{"id":"https://openalex.org/W2945184484","doi":"https://doi.org/10.1109/rivf.2019.8713709","title":"QMSpy: An Integrated Modular and Scalable Platform for Quantitative Metagenomics in Pyspark","display_name":"QMSpy: An Integrated Modular and Scalable Platform for Quantitative Metagenomics in Pyspark","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2945184484","doi":"https://doi.org/10.1109/rivf.2019.8713709","mag":"2945184484"},"language":"en","primary_location":{"id":"doi:10.1109/rivf.2019.8713709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf.2019.8713709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF)","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/A5027800213","display_name":"Ari Ugarte","orcid":null},"institutions":[{"id":"https://openalex.org/I4210154657","display_name":"Fondation pour l\u2019innovation en Cadiom\u00e9tabolisme et Nutrition","ror":"https://ror.org/050c3pq49","country_code":"FR","type":"other","lineage":["https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210097159","https://openalex.org/I4210154657"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ari Ugarte","raw_affiliation_strings":["ICAN, Integromics, Institute of Cardiometabolism and Nutrition, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICAN, Integromics, Institute of Cardiometabolism and Nutrition, Paris, France","institution_ids":["https://openalex.org/I4210154657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001546026","display_name":"Minh Quang-Dao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153851","display_name":"Unit\u00e9 de Mod\u00e9lisation Math\u00e9matique et Informatique des Syst\u00e8mes Complexes","ror":"https://ror.org/053kxkj53","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1327553481","https://openalex.org/I154202486","https://openalex.org/I2799535048","https://openalex.org/I2802818602","https://openalex.org/I39804081","https://openalex.org/I4210088668","https://openalex.org/I4210090127","https://openalex.org/I4210113730","https://openalex.org/I4210131494","https://openalex.org/I4210153851","https://openalex.org/I4210166444","https://openalex.org/I4405257220"]},{"id":"https://openalex.org/I4210154657","display_name":"Fondation pour l\u2019innovation en Cadiom\u00e9tabolisme et Nutrition","ror":"https://ror.org/050c3pq49","country_code":"FR","type":"other","lineage":["https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210097159","https://openalex.org/I4210154657"]},{"id":"https://openalex.org/I4210166444","display_name":"Institut de Recherche pour le D\u00e9veloppement","ror":"https://ror.org/05q3vnk25","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1327553481","https://openalex.org/I154202486","https://openalex.org/I2799535048","https://openalex.org/I2802818602","https://openalex.org/I4210088668","https://openalex.org/I4210090127","https://openalex.org/I4210113730","https://openalex.org/I4210131494","https://openalex.org/I4210166444","https://openalex.org/I4405257220"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Minh Quang-Dao","raw_affiliation_strings":["ICAN, IRD, UMMISCO, Integromics, Institute of Cardiometabolism and Nutrition, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICAN, IRD, UMMISCO, Integromics, Institute of Cardiometabolism and Nutrition, Paris, France","institution_ids":["https://openalex.org/I4210154657","https://openalex.org/I4210153851","https://openalex.org/I4210166444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017730405","display_name":"Bich Hai Ho","orcid":"https://orcid.org/0000-0002-6344-0180"},"institutions":[{"id":"https://openalex.org/I70349855","display_name":"Vietnam Academy of Science and Technology","ror":"https://ror.org/02wsd5p50","country_code":"VN","type":"government","lineage":["https://openalex.org/I70349855"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Bich Hai Ho","raw_affiliation_strings":["IOIT, IRD, UMMISCO, Vietnam Academy of Science and Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IOIT, IRD, UMMISCO, Vietnam Academy of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I70349855"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031089868","display_name":"Chlo\u00e9 Vigliotti","orcid":"https://orcid.org/0000-0002-3537-9650"},"institutions":[{"id":"https://openalex.org/I4210154657","display_name":"Fondation pour l\u2019innovation en Cadiom\u00e9tabolisme et Nutrition","ror":"https://ror.org/050c3pq49","country_code":"FR","type":"other","lineage":["https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210097159","https://openalex.org/I4210154657"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Chloe Vigliotti","raw_affiliation_strings":["ICAN, Integromics, Institute of Cardiometabolism and