{"id":"https://openalex.org/W7225638945","doi":"https://doi.org/10.64898/2026.11.05.764740","title":"Homology-aware average nucleotide identity estimation at scale with TurboANI","display_name":"Homology-aware average nucleotide identity estimation at scale with TurboANI","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225638945","doi":"https://doi.org/10.64898/2026.11.05.764740"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.05.764740","doi":"https://doi.org/10.64898/2026.11.05.764740","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.05.764740","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.05.764740.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"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/2026/11/09/2026.11.05.764740.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054580805","display_name":"Jianshu Zhao","orcid":"https://orcid.org/0000-0002-2586-3852","observed_orcids":["https://orcid.org/0000-0002-2586-3852"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianshu Zhao","raw_affiliation_strings":["University of California San Diego;"],"raw_orcid":"https://orcid.org/0000-0002-2586-3852","affiliations":[{"raw_affiliation_string":"University of California San Diego;","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022461817","display_name":"Daniel T. McDonald","orcid":"https://orcid.org/0000-0003-0876-9060","observed_orcids":["https://orcid.org/0000-0003-0876-9060"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel McDonald","raw_affiliation_strings":["University of California San Diego;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego;","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042488207","display_name":"Lucas Patel","orcid":"https://orcid.org/0000-0001-8607-2782","observed_orcids":["https://orcid.org/0000-0001-8607-2782"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lucas Patel","raw_affiliation_strings":["University of California San Diego;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego;","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161338141","display_name":"Claire Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claire Wang","raw_affiliation_strings":["University of California San Diego;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego;","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101532298","display_name":"Antonio Gonz\u00e1lez","orcid":"https://orcid.org/0000-0002-5900-3965","observed_orcids":["https://orcid.org/0000-0002-5900-3965"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Gonzalez","raw_affiliation_strings":["University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033881627","display_name":"Rob D. Knight","orcid":"https://orcid.org/0000-0002-0975-9019","observed_orcids":["https://orcid.org/0000-0002-0975-9019","https://orcid.org/0000-0001-7531-0087"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rob Knight","raw_affiliation_strings":["University of California San Diego;"],"raw_orcid":"https://orcid.org/0000-0002-0975-9019","affiliations":[{"raw_affiliation_string":"University of California San Diego;","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5033881627"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"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":0.9940999746322632,"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":0.9940999746322632,"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/T11269","display_name":"Algorithms and Data Compression","score":0.003599999938160181,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.000699999975040555,"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/average-nucleotide-identity","display_name":"average nucleotide identity","score":0.9959999918937683},{"id":"https://openalex.org/keywords/bacterial-strain-classification","display_name":"bacterial strain classification","score":0.5479999780654907}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6820999979972839},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6516000032424927},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5552999973297119},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5347999930381775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5253000259399414},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5220999717712402},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37279999256134033},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.05.764740","doi":"https://doi.org/10.64898/2026.11.05.764740","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.05.764740","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.05.764740.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.05.764740","doi":"https://doi.org/10.64898/2026.11.05.764740","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.05.764740","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.05.764740.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320329315","display_name":"Minderoo Foundation","ror":"https://ror.org/0289t9g81"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337337","display_name":"National Institute on Aging","ror":"https://ror.org/049v75w11"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225638945.pdf","grobid_xml":"https://content.openalex.org/works/W7225638945.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W7163409328"],"related_works":["https://openalex.org/W4412191927","https://openalex.org/W2588775853","https://openalex.org/W6980126643","https://openalex.org/W2206071891","https://openalex.org/W4411256798","https://openalex.org/W7154035708","https://openalex.org/W3137842111","https://openalex.org/W3042353254","https://openalex.org/W4402599632","https://openalex.org/W4400678885"],"abstract_inverted_index":{"Here":[0],"we":[1],"introduce":[2],"TurboANI,":[3],"a":[4,68],"fast":[5],"homology-aware":[6],"average":[7],"nucleotide":[8],"identity":[9],"(ANI)":[10],"estimation":[11],"algorithm":[12,40],"that":[13],"implements":[14],"the":[15,37,50,63],"seed-chain-quasi-alignment":[16],"scheme":[17],"using":[18],"SIMD":[19],"seeding,":[20],"compact":[21],"indexing,":[22],"lightweight":[23],"chaining,":[24],"and":[25,53],"cache-friendly":[26],"bitset":[27],"sliding":[28],"minwise":[29],"hashing,":[30],"achieving":[31],"up":[32],"to":[33],"~40,000-fold":[34],"speedup":[35],"over":[36],"alignment-based":[38],"ANI":[39],"with":[41],"near-perfect":[42],"agreement.":[43],"TurboANI":[44],"is":[45],"also":[46],">40-fold":[47],"faster":[48,55],"than":[49,56,74],"state-of-the-art":[51],"FastANI":[52],"ten-fold":[54,69],"skani":[57],"while":[58],"maintaining":[59],"better":[60],"accuracy.":[61],"In":[62],"sensitive":[64],"mode,":[65],"it":[66],"has":[67],"higher":[70],"true-ANI":[71],"recovery":[72],"rate":[73],"skani.":[75]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}
