{"id":"https://openalex.org/W2750586496","doi":"https://doi.org/10.1186/s12859-019-2684-x","title":"From trash to treasure: detecting unexpected contamination in unmapped NGS data","display_name":"From trash to treasure: detecting unexpected contamination in unmapped NGS data","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W2750586496","doi":"https://doi.org/10.1186/s12859-019-2684-x","mag":"2750586496","pmid":"https://pubmed.ncbi.nlm.nih.gov/30999839","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/6472186"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2684-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-2684-x","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-2684-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069419408","display_name":"Mara Sangiovanni","orcid":"https://orcid.org/0000-0003-4511-5031"},"institutions":[{"id":"https://openalex.org/I2802779139","display_name":"Stazione Zoologica Anton Dohrn","ror":"https://ror.org/03v5jj203","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2802779139"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mara Sangiovanni","raw_affiliation_strings":["Stazione Zoologica Anton Dohrn, Villa Comunale, Napoli, 80121, Italy"],"affiliations":[{"raw_affiliation_string":"Stazione Zoologica Anton Dohrn, Villa Comunale, Napoli, 80121, Italy","institution_ids":["https://openalex.org/I2802779139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027202141","display_name":"Ilaria Granata","orcid":"https://orcid.org/0000-0002-3450-4667"},"institutions":[{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Ilaria Granata","raw_affiliation_strings":["High Performance Computing and Networking Institute, National Research Council of Italy, Via P. Castellino, 111, Napoli, 80131, Italy"],"affiliations":[{"raw_affiliation_string":"High Performance Computing and Networking Institute, National Research Council of Italy, Via P. Castellino, 111, Napoli, 80131, Italy","institution_ids":["https://openalex.org/I4210155236","https://openalex.org/I3005160176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072684272","display_name":"Amarinder Singh Thind","orcid":"https://orcid.org/0000-0003-4592-0380"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Amarinder Singh Thind","raw_affiliation_strings":["High Performance Computing and Networking Institute, National Research Council of Italy, Via P. Castellino, 111, Napoli, 80131, Italy"],"affiliations":[{"raw_affiliation_string":"High Performance Computing and Networking Institute, National Research Council of Italy, Via P. Castellino, 111, Napoli, 80131, Italy","institution_ids":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023713760","display_name":"Mario Rosario Guarracino","orcid":"https://orcid.org/0000-0003-2870-8134"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mario Rosario Guarracino","raw_affiliation_strings":["High Performance Computing and Networking Institute, National Research Council of Italy, Via P. Castellino, 111, Napoli, 80131, Italy"],"affiliations":[{"raw_affiliation_string":"High Performance Computing and Networking Institute, National Research Council of Italy, Via P. Castellino, 111, Napoli, 80131, Italy","institution_ids":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027202141"],"corresponding_institution_ids":["https://openalex.org/I4210155236","https://openalex.org/I3005160176"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072,"provenance":"doaj"},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072,"provenance":"doaj"},"fwci":3.766,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":72,"citation_normalized_percentile":{"value":0.999945,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"20","issue":"S4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11588","display_name":"Atmospheric and Environmental Gas Dynamics","score":0.979,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"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/T11588","display_name":"Atmospheric and Environmental Gas Dynamics","score":0.979,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"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/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.9504,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.9473,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/treasure","display_name":"Treasure","score":0.92050487}],"concepts":[{"id":"https://openalex.org/C2776084483","wikidata":"https://www.wikidata.org/wiki/Q272937","display_name":"Treasure","level":2,"score":0.92050487},{"id":"https://openalex.org/C112570922","wikidata":"https://www.wikidata.org/wiki/Q60528603","display_name":"Contamination","level":2,"score":0.64376354},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.48921704},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.48762217},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.48278558},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41034272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35743237},{"id":"https://openalex.org/C150903083","wikidata":"https://www.wikidata.org/wiki/Q7108","display_name":"Biotechnology","level":1,"score":0.35521597},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3401159},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.30255526},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1972313},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.17871025},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.10625973},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.06701991},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D059018","descriptor_name":"DNA Contamination","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005658","descriptor_name":"Fungi","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005658","descriptor_name":"Fungi","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014780","descriptor_name":"Viruses","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014780","descriptor_name":"Viruses","qualifier_ui":"","qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2684-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-2684-x","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6472186","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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30999839","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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-2684-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-2684-x","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310320256"],"host_organization_lineage_names":["Springer