{"id":"https://openalex.org/W1990752744","doi":"https://doi.org/10.1109/iccabs.2013.6629243","title":"Workflow-driven programming paradigms for distributed analysis of biological big data","display_name":"Workflow-driven programming paradigms for distributed analysis of biological big data","publication_year":2013,"publication_date":"2013-06-01","ids":{"openalex":"https://openalex.org/W1990752744","doi":"https://doi.org/10.1109/iccabs.2013.6629243","mag":"1990752744"},"language":"en","primary_location":{"id":"doi:10.1109/iccabs.2013.6629243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccabs.2013.6629243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 3rd International Conference on Computational Advances in Bio and medical Sciences (ICCABS)","raw_type":"proceedings-article"},"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/A5028701796","display_name":"\u0130lkay Alt\u0131nta\u015f","orcid":"https://orcid.org/0000-0002-2196-0305"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ilkay Altintas","raw_affiliation_strings":["SAn Diego Supercomput. Center, Univ. of California, San Diego, La Jolla, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAn Diego Supercomput. Center, Univ. of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5028701796"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.15784713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9980999827384949,"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":0.9980999827384949,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9872000217437744,"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/T10885","display_name":"Gene expression and cancer classification","score":0.982699990272522,"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/workflow","display_name":"Workflow","score":0.8982599377632141},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8085764646530151},{"id":"https://openalex.org/keywords/cyberinfrastructure","display_name":"Cyberinfrastructure","score":0.6973865628242493},{"id":"https://openalex.org/keywords/workflow-management-system","display_name":"Workflow management system","score":0.5429527163505554},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5393704175949097},{"id":"https://openalex.org/keywords/e-science","display_name":"e-Science","score":0.5192180275917053},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.5112433433532715},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4665890038013458},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.259318470954895},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.17050451040267944}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8982599377632141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8085764646530151},{"id":"https://openalex.org/C2776397876","wikidata":"https://www.wikidata.org/wiki/Q1450531","display_name":"Cyberinfrastructure","level":2,"score":0.6973865628242493},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.5429527163505554},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5393704175949097},{"id":"https://openalex.org/C517757529","wikidata":"https://www.wikidata.org/wiki/Q1273268","display_name":"e-Science","level":3,"score":0.5192180275917053},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5112433433532715},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4665890038013458},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.259318470954895},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.17050451040267944},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccabs.2013.6629243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccabs.2013.6629243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 3rd International Conference on Computational Advances in Bio and medical Sciences (ICCABS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2375304607","https://openalex.org/W2391168633","https://openalex.org/W2035995658","https://openalex.org/W2353477037","https://openalex.org/W1574425962","https://openalex.org/W2385499106","https://openalex.org/W2354357087","https://openalex.org/W2352774566","https://openalex.org/W4243836028","https://openalex.org/W2287633205"],"abstract_inverted_index":{"Scientific":[0,58,77,98,127,361],"workflows":[1,19,59,78,99,116,128,164,187,206,232,260,362],"have":[2],"been":[3],"used":[4,234],"as":[5,365,389,438],"a":[6,47,149,289,366,439],"programming":[7,75,330,378],"model":[8,174],"to":[9,17,52,82,92,113,188,248,332,335,353,450],"automate":[10],"scientific":[11,31,38,163,186,203,231,459],"tasks":[12],"ranging":[13,85],"from":[14,86,246],"short":[15],"pipelines":[16],"complex":[18,63],"that":[20,120