{"id":"https://openalex.org/W2098718123","doi":"https://doi.org/10.1186/1471-2105-12-61","title":"A lightweight, flow-based toolkit for parallel and distributed bioinformatics pipelines","display_name":"A lightweight, flow-based toolkit for parallel and distributed bioinformatics pipelines","publication_year":2011,"publication_date":"2011-02-25","ids":{"openalex":"https://openalex.org/W2098718123","doi":"https://doi.org/10.1186/1471-2105-12-61","mag":"2098718123","pmid":"https://pubmed.ncbi.nlm.nih.gov/21352538"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-12-61","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-61","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-61","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-61","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051824786","display_name":"Marcin Cie\u015blik","orcid":"https://orcid.org/0000-0002-5467-1040"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcin Cie\u015blik","raw_affiliation_strings":["Department of Chemistry, University of Virginia, Charlottesville, VA 22904-4319, USA","Department of Chemistry, University of Virginia, Charlottesville, VA, 22904-4319, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Virginia, Charlottesville, VA 22904-4319, USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Department of Chemistry, University of Virginia, Charlottesville, VA, 22904-4319, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022761529","display_name":"Cameron Mura","orcid":"https://orcid.org/0000-0001-7985-2561"},"institutions":[{"id":"https://openalex.org/I2799765794","display_name":"University of Virginia Health System","ror":"https://ror.org/00wn7d965","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799765794"]},{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cameron Mura","raw_affiliation_strings":["Department of Chemistry, University of Virginia, Charlottesville, VA, 22904-4319, USA","Structural, Computational Biology & Biophysics, University of Virginia Health Sciences, Charlottesville, VA, 22908, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Virginia, Charlottesville, VA, 22904-4319, USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"Structural, Computational Biology & Biophysics, University of Virginia Health Sciences, Charlottesville, VA, 22908, USA","institution_ids":["https://openalex.org/I51556381","https://openalex.org/I2799765794"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5022761529"],"corresponding_institution_ids":["https://openalex.org/I2799765794","https://openalex.org/I51556381"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":3.7618,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93428966,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"12","issue":"1","first_page":"61","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9402999877929688,"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":0.9402999877929688,"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":0.014399999752640724,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.009999999776482582,"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":0.6781681776046753},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.48194265365600586},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3442038297653198},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.16492560505867004},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15831533074378967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6781681776046753},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.48194265365600586},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3442038297653198},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16492560505867004},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15831533074378967},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D003205","descriptor_name":"Computing Methodologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003205","descriptor_name":"Computing Methodologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003205","descriptor_name":"Computing Methodologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-12-61","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-61","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-61","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:21352538","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21352538","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:380ec38d3e79408b822a199499ba8c1b","is_oa":false,"landing_page_url":"https://doaj.org/article/380ec38d3e79408b822a199499ba8c1b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 12, Iss 1, p 61 (2011)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:3051902","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3051902","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-12-61","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-61","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-61","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G5759761504","display_name":null,"funder_award_id":"J-971","funder_id":"https://openalex.org/F4320309424","funder_display_name":"Thomas F. and Kate Miller Jeffress Memorial Trust"}],"funders":[{"id":"https://openalex.org/F4320309424","display_name":"Thomas F. and Kate Miller Jeffress Memorial Trust","ror":"https://ror.org/006tvg625"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2098718123.pdf","grobid_xml":"https://content.openalex.org/works/W2098718123.