{"id":"https://openalex.org/W7213780244","doi":"https://doi.org/10.64898/2026.09.14.748778","title":"Scaling Functional Annotation Across Proteomes, Pangenomes and Metagenomes with Sma3s v3","display_name":"Scaling Functional Annotation Across Proteomes, Pangenomes and Metagenomes with Sma3s v3","publication_year":2026,"publication_date":"2026-09-19","ids":{"openalex":"https://openalex.org/W7213780244","doi":"https://doi.org/10.64898/2026.09.14.748778"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.14.748778","doi":"https://doi.org/10.64898/2026.09.14.748778","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.14.748778","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/19/2026.09.14.748778.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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/2026/09/19/2026.09.14.748778.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028633787","display_name":"Alejandro Rubio","orcid":"https://orcid.org/0000-0002-6736-6141","observed_orcids":["https://orcid.org/0000-0002-6736-6141"]},"institutions":[{"id":"https://openalex.org/I2801357902","display_name":"Instituto de Salud Carlos III","ror":"https://ror.org/00ca2c886","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I2801357902","https://openalex.org/I4387152914"]},{"id":"https://openalex.org/I4210086910","display_name":"Fundaci\u00f3n Progreso y Salud","ror":"https://ror.org/0048t7e91","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210086910","https://openalex.org/I4210152975","https://openalex.org/I918821925"]},{"id":"https://openalex.org/I4210111366","display_name":"Centre for Biomedical Network Research on Rare Diseases","ror":"https://ror.org/01ygm5w19","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210111366"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alejandro Rubio","raw_affiliation_strings":["Andalusian Platform for Computational Medicine, Andalusian Public Foundation Progress and Health-FPS, Seville, Spain","Centro de Investigaci\u00f3n Biom\u00e9dica en Red de Enfermedades Raras (CIBERER-ISCIII), U715, Seville, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Andalusian Platform for Computational Medicine, Andalusian Public Foundation Progress and Health-FPS, Seville, Spain","institution_ids":["https://openalex.org/I4210086910"]},{"raw_affiliation_string":"Centro de Investigaci\u00f3n Biom\u00e9dica en Red de Enfermedades Raras (CIBERER-ISCIII), U715, Seville, Spain","institution_ids":["https://openalex.org/I2801357902","https://openalex.org/I4210111366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144220820","display_name":"Jes\u00fas L Garc\u00eda-Junco Alcal\u00e1","orcid":"https://orcid.org/0009-0003-0581-7714","observed_orcids":["https://orcid.org/0009-0003-0581-7714"]},"institutions":[{"id":"https://openalex.org/I4210111405","display_name":"Centro Andaluz de Biolog\u00eda del Desarrollo","ror":"https://ror.org/01v5e3436","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210111405","https://openalex.org/I918821925","https://openalex.org/I95013407"]},{"id":"https://openalex.org/I95013407","display_name":"Universidad Pablo de Olavide","ror":"https://ror.org/02z749649","country_code":"ES","type":"education","lineage":["https://openalex.org/I95013407"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jesus L. Garc\u00eda-Junco Alcal\u00e1","raw_affiliation_strings":["Andalusian Centre for Developmental Biology (CABD, UPO-CSIC-JA), Faculty of Experimental Sciences (Genetics Area), University Pablo de Olavide, Avda. Rectora Rosario Valpuesta, 1 41089 Dos Hermanas-Sevilla (Espa\u00f1a)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Andalusian Centre for Developmental Biology (CABD, UPO-CSIC-JA), Faculty of Experimental Sciences (Genetics Area), University Pablo de Olavide, Avda. Rectora Rosario Valpuesta, 1 41089 Dos Hermanas-Sevilla (Espa\u00f1a)","institution_ids":["https://openalex.org/I4210111405","https://openalex.org/I95013407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119895599","display_name":"Elisa Luque-Jim\u00e9nez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210111405","display_name":"Centro