,402],"span":[21],"across":[22,36],"heterogeneous":[23,95,273],"data":[24,225,244,256,288,297,319,406],"and":[25,42,54,73,89,94,117,141,156,170,178,182,195,200,219,227,250,271,284,302,309,329,368,380,411,417,428,446],"computing":[26],"resources.":[27,97],"While":[28,159,198],"utilization":[29],"of":[30,50,62,102,151,215,242,252,286,316,345,349,376,386,422,432,441,456],"workflow":[32,134,137,460],"technologies":[33],"varies":[34],"slightly":[35],"different":[37,240],"disciplines,":[39],"all":[40,161],"informatics":[41],"computational":[43,327,381,420],"science":[44],"disciplines":[45],"provide":[46,60,212],"common":[48],"set":[49],"attributes":[51],"facilitate":[53],"accelerate":[55],"workflow-driven":[56],"research.":[57],"assembly":[61],"processing":[64,112],"easily":[65],"in":[66,124,146,236,305,358],"local":[67,87],"or":[68],"distributed":[69,405],"environments":[70],"via":[71,374],"rich":[72],"expressive":[74],"models.":[76],"enable":[79],"transparent":[80],"access":[81],"diverse":[83],"resources":[84,274,298],"clusters":[88],"traditional":[90],"supercomputers":[91],"elastic":[93],"Cloud":[96],"support":[100],"incorporation":[101],"multiple":[103],"software":[104],"tools":[105,109,119,424],"including":[106,307],"domain":[107],"specific":[108,224],"for":[110,343],"standard":[111],"custom":[114],"generalized":[115],"middleware":[118],"can":[121,261,363,447],"be":[122,262,333,448],"reused":[123],"various":[125],"contexts.":[126],"often":[129,165],"collect":[130],"provenance":[131],"information":[132],"on":[133,176],"entities,":[135],"e.g.,":[136,409,415],"definitions,":[138],"their":[139],"executions":[140],"run":[142],"time":[143],"parameters,":[144],"and,":[145],"turn,":[147],"assure":[148],"level":[150],"reproducibility":[152],"while":[153],"enabling":[154],"referencing":[155],"replicating":[157],"results.":[158],"doing":[160],"these,":[162],"foster":[166],"an":[167,400],"open-source,":[168],"open-access":[169],"standards-driven":[171],"community":[172],"development":[173],"based":[175],"sharing":[177],"collaborations.":[179],"Cyberinfrastructure":[180],"platforms":[181],"gateways":[183],"commonly":[184],"employ":[185],"bridge":[189],"the":[190,193,202,282,314,384,419,433,442,453,457],"gap":[191],"between":[192,210],"infrastructure":[194],"users":[196],"needs.":[197],"capturing":[199],"communicating":[201],"process":[204,372],"formally,":[205],"ensure":[207,220],"flexibility,":[208],"synergy":[209],"users,":[211],"optimized":[213],"usage":[214],"resources,":[216],"increase":[217],"reuse":[218],"compliance":[221],"with":[222,383,425],"system":[223,461],"models":[226,328,379,382],"community-driven":[228],"standards.":[229],"Currently,":[230],"are":[233,299],"widely":[235],"life":[237,354],"sciences":[238,355],"at":[239,275,278],"stages":[241],"end-to-end":[243],"lifecycle":[245],"generation":[247],"analysis":[249,283,315,344],"publication":[251],"biological":[253,296,318,336,387],"data.":[254],"The":[255,430],"handled":[257],"by":[258,264],"such":[259,287,399,426],"produced":[263],"sequencers,":[265],"sensor":[266],"networks,":[267],"medical":[268],"imaging":[269],"instruments":[270],"other":[272],"significant":[276],"rates":[277],"decreasing":[279],"costs":[280],"making":[281,300],"archival":[285],"'big":[290],"data'":[291],"challenge.":[292],"Additionally,":[293],"these":[294,350],"new":[295,301,325,340],"exciting":[303],"research":[304],"areas":[306],"metagenomics":[308],"personalized":[310],"medicine":[311],"possible.":[312],"However,":[313],"big":[317,346],"is":[320,356,436],"still":[321,357],"very":[322],"costly":[323],"requiring":[324],"scalable":[326],"paradigms":[331,341],"applied":[334],"analysis.":[337],"Although,":[338],"some":[339],"exists":[342],"data,":[347],"application":[348],"best":[351],"practices":[352],"its":[359],"infancy.":[360],"act":[364],"scaffold":[367],"help":[369],"speed":[370],"this":[371,393],"up":[373],"combination":[375],"existing":[377],"challenges":[385],"problems":[388],"reusable":[390],"blocks.":[391],"In":[392],"talk,":[394],"I":[395],"will":[396],"talk":[397],"about":[398],"approach":[401,435],"builds":[403],"upon":[404],"parallel":[407],"patterns,":[408],"MapReduce,":[410],"underlying":[412],"execution":[413],"engines,":[414],"Hadoop,":[416],"matches":[418],"requirements":[421],"bioinformatics":[423],"patterns":[427],"engines.":[429],"results":[431],"presented":[434],"developed":[437],"part":[440],"bioKepler":[443],"(bioKepler.org)":[444],"module":[445],"downloaded":[449],"work":[451],"within":[452],"release":[454],"2.4":[455],"Kepler":[458],"(kepler-project.org).":[462]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
