{"id":"https://openalex.org/W4382631184","doi":"https://doi.org/10.1093/bioinformatics/btad238","title":"Finding phylogeny-aware and biologically meaningful averages of metagenomic samples: L2UniFrac","display_name":"Finding phylogeny-aware and biologically meaningful averages of metagenomic samples: L2UniFrac","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4382631184","doi":"https://doi.org/10.1093/bioinformatics/btad238","pmid":"https://pubmed.ncbi.nlm.nih.gov/36778267","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/9915697"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad238","doi":"https://doi.org/10.1093/bioinformatics/btad238","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad238","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i57/50741948/btad238.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i57/50741948/btad238.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100323674","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0002-0733-5060","observed_orcids":["https://orcid.org/0000-0002-0733-5060"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["Huck Institutes of the Life Sciences, Pennsylvania State University, University Park, PA 16802, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huck Institutes of the Life Sciences, Pennsylvania State University, University Park, PA 16802, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andrew Millward","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Millward","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA 16802, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA 16802, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002668669","display_name":"David Koslicki","orcid":"https://orcid.org/0000-0002-0640-954X","observed_orcids":["https://orcid.org/0000-0002-0640-954X"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Koslicki","raw_affiliation_strings":["Department of Biology, Pennsylvania State University , University Park, PA 16802, United States","Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA 16802, United States","Huck Institutes of the Life Sciences, Pennsylvania State University, University Park, PA 16802, United States"],"raw_orcid":"https://orcid.org/0000-0002-0640-954X","affiliations":[{"raw_affiliation_string":"Department of Biology, Pennsylvania State University , University Park, PA 16802, United States","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA 16802, United States","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Huck Institutes of the Life Sciences, Pennsylvania State University, University Park, PA 16802, United States","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002668669"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0864,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.29621917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"39","issue":"Supplement_1","first_page":"i57","last_page":"i65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8359000086784363,"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":0.8359000086784363,"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":0.11990000307559967,"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/T10066","display_name":"Gut microbiota and health","score":0.011900000274181366,"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/unifrac-distance","display_name":"UniFrac distance","score":0.8899999856948853},{"id":"https://openalex.org/keywords/metagenomics","display_name":"metagenomics","score":0.7829999923706055},{"id":"https://openalex.org/keywords/evolutionary-distance","display_name":"phylogenetic distance","score":0.6880000233650208},{"id":"https://openalex.org/keywords/barycenter","display_name":"barycenter","score":0.8579999804496765},{"id":"https://openalex.org/keywords/representative-samples","display_name":"representative samples","score":0.7620000243186951},{"id":"https://openalex.org/keywords/microbial-community-composition","display_name":"microbial community composition","score":0.6290000081062317}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.8548797965049744},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.6338448524475098},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5086392164230347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4352157413959503},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.41526931524276733},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4124917984008789},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.3256813883781433},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1395563781261444},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.12172317504882812},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06441351771354675}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1093/bioinformatics/btad238","doi":"https://doi.org/10.1093/bioinformatics/btad238","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad238","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i57/50741948/btad238.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"doi:10.1101/2023.02.02.526854","doi":"https://doi.org/10.1101/2023.02.02.526854","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2023.02.02.526854","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2023/02/03/2023.02.02.526854.