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W184479012","https://openalex.org/W1557561422","https://openalex.org/W1593488045","https://openalex.org/W1835740130","https://openalex.org/W1979900513","https://openalex.org/W1980731367","https://openalex.org/W1982122105","https://openalex.org/W1983833794","https://openalex.org/W1988431525","https://openalex.org/W1996138408","https://openalex.org/W1996591641","https://openalex.org/W2000729083","https://openalex.org/W2003016263","https://openalex.org/W2027029632","https://openalex.org/W2036499039","https://openalex.org/W2073357440","https://openalex.org/W2099630507","https://openalex.org/W2100445717","https://openalex.org/W2111904946","https://openalex.org/W2115570304","https://openalex.org/W2121762798","https://openalex.org/W2129466958","https://openalex.org/W2129666400","https://openalex.org/W2131736388","https://openalex.org/W2138106181","https://openalex.org/W2141920771","https://openalex.org/W2150424267","https://openalex.org/W2153423033","https://openalex.org/W2154055222","https://openalex.org/W2154513453","https://openalex.org/W2157302781","https://openalex.org/W2158351585","https://openalex.org/W2158528359","https://openalex.org/W2168103533","https://openalex.org/W2169180789","https://openalex.org/W2169912040","https://openalex.org/W2170171286","https://openalex.org/W2173213060","https://openalex.org/W2535798755","https://openalex.org/W2911830835","https://openalex.org/W3098919389","https://openalex.org/W4213369217"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"BACKGROUND:":[0],"Bioinformatic":[1],"analyses":[2],"typically":[3],"proceed":[4],"as":[5,57,218,251],"chains":[6],"of":[7,26,59,80,122,142,165,198,231],"data-processing":[8,202],"tasks.":[9],"A":[10,95],"pipeline,":[11],"or":[12,134],"'workflow',":[13],"is":[14,98,248],"a":[15,19,30,86,107,190,219],"well-defined":[16],"protocol,":[17],"with":[18],"specific":[20,171],"structure":[21],"defined":[22],"by":[23,104,168],"the":[24,35,45,75,150,163,194,239],"topology":[25],"data-flow":[27],"interdependencies,":[28],"and":[29,78,154,179,196,200,229,244,257,261],"particular":[31],"functionality":[32,180,207],"arising":[33],"from":[34,100,208],"data":[36,124],"transformations":[37,121],"applied":[38],"at":[39,255],"each":[40],"step.":[41],"In":[42],"computer":[43],"science,":[44],"dataflow":[46],"programming":[47],"(DFP)":[48],"paradigm":[49],"defines":[50],"software":[51],"systems":[52],"constructed":[53],"in":[54,92,140],"this":[55],"manner,":[56],"networks":[58],"message-passing":[60],"components.":[61],"Thus,":[62],"bioinformatic":[63],"workflows":[64,167],"can":[65,215],"be":[66,216],"naturally":[67],"mapped":[68],"onto":[69],"DFP":[70],"concepts.":[71],"RESULTS:":[72],"To":[73],"enable":[74],"flexible":[76],"creation":[77,164,195],"execution":[79],"bioinformatics":[81,166,225],"dataflows,":[82],"we":[83],"have":[84],"written":[85],"modular":[87,191],"framework":[88,192],"for":[89,174,193,222],"parallel":[90,199],"pipelines":[91,234],"Python":[93,253],"('PaPy').":[94],"PaPy":[96,188,213,233,247],"workflow":[97],"created":[99],"re-usable":[101],"components":[102],"connected":[103],"data-pipes":[105],"into":[106],"directed":[108],"acyclic":[109],"graph,":[110],"which":[111],"together":[112],"define":[113],"nested":[114],"higher-order":[115],"map":[116],"functions.":[117],"The":[118,227],"successive":[119],"functional":[120],"input":[123],"are":[125,138],"evaluated":[126],"on":[127],"flexibly":[128],"pooled":[129],"compute":[130],"resources,":[131],"either":[132],"local":[133],"remote.":[135],"Input":[136],"items":[137],"processed":[139],"batches":[141],"adjustable":[143],"size,":[144],"all":[145],"flowing":[146],"one":[147],"to":[148,182],"tune":[149],"trade-off":[151],"between":[152,241],"parallelism":[153],"lazy-evaluation":[155],"(memory":[156],"consumption).":[157],"An":[158],"add-on":[159],"module":[160],"('NuBio')":[161],"facilitates":[162],"providing":[169],"domain":[170],"data-containers":[172],"(e.g.,":[173,181],"biomolecular":[175],"sequences,":[176],"alignments,":[177],"structures)":[178],"parse/write":[183],"standard":[184],"file":[185],"formats).":[186],"CONCLUSIONS:":[187],"offers":[189],"deployment":[197],"distributed":[201,232,250],"workflows.":[203],"Pipelines":[204],"derive":[205],"their":[206],"user-written,":[209],"data-coupled":[210],"components,":[211],"so":[212],"also":[214],"viewed":[217],"lightweight":[220],"toolkit":[221],"extensible,":[223],"flow-based":[224],"data-processing.":[226],"simplicity":[228],"flexibility":[230],"may":[235],"help":[236],"users":[237],"bridge":[238],"gap":[240],"traditional":[242],"desktop/workstation":[243],"grid":[245],"computing.":[246],"freely":[249],"open-source":[252],"code":[254],"http://muralab.org/PaPy,":[256],"includes":[258],"extensive":[259],"documentation":[260],"annotated":[262],"usage":[263],"examples.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}