{"id":"https://openalex.org/W7213982299","doi":"https://doi.org/10.64898/2026.09.17.752478","title":"Vritra: gene-specific reference construction for species-resolved functional profiling of metagenomic and metatranscriptomic data","display_name":"Vritra: gene-specific reference construction for species-resolved functional profiling of metagenomic and metatranscriptomic data","publication_year":2026,"publication_date":"2026-09-21","ids":{"openalex":"https://openalex.org/W7213982299","doi":"https://doi.org/10.64898/2026.09.17.752478"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.17.752478","doi":"https://doi.org/10.64898/2026.09.17.752478","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.752478","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/21/2026.09.17.752478.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":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/21/2026.09.17.752478.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047437386","display_name":"Boyan Zhou","orcid":"https://orcid.org/0000-0001-7067-4578","observed_orcids":["https://orcid.org/0000-0001-7067-4578"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boyan Zhou","raw_affiliation_strings":["Division of Biostatistics, Department of Population Health, New York University School of Medicine, New York, New York 10016, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biostatistics, Department of Population Health, New York University School of Medicine, New York, New York 10016, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152874113","display_name":"Menghan Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Menghan Liu","raw_affiliation_strings":["Department of Biological Sciences, Columbia University in the City of New York, New York, NY, 10027, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Columbia University in the City of New York, New York, NY, 10027, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051186379","display_name":"Gary C. Curhan","orcid":"https://orcid.org/0000-0001-7386-6305","observed_orcids":["https://orcid.org/0000-0001-7386-6305"]},"institutions":[{"id":"https://openalex.org/I1283280774","display_name":"Brigham and Women's Hospital","ror":"https://ror.org/04b6nzv94","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I121934306","https://openalex.org/I1283280774","https://openalex.org/I48633490"]},{"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":false,"raw_author_name":"Gary Curhan","raw_affiliation_strings":["Department of Medicine, Brigham and Women\u2019s Hospital, Harvard Medical School, Boston, MA 02115, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicine, Brigham and Women\u2019s Hospital, Harvard Medical School, Boston, MA 02115, USA","institution_ids":["https://openalex.org/I1283280774","https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152430422","display_name":"gregory Peck","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory Peck","raw_affiliation_strings":["Department of Surgery, Robert Wood Johnson Medical School, Rutgers University, New Brunswick, NJ 08901, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Surgery, Robert Wood Johnson Medical School, Rutgers University, New Brunswick, NJ 08901, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087655468","display_name":"Hyon K. Choi","orcid":"https://orcid.org/0000-0002-2862-0442","observed_orcids":["https://orcid.org/0000-0002-2862-0442"]},"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"]},{"id":"https://openalex.org/I4210087915","display_name":"Massachusetts General Hospital","ror":"https://ror.org/002pd6e78","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210087915","https://openalex.org/I48633490"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyon Choi","raw_affiliation_strings":["Division of Rheumatology, Allergy and Immunology, Department of Medicine, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02115, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Rheumatology, Allergy and Immunology, Department of Medicine, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02115, USA","institution_ids":["https://openalex.org/I136199984","https://openalex.org/I4210087915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086593391","display_name":"Lama Nazzal","orcid":"https://orcid.org/0000-0003-0106-5060","observed_orcids":["https://orcid.org/0000-0003-0106-5060"]},"institutions":[{"id":"https://openalex.org/I4210086933","display_name":"NYU Langone Health","ror":"https://ror.org/005dvqh91","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210086933"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lama Nazzal","raw_affiliation_strings":["Department of Medicine, Division of Nephrology, NYU Langone Medical Center, New York, NY, 