{"id":"https://openalex.org/W3000238463","doi":"https://doi.org/10.1111/1755-0998.13135","title":"The impact of contaminants on the accuracy of genome skimming and the effectiveness of exclusion read filters","display_name":"The impact of contaminants on the accuracy of genome skimming and the effectiveness of exclusion read filters","publication_year":2020,"publication_date":"2020-01-13","ids":{"openalex":"https://openalex.org/W3000238463","doi":"https://doi.org/10.1111/1755-0998.13135","mag":"3000238463","pmid":"https://pubmed.ncbi.nlm.nih.gov/31943790"},"language":"en","primary_location":{"id":"doi:10.1111/1755-0998.13135","doi":"https://doi.org/10.1111/1755-0998.13135","is_oa":false,"landing_page_url":"https://doi.org/10.1111/1755-0998.13135","pdf_url":null,"source":{"id":"https://openalex.org/S64961995","display_name":"Molecular Ecology Resources","issn_l":"1755-098X","issn":["1755-098X","1755-0998"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-b","jufo-2","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Molecular Ecology Resources","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2019/11/05/831941.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040053145","display_name":"Eleonora Rachtman","orcid":"https://orcid.org/0000-0002-6104-5750","observed_orcids":["https://orcid.org/0000-0002-6104-5750"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eleonora Rachtman","raw_affiliation_strings":["Bioinformatics and Systems Biology Graduate Program, UC San Diego, CA 92093, USA","Bioinformatics and Systems Biology Graduate Program, UC San Diego, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6104-5750","affiliations":[{"raw_affiliation_string":"Bioinformatics and Systems Biology Graduate Program, UC San Diego, CA 92093, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Bioinformatics and Systems Biology Graduate Program, UC San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083364801","display_name":"Metin Balaban","orcid":"https://orcid.org/0000-0002-6947-5915","observed_orcids":["https://orcid.org/0000-0002-6947-5915"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Metin Balaban","raw_affiliation_strings":["Bioinformatics and Systems Biology Graduate Program, UC San Diego, CA 92093, USA","Bioinformatics and Systems Biology Graduate Program, UC San Diego, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6947-5915","affiliations":[{"raw_affiliation_string":"Bioinformatics and Systems Biology Graduate Program, UC San Diego, CA 92093, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Bioinformatics and Systems Biology Graduate Program, UC San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028801735","display_name":"Vineet Bafna","orcid":"https://orcid.org/0000-0002-5810-6241","observed_orcids":["https://orcid.org/0000-0002-5810-6241"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vineet Bafna","raw_affiliation_strings":["Department of Computer Science and Engineering, UC San Diego, CA 92093, USA","Department of Computer Science and Engineering, UC San Diego, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5810-6241","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, UC San Diego, CA 92093, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, UC San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087959579","display_name":"Siavash Mirarab","orcid":"https://orcid.org/0000-0001-5410-1518","observed_orcids":["https://orcid.org/0000-0001-5410-1518"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Siavash Mirarab","raw_affiliation_strings":["Department of Electrical and Computer Engineering, UC San Diego, CA 92093, USA","Department of Electrical and Computer Engineering, UC San Diego, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5410-1518","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, UC San Diego, CA 92093, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, UC San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5087959579"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":{"value":4300,"currency":"USD","value_usd":4300},"apc_paid":null,"fwci":1.9532,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.84640712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"20","issue":"3","first_page":"649","last_page":"661"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.5062999725341797,"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"}},"topics":[{"id":"https://openalex.org/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.5062999725341797,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.49149999022483826,"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/T12388","display_name":"Identification