Andaluz de Biolog\u00eda del Desarrollo","ror":"https://ror.org/01v5e3436","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210111405","https://openalex.org/I918821925","https://openalex.org/I95013407"]},{"id":"https://openalex.org/I95013407","display_name":"Universidad Pablo de Olavide","ror":"https://ror.org/02z749649","country_code":"ES","type":"education","lineage":["https://openalex.org/I95013407"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Elisa Luque-Jim\u00e9nez","raw_affiliation_strings":["Andalusian Centre for Developmental Biology (CABD, UPO-CSIC-JA), Faculty of Experimental Sciences (Genetics Area), University Pablo de Olavide, Avda. Rectora Rosario Valpuesta, 1 41089 Dos Hermanas-Sevilla (Espa\u00f1a)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Andalusian Centre for Developmental Biology (CABD, UPO-CSIC-JA), Faculty of Experimental Sciences (Genetics Area), University Pablo de Olavide, Avda. Rectora Rosario Valpuesta, 1 41089 Dos Hermanas-Sevilla (Espa\u00f1a)","institution_ids":["https://openalex.org/I4210111405","https://openalex.org/I95013407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152273106","display_name":"Angel Martin Dominguez","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Angel Martin Dominguez","raw_affiliation_strings":["BiotaScope"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BiotaScope","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136761968","display_name":"Joaqu\u00edn Dopazo","orcid":"https://orcid.org/0000-0003-3318-120X","observed_orcids":["https://orcid.org/0000-0003-3318-120X"]},"institutions":[{"id":"https://openalex.org/I4210086910","display_name":"Fundaci\u00f3n Progreso y Salud","ror":"https://ror.org/0048t7e91","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210086910","https://openalex.org/I4210152975","https://openalex.org/I918821925"]},{"id":"https://openalex.org/I4210128274","display_name":"Barcelona\u03b2eta Brain Research Center","ror":"https://ror.org/03k4wdb90","country_code":"ES","type":"facility","lineage":["https://openalex.org/I170486558","https://openalex.org/I4210107429","https://openalex.org/I4210128274"]},{"id":"https://openalex.org/I4210156109","display_name":"Hospital del Mar Research Institute","ror":"https://ror.org/042nkmz09","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210156109","https://openalex.org/I4387153040"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Joaqu\u00edn Dopazo","raw_affiliation_strings":["Andalusian Platform for Computational Medicine, Andalusian Public Foundation Progress and Health-FPS, Seville, Spain","Barcelona\u03b2eta Brain Research Center, Barcelona, Spain","Hospital del Mar Research Institute Barcelona (HMRIB), Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Andalusian Platform for Computational Medicine, Andalusian Public Foundation Progress and Health-FPS, Seville, Spain","institution_ids":["https://openalex.org/I4210086910"]},{"raw_affiliation_string":"Barcelona\u03b2eta Brain Research Center, Barcelona, Spain","institution_ids":["https://openalex.org/I4210128274"]},{"raw_affiliation_string":"Hospital del Mar Research Institute Barcelona (HMRIB), Barcelona, Spain","institution_ids":["https://openalex.org/I4210156109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029314813","display_name":"Antonio J. P\u00e9rez\u2010Pulido","orcid":"https://orcid.org/0000-0003-3343-2822","observed_orcids":["https://orcid.org/0000-0003-3343-2822"]},"institutions":[{"id":"https://openalex.org/I4210111405","display_name":"Centro Andaluz de Biolog\u00eda del Desarrollo","ror":"https://ror.org/01v5e3436","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210111405","https://openalex.org/I918821925","https://openalex.org/I95013407"]},{"id":"https://openalex.org/I95013407","display_name":"Universidad Pablo de Olavide","ror":"https://ror.org/02z749649","country_code":"ES","type":"education","lineage":["https://openalex.org/I95013407"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Antonio J. Perez-Pulido","raw_affiliation_strings":["Andalusian Centre for