10016, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicine, Division of Nephrology, NYU Langone Medical Center, New York, NY, 10016, USA","institution_ids":["https://openalex.org/I4210086933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100710993","display_name":"Huilin Li","orcid":"https://orcid.org/0000-0002-8288-7068","observed_orcids":["https://orcid.org/0000-0002-8288-7068"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Huilin Li","raw_affiliation_strings":["Division of Biostatistics, Department of Population Health, New York University School of Medicine, New York, New York 10016, USA"],"raw_orcid":"https://orcid.org/0000-0002-8288-7068","affiliations":[{"raw_affiliation_string":"Division of Biostatistics, Department of Population Health, New York University School of Medicine, New York, New York 10016, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100710993"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9775000214576721,"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":0.9775000214576721,"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/T10066","display_name":"Gut microbiota and health","score":0.016499999910593033,"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":0.0024999999441206455,"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":0.9179999828338623},{"id":"https://openalex.org/keywords/metatranscriptomics","display_name":"metatranscriptomics","score":1.0},{"id":"https://openalex.org/keywords/sequence-similarity-networks","display_name":"sequence similarity networks","score":0.7039999961853027},{"id":"https://openalex.org/keywords/microbial-taxonomy","display_name":"microbial taxonomy","score":0.6759999990463257},{"id":"https://openalex.org/keywords/oxalate-metabolism","display_name":"oxalate metabolism","score":0.8180000185966492},{"id":"https://openalex.org/keywords/uric-acid-metabolism","display_name":"uric acid metabolism","score":0.9950000047683716},{"id":"https://openalex.org/keywords/bile-acid-metabolism","display_name":"bile acid metabolism","score":0.9990000128746033},{"id":"https://openalex.org/keywords/microbiome","display_name":"microbiome","score":0.5220000147819519}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.8704000115394592},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.7495999932289124},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.7330999970436096},{"id":"https://openalex.org/C190944805","wikidata":"https://www.wikidata.org/wiki/Q3922751","display_name":"Human Microbiome Project","level":4,"score":0.6958000063896179},{"id":"https://openalex.org/C143121216","wikidata":"https://www.wikidata.org/wiki/Q1330402","display_name":"Microbiome","level":2,"score":0.5924000144004822},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5759999752044678},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.3594000041484833},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.3555000126361847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3370000123977661},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.2971000075340271},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C91478284","wikidata":"https://www.wikidata.org/wiki/Q6623796","display_name":"Human microbiome","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C18431079","wikidata":"https://www.wikidata.org/wiki/Q1502169","display_name":"Gene expression profiling","level":4,"score":0.2842999994754791},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.28279998898506165},{"id":"https://openalex.org/C48702757","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Biological classification","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.2614000141620636},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.17.752478","doi":"https://doi.org/10.64898/2026.09.17.752478","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.752478","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/21/2026.09.17.752478.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":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.17.752478","doi":"https://doi.org/10.64898/2026.09.17.752478","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.752478","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/21/2026.09.17.752478.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":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000865389","display_name":"The role of the microbiome and other host related factors in determining urine oxalate levels","funder_award_id":"R01DK137473","funder_id":"https://openalex.org/F4320337357","funder_display_name":"National Institute of Diabetes and Digestive and Kidney Diseases"},{"id":"https://openalex.org/G9000877880","display_name":"Novel Computational Methods for Microbiome Data Analysis in Longitudinal Study","funder_award_id":"R01LM014085","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337357","display_name":"National Institute of Diabetes and Digestive and Kidney Diseases","ror":"https://ror.org/00adh9b73"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213982299.pdf","grobid_xml":"https://content.openalex.org/works/W7213982299.