and Quantification in Food","score":0.0005000000237487257,"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/genome-skimming","display_name":"genome skimming","score":0.9950000047683716},{"id":"https://openalex.org/keywords/contamination","display_name":"contamination","score":0.453000009059906},{"id":"https://openalex.org/keywords/specimen-identification","display_name":"specimen identification","score":0.7099999785423279},{"id":"https://openalex.org/keywords/metagenomic-sequencing","display_name":"metagenomic sequencing","score":0.4129999876022339}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7234010696411133},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6611483693122864},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6173644065856934},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5311395525932312},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5126951932907104},{"id":"https://openalex.org/C101985253","wikidata":"https://www.wikidata.org/wiki/Q1073526","display_name":"Shotgun sequencing","level":4,"score":0.495625376701355},{"id":"https://openalex.org/C112570922","wikidata":"https://www.wikidata.org/wiki/Q60528603","display_name":"Contamination","level":2,"score":0.44514602422714233},{"id":"https://openalex.org/C2779969263","wikidata":"https://www.wikidata.org/wiki/Q25098939","display_name":"Environmental DNA","level":3,"score":0.41953855752944946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3645917475223541},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3410518765449524},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.24086561799049377},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.1963644027709961},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07877650856971741},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C130217890","wikidata":"https://www.wikidata.org/wiki/Q47041","display_name":"Biodiversity","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1111/1755-0998.13135","doi":"https://doi.org/10.1111/1755-0998.13135","is_oa":false,"landing_page_url":"https://doi.org/10.1111/1755-0998.13135","pdf_url":null,"source":{"id":"https://openalex.org/S64961995","display_name":"Molecular Ecology Resources","issn_l":"1755-098X","issn":["1755-098X","1755-0998"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-b","jufo-2","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Molecular Ecology Resources","raw_type":"journal-article"},{"id":"doi:10.1101/831941","doi":"https://doi.org/10.1101/831941","is_oa":true,"landing_page_url":"https://doi.org/10.1101/831941","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2019/11/05/831941.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:31943790","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31943790","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,"listed_in":[],"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":"Molecular ecology resources","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1101/831941","doi":"https://doi.org/10.1101/831941","is_oa":true,"landing_page_url":"https://doi.org/10.1101/831941","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2019/11/05/831941.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3519978166","display_name":"III: Small: New algorithms for genome skimming and its applications","funder_award_id":"1815485","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3000238463.pdf","grobid_xml":"https://content.openalex.org/works/W3000238463.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1533146036","https://openalex.org/W1575156628","https://openalex.org/W1619833779","https://openalex.org/W1968339870","https://openalex.org/W1973235805","https://openalex.org/W2003347102","https://openalex.org/W2041076979","https://openalex.org/W2055043387","https://openalex.org/W2060425093","https://openalex.org/W2071510336","https://openalex.org/W2096128575","https://openalex.org/W2099901798","https://openalex.org/W2103961200","https://openalex.org/W2109560743","https://openalex.org/W2109782899","https://openalex.org/W2110375946","https://openalex.org/W2116412478","https://openalex.org/W2127727801","https://openalex.org/W2128964206","https://openalex.org/W2131026689","https://openalex.org/W2135515858","https