{"id":"https://openalex.org/W2121180999","doi":"https://doi.org/10.1093/bioinformatics/btr026","title":"Quality control and preprocessing of metagenomic datasets","display_name":"Quality control and preprocessing of metagenomic datasets","publication_year":2011,"publication_date":"2011-01-28","ids":{"openalex":"https://openalex.org/W2121180999","doi":"https://doi.org/10.1093/bioinformatics/btr026","mag":"2121180999","pmid":"https://pubmed.ncbi.nlm.nih.gov/21278185"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btr026","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btr026","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/27/6/863/48863248/bioinformatics_27_6_863.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/27/6/863/48863248/bioinformatics_27_6_863.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021759346","display_name":"Robert Schmieder","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I26538001","display_name":"San Diego State University","ror":"https://ror.org/0264fdx42","country_code":"US","type":"education","lineage":["https://openalex.org/I26538001"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Robert Schmieder","raw_affiliation_strings":["1 Department of Computer Science, 2Computational Science Research Center, San Diego State University, San Diego, CA 92182 and 3Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL 60439, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science, 2Computational Science Research Center, San Diego State University, San Diego, CA 92182 and 3Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL 60439, USA","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I26538001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036802114","display_name":"Robert A. Edwards","orcid":"https://orcid.org/0000-0001-8383-8949"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I26538001","display_name":"San Diego State University","ror":"https://ror.org/0264fdx42","country_code":"US","type":"education","lineage":["https://openalex.org/I26538001"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Robert Edwards","raw_affiliation_strings":["1 Department of Computer Science, 2Computational Science Research Center, San Diego State University, San Diego, CA 92182 and 3Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL 60439, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science, 2Computational Science Research Center, San Diego State University, San Diego, CA 92182 and 3Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL 60439, USA","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I26538001"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021759346","https://openalex.org/A5036802114"],"corresponding_institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I26538001"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":36.5904,"has_fulltext":true,"cited_by_count":5404,"citation_normalized_percentile":{"value":0.99889684,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"27","issue":"6","first_page":"863","last_page":"864"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9993000030517578,"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":0.9993000030517578,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9948999881744385,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.982200026512146,"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/perl","display_name":"Perl","score":0.8610258102416992},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.798566460609436},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7951518297195435},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.6692670583724976},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.6518815755844116},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6284000277519226},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5145627856254578},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5106845498085022},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5088448524475098},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4722145199775696},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46030759811401367},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44490084052085876},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32293206453323364},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.237665593624115},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16901856660842896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15062066912651062},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12774565815925598},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1102096438407898}],"concepts":[{"id":"https://openalex.org/C2777002779","wikidata":"https://www.wikidata.org/wiki/Q42478","display_name":"Perl","level":2,"score":0.8610258102416992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.798566460609436},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7951518297195435},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.6692670583724976},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.6518815755844116},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6284000277519226},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5145627856254578},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5106845498085022},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5088448524475098},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4722145199775696},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46030759811401367},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44490084052085876},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32293206453323364},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.237665593624115},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16901856660842896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15062066912651062},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12774565815925598},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1102096438407898},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btr026","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btr026","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/27/6/863/48863248/bioinformatics_27_6_863.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:21278185","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21278185","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:3051327","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3051327","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:osti.gov:1625274","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1625274","pdf_url":"https://www.osti.gov/servlets/purl/1625274","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btr026","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btr026","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/27/6/863/48863248/bioinformatics_27_6_863.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8278258816","display_name":"Collaborative Research:  PHANTOME:  PHage ANnotation TOols and MEthods","funder_award_id":"0850356","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2121180999.pdf","grobid_xml":"https://content.openalex.org/works/W2121180999.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1973862547","https://openalex.org/W1974860827","https://openalex.org/W1976608804","https://openalex.org/W2037532428","https://openalex.org/W2097205777","https://openalex.org/W2107493728","https://openalex.org/W2118903236"],"related_works":["https://openalex.org/W2480056510","https://openalex.org/W2113128227","https://openalex.org/W632256878","https://openalex.org/W4211197663","https://openalex.org/W2491403535","https://openalex.org/W3123068371","https://openalex.org/W2624709009","https://openalex.org/W2479811461","https://openalex.org/W2104915799","https://openalex.org/W2355429491"],"abstract_inverted_index":{"SUMMARY:":[0],"Here,":[1],"we":[2],"present":[3],"PRINSEQ":[4],"for":[5],"easy":[6],"and":[7,11,16,32,35,41,62,84],"rapid":[8],"quality":[9],"control":[10],"data":[12],"preprocessing":[13],"of":[14,21,46],"genomic":[15],"metagenomic":[17],"datasets.":[18],"Summary":[19],"statistics":[20],"FASTA":[22],"(and":[23],"QUAL)":[24],"or":[25,71],"FASTQ":[26],"files":[27],"are":[28,87],"generated":[29],"in":[30,60],"tabular":[31],"graphical":[33],"form":[34],"sequences":[36],"can":[37,63],"be":[38,64],"filtered,":[39],"reformatted":[40],"trimmed":[42],"by":[43],"a":[44,67,75],"variety":[45],"options":[47],"to":[48],"improve":[49],"downstream":[50],"analysis.":[51],"AVAILABILITY":[52],"AND":[53],"IMPLEMENTATION:":[54],"This":[55],"open-source":[56],"application":[57],"was":[58],"implemented":[59],"Perl":[61],"used":[65],"as":[66],"stand":[68],"alone":[69],"version":[70],"accessed":[72],"online":[73],"through":[74],"user-friendly":[76],"web":[77],"interface.":[78],"The":[79],"source":[80],"code,":[81],"user":[82],"help":[83],"additional":[85],"information":[86],"available":[88],"at":[89],"http://prinseq.sourceforge.net/.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":144},{"year":2025,"cited_by_count":314},{"year":2024,"cited_by_count":482},{"year":2023,"cited_by_count":424},{"year":2022,"cited_by_count":539},{"year":2021,"cited_by_count":645},{"year":2020,"cited_by_count":621},{"year":2019,"cited_by_count":508},{"year":2018,"cited_by_count":490},{"year":2017,"cited_by_count":423},{"year":2016,"cited_by_count":316},{"year":2015,"cited_by_count":216},{"year":2014,"cited_by_count":167},{"year":2013,"cited_by_count":77},{"year":2012,"cited_by_count":29}],"updated_date":"2026-07-12T07:33:03.550515","created_date":"2025-10-10T00:00:00"}