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4310663915","https://openalex.org/W3152849815","https://openalex.org/W4315796969","https://openalex.org/W2112701562","https://openalex.org/W2124927293","https://openalex.org/W7131061801","https://openalex.org/W2131026689","https://openalex.org/W7196942065","https://openalex.org/W2037540348","https://openalex.org/W7220371308"],"abstract_inverted_index":{"Abstract":[0],"Species-resolved":[1],"profiling":[2,20,169,239,313,355],"of":[3,116,143,170,314],"microbial":[4,11,101,178,221,280,316,325,346],"functional":[5,19,83,171,238,276,354],"genes":[6,29,77,104,126,153,172,205,251,277,303],"is":[7,215],"important":[8],"for":[9,56,61,74,123,150,190,200,236,244,269,344],"linking":[10],"community":[12],"composition":[13],"to":[14,25,90,99,148,160,218,290,332],"biological":[15],"function,":[16],"but":[17,240],"existing":[18],"approaches":[21,232],"are":[22,233,252],"not":[23],"designed":[24],"systematically":[26],"define":[27],"user-specified":[28,75,299],"and":[30,51,63,68,82,94,109,162,173,182,293,296,330,335],"resolve":[31],"their":[32],"contributing":[33],"species.":[34],"We":[35],"developed":[36],"Vritra":[37,66,113,185,261,318],"(":[38],"V":[39],"ersatile":[40],"gene-guided":[41],"R":[42,49],"eads-identification":[43],"with":[44,177,278],"I":[45],"mpartial":[46],"T":[47],"axonomic":[48],"efinement":[50],"A":[52],"ssignment),":[53],"a":[54,187,267,341],"framework":[55,189,268,339],"constructing":[57],"gene-specific":[58,175,271],"reference":[59,259,272],"databases":[60,273],"metagenomic":[62,292],"metatranscriptomic":[64,294],"data.":[65],"expands":[67],"refines":[69],"the":[70,96,130,138,279],"UniRef-based":[71],"sequence":[72,132,157,194],"space":[73],"target":[76,300],"using":[78],"sequence-similarity":[79],"network":[80],"connectivity":[81],"annotations,":[84],"retains":[85],"related":[86],"homologs":[87],"as":[88],"decoys":[89],"reduce":[91],"assignment":[92],"ambiguity,":[93],"links":[95],"resulting":[97],"sequences":[98,117],"standardized":[100],"taxonomy.":[102],"Across":[103],"involved":[105],"in":[106,227],"oxalate,":[107],"urate,":[108],"bile":[110],"acid":[111],"metabolism,":[112],"recovered":[114],">97%":[115],"represented":[118,131,256],"by":[119,146,265,352],"established":[120],"annotation":[121],"resources":[122,195],"most":[124],"evaluated":[125],"while":[127,154],"substantially":[128],"expanding":[129,193],"space.":[133],"In":[134],"real":[135],"microbiome":[136,165,201,229],"datasets,":[137],"expanded":[139],"references":[140,199],"increased":[141],"recovery":[142],"target-gene":[144],"reads":[145],"up":[147],"threefold":[149],"poorly":[151,253],"annotated":[152],"maintaining":[155],"high":[156],"identity.":[158],"Application":[159],"population-based":[161],"publicly":[163],"available":[164],"datasets":[166],"enabled":[167],"species-resolved":[168,198,312],"revealed":[174],"associations":[176],"taxa,":[179],"dietary":[180],"factors,":[181],"disease-related":[183,336],"phenotypes.":[184],"provides":[186,340],"scalable":[188],"translating":[191],"continuously":[192],"into":[196],"gene-specific,":[197],"studies.":[202],"Importance":[203],"Microbial":[204],"encode":[206],"functions":[207,226,347],"that":[208,274,282,348],"can":[209,287,297,319],"influence":[210],"human":[211],"health,":[212],"yet":[213],"it":[214],"often":[216],"difficult":[217],"determine":[219],"which":[220],"species":[222,281],"carry":[223,283],"out":[224],"specific":[225,324],"complex":[228],"communities.":[230],"Existing":[231],"well":[234],"suited":[235],"broad":[237,353],"provide":[241],"limited":[242],"flexibility":[243],"studying":[245,345],"individual":[246],"genes,":[247,301],"particularly":[248],"when":[249],"those":[250],"characterized":[254,308],"or":[255,306],"inconsistently":[257],"across":[258,328],"resources.":[260],"addresses":[262],"this":[263],"gap":[264],"providing":[266],"building":[270],"connect":[275],"them.":[284],"The":[285],"approach":[286,343],"be":[288,350],"applied":[289],"both":[291],"data":[295],"accommodate":[298],"including":[302],"from":[304],"emerging":[305],"incompletely":[307],"pathways.":[309],"By":[310],"enabling":[311],"selected":[315],"functions,":[317],"help":[320],"researchers":[321],"investigate":[322],"how":[323],"activities":[326],"vary":[327],"individuals":[329],"relate":[331],"dietary,":[333],"ecological,":[334],"factors.":[337],"This":[338],"practical":[342],"may":[349],"overlooked":[351],"methods.":[356]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-09-22T00:00:00"}