Nutrition, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICAN, Integromics, Institute of Cardiometabolism and Nutrition, Paris, France","institution_ids":["https://openalex.org/I4210154657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056937785","display_name":"Eugeni Belda","orcid":"https://orcid.org/0000-0003-4307-5072"},"institutions":[{"id":"https://openalex.org/I4210154657","display_name":"Fondation pour l\u2019innovation en Cadiom\u00e9tabolisme et Nutrition","ror":"https://ror.org/050c3pq49","country_code":"FR","type":"other","lineage":["https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210097159","https://openalex.org/I4210154657"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Eugeni Belda","raw_affiliation_strings":["ICAN, Integromics, Institute of Cardiometabolism and Nutrition, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICAN, Integromics, Institute of Cardiometabolism and Nutrition, Paris, France","institution_ids":["https://openalex.org/I4210154657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088630634","display_name":"Jean\u2010Daniel Zucker","orcid":"https://orcid.org/0000-0002-5597-7922"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210153851","display_name":"Unit\u00e9 de Mod\u00e9lisation Math\u00e9matique et Informatique des Syst\u00e8mes Complexes","ror":"https://ror.org/053kxkj53","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1327553481","https://openalex.org/I154202486","https://openalex.org/I2799535048","https://openalex.org/I2802818602","https://openalex.org/I39804081","https://openalex.org/I4210088668","https://openalex.org/I4210090127","https://openalex.org/I4210113730","https://openalex.org/I4210131494","https://openalex.org/I4210153851","https://openalex.org/I4210166444","https://openalex.org/I4405257220"]},{"id":"https://openalex.org/I4210166444","display_name":"Institut de Recherche pour le D\u00e9veloppement","ror":"https://ror.org/05q3vnk25","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1327553481","https://openalex.org/I154202486","https://openalex.org/I2799535048","https://openalex.org/I2802818602","https://openalex.org/I4210088668","https://openalex.org/I4210090127","https://openalex.org/I4210113730","https://openalex.org/I4210131494","https://openalex.org/I4210166444","https://openalex.org/I4405257220"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Daniel Zucker","raw_affiliation_strings":["IRD, UMMISCO, Sorbonne University, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRD, UMMISCO, Sorbonne University, Paris, France","institution_ids":["https://openalex.org/I4210153851","https://openalex.org/I39804081","https://openalex.org/I4210166444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051022071","display_name":"Edi Prifti","orcid":"https://orcid.org/0000-0001-8861-1305"},"institutions":[{"id":"https://openalex.org/I4210154657","display_name":"Fondation pour l\u2019innovation en Cadiom\u00e9tabolisme et Nutrition","ror":"https://ror.org/050c3pq49","country_code":"FR","type":"other","lineage":["https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210097159","https://openalex.org/I4210154657"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Edi Prifti","raw_affiliation_strings":["ICAN, Integromics, Institute of Cardiometabolism and Nutrition, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICAN, Integromics, Institute of Cardiometabolism and Nutrition, Paris, France","institution_ids":["https://openalex.org/I4210154657"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0855,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46477775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9940999746322632,"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"}},"topics":[{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9940999746322632,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9860000014305115,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9814000129699707,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8722715377807617},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.780570387840271},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.7198996543884277},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.6948994398117065},{"id":"https://openalex.org/keywords/modularity","display_name":"Modularity (biology)","score":0.648650050163269},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6242197155952454},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5647842884063721},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4890616834163666},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4476821720600128},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.22847118973731995},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11357870697975159},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10033807158470154}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8722715377807617},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.780570387840271},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7198996543884277},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.6948994398117065},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.648650050163269},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6242197155952454},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5647842884063721},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4890616834163666},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4476821720600128},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22847118973731995},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11357870697975159},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10033807158470154},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rivf.2019.8713709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf.2019.8713709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/12","display_name":"Responsible consumption and production","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1971403296","https://openalex.org/W1990073900","https://openalex.org/W1992595091","https://openalex.org/W2001561488","https://openalex.org/W2092784580","https://openalex.org/W2097124003","https://openalex.org/W2103901746","https://openalex.org/W2119738171","https://openalex.org/W2125826054","https://openalex.org/W2131975293","https://openalex.org/W2145336165","https://openalex.org/W2398924165","https://openalex.org/W2568237575","https://openalex.org/W2771381340","https://openalex.org/W6679815717"],"related_works":["https://openalex.org/W4726072","https://openalex.org/W7696661","https://openalex.org/W4093994","https://openalex.org/W3097053","https://openalex.org/W6162201","https://openalex.org/W8317513","https://openalex.org/W9937398","https://openalex.org/W12204934","https://openalex.org/W12183970","https://openalex.org/W9305138"],"abstract_inverted_index":{"With":[0],"the":[1,7,21,93,100,112,116,165,179,186],"advent":[2],"of":[3,30,43,151,175],"next-generation":[4],"sequencing":[5],"and":[6,39,50,66,81,148,160,185,199],"ever-growing":[8],"interest":[9],"in":[10,36,72,92],"quantitative":[11],"metagenomics,":[12],"we":[13,55,155],"are":[14,28,70,76,90],"facing":[15],"unprecedented":[16],"computational":[17],"bottlenecks":[18],"to":[19,98,139,163,178,196],"process":[20,99],"massive":[22],"metagenomics":[23,26],"datasets.":[24],"Traditional":[25],"pipelines":[27],"composed":[29],"multiple":[31],"stages,":[32],"often":[33],"coded":[34],"separately":[35],"different":[37],"languages":[38],"standards.":[40],"The":[41],"lack":[42],"integrated":[44,91],"modularity":[45],"makes":[46],"their":[47],"maintenance,":[48],"evolution":[49],"scalability":[51,136,184],"a":[52,58,204],"challenge.":[53],"Consequently,":[54],"designed":[56],"QMSpy,":[57],"novel":[59,142],"all-in-one":[60],"platform":[61,94],"that":[62,144,170,188],"is":[63,109,120,190],"both":[64],"modular":[65,101],"scalable.":[67],"Raw":[68],"reads":[69],"transformed":[71],"distributed":[73],"objects,":[74],"which":[75],"processed,":[77],"mapped":[78],"against":[79],"catalogs":[80],"smart-counted.":[82],"Well-known":[83],"tools":[84],"such":[85,128],"as":[86,129],"Trimmomatic,":[87],"Bowtie2,":[88],"etc.":[89,134],"using":[95],"ad-hoc":[96],"APIs":[97],"objects.":[102],"QMSpy":[103,157],"supports":[104],"creating":[105],"customizable":[106],"workflows.":[107],"It":[108,119],"implemented":[110],"with":[111,158],"PySpark":[113],"framework,":[114],"extending":[115],"MapReduce":[117],"model.":[118],"deployable":[121],"on":[122],"most":[123],"popular":[124],"high-performance":[125],"computing":[126],"cluster":[127],"Google":[130],"Cloud,":[131],"Amazon":[132],"EC2,":[133],"Such":[135],"allows":[137],"us,":[138],"propose":[140],"several":[141],"algorithms":[143],"improves":[145],"gene,":[146],"taxonomic":[147],"functional":[149],"quantifications":[150],"microbial":[152],"ecosystems.":[153],"Finally,":[154],"benchmarked":[156],"real":[159],"simulated":[161],"data":[162],"establish":[164],"best":[166],"hyperparameters.":[167],"We":[168],"believe":[169],"this":[171],"resource":[172],"will":[173,193],"be":[174],"great":[176],"value":[177],"scientific":[180],"community.":[181],"Its":[182],"modularity,":[183],"fact":[187],"it":[189,201],"open":[191],"source":[192],"allow":[194],"users":[195],"easily":[197],"contribute":[198],"grow":[200],"further":[202],"for":[203],"broader":[205],"acceptance.":[206],"Contact:":[207],"e.prifti[at]ican-institute.org.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
