{"id":"https://openalex.org/W2771177173","doi":"https://doi.org/10.1147/jrd.2017.2736278","title":"Dataflow representation of data analyses: Toward a platform for collaborative data science","display_name":"Dataflow representation of data analyses: Toward a platform for collaborative data science","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2771177173","doi":"https://doi.org/10.1147/jrd.2017.2736278","mag":"2771177173"},"language":"en","primary_location":{"id":"doi:10.1147/jrd.2017.2736278","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2017.2736278","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-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/A5006534234","display_name":"Evan Patterson","orcid":"https://orcid.org/0000-0002-8600-949X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E. Patterson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050976625","display_name":"Robert McBurney","orcid":"https://orcid.org/0000-0003-1747-1004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R. McBurney","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050734106","display_name":"Hannes Schmidt","orcid":"https://orcid.org/0000-0003-4288-4257"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H. Schmidt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073341059","display_name":"Ioana Baldini","orcid":"https://orcid.org/0000-0002-8257-9866"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"I. Baldini","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072597892","display_name":"Aleksandra Mojsilovi\u0107","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Mojsilovic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015286159","display_name":"Kush R. Varshney","orcid":"https://orcid.org/0000-0002-7376-5536"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K. R. Varshney","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3301,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.94101977,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"61","issue":"6","first_page":"9:1","last_page":"9:13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9948999881744385,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/dataflow","display_name":"Dataflow","score":0.7898189425468445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7356767058372498},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.7102749347686768},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6871110796928406},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.517985463142395},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48243746161460876},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.4768734574317932},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.46511295437812805},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.45358753204345703},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.4347406327724457},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.41245827078819275},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.41231244802474976},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23621481657028198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19264450669288635},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.14810359477996826}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.7898189425468445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7356767058372498},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.7102749347686768},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6871110796928406},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.517985463142395},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48243746161460876},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.4768734574317932},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.46511295437812805},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.45358753204345703},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.4347406327724457},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.41245827078819275},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.41231244802474976},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23621481657028198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19264450669288635},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.14810359477996826},{"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/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1147/jrd.2017.2736278","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2017.2736278","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4099999964237213,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307762","display_name":"International Business Machines Corporation","ror":"https://ror.org/05hh8d621"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W195157153","https://openalex.org/W204615560","https://openalex.org/W1491178396","https://openalex.org/W1507612039","https://openalex.org/W1541203236","https://openalex.org/W1545590260","https://openalex.org/W1662456638","https://openalex.org/W1792506368","https://openalex.org/W1857886188","https://openalex.org/W1907286193","https://openalex.org/W1965287291","https://openalex.org/W1987993132","https://openalex.org/W1994326726","https://openalex.org/W1996138408","https://openalex.org/W2001914359","https://openalex.org/W2017971446","https://openalex.org/W2061939373","https://openalex.org/W2101234009","https://openalex.org/W2103017472","https://openalex.org/W2108980486","https://openalex.org/W2109384743","https://openalex.org/W2111273501","https://openalex.org/W2131660156","https://openalex.org/W2132862423","https://openalex.org/W2136482257","https://openalex.org/W2145154883","https://openalex.org/W2157121418","https://openalex.org/W2168103533","https://openalex.org/W2316180315","https://openalex.org/W2400570668","https://openalex.org/W2468426028","https://openalex.org/W2560096094","https://openalex.org/W2911738047","https://openalex.org/W4212943651","https://openalex.org/W4230059447","https://openalex.org/W4252427272","https://openalex.org/W6600159693","https://openalex.org/W6607795440","https://openalex.org/W6630299558","https://openalex.org/W6632463041","https://openalex.org/W6639364128","https://openalex.org/W6675354045","https://openalex.org/W6676713131","https://openalex.org/W6719632182","https://openalex.org/W6758327135"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W2171015181","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W1533576465","https://openalex.org/W2094554679"],"abstract_inverted_index":{"Data":[0],"science":[1,57,188],"plays":[2],"an":[3,29,129],"increasingly":[4],"important":[5],"role":[6],"in":[7,48,157],"solving":[8],"today's":[9],"scientific":[10],"and":[11,34,83,86,94,138,153,165,176],"social":[12],"challenges.":[13],"To":[14],"promote":[15],"progress":[16],"toward":[17],"a":[18,63,67,75,114,119,185],"cure":[19],"for":[20,66,70,91,184],"multiple":[21,40],"sclerosis,":[22],"the":[23,52,59,150],"Accelerated":[24],"Cure":[25],"Project":[26],"has":[27],"created":[28,47],"open":[30],"repository":[31],"of":[32,56],"biological":[33],"survey":[35],"data":[36,72,84,96,120,126,151,187],"on":[37],"patients":[38],"with":[39],"sclerosis.":[41],"Similar":[42],"large-scale":[43],"repositories":[44],"are":[45,136],"being":[46],"other":[49],"domains.":[50],"As":[51],"open,":[53],"data-driven":[54],"model":[55],"proliferates,":[58],"research":[60],"community":[61],"faces":[62],"growing":[64],"need":[65],"cloud":[68],"platform":[69,76],"collaborative":[71,186],"science.":[73],"Such":[74],"should":[77],"facilitate":[78],"collaboration":[79],"between":[80],"domain":[81],"experts":[82],"scientists":[85],"possess":[87],"artificial":[88],"intelligence":[89],"capabilities":[90],"organizing,":[92],"recommending,":[93],"manipulating":[95],"analyses.":[97],"In":[98,167],"this":[99,108,168],"paper,":[100,169],"we":[101,170],"present":[102],"some":[103],"foundational":[104],"technologies":[105],"motivated":[106],"by":[107],"vision.":[109],"Our":[110],"system":[111,144,174],"automatically":[112],"extracts":[113],"high-level":[115],"dataflow":[116],"graph":[117,123],"from":[118,149],"analysis.":[121],"This":[122],"describes":[124],"how":[125,139,172,177],"flows":[127],"through":[128],"analysis":[130],"pipeline,":[131],"including":[132],"which":[133],"statistical":[134],"methods":[135],"used":[137],"they":[140],"fit":[141],"together.":[142],"The":[143],"requires":[145],"no":[146],"special":[147],"annotations":[148],"analyst":[152],"consumes":[154],"analyses":[155],"written":[156],"Python":[158],"using":[159],"standard":[160],"tools,":[161],"such":[162],"as":[163],"Scikit-learn":[164],"Statsmodels.":[166],"explain":[171],"our":[173,181],"works":[175],"it":[178],"fits":[179],"into":[180],"larger":[182],"vision":[183],"platform.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}