Developmental Biology (CABD, UPO-CSIC-JA), Faculty of Experimental Sciences (Genetics Area), University Pablo de Olavide, Avda. Rectora Rosario Valpuesta, 1 41089 Dos Hermanas-Sevilla (Espa\u00f1a)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Andalusian Centre for Developmental Biology (CABD, UPO-CSIC-JA), Faculty of Experimental Sciences (Genetics Area), University Pablo de Olavide, Avda. Rectora Rosario Valpuesta, 1 41089 Dos Hermanas-Sevilla (Espa\u00f1a)","institution_ids":["https://openalex.org/I4210111405","https://openalex.org/I95013407"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081405880","display_name":"Carlos S. Casimiro\u2010Soriguer","orcid":"https://orcid.org/0000-0003-1774-2580","observed_orcids":["https://orcid.org/0000-0003-1774-2580"]},"institutions":[{"id":"https://openalex.org/I4210086910","display_name":"Fundaci\u00f3n Progreso y Salud","ror":"https://ror.org/0048t7e91","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210086910","https://openalex.org/I4210152975","https://openalex.org/I918821925"]},{"id":"https://openalex.org/I4210133602","display_name":"Instituto de Biomedicina de Sevilla","ror":"https://ror.org/031zwx660","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I158283456","https://openalex.org/I4210133602","https://openalex.org/I79238269","https://openalex.org/I918821925"]},{"id":"https://openalex.org/I4210153139","display_name":"Hospital Universitario Virgen del Roc\u00edo","ror":"https://ror.org/04vfhnm78","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210153139"]},{"id":"https://openalex.org/I79238269","display_name":"Universidad de Sevilla","ror":"https://ror.org/03yxnpp24","country_code":"ES","type":"education","lineage":["https://openalex.org/I79238269"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos S. Casimiro-Soriguer","raw_affiliation_strings":["Andalusian Platform for Computational Medicine, Andalusian Public Foundation Progress and Health-FPS, Seville, Spain","Institute of Biomedicine of Seville, IBiS, University Hospital Virgen del Roc\u00edo/CSIC/University of Sevilla, 41013 Sevilla, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Andalusian Platform for Computational Medicine, Andalusian Public Foundation Progress and Health-FPS, Seville, Spain","institution_ids":["https://openalex.org/I4210086910"]},{"raw_affiliation_string":"Institute of Biomedicine of Seville, IBiS, University Hospital Virgen del Roc\u00edo/CSIC/University of Sevilla, 41013 Sevilla, Spain","institution_ids":["https://openalex.org/I4210133602","https://openalex.org/I4210153139","https://openalex.org/I79238269"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5029314813"],"corresponding_institution_ids":["https://openalex.org/I4210111405","https://openalex.org/I95013407"],"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":0.9916999936103821,"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":0.9916999936103821,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.004900000058114529,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.00039999998989515007,"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/protein-function-annotation","display_name":"protein annotation","score":0.8709999918937683},{"id":"https://openalex.org/keywords/pan-genome","display_name":"pan-genome","score":0.5270000100135803},{"id":"https://openalex.org/keywords/mmseqs2","display_name":"MMseqs2","score":0.8539999723434448},{"id":"https://openalex.org/keywords/vibrio-cholerae","display_name":"Vibrio cholerae","score":0.7279999852180481},{"id":"https://openalex.org/keywords/horizontal-gene-transfer","display_name":"horizontal gene transfer","score":0.8600000143051147},{"id":"https://openalex.org/keywords/gene-clusters","display_name":"gene clusters","score":0.574999988079071},{"id":"https://openalex.org/keywords/gene-ontology","display_name":"Gene