://openalex.org/W2149415648","https://openalex.org/W2151450114","https://openalex.org/W2154966699","https://openalex.org/W2156542082","https://openalex.org/W2157539385","https://openalex.org/W2159954944","https://openalex.org/W2161973008","https://openalex.org/W2164747063","https://openalex.org/W2166016615","https://openalex.org/W2171894968","https://openalex.org/W2266239166","https://openalex.org/W2311491794","https://openalex.org/W2345658906","https://openalex.org/W2622731166","https://openalex.org/W2750586496","https://openalex.org/W2765281411","https://openalex.org/W2773939681","https://openalex.org/W2809649683","https://openalex.org/W2888572754","https://openalex.org/W2920716817","https://openalex.org/W2949351818","https://openalex.org/W2950150251","https://openalex.org/W2950964375","https://openalex.org/W2951002538","https://openalex.org/W2951160681","https://openalex.org/W2951676949","https://openalex.org/W2952152744","https://openalex.org/W2953328352","https://openalex.org/W2968450569","https://openalex.org/W2975848703","https://openalex.org/W2990618091","https://openalex.org/W2990925943","https://openalex.org/W3084201551","https://openalex.org/W3121953277","https://openalex.org/W4248560264","https://openalex.org/W4250406710","https://openalex.org/W6893583775","https://openalex.org/W6949929046","https://openalex.org/W7073543265"],"related_works":["https://openalex.org/W3193020855","https://openalex.org/W2913482272","https://openalex.org/W6979813869","https://openalex.org/W2953328352","https://openalex.org/W4376503838","https://openalex.org/W4391385576","https://openalex.org/W2963999695","https://openalex.org/W4402124848","https://openalex.org/W4412514441","https://openalex.org/W4396219526"],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,21,47,63,99,165,222],"detect":[3],"the":[4,22,30,37,56,61,65,75,100,108,117,136,154,166,195,232],"identity":[5],"of":[6,16,25,32,67,102,119,125,153,156,179,197,217],"a":[7,14,123,150,163,172,215,225],"sample":[8,68,82],"obtained":[9],"from":[10,104,145],"its":[11],"environment":[12],"is":[13,42,92],"cornerstone":[15],"molecular":[17],"ecological":[18],"research.":[19],"Thanks":[20],"falling":[23],"price":[24],"shotgun":[26],"sequencing,":[27],"genome":[28,38,86,126,173],"skimming,":[29],"acquisition":[31],"short":[33],"reads":[34,143,170],"spread":[35],"across":[36,55],"at":[39],"low":[40],"coverage,":[41],"emerging":[43],"as":[44,214],"an":[45,176],"alternative":[46],"traditional":[48,71],"barcoding.":[49],"By":[50],"obtaining":[51],"far":[52],"more":[53],"data":[54],"whole":[57],"genome,":[58],"skimming":[59],"has":[60],"promise":[62],"increase":[64],"precision":[66],"identification":[69,83],"beyond":[70],"barcoding":[72],"while":[73],"keeping":[74],"costs":[76],"manageable.":[77],"While":[78],"methods":[79,97],"for":[80,227],"assembly-free":[81],"based":[84,128],"on":[85,129],"skims":[87,127,137],"are":[88],"now":[89],"available,":[90],"little":[91],"known":[93],"about":[94],"how":[95],"these":[96],"react":[98],"presence":[101],"DNA":[103],"organisms":[105],"other":[106,146],"than":[107],"target":[109],"species.":[110],"In":[111],"this":[112,198],"paper,":[113],"we":[114],"show":[115,209],"that":[116,191],"accuracy":[118,213],"distances":[120],"computed":[121],"between":[122],"pair":[124],"k-mer":[130],"similarity":[131],"can":[132],"degrade":[133],"dramatically":[134],"if":[135],"include":[138],"contaminant":[139,233],"reads;":[140],"i.e.,":[141],"any":[142,189],"originating":[144],"organisms.":[147],"We":[148,158,193],"establish":[149],"theoretical":[151],"model":[152],"impact":[155],"contamination.":[157],"then":[159],"suggest":[160],"and":[161,186],"evaluate":[162,194],"solution":[164],"contamination":[167],"problem:":[168],"Query":[169],"in":[171,204,212,231],"skim":[174],"against":[175],"extensive":[177],"database":[178],"possible":[180],"contaminants":[181],"(e.g.,":[182],"all":[183],"microbial":[184],"organisms)":[185],"filter":[187],"out":[188],"read":[190],"matches.":[192],"effectiveness":[196],"strategy":[199],"when":[200],"implemented":[201],"using":[202],"Kraken-II,":[203],"detailed":[205],"analyses.":[206],"Our":[207],"results":[208],"substantial":[210],"improvements":[211],"result":[216],"filtering":[218],"but":[219],"also":[220],"point":[221],"limitations,":[223],"including":[224],"need":[226],"relatively":[228],"close":[229],"matches":[230],"database.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-01-23T00:00:00"}
