{"id":"https://openalex.org/W2142915116","doi":"https://doi.org/10.1093/bioinformatics/btu546","title":"Pooled assembly of marine metagenomic datasets: enriching annotation through chimerism","display_name":"Pooled assembly of marine metagenomic datasets: enriching annotation through chimerism","publication_year":2014,"publication_date":"2014-10-11","ids":{"openalex":"https://openalex.org/W2142915116","doi":"https://doi.org/10.1093/bioinformatics/btu546","mag":"2142915116","pmid":"https://pubmed.ncbi.nlm.nih.gov/25306399"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btu546","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu546","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/3/311/49012104/bioinformatics_31_3_311.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":null,"license_id":null,"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":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/31/3/311/49012104/bioinformatics_31_3_311.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041935821","display_name":"Jonathan D. Magasin","orcid":"https://orcid.org/0000-0003-4187-4778"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]},{"id":"https://openalex.org/I4210163760","display_name":"Foundation for Applied Molecular Evolution","ror":"https://ror.org/052x5ps19","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210163760"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan D. Magasin","raw_affiliation_strings":["1 Department of Biomolecular Engineering, University of California, Santa Cruz, CA 95064 and 2 Foundation for Applied Molecular Evolution (FfAME), Gainesville, FL 32604, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Biomolecular Engineering, University of California, Santa Cruz, CA 95064 and 2 Foundation for Applied Molecular Evolution (FfAME), Gainesville, FL 32604, USA","institution_ids":["https://openalex.org/I185103710","https://openalex.org/I4210163760"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090286378","display_name":"Dietlind L. Gerloff","orcid":null},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]},{"id":"https://openalex.org/I4210163760","display_name":"Foundation for Applied Molecular Evolution","ror":"https://ror.org/052x5ps19","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210163760"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dietlind L. Gerloff","raw_affiliation_strings":["1 Department of Biomolecular Engineering, University of California, Santa Cruz, CA 95064 and 2 Foundation for Applied Molecular Evolution (FfAME), Gainesville, FL 32604, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Biomolecular Engineering, University of California, Santa Cruz, CA 95064 and 2 Foundation for Applied Molecular Evolution (FfAME), Gainesville, FL 32604, USA","institution_ids":["https://openalex.org/I185103710","https://openalex.org/I4210163760"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090286378"],"corresponding_institution_ids":["https://openalex.org/I185103710","https://openalex.org/I4210163760"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.3899,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.61576088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"31","issue":"3","first_page":"311","last_page":"317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8855999708175659,"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":0.8855999708175659,"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/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.04050000011920929,"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/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.025800000876188278,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.9582809209823608},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7350375056266785},{"id":"https://openalex.org/keywords/contig","display_name":"Contig","score":0.6667341589927673},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.6491942405700684},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6411511898040771},{"id":"https://openalex.org/keywords/pyrosequencing","display_name":"Pyrosequencing","score":0.5860405564308167},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.5237988233566284},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5204794406890869},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.47003716230392456},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.27827537059783936},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.27554643154144287},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.19894513487815857}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.9582809209823608},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7350375056266785},{"id":"https://openalex.org/C59582021","wikidata":"https://www.wikidata.org/wiki/Q1128751","display_name":"Contig","level":4,"score":0.6667341589927673},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6491942405700684},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6411511898040771},{"id":"https://openalex.org/C125009961","wikidata":"https://www.wikidata.org/wiki/Q2342248","display_name":"Pyrosequencing","level":3,"score":0.5860405564308167},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.5237988233566284},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5204794406890869},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.47003716230392456},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.27827537059783936},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.27554643154144287},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.19894513487815857},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0}],"mesh":[{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"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":"D019843","descriptor_name":"Archaeal Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D019843","descriptor_name":"Archaeal Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D019843","descriptor_name":"Archaeal Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020745","descriptor_name":"Genome, Archaeal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020745","descriptor_name":"Genome, Archaeal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020745","descriptor_name":"Genome, Archaeal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D046528","descriptor_name":"Chimerism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D046528","descriptor_name":"Chimerism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D046528","descriptor_name":"Chimerism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btu546","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu546","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/3/311/49012104/bioinformatics_31_3_311.