{"id":"https://openalex.org/W1162253361","doi":"https://doi.org/10.7717/peerj-cs.20","title":"CFSAN SNP Pipeline: an automated method for constructing SNP matrices from next-generation sequence data","display_name":"CFSAN SNP Pipeline: an automated method for constructing SNP matrices from next-generation sequence data","publication_year":2015,"publication_date":"2015-08-26","ids":{"openalex":"https://openalex.org/W1162253361","doi":"https://doi.org/10.7717/peerj-cs.20","mag":"1162253361"},"language":"en","primary_location":{"id":"doi:10.7717/peerj-cs.20","is_oa":true,"landing_page_url":"https://doi.org/10.7717/peerj-cs.20","pdf_url":null,"source":{"id":"https://openalex.org/S4210178049","display_name":"PeerJ Computer Science","issn_l":"2376-5992","issn":["2376-5992"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320104","host_organization_name":"PeerJ, Inc.","host_organization_lineage":["https://openalex.org/P4310320104"],"host_organization_lineage_names":["PeerJ, Inc."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.7717/peerj-cs.20","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063434341","display_name":"Steve Davis","orcid":"https://orcid.org/0000-0002-5581-1922"},"institutions":[{"id":"https://openalex.org/I1285792802","display_name":"Center for Food Safety and Applied Nutrition","ror":"https://ror.org/05hzdft06","country_code":"US","type":"facility","lineage":["https://openalex.org/I1285792802","https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Steve Davis","raw_affiliation_strings":["Biostatistics and Bioinformatics Staff, Center for Food Safety and Applied Nutrition, Food and Drug Administration, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Biostatistics and Bioinformatics Staff, Center for Food Safety and Applied Nutrition, Food and Drug Administration, College Park, MD, USA","institution_ids":["https://openalex.org/I1285792802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033872060","display_name":"James Pettengill","orcid":"https://orcid.org/0000-0001-7985-7434"},"institutions":[{"id":"https://openalex.org/I1285792802","display_name":"Center for Food Safety and Applied Nutrition","ror":"https://ror.org/05hzdft06","country_code":"US","type":"facility","lineage":["https://openalex.org/I1285792802","https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James B. Pettengill","raw_affiliation_strings":["Biostatistics and Bioinformatics Staff, Center for Food Safety and Applied Nutrition, Food and Drug Administration, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Biostatistics and Bioinformatics Staff, Center for Food Safety and Applied Nutrition, Food and Drug Administration, College Park, MD, USA","institution_ids":["https://openalex.org/I1285792802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057489503","display_name":"Yan Luo","orcid":"https://orcid.org/0000-0001-8156-6572"},"institutions":[{"id":"https://openalex.org/I1285792802","display_name":"Center for Food Safety and Applied Nutrition","ror":"https://ror.org/05hzdft06","country_code":"US","type":"facility","lineage":["https://openalex.org/I1285792802","https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Luo","raw_affiliation_strings":["Biostatistics and Bioinformatics Staff, Center for Food Safety and Applied Nutrition, Food and Drug Administration, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Biostatistics and Bioinformatics Staff, Center for Food Safety and Applied Nutrition, Food and Drug Administration, College Park, MD, USA","institution_ids":["https://openalex.org/I1285792802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003363361","display_name":"Justin L. Payne","orcid":"https://orcid.org/0000-0002-3953-7783"},"institutions":[{"id":"https://openalex.org/I1285792802","display_name":"Center for Food Safety and Applied Nutrition","ror":"https://ror.org/05hzdft06","country_code":"US","type":"facility","lineage":["https://openalex.org/I1285792802","https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Payne","raw_affiliation_strings":["Division of Microbiology, Center for Food Safety and Applied Nutrition, Food and Drug Administration, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Division of Microbiology, Center for Food Safety and Applied Nutrition, Food and Drug Administration, College Park, MD, USA","institution_ids":["https://openalex.org/I1285792802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000994090","display_name":"Al Shpuntoff","orcid":null},"institutions":[{"id":"https://openalex.org/I1285792802","display_name":"Center for Food Safety and Applied Nutrition","ror":"https://ror.org/05hzdft06","country_code":"US","type":"facility","lineage":["https://openalex.org/I1285792802","https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Al Shpuntoff","raw_affiliation_strings":["Center for Food Safety and Applied Nutrition Scientific Engineering, Engility Corporation at FDA, Food and Drug Administration, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Food