{"id":"https://openalex.org/W2965715058","doi":"https://doi.org/10.1093/bioinformatics/btz577","title":"MetaBMF: a scalable binning algorithm for large-scale reference-free metagenomic studies","display_name":"MetaBMF: a scalable binning algorithm for large-scale reference-free metagenomic studies","publication_year":2019,"publication_date":"2019-07-24","ids":{"openalex":"https://openalex.org/W2965715058","doi":"https://doi.org/10.1093/bioinformatics/btz577","mag":"2965715058","pmid":"https://pubmed.ncbi.nlm.nih.gov/31347687"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz577","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz577","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/2/356/31962891/btz577.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/36/2/356/31962891/btz577.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059721142","display_name":"Terry Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Terry Ma","raw_affiliation_strings":["Department of Statistics, University of Georgia , Athens, GA 30601"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Georgia , Athens, GA 30601","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101352278","display_name":"Di Xiao","orcid":"https://orcid.org/0009-0002-6567-5466"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di Xiao","raw_affiliation_strings":["Department of Statistics, University of Georgia , Athens, GA 30601"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Georgia , Athens, GA 30601","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091115266","display_name":"Xin Xing","orcid":"https://orcid.org/0000-0001-9121-0086"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Xing","raw_affiliation_strings":["Department of Statistics, Harvard University , Cambridge, MA 02138, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Harvard University , Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091115266"],"corresponding_institution_ids":["https://openalex.org/I136199984"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.0647,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.76231903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"36","issue":"2","first_page":"356","last_page":"363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10066","display_name":"Gut microbiota and health","score":0.7181000113487244,"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/T10066","display_name":"Gut microbiota and health","score":0.7181000113487244,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0892999991774559,"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":0.028999999165534973,"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":0.910698413848877},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5629913210868835},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5489524006843567},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5171374678611755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5054049491882324},{"id":"https://openalex.org/keywords/shotgun-sequencing","display_name":"Shotgun sequencing","score":0.4420592188835144},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4207492768764496},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4172897934913635},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.37102624773979187},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35751691460609436},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.3370124101638794},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.17638811469078064},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.11020448803901672},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.10888490080833435}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.910698413848877},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5629913210868835},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5489524006843567},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5171374678611755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5054049491882324},{"id":"https://openalex.org/C101985253","wikidata":"https://www.wikidata.org/wiki/Q1073526","display_name":"Shotgun sequencing","level":4,"score":0.4420592188835144},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4207492768764496},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4172897934913635},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.37102624773979187},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35751691460609436},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.3370124101638794},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.17638811469078064},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.11020448803901672},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.10888490080833435},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017753","descriptor_name":"Ecosystem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017753","descriptor_name":"Ecosystem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017753","descriptor_name":"Ecosystem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","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":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":3,"locations":[{"id":"doi:10.1093/bioinformatics/btz577","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz577","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/2/356/31962891/btz577.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:31347687","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31347687","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:7868002","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7868002","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btz577","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz577","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/2/356/31962891/btz577.