology":[22],"which":[23,79],"increases":[24],"interests":[25],"in":[26,33,69],"processing":[27],"the":[28,45,88,94,98,105,119],"huge":[29],"amount":[30],"of":[31,122],"information":[32],"a":[34],"timely":[35],"fashion.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40,96],"focus":[41],"on":[42,51,87,129],"testing":[43],"whether":[44],"healthcare":[46],"can":[48,126],"scale":[49],"commercial":[52],"platforms":[55],"that":[56,118],"implement":[57],"MapReduce":[58,90,130],"framework.":[59,91],"We":[60],"selected":[61],"short":[62],"read":[63],"sequence":[64],"alignment":[65],"and":[66,73,77,116,136],"assembly":[67],"workloads":[68],"genome":[70],"analysis":[71,124],"workloads,":[72],"chose":[74],"Bowtie,":[75],"Blast":[76],"Contrail-bio":[78],"are":[80,108,113],"publically":[81],"available":[82],"designed":[84],"to":[85],"run":[86],"Hadoop":[89],"To":[92],"speed-up":[93],"processes":[95],"compressed":[97],"intermediate":[99],"using":[101],"various":[102],"compression":[103,106],"schemes":[104,107],"compared.":[109],"The":[110],"test":[111],"results":[112],"very":[114],"promising":[115],"indicate":[117],"wide":[120],"range":[121],"genomic":[123],"workflows":[125],"be":[127],"optimized":[128],"frameworks":[131],"great":[133],"computational":[134],"efficiency":[135],"scalability.":[137]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}