Safety and Applied Nutrition Scientific Engineering, Engility Corporation at FDA, Food and Drug Administration, College Park, MD, USA","institution_ids":["https://openalex.org/I1285792802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037593913","display_name":"Hugh Rand","orcid":null},"institutions":[{"id":"https://openalex.org/I1285792802","display_name":"Center for Food Safety and Applied Nutrition","ror":"https://ror.org/05hzdft06","country_code":"US","type":"facility","lineage":["https://openalex.org/I1285792802","https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hugh Rand","raw_affiliation_strings":["Biostatistics and Bioinformatics Staff, Center for Food Safety and Applied Nutrition, Food and Drug Administration, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Biostatistics and Bioinformatics Staff, Center for Food Safety and Applied Nutrition, Food and Drug Administration, College Park, MD, USA","institution_ids":["https://openalex.org/I1285792802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047193176","display_name":"Errol Strain","orcid":"https://orcid.org/0000-0003-2346-3668"},"institutions":[{"id":"https://openalex.org/I1285792802","display_name":"Center for Food Safety and Applied Nutrition","ror":"https://ror.org/05hzdft06","country_code":"US","type":"facility","lineage":["https://openalex.org/I1285792802","https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Errol Strain","raw_affiliation_strings":["Biostatistics and Bioinformatics Staff, Center for Food Safety and Applied Nutrition, Food and Drug Administration, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Biostatistics and Bioinformatics Staff, Center for Food Safety and Applied Nutrition, Food and Drug Administration, College Park, MD, USA","institution_ids":["https://openalex.org/I1285792802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5063434341"],"corresponding_institution_ids":["https://openalex.org/I1285792802"],"apc_list":{"value":1395,"currency":"USD","value_usd":1395},"apc_paid":{"value":1395,"currency":"USD","value_usd":1395},"fwci":9.0437,"has_fulltext":false,"cited_by_count":322,"citation_normalized_percentile":{"value":0.98481748,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"1","issue":null,"first_page":"e20","last_page":"e20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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":0.9997000098228455,"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/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9789000153541565,"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/snp","display_name":"SNP","score":0.6065191626548767},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.581824541091919},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5424060225486755},{"id":"https://openalex.org/keywords/single-nucleotide-polymorphism","display_name":"Single-nucleotide polymorphism","score":0.5253433585166931},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5138135552406311},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4382402002811432},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42825794219970703},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.415108859539032},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3837680518627167},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3589108884334564},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.11505359411239624},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09560459852218628}],"concepts":[{"id":"https://openalex.org/C139275648","wikidata":"https://www.wikidata.org/wiki/Q17134011","display_name":"SNP","level":5,"score":0.6065191626548767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.581824541091919},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5424060225486755},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.5253433585166931},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5138135552406311},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4382402002811432},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42825794219970703},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.415108859539032},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3837680518627167},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3589108884334564},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11505359411239624},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09560459852218628},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.7717/peerj-cs.20","is_oa":true,"landing_page_url":"https://doi.org/10.7717/peerj-cs.20","pdf_url":null,"source":{"id":"https://openalex.org/S4210178049","display_name":"PeerJ Computer Science","issn_l":"2376-5992","issn":["2376-5992"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320104","host_organization_name":"PeerJ, Inc.","host_organization_lineage":["https://openalex.org/P4310320104"],"host_organization_lineage_names":["PeerJ, Inc."