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":0.6800000071525574,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G2417438933","display_name":"Collaborative Research: ATD: Integrated statistical algorithms with ultra-high performance computing for discovering SNPs from massive next-generation metagenomic sequencing data","funder_award_id":"1440037","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7728125046","display_name":"Novel statistical tools for cell line specific epigenetic analysis","funder_award_id":"5r01gm113242-04","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8373856813","display_name":"Collaborative Research: Leverage Subsampling for Regression and Dimension Reduction","funder_award_id":"1440038","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G855370250","display_name":null,"funder_award_id":"R01 GM113242","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965715058.pdf","grobid_xml":"https://content.openalex.org/works/W2965715058.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1584790813","https://openalex.org/W1878521557","https://openalex.org/W1983789014","https://openalex.org/W1987971958","https://openalex.org/W1988429087","https://openalex.org/W1989628346","https://openalex.org/W1996758006","https://openalex.org/W1997742538","https://openalex.org/W2003347102","https://openalex.org/W2010002522","https://openalex.org/W2033829415","https://openalex.org/W2060915038","https://openalex.org/W2081676964","https://openalex.org/W2083667275","https://openalex.org/W2093401639","https://openalex.org/W2103901746","https://openalex.org/W2113679889","https://openalex.org/W2115742500","https://openalex.org/W2116844657","https://openalex.org/W2116895571","https://openalex.org/W2135046866","https://openalex.org/W2138913478","https://openalex.org/W2141202455","https://openalex.org/W2146281049","https://openalex.org/W2159954944","https://openalex.org/W2167062509","https://openalex.org/W2172874193","https://openalex.org/W2318393934","https://openalex.org/W2594112302","https://openalex.org/W2761479686","https://openalex.org/W2761865284","https://openalex.org/W3144526075","https://openalex.org/W4241184565"],"related_works":["https://openalex.org/W3043668926","https://openalex.org/W3036436206","https://openalex.org/W4389452281","https://openalex.org/W4238948313","https://openalex.org/W3111832393","https://openalex.org/W3000916974","https://openalex.org/W3183189600","https://openalex.org/W3134948850","https://openalex.org/W4394325869","https://openalex.org/W4394082811"],"abstract_inverted_index":{"MOTIVATION:":[0],"Metagenomics":[1],"studies":[2],"microbial":[3,19,89,148,244],"genomes":[4,69],"in":[5,158,195,219,228],"an":[6],"ecosystem":[7],"such":[8],"as":[9,112],"the":[10,37,40,99,151,155,202,212,238],"gastrointestinal":[11],"tract":[12],"of":[13,17,23,42,67,101,132,235,243,249],"a":[14,52,77,118,130,133,137,171,184,190],"human.":[15],"Identification":[16],"novel":[18],"species":[20,149,156,185],"and":[21,70,116,136,150,163,233,241,246],"quantification":[22,242],"their":[24],"distributional":[25],"variations":[26],"among":[27],"different":[28,110,159],"samples":[29,111],"that":[30,91,168],"are":[31,92],"sequenced":[32],"using":[33],"next-generation-sequencing":[34],"technology":[35,236],"hold":[36],"key":[38],"to":[39,86,124,146,211,224],"success":[41],"most":[43],"metagenomic":[44,56,229],"studies.":[45],"To":[46],"achieve":[47],"these":[48,220],"goals,":[49],"we":[50,97,166,198],"propose":[51,117],"simple":[53],"yet":[54],"powerful":[55],"binning":[57,173],"method,":[58],"MetaBMF.":[59],"The":[60,140,260],"method":[61],"does":[62],"not":[63,93,177],"require":[64],"prior":[65],"knowledge":[66],"reference":[68],"produces":[71],"highly":[72],"accurate":[73],"results,":[74],"even":[75],"at":[76,183,189,264],"strain":[78,191,208],"level.":[79,192],"Thus,":[80],"it":[81],"can":[82,143,176,199],"be":[83,144],"broadly":[84],"used":[85,145],"identify":[87,201],"disease-related":[88],"organisms":[90],"well-studied.":[94],"RESULTS:":[95],"Mathematically,":[96],"count":[98,127],"number":[100],"mapped":[102],"reads":[103],"on":[104],"each":[105],"assembled":[106],"genomic":[107],"fragment":[108],"cross":[109],"our":[113,196],"input":[114],"matrix":[115,128,135,142,153],"scalable":[119],"stratified":[120],"angle":[121],"regression":[122],"algorithm":[123],"factorize":[125],"this":[126],"into":[129],"product":[131],"binary":[134,141],"nonnegative":[138,152],"matrix.":[139],"separate":[147],"quantifies":[154],"distributions":[157,245],"samples.":[160],"In":[161],"simulation":[162],"empirical":[164],"studies,":[165],"demonstrate":[167],"MetaBMF":[169],"has":[170],"high":[172],"accuracy.":[174],"It":[175],"only":[178],"bin":[179],"DNA":[180],"fragments":[181],"accurately":[182,200],"level":[186],"but":[187],"also":[188],"As":[193],"shown":[194],"example,":[197],"Shiga-toxigenic":[203],"Escherichia":[204],"coli":[205],"O104:":[206],"H4":[207],"which":[209],"led":[210],"2011":[213],"German":[214],"E.coli":[215],"outbreak.":[216],"Our":[217],"efforts":[218],"areas":[221],"should":[222],"lead":[223],"(i)":[225],"fundamental":[226],"advances":[227],"binning,":[230],"(ii)":[231],"development":[232],"refinement":[234],"for":[237],"rapid":[239],"identification":[240],"(iii)":[247],"finding":[248],"potential":[250],"probiotics":[251],"or":[252],"reliable":[253],"pathogenic":[254],"bacterial":[255],"strains.":[256],"AVAILABILITY":[257],"AND":[258],"IMPLEMENTATION:":[259],"software":[261],"is":[262],"available":[263],"https://github.com/didi10384/MetaBMF.":[265]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
