{"id":"https://openalex.org/W2125024348","doi":"https://doi.org/10.1186/1751-0473-6-13","title":"Nephele: genotyping via complete composition vectors and MapReduce","display_name":"Nephele: genotyping via complete composition vectors and MapReduce","publication_year":2011,"publication_date":"2011-08-18","ids":{"openalex":"https://openalex.org/W2125024348","doi":"https://doi.org/10.1186/1751-0473-6-13","mag":"2125024348","pmid":"https://pubmed.ncbi.nlm.nih.gov/21851626"},"language":"en","primary_location":{"id":"doi:10.1186/1751-0473-6-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1751-0473-6-13","pdf_url":"https://scfbm.biomedcentral.com/counter/pdf/10.1186/1751-0473-6-13","source":{"id":"https://openalex.org/S45786803","display_name":"Source Code for Biology and Medicine","issn_l":"1751-0473","issn":["1751-0473"],"is_oa":false,"is_in_doaj":false,"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":"Source Code for Biology and Medicine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://scfbm.biomedcentral.com/counter/pdf/10.1186/1751-0473-6-13","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082822281","display_name":"Marc Colosimo","orcid":null},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Marc E Colosimo","raw_affiliation_strings":["The MITRE Corporation, 202 Burlington Rd, Bedford MA 01730, USA. mcolosimo@mitre.org","The MITRE Corporation Bedford, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, 202 Burlington Rd, Bedford MA 01730, USA. mcolosimo@mitre.org","institution_ids":[]},{"raw_affiliation_string":"The MITRE Corporation Bedford, USA","institution_ids":["https://openalex.org/I44896327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086629705","display_name":"Matthew Peterson","orcid":"https://orcid.org/0000-0003-4422-4463"},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew W Peterson","raw_affiliation_strings":["The MITRE Corporation, 202 Burlington Rd, Bedford, MA, 01730, USA","The MITRE Corporation Bedford, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, 202 Burlington Rd, Bedford, MA, 01730, USA","institution_ids":["https://openalex.org/I44896327"]},{"raw_affiliation_string":"The MITRE Corporation Bedford, USA","institution_ids":["https://openalex.org/I44896327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019473957","display_name":"Scott Mardis","orcid":null},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Mardis","raw_affiliation_strings":["The MITRE Corporation, 202 Burlington Rd, Bedford, MA, 01730, USA","The MITRE Corporation Bedford, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, 202 Burlington Rd, Bedford, MA, 01730, USA","institution_ids":["https://openalex.org/I44896327"]},{"raw_affiliation_string":"The MITRE Corporation Bedford, USA","institution_ids":["https://openalex.org/I44896327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068115280","display_name":"Lynette Hirschman","orcid":"https://orcid.org/0000-0001-8442-0720"},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lynette Hirschman","raw_affiliation_strings":["The MITRE Corporation, 202 Burlington Rd, Bedford, MA, 01730, USA","The MITRE Corporation Bedford, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, 202 Burlington Rd, Bedford, MA, 01730, USA","institution_ids":["https://openalex.org/I44896327"]},{"raw_affiliation_string":"The MITRE Corporation Bedford, USA","institution_ids":["https://openalex.org/I44896327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082822281"],"corresponding_institution_ids":["https://openalex.org/I44896327"],"apc_list":null,"apc_paid":null,"fwci":0.6651,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.6937947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"6","issue":"1","first_page":"13","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8747000098228455,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8747000098228455,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.011300000362098217,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10751","display_name":"Forensic and Genetic