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:25306399","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25306399","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:ark:/13030/qt9fc1756g","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:escholarship.org:ark:/13030/qt9fc1756g","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/9fc1756g","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"Bioinformatics, vol 31, iss 3","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btu546","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu546","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/3/311/49012104/bioinformatics_31_3_311.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8899999856948853,"display_name":"Life below water","id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337386","display_name":"Division of Ocean Sciences","ror":"https://ror.org/05wqqhv83"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2142915116.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1701869895","https://openalex.org/W1966952999","https://openalex.org/W1978126958","https://openalex.org/W1979006961","https://openalex.org/W1983169073","https://openalex.org/W1989348205","https://openalex.org/W2001447987","https://openalex.org/W2006465310","https://openalex.org/W2021457453","https://openalex.org/W2022472106","https://openalex.org/W2026469821","https://openalex.org/W2040890279","https://openalex.org/W2047927409","https://openalex.org/W2048091446","https://openalex.org/W2048818637","https://openalex.org/W2069689025","https://openalex.org/W2085631282","https://openalex.org/W2093830129","https://openalex.org/W2100896078","https://openalex.org/W2101181144","https://openalex.org/W2107854630","https://openalex.org/W2113601822","https://openalex.org/W2120267228","https://openalex.org/W2120330409","https://openalex.org/W2122646534","https://openalex.org/W2124351063","https://openalex.org/W2131342905","https://openalex.org/W2132415967","https://openalex.org/W2137597742","https://openalex.org/W2141885858","https://openalex.org/W2159406441","https://openalex.org/W2171777099","https://openalex.org/W4320301318","https://openalex.org/W6680215730"],"related_works":["https://openalex.org/W2330186985","https://openalex.org/W2950447380","https://openalex.org/W2345730070","https://openalex.org/W2107854630","https://openalex.org/W4319294554","https://openalex.org/W2122646534","https://openalex.org/W2158877985","https://openalex.org/W2055448750","https://openalex.org/W3134563641","https://openalex.org/W1986608492"],"abstract_inverted_index":{"MOTIVATION:":[0],"Despite":[1],"advances":[2],"in":[3,185,195,226],"high-throughput":[4],"sequencing,":[5],"marine":[6,98],"metagenomic":[7,32,99],"samples":[8],"remain":[9],"largely":[10],"opaque.":[11],"A":[12],"typical":[13],"sample":[14],"contains":[15],"billions":[16],"of":[17,22,26,39,42,47,75,86,97,143,198,223],"microbial":[18],"organisms":[19],"from":[20,69],"thousands":[21],"genomes":[23],"and":[24,45,52,62,80,146,169,211],"quadrillions":[25],"DNA":[27],"base":[28],"pairs.":[29],"Its":[30],"derived":[31],"dataset":[33],"underrepresents":[34],"this":[35,108],"complexity":[36,117],"by":[37,154],"orders":[38],"magnitude":[40],"because":[41],"the":[43,73,87,126,141,186],"sparseness":[44],"shortness":[46,51],"sequencing":[48,53],"reads.":[49],"Read":[50],"errors":[54],"pose":[55],"a":[56,120],"major":[57],"challenge":[58],"to":[59],"accurate":[60],"species":[61,116,128,225],"functional":[63],"annotation.":[64],"This":[65],"includes":[66],"distinguishing":[67],"known":[68],"novel":[70],"species.":[71],"Often":[72],"majority":[74],"reads":[76,100],"cannot":[77,82],"be":[78,193],"annotated":[79,144],"thus":[81],"help":[83],"our":[84,214],"interpretation":[85],"sample.":[88],"RESULTS:":[89],"Here,":[90],"we":[91],"demonstrate":[92],"quantitatively":[93],"how":[94],"careful":[95],"assembly":[96,139,205],"within,":[101],"but":[102],"also":[103,216],"across,":[104],"datasets":[105,151],"can":[106],"alleviate":[107],"problem.":[109],"For":[110,133],"10":[111],"simulated":[112],"datasets,":[113,138],"each":[114],"with":[115],"modeled":[118],"on":[119,155],"real":[121,135],"counterpart,":[122],"chimerism":[123],"remained":[124],"within":[125],"same":[127],"for":[129,160,165,173,182,208,220],"most":[130],"contigs":[131],"(97%).":[132],"42":[134],"pyrosequencing":[136],"('454')":[137],"increased":[140],"proportion":[142],"reads,":[145],"even":[147],"more":[148],"so":[149],"when":[150],"were":[152],"pooled,":[153],"average":[156],"1.6%":[157],"(max":[158,163,171],"6.6%)":[159],"species,":[161],"9.0%":[162],"28.7%)":[164],"Pfam":[166],"protein":[167],"domains":[168],"9.4%":[170],"22.9%)":[172],"PANTHER":[174],"gene":[175],"families.":[176],"Our":[177],"results":[178],"outline":[179],"exciting":[180],"prospects":[181,219],"data":[183,234],"sharing":[184],"metagenomics":[187,199],"community.":[188],"While":[189],"chimeric":[190],"sequences":[191],"should":[192],"avoided":[194],"other":[196],"areas":[197],"(e.g.":[200],"biodiversity":[201],"analyses),":[202],"conservative":[203],"pooled":[204],"is":[206],"advantageous":[207],"annotation":[209],"specificity":[210],"sensitivity.":[212],"Intriguingly,":[213],"experiment":[215],"found":[217],"potential":[218],"(low-cost)":[221],"discovery":[222],"new":[224],"'old'":[227],"data.":[228],"CONTACT:":[229],"dgerloff@ffame.org":[230],"SUPPLEMENTARY":[231],"INFORMATION:":[232],"Supplementary":[233],"are":[235],"available":[236],"at":[237],"Bioinformatics":[238],"online.":[239]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}