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5aefdd67fe624e51ba3f55fbd96c181e","is_oa":true,"landing_page_url":"https://doaj.org/article/5aefdd67fe624e51ba3f55fbd96c181e","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PeerJ Computer Science, Vol 1, p e20 (2015)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.7717/peerj-cs.20","is_oa":true,"landing_page_url":"https://doi.org/10.7717/peerj-cs.20","pdf_url":null,"source":{"id":"https://openalex.org/S4210178049","display_name":"PeerJ Computer Science","issn_l":"2376-5992","issn":["2376-5992"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320104","host_organization_name":"PeerJ, Inc.","host_organization_lineage":["https://openalex.org/P4310320104"],"host_organization_lineage_names":["PeerJ, Inc."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1966966274","https://openalex.org/W1974599898","https://openalex.org/W1983426138","https://openalex.org/W2048377291","https://openalex.org/W2063678249","https://openalex.org/W2094740601","https://openalex.org/W2108234281","https://openalex.org/W2124676809","https://openalex.org/W2143007385","https://openalex.org/W2155943701","https://openalex.org/W2157539385","https://openalex.org/W2170551349","https://openalex.org/W2951899931","https://openalex.org/W2978270876","https://openalex.org/W6768400487"],"related_works":["https://openalex.org/W2164855536","https://openalex.org/W1997352593","https://openalex.org/W2143489661","https://openalex.org/W2070581548","https://openalex.org/W4281711902","https://openalex.org/W3206555169","https://openalex.org/W3016573916","https://openalex.org/W3157359833","https://openalex.org/W3024317680","https://openalex.org/W1511048503"],"abstract_inverted_index":{"The":[0,49],"analysis":[1],"of":[2,17,47,53,82,92,100,107,133,179,189,198],"next-generation":[3],"sequence":[4,33],"(NGS)":[5],"data":[6],"is":[7,218,226,251],"often":[8,61],"a":[9,31,41,45,63,77,86,108,118,127,185,219,233,242,249],"fragmented":[10],"step-wise":[11],"process.":[12],"For":[13,169],"example,":[14],"multiple":[15],"pieces":[16,56],"software":[18,55],"are":[19],"typically":[20],"needed":[21],"to":[22,85,230,240,253],"map":[23],"NGS":[24,83,246],"reads,":[25],"extract":[26],"variant":[27,101],"sites,":[28],"and":[29,51,57,65,105,155,165,183,202,221],"construct":[30],"DNA":[32],"matrix":[34,110,244],"containing":[35,159],"only":[36],"single":[37,78,234],"nucleotide":[38],"polymorphisms":[39],"(i.e.,":[40],"SNP":[42,72,109,122,175,216,243],"matrix)":[43],"for":[44,193,268],"set":[46],"individuals.":[48],"management":[50],"chaining":[52],"these":[54,213],"their":[58],"outputs":[59],"can":[60],"be":[62],"cumbersome":[64],"difficult":[66],"task.":[67],"Here,":[68],"we":[69,138],"present":[70],"CFSAN":[71,174,215],"Pipeline,":[73],"which":[74,137],"combines":[75],"into":[76,232],"package":[79,120],"the":[80,170,173,180,194,203,228,236],"mapping":[81,94],"reads":[84],"reference":[87,128],"genome":[88,129],"with":[89],"Bowtie2,":[90],"processing":[91],"those":[93,254,269],"(BAM)":[95],"files":[96],"using":[97,103,111],"SAMtools,":[98],"identification":[99],"sites":[102],"VarScan,":[104],"production":[106],"custom":[112],"Python":[113,119],"scripts.":[114],"We":[115,142],"also":[116],"introduce":[117],"(CFSAN":[121],"Mutator)":[123],"that":[124,224],"when":[125],"given":[126],"will":[130],"generate":[131],"variants":[132],"known":[134],"position":[135],"against":[136],"validate":[139],"our":[140],"pipeline.":[141],"created":[143],"1,000":[144],"simulated":[145],"Salmonella":[146],"enterica":[147,149],"sp.":[148],"Serovar":[150],"Agona":[151],"genomes":[152],"at":[153],"100\u00d7":[154,171],"20\u00d7":[156,195],"coverage,":[157],"each":[158],"500":[160],"SNPs,":[161],"20":[162,166],"single-base":[163,167],"insertions":[164],"deletions.":[168],"dataset,":[172],"Pipeline":[176,217],"recovered":[177,201],"98.9%":[178],"introduced":[181],"SNPs":[182,199],"had":[184],"false":[186,204],"positive":[187,205],"rate":[188,206],"1.04":[190],"\u00d7":[191,209],"10\u22126;":[192],"dataset":[196],"98.8%":[197],"were":[200],"was":[207],"8.34":[208],"10\u22127.":[210],"Based":[211],"on":[212],"results,":[214],"robust":[220],"accurate":[222],"tool":[223,250],"it":[225],"among":[227],"first":[229],"combine":[231],"executable":[235],"myriad":[237],"steps":[238],"required":[239],"produce":[241],"from":[245],"data.":[247],"Such":[248],"useful":[252],"working":[255],"in":[256,271],"an":[257],"applied":[258],"setting":[259],"(e.g.,":[260],"food":[261],"safety":[262],"traceback":[263],"investigations)":[264],"as":[265,267],"well":[266],"interested":[270],"evolutionary":[272],"questions.":[273]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":40},{"year":2024,"cited_by_count":42},{"year":2023,"cited_by_count":42},{"year":2022,"cited_by_count":28},{"year":2021,"cited_by_count":40},{"year":2020,"cited_by_count":39},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":25},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