Research","score":0.007199999876320362,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.7396566271781921},{"id":"https://openalex.org/keywords/genotyping","display_name":"Genotyping","score":0.6533576250076294},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.5514626502990723},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.504020631313324},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3476791977882385},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3457064628601074},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.12462541460990906},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10037383437156677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7396566271781921},{"id":"https://openalex.org/C31467283","wikidata":"https://www.wikidata.org/wiki/Q912147","display_name":"Genotyping","level":4,"score":0.6533576250076294},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.5514626502990723},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.504020631313324},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3476791977882385},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3457064628601074},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.12462541460990906},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10037383437156677},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/1751-0473-6-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1751-0473-6-13","pdf_url":"https://scfbm.biomedcentral.com/counter/pdf/10.1186/1751-0473-6-13","source":{"id":"https://openalex.org/S45786803","display_name":"Source Code for Biology and Medicine","issn_l":"1751-0473","issn":["1751-0473"],"is_oa":false,"is_in_doaj":false,"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":"Source Code for Biology and Medicine","raw_type":"journal-article"},{"id":"pmid:21851626","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21851626","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":"Source code for biology and medicine","raw_type":null},{"id":"pmh:oai:doaj.org/article:1af4c58be58a4fe3887da6b93f0e4352","is_oa":true,"landing_page_url":"https://doaj.org/article/1af4c58be58a4fe3887da6b93f0e4352","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Source Code for Biology and Medicine, Vol 6, Iss 1, p 13 (2011)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:3182884","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3182884","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":"Source Code Biol Med","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1751-0473-6-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1751-0473-6-13","pdf_url":"https://scfbm.biomedcentral.com/counter/pdf/10.1186/1751-0473-6-13","source":{"id":"https://openalex.org/S45786803","display_name":"Source Code for Biology and Medicine","issn_l":"1751-0473","issn":["1751-0473"],"is_oa":false,"is_in_doaj":false,"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":"Source Code for Biology and Medicine","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2125024348.pdf","grobid_xml":"https://content.openalex.org/works/W2125024348.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W143898729","https://openalex.org/W1506435375","https://openalex.org/W1509766895","https://openalex.org/W1519266993","https://openalex.org/W1576737979","https://openalex.org/W1741410789","https://openalex.org/W1825216778","https://openalex.org/W1960151799","https://openalex.org/W1963867650","https://openalex.org/W1965435557","https://openalex.org/W1990738356","https://openalex.org/W2010808181","https://openalex.org/W2021440326","https://openalex.org/W2030154486","https://openalex.org/W2033339460","https://openalex.org/W2034171026","https://openalex.org/W2035679446","https://openalex.org/W2056584399","https://openalex.org/W2058445956","https://openalex.org/W2080805434","https://openalex.org/W2097706568","https://openalex.org/W2099510258","https://openalex.org/W2104644701","https://openalex.org/W2106882534","https://openalex.org/W2107007770","https://openalex.org/W2108308364","https://openalex.org/W2109158136","https://openalex.org/W2110670805","https://openalex.org/W2111554887","https://openalex.org/W2113708808","https://openalex.org/W2117463702","https://openalex.org/W2119180969","https://openalex.org/W2121762798","https://openalex.org/W2136198635","https://openalex.org/W2136445954","https://openalex.org/W2138369959","https://openalex.org/W2140872496","https://openalex.org/W2141497252","https://openalex.org/W2144362290","https://openalex.org/W2147053096","https://openalex.org/W2160445700","https://openalex.org/W2162275552","https://openalex.org/W2165232124","https://openalex.org/W2167272772","https://openalex.org/W2169702034","https://openalex.org/W2173213060","https://openalex.org/W2207462415","https://openalex.org/W3150974748","https://openalex.org/W4248125749","https://openalex.org/W4256077941"],"related_works":["https://openalex.org/W2378369506","https://openalex.org/W2353370357","https://openalex.org/W2806032235","https://openalex.org/W2755824586","https://openalex.org/W4280553679","https://openalex.org/W4212927541","https://openalex.org/W2975902501","https://openalex.org/W4248994802","https://openalex.org/W2160549327","https://openalex.org/W3021066823"],"abstract_inverted_index":{"BACKGROUND:":[0],"Current":[1],"sequencing":[2,188],"technology":[3],"makes":[4],"it":[5],"practical":[6],"to":[7,47,68,81,116,216,243,293,303,337],"sequence":[8,93,159,181,219,237,344],"many":[9],"samples":[10,86,312],"of":[11,23,41,51,62,71,85,111,126,168,200,207,272,276,291,308,335,339],"a":[12,83,119,157,205,224,251,270,305],"given":[13],"organism,":[14,53],"raising":[15],"new":[16],"challenges":[17],"for":[18,37,59,135,142,178,235,331],"the":[19,39,49,60,63,69,76,79,122,198,211,221,233,245,255,273,287,327],"processing":[20,328],"and":[21,44,107,124,239],"interpretation":[22],"large":[24],"genomics":[25],"data":[26],"sets":[27],"with":[28,78,100,156,197,264],"associated":[29,99],"metadata.":[30],"Traditional":[31],"computational":[32,194,274],"phylogenetic":[33,153,169,278],"methods":[34,74,175,258,279],"are":[35,55,162,176],"ideal":[36,58],"studying":[38],"evolution":[40,50],"gene/protein":[42],"families":[43],"using":[45,296,322],"those":[46],"infer":[48],"an":[52],"but":[54],"less":[56,314],"than":[57,315],"study":[61],"whole":[64],"organism":[65],"mainly":[66],"due":[67],"presence":[70],"insertions/deletions/rearrangements.":[72],"These":[73],"provide":[75],"researcher":[77],"ability":[80],"group":[82,244],"set":[84],"into":[87,133,247],"distinct":[88],"genotypic":[89],"groups":[90],"based":[91,151,249],"on":[92,152,250,281],"similarity,":[94],"which":[95],"can":[96,285,324],"then":[97,163],"be":[98],"metadata,":[101],"such":[102],"as":[103,139,141,223],"host":[104],"information,":[105],"pathogenicity,":[106],"time":[108,329],"or":[109,267],"location":[110],"occurrence.":[112],"Genotyping":[113],"is":[114,131,204],"critical":[115],"understanding,":[117],"at":[118,269,341],"genomic":[120],"level,":[121],"origin":[123],"spread":[125],"infectious":[127],"diseases.":[128],"Increasingly,":[129],"genotyping":[130,147],"coming":[132],"use":[134,286],"disease":[136],"surveillance":[137],"activities,":[138],"well":[140,263],"microbial":[143],"forensics.":[144],"The":[145],"classic":[146],"approach":[148],"has":[149],"been":[150],"analysis,":[154],"starting":[155],"multiple":[158,236,297],"alignment.":[160],"Genotypes":[161],"established":[164],"by":[165,185,231],"expert":[166],"examination":[167],"trees.":[170],"However,":[171],"these":[172],"traditional":[173,277,282],"single-processor":[174],"suboptimal":[177],"rapidly":[179],"growing":[180],"datasets":[182],"being":[183],"generated":[184],"next-generation":[186],"DNA":[187],"machines,":[189],"because":[190],"they":[191],"increase":[192],"in":[193,220,313],"complexity":[195],"quickly":[196],"number":[199],"sequences.":[201],"RESULTS:":[202],"Nephele":[203,284,323],"suite":[206],"tools":[208],"that":[209,261,321],"uses":[210],"complete":[212],"composition":[213],"vector":[214,225],"algorithm":[215],"represent":[217],"each":[218],"dataset":[222],"derived":[226],"from":[227],"its":[228],"constituent":[229],"k-mers":[230],"passing":[232],"need":[234],"alignment,":[238],"affinity":[240],"propagation":[241],"clustering":[242],"sequences":[246],"genotypes":[248],"distance":[252],"measure":[253],"over":[254,309],"vectors.":[256],"Our":[257],"produce":[259],"results":[260],"correlate":[262],"expert-defined":[265],"clades":[266],"genotypes,":[268],"fraction":[271],"cost":[275],"run":[280],"hardware.":[283],"open-source":[288],"Hadoop":[289],"implementation":[290],"MapReduce":[292],"parallelize":[294],"execution":[295],"compute":[298],"nodes.":[299],"We":[300,319],"were":[301],"able":[302],"generate":[304],"neighbour-joined":[306],"tree":[307],"10,000":[310],"16S":[311],"2":[316],"hours.":[317],"CONCLUSIONS:":[318],"conclude":[320],"substantially":[325],"decrease":[326],"required":[330],"generating":[332],"genotype":[333],"trees":[334],"tens":[336],"hundreds":[338],"organisms":[340],"genome":[342],"scale":[343],"coverage.":[345]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}