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:10311324","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10311324","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10311324/pdf/btad238.pdf","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"Text"},{"id":"pmid:36778267","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36778267","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":"bioRxiv : the preprint server for biology","raw_type":"Preprint"},{"id":"pmid:37387190","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37387190","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":"Bioinformatics (Oxford, England)","raw_type":"Journal Article"},{"id":"pmh:oai:scholarsphere.psu.edu:3a4b30f9-a81e-403d-b80a-13875cddc04a","doi":null,"is_oa":true,"landing_page_url":"https://scholarsphere.psu.edu/resources/3a4b30f9-a81e-403d-b80a-13875cddc04a","pdf_url":"https://scholarsphere.psu.edu/resources/4cba12d1-1196-4bd1-bf8b-1e6577817731/downloads/34277","source":{"id":"https://openalex.org/S4306401507","display_name":"ScholarSphere (Penn State Libraries)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I3130638595","host_organization_name":"Pangasinan State University","host_organization_lineage":["https://openalex.org/I3130638595"],"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":"Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9915697","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9915697","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9915697/pdf/nihpp-2023.02.02.526854v1.pdf","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,"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad238","doi":"https://doi.org/10.1093/bioinformatics/btad238","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad238","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i57/50741948/btad238.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000871591","display_name":"Leveraging k-mer sketching statistics to enhance metagenomic methods and alignment algorithms","funder_award_id":"R01GM146462","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"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/W4382631184.pdf","grobid_xml":"https://content.openalex.org/works/W4382631184.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W612202943","https://openalex.org/W2055151521","https://openalex.org/W2073212972","https://openalex.org/W2139297600","https://openalex.org/W2170024099","https://openalex.org/W2580859631","https://openalex.org/W2581406049","https://openalex.org/W2887158859","https://openalex.org/W2892206041","https://openalex.org/W2896638680","https://openalex.org/W2949004447","https://openalex.org/W2952915499","https://openalex.org/W3039673345","https://openalex.org/W3109640704","https://openalex.org/W3161036992","https://openalex.org/W4308909959","https://openalex.org/W6929080665"],"related_works":["https://openalex.org/W2055615060","https://openalex.org/W2952915499","https://openalex.org/W7099162681","https://openalex.org/W2139297600","https://openalex.org/W2052745168","https://openalex.org/W7204579458","https://openalex.org/W4394946666","https://openalex.org/W2000190756","https://openalex.org/W4398143653","https://openalex.org/W6929080665"],"abstract_inverted_index":{"MOTIVATION:":[0],"Metagenomic":[1],"samples":[2,69,148],"have":[3],"high":[4],"spatiotemporal":[5],"variability.":[6],"Hence,":[7],"it":[8,77,88],"is":[9,26,78,181],"useful":[10],"to":[11,72,127,169],"summarize":[12],"and":[13,29,38,124,163,167,188],"characterize":[14],"the":[15,44,52,62,65,68,73,110,117,121,133,143,152,170],"microbial":[16],"makeup":[17],"of":[18,54,94,109,120,145,155,160,173],"a":[19,23,36,82,91,95,106],"given":[20],"environment":[21],"in":[22,157],"way":[24],"that":[25,51,80],"biologically":[27,136],"reasonable":[28],"interpretable.":[30],"The":[31],"UniFrac":[32,74,111,123],"metric":[33,41],"has":[34],"been":[35],"robust":[37],"widely":[39],"used":[40],"for":[42],"measuring":[43],"variability":[45],"between":[46],"metagenomic":[47,55,96,161],"samples.":[48],"We":[49,141],"propose":[50,105],"characterization":[53],"environments":[56],"can":[57,130,190],"be":[58,191],"improved":[59],"by":[60],"finding":[61],"average,":[63,134],"a.k.a.":[64],"barycenter,":[66],"among":[67],"with":[70,125],"respect":[71,126],"distance.":[75],"However,":[76],"possible":[79],"such":[81,146],"UniFrac-average":[83],"includes":[84],"negative":[85],"entries,":[86],"making":[87],"no":[89],"longer":[90],"valid":[92],"representation":[93],"community.":[97],"RESULTS:":[98],"To":[99],"overcome":[100],"this":[101],"intrinsic":[102],"issue,":[103],"we":[104],"special":[107],"version":[108],"metric,":[112],"termed":[113],"L2UniFrac,":[114],"which":[115,128],"inherits":[116],"phylogenetic":[118],"nature":[119],"traditional":[122],"one":[129],"easily":[131],"compute":[132],"producing":[135],"meaningful":[137],"environment-specific":[138],"\"representative":[139],"samples.\"":[140],"demonstrate":[142],"usefulness":[144],"representative":[147],"as":[149,151],"well":[150],"extended":[153],"usage":[154],"L2UniFrac":[156],"efficient":[158],"clustering":[159],"samples,":[162],"provide":[164],"mathematical":[165],"characterizations":[166],"proofs":[168],"desired":[171],"properties":[172],"L2UniFrac.":[174],"AVAILABILITY":[175],"AND":[176],"IMPLEMENTATION:":[177],"A":[178],"prototype":[179],"implementation":[180],"provided":[182],"at":[183,193],"https://github.com/KoslickiLab/L2-UniFrac.git.":[184],"All":[185],"figures,":[186],"data,":[187],"analysis":[189],"reproduced":[192],"https://github.com/KoslickiLab/L2-UniFrac-Paper.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2023-07-01T00:00:00"}
