{"id":"https://openalex.org/W3044841724","doi":"https://doi.org/10.1145/3311790.3396664","title":"MetaFlow|mics: Scalable and Reproducible Nextflow Pipelines for the Analysis of Microbiome Marker Data","display_name":"MetaFlow|mics: Scalable and Reproducible Nextflow Pipelines for the Analysis of Microbiome Marker Data","publication_year":2020,"publication_date":"2020-07-22","ids":{"openalex":"https://openalex.org/W3044841724","doi":"https://doi.org/10.1145/3311790.3396664","mag":"3044841724"},"language":"en","primary_location":{"id":"doi:10.1145/3311790.3396664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3311790.3396664","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3311790.3396664","source":{"id":"https://openalex.org/S4306523034","display_name":"Practice and Experience in Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3311790.3396664","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083440317","display_name":"C\u00e9dric Arisdakessian","orcid":"https://orcid.org/0000-0001-5255-0942"},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C\u00e9dric Arisdakessian","raw_affiliation_strings":["University of Hawaii at Manoa, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hawaii at Manoa, USA","institution_ids":["https://openalex.org/I117965899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080587331","display_name":"Sean B. Cleveland","orcid":"https://orcid.org/0000-0002-7130-3434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sean B. Cleveland","raw_affiliation_strings":["University oh Hawaii System, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University oh Hawaii System, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035080938","display_name":"Mahdi Belcaid","orcid":"https://orcid.org/0009-0004-5185-0643"},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahdi Belcaid","raw_affiliation_strings":["University of Hawaii at Manoa, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hawaii at Manoa, USA","institution_ids":["https://openalex.org/I117965899"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.7365,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.9713975,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9958000183105469,"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/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.79875648021698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7891192436218262},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7680672407150269},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7321768999099731},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6956353187561035},{"id":"https://openalex.org/keywords/cyberinfrastructure","display_name":"Cyberinfrastructure","score":0.686698853969574},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.6508063077926636},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5319975018501282},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5022599697113037},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5018386840820312},{"id":"https://openalex.org/keywords/microservices","display_name":"Microservices","score":0.43210506439208984},{"id":"https://openalex.org/keywords/workflow-management-system","display_name":"Workflow management system","score":0.4304143190383911},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4252523183822632},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3406674563884735},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32382911443710327},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2794012725353241},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.21759459376335144},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12086862325668335}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.79875648021698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891192436218262},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7680672407150269},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7321768999099731},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6956353187561035},{"id":"https://openalex.org/C2776397876","wikidata":"https://www.wikidata.org/wiki/Q1450531","display_name":"Cyberinfrastructure","level":2,"score":0.686698853969574},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.6508063077926636},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5319975018501282},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5022599697113037},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5018386840820312},{"id":"https://openalex.org/C2778505942","wikidata":"https://www.wikidata.org/wiki/Q18344624","display_name":"Microservices","level":3,"score":0.43210506439208984},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.4304143190383911},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4252523183822632},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3406674563884735},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32382911443710327},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2794012725353241},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.21759459376335144},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12086862325668335},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3311790.3396664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3311790.3396664","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3311790.3396664","source":{"id":"https://openalex.org/S4306523034","display_name":"Practice and Experience in Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3311790.3396664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3311790.3396664","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3311790.3396664","source":{"id":"https://openalex.org/S4306523034","display_name":"Practice and Experience in Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G3600450027","display_name":"Collaborative Research: SS2-SSI: The Agave Platform: An Open Science-As-A-Service Cloud Platform for Reproducible Science","funder_award_id":"1450413","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6831401517","display_name":"Investigation of viruses and microbes circulating deep in the seafloor","funder_award_id":"1636402","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6931099938","display_name":null,"funder_award_id":"1557349","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7051972930","display_name":null,"funder_award_id":"1931575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7548537526","display_name":null,"funder_award_id":"1931439,1931575,1557349,145041","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7849269413","display_name":null,"funder_award_id":"1931439","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"},{"id":"https://openalex.org/F4320337378","display_name":"Office of Integrative Activities","ror":"https://ror.org/04k9mqs78"},{"id":"https://openalex.org/F4320337386","display_name":"Division of Ocean Sciences","ror":"https://ror.org/05wqqhv83"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3044841724.pdf","grobid_xml":"https://content.openalex.org/works/W3044841724.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1822648038","https://openalex.org/W1985222265","https://openalex.org/W2108718991","https://openalex.org/W2120644786","https://openalex.org/W2146176543","https://openalex.org/W2401404581","https://openalex.org/W2513506562","https://openalex.org/W2591172920","https://openalex.org/W2822964098","https://openalex.org/W2897204056"],"related_works":["https://openalex.org/W3181741639","https://openalex.org/W273500195","https://openalex.org/W4210334847","https://openalex.org/W4367181468","https://openalex.org/W2043019925","https://openalex.org/W4236056781","https://openalex.org/W4293768956","https://openalex.org/W2773781927","https://openalex.org/W2184477657","https://openalex.org/W90628286"],"abstract_inverted_index":{"Computational":[0],"scalability":[1,92],"has":[2,39],"become":[3],"an":[4,118,147],"important":[5],"requirement":[6],"for":[7,72],"processing":[8],"the":[9,41,47,73,122,140,159,169],"massive":[10],"amounts":[11],"of":[12,21,75,131,139],"data":[13,78],"generated":[14],"in":[15,46],"contemporary":[16],"sequencing-based":[17],"experiments.":[18],"The":[19],"availability":[20],"large":[22,115],"computational":[23],"resources":[24],"through":[25,35],"academic,":[26],"regional":[27],"or":[28,120],"national":[29],"cyber-infrastructure":[30],"efforts,":[31],"as":[32,34],"well":[33],"inexpensive":[36],"cloud":[37],"offerings,":[38],"shifted":[40],"bottleneck,":[42],"which":[43],"now":[44],"lies":[45],"extensive":[48],"expertise":[49],"necessary":[50],"to":[51,61,86,97,110,127,164],"create":[52],"reproducible":[53],"and":[54,58,82,93,99,109,145,154,161,167],"scalable":[55],"bioinformatics":[56],"pipelines":[57,102],"deploy":[59,166],"them":[60,113],"such":[62],"diverse":[63],"infrastructures.":[64],"We":[65],"present":[66],"here":[67],"MetaFlow|mics,":[68],"a":[69,104,125,128],"comprehensive":[70],"pipeline":[71],"analysis":[74],"microbiome":[76],"marker":[77],"using":[79],"best":[80],"practices":[81],"state-of-the-art":[83],"cyberinfrastructure":[84],"standards":[85],"ensure":[87],"reproducibility.":[88],"MetaFlow|mics":[89],"provides":[90,146],"seamless":[91],"extensibility,":[94],"allowing":[95],"users":[96],"build":[98],"test":[100],"their":[101],"on":[103,114,117,121,137],"laptop":[105],"with":[106,124,157],"small":[107],"datasets":[108,116],"subsequently":[111],"run":[112],"HPC":[119],"Cloud":[123],"change":[126],"single":[129],"line":[130],"code.":[132],"Our":[133],"framework":[134],"is":[135],"built":[136],"top":[138],"Nextflow":[141],"workflow":[142],"management":[143],"system":[144],"interoperable":[148],"architecture":[149],"that":[150],"leverages":[151],"self-contained":[152],"Docker":[153],"Singularity":[155],"instances":[156],"all":[158],"dependencies":[160],"requirements":[162],"needed":[163],"quickly":[165],"use":[168],"pipeline.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