Nature","BioMed Central"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":["https://openalex.org/W4394089582"],"versions":[],"referenced_works_count":66,"referenced_works":["https://openalex.org/W117143873","https://openalex.org/W1580497440","https://openalex.org/W1859890772","https://openalex.org/W1970729332","https://openalex.org/W1972025764","https://openalex.org/W1974764034","https://openalex.org/W1978578392","https://openalex.org/W1980764720","https://openalex.org/W1988460088","https://openalex.org/W1996173530","https://openalex.org/W2007853991","https://openalex.org/W2016488959","https://openalex.org/W2027908094","https://openalex.org/W2030767781","https://openalex.org/W2035899956","https://openalex.org/W2045940518","https://openalex.org/W2046372228","https://openalex.org/W2047242127","https://openalex.org/W2047427120","https://openalex.org/W2053369230","https://openalex.org/W2055666215","https://openalex.org/W2066447073","https://openalex.org/W2066745538","https://openalex.org/W2070791418","https://openalex.org/W2073924079","https://openalex.org/W2085675020","https://openalex.org/W2085800524","https://openalex.org/W2086569072","https://openalex.org/W2088507947","https://openalex.org/W2094597685","https://openalex.org/W2097065948","https://openalex.org/W2107097628","https://openalex.org/W2108234281","https://openalex.org/W2113327952","https://openalex.org/W2114315172","https://openalex.org/W2120472610","https://openalex.org/W2124799197","https://openalex.org/W2133546130","https://openalex.org/W2135334986","https://openalex.org/W2135989088","https://openalex.org/W2137662380","https://openalex.org/W2140612008","https://openalex.org/W2142457917","https://openalex.org/W2144693556","https://openalex.org/W2144883401","https://openalex.org/W2149507559","https://openalex.org/W2154896150","https://openalex.org/W2162755780","https://openalex.org/W2170486072","https://openalex.org/W2171777347","https://openalex.org/W2256668945","https://openalex.org/W2281515178","https://openalex.org/W2294080666","https://openalex.org/W2342540743","https://openalex.org/W2394897061","https://openalex.org/W2403288892","https://openalex.org/W2406298684","https://openalex.org/W2463042271","https://openalex.org/W2469323929","https://openalex.org/W2508337372","https://openalex.org/W2547980289","https://openalex.org/W2575568020","https://openalex.org/W2598650907","https://openalex.org/W2885727518","https://openalex.org/W323797365","https://openalex.org/W590963527"],"related_works":["https://openalex.org/W640718562","https://openalex.org/W4285698275","https://openalex.org/W4248194279","https://openalex.org/W378221013","https://openalex.org/W369913426","https://openalex.org/W2492411721","https://openalex.org/W2476851620","https://openalex.org/W2360017572","https://openalex.org/W2223042459","https://openalex.org/W1504426902"],"abstract_inverted_index":{"Next":[0],"Generation":[1],"Sequencing":[2],"(NGS)":[3],"experiments":[4],"produce":[5],"millions":[6],"of":[7,28,49,75,87,113,150,217,229,256,264,277],"short":[8],"sequences":[9,115,219],"that,":[10],"mapped":[11],"to":[12,33,57,82,92,109,125,138,145,192,213],"a":[13,46,107,122,147,208,283],"reference":[14,35,70],"genome,":[15],"provide":[16,146],"biological":[17,245],"insights":[18],"at":[19,204],"genomic,":[20],"transcriptomic":[21],"and":[22,40,68,91,129,144,162,175,211,247,259,286],"epigenomic":[23],"level.":[24],"Typically":[25],"the":[26,34,65,69,73,76,85,88,111,117,141,182,215,227,274],"amount":[27],"reads":[29,67,78],"that":[30,235],"correctly":[31],"maps":[32],"genome":[36,131],"ranges":[37],"between":[38,64],"70%":[39],"90%,":[41],"leaving":[42],"in":[43,195,220,232,248],"some":[44],"cases":[45,250],"consistent":[47],"fraction":[48],"unmapped":[50,77,118,221],"sequences.":[51],"This":[52],"'misalignment'":[53],"can":[54,225,251],"be":[55,252],"ascribed":[56],"low":[58],"quality":[59,86,155],"bases":[60],"or":[61,97,242],"sequence":[62],"differences":[63],"sample":[66],"genome.":[71],"Investigating":[72],"source":[74],"is":[79,201,207,266],"definitely":[80],"important":[81],"better":[83],"assess":[84],"whole":[89],"experiment":[90],"check":[93],"for":[94],"possible":[95],"downstream":[96],"upstream":[98],"'contamination'":[99],"from":[100,239,243],"exogenous":[101],"nucleic":[102],"acids.Here":[103],"we":[104],"propose":[105],"DecontaMiner,":[106],"tool":[108,209],"unravel":[110],"presence":[112,216,228],"contaminating":[114,218,230],"among":[116,164],"reads.":[119],"It":[120,224],"uses":[121],"subtraction":[123],"approach":[124],"identify":[126],"bacteria,":[127],"fungi":[128],"viruses":[130],"contamination.":[132],"DecontaMiner":[133,166,187,265],"generates":[134],"several":[135],"output":[136],"files":[137],"track":[139],"all":[140],"processed":[142],"reads,":[143],"complete":[148],"report":[149],"their":[151,244],"characteristics.":[152],"The":[153,177,199,262],"good":[154],"matches":[156],"on":[157],"microorganism":[158],"genomes":[159],"are":[160,179],"counted":[161],"compared":[163],"samples.":[165],"builds":[167],"an":[168],"offline":[169],"HTML":[170],"page":[171],"containing":[172],"summary":[173],"statistics":[174],"plots.":[176],"latter":[178],"obtained":[180],"using":[181],"state-of-the-art":[183],"D3":[184],"javascript":[185],"libraries.":[186],"has":[188],"been":[189],"mainly":[190,267],"used":[191],"detect":[193],"contamination":[194,241],"human":[196],"RNA-Seq":[197],"data.":[198,223],"software":[200],"freely":[202],"available":[203],"http://www-labgtp.na.icar.cnr.it/decontaminer":[205],".DecontaMiner":[206],"designed":[210],"developed":[212],"investigate":[214],"NGS":[222,278],"suggest":[226],"organisms":[231],"sequenced":[233],"samples,":[234],"might":[236],"derive":[237],"either":[238],"laboratory":[240],"source,":[246],"both":[249],"considered":[253],"as":[254],"worthy":[255],"further":[257],"investigation":[258],"experimental":[260],"validation.":[261],"novelty":[263],"represented":[268],"by":[269],"its":[270],"easy":[271],"integration":[272],"with":[273],"standard":[275],"procedures":[276],"data":[279],"analysis,":[280],"while":[281],"providing":[282],"complete,":[284],"reliable,":[285],"automatic":[287],"pipeline.":[288]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2750586496","counts_by_year":[{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4}],"updated_date":"2024-12-29T21:24:58.123391","created_date":"2017-09-15"}