Ontology","score":0.8460000157356262}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8578000068664551},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.7910000085830688},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6678000092506409},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.6061999797821045},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5735999941825867},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5501000285148621},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5232999920845032},{"id":"https://openalex.org/C89566754","wikidata":"https://www.wikidata.org/wiki/Q2273828","display_name":"Genome project","level":4,"score":0.49309998750686646},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C2987395477","wikidata":"https://www.wikidata.org/wiki/Q135085","display_name":"Gene ontology","level":4,"score":0.45190000534057617},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4449000060558319},{"id":"https://openalex.org/C152724338","wikidata":"https://www.wikidata.org/wiki/Q909442","display_name":"KEGG","level":5,"score":0.4198000133037567},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.34950000047683716},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.3336000144481659},{"id":"https://openalex.org/C92938381","wikidata":"https://www.wikidata.org/wiki/Q83185","display_name":"Horizontal gene transfer","level":4,"score":0.3077999949455261},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.28929999470710754},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.2888999879360199},{"id":"https://openalex.org/C178180057","wikidata":"https://www.wikidata.org/wiki/Q7251477","display_name":"Protein superfamily","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C190944805","wikidata":"https://www.wikidata.org/wiki/Q3922751","display_name":"Human Microbiome Project","level":4,"score":0.2782999873161316},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C2778643871","wikidata":"https://www.wikidata.org/wiki/Q160821","display_name":"Vibrio cholerae","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.25529998540878296},{"id":"https://openalex.org/C2778458500","wikidata":"https://www.wikidata.org/wiki/Q135183","display_name":"Vibrio vulnificus","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.14.748778","doi":"https://doi.org/10.64898/2026.09.14.748778","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.14.748778","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/19/2026.09.14.748778.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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.14.748778","doi":"https://doi.org/10.64898/2026.09.14.748778","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.14.748778","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/19/2026.09.14.748778.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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213780244.pdf","grobid_xml":"https://content.openalex.org/works/W7213780244.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1517724123","https://openalex.org/W1796085206","https://openalex.org/W1969934618","https://openalex.org/W1973012451","https://openalex.org/W1980948656","https://openalex.org/W2069372034","https://openalex.org/W2100320834","https://openalex.org/W2100761975","https://openalex.org/W2107772251","https://openalex.org/W2117486996","https://openalex.org/W2126317773","https://openalex.org/W2128049108","https://openalex.org/W2131163504","https://openalex.org/W2166637863","https://openalex.org/W2180695509","https://openalex.org/W2559998249","https://openalex.org/W2616925367","https://openalex.org/W2765745983","https://openalex.org/W2799910753","https://openalex.org/W2815500692","https://openalex.org/W2950954328","https://openalex.org/W2968334948","https://openalex.org/W2981233334","https://openalex.org/W2989608901","https://openalex.org/W2990427812","https://openalex.org/W3024553150","https://openalex.org/W3042305844","https://openalex.org/W3045244624","https://openalex.org/W3048272826","https://openalex.org/W3109735703","https://openalex.org/W3159504416","https://openalex.org/W3164712750","https://openalex.org/W3172496429","https://openalex.org/W3203343200","https://openalex.org/W3209528471","https://openalex.org/W4251386234","https://openalex.org/W4289959859","https://openalex.org/W4294001681","https://openalex.org/W4310957810","https://openalex.org/W4321611856","https://openalex.org/W4375858802","https://openalex.org/W4386923678","https://openalex.org/W4387541035","https://openalex.org/W4388592083","https://openalex.org/W4389890051","https://openalex.org/W4391821988","https://openalex.org/W4392469688","https://openalex.org/W4393342758","https://openalex.org/W4393932945","https://openalex.org/W4402098128","https://openalex.org/W4403487712","https://openalex.org/W4404458588","https://openalex.org/W4404474315","https://openalex.org/W4404531735","https://openalex.org/W4405907961","https://openalex.org/W4408113117","https://openalex.org/W4409525624","https://openalex.org/W4410872352","https://openalex.org/W4417524991"],"related_works":["https://openalex.org/W2616925367","https://openalex.org/W2126317773","https://openalex.org/W7055734124","https://openalex.org/W3096331141","https://openalex.org/W3119059272","https://openalex.org/W2100816892","https://openalex.org/W1975879553","https://openalex.org/W2169230701","https://openalex.org/W4406799200","https://openalex.org/W2949841808"],"abstract_inverted_index":{"Abstract":[0],"High-throughput":[1],"sequencing":[2],"has":[3],"generated":[4],"protein":[5,168,234],"datasets":[6],"whose":[7],"scale":[8],"increasingly":[9],"exceeds":[10],"the":[11,27,68,75,150,190],"practical":[12],"limits":[13],"of":[14,26,229],"conventional":[15],"functional":[16,42,211,225],"annotation":[17,30,152,226],"workflows.":[18],"We":[19,73],"present":[20],"Sma3s":[21,28,47,102,136,193,216],"v3,":[22],"a":[23,78,92,219],"scalable":[24,220],"reimplementation":[25],"three-step":[29],"strategy,":[31],"which":[32],"combines":[33],"transfer":[34],"from":[35,86],"highly":[36],"similar":[37],"homologs,":[38],"orthology-based":[39],"inference,":[40],"and":[41,54,63,90,113,146,159,164,185,206,221,227,232],"enrichment":[43],"among":[44],"homologous":[45],"proteins.":[46,97],"v3":[48,103,137,194,217],"replaces":[49],"BLAST-based":[50],"searches":[51],"with":[52,135,200],"MMseqs2":[53],"introduces":[55],"parallel":[56],"processing,":[57],"reusable":[58],"SQLite":[59],"caches,":[60],"taxonomic":[61],"filtering,":[62],"traceable":[64],"outputs":[65],"that":[66],"retain":[67],"evidence":[69],"underlying":[70],"each":[71],"assignment.":[72],"evaluated":[74],"method":[76],"on":[77,91],"Vibrio":[79],"cholerae":[80],"pangenome":[81,106],"comprising":[82],"50,415":[83],"gene":[84],"clusters":[85,107,158,178],"11,295":[87],"quality-filtered":[88],"genomes":[89],"metagenomic":[93,191,233],"catalogue":[94],"containing":[95],"843,935":[96],"After":[98],"excluding":[99],"non-informative":[100],"assignments,":[101],"annotated":[104,195],"30,662":[105],"(60.8%),":[108],"comparable":[109],"to":[110,170],"InterProScan":[111,204],"(60.2%)":[112],"exceeding":[114],"eggNOG-mapper":[115],"(41.4%),":[116],"while":[117],"providing":[118],"5,747":[119],"annotations":[120],"not":[121],"recovered":[122,207],"by":[123],"either":[124],"comparator.":[125],"Gene":[126],"Ontology":[127],"comparisons":[128],"showed":[129],"broad":[130],"semantic":[131],"agreement":[132],"between":[133],"methods,":[134],"frequently":[138],"contributing":[139],"more":[140],"non-redundant":[141],"information":[142],"in":[143,180],"Molecular":[144],"Function":[145],"Biological":[147],"Process.":[148],"Within":[149],"pangenome,":[151],"coverage":[153],"reached":[154],"97.1%":[155],"for":[156,162,224],"core":[157],"approximately":[160,208],"59%":[161],"accessory":[163],"unique":[165,210],"clusters.":[166],"Exact":[167],"matches":[169],"non-Vibrio":[171],"genera":[172],"identified":[173],"1,838":[174],"candidate":[175],"horizontally":[176],"transferred":[177],"enriched":[179],"genetic":[181],"mobility,":[182],"antimicrobial":[183],"resistance,":[184],"metal":[186],"tolerance":[187],"functions.":[188],"In":[189],"catalogue,":[192],"728,014":[196],"proteins":[197],"(86.3%),":[198],"compared":[199],"616,895":[201],"(73.1%)":[202],"using":[203],"2026,":[205],"20,000":[209],"terms.":[212],"These":[213],"results":[214],"establish":[215],"as":[218],"interpretable":[222],"tool":[223],"re-annotation":[228],"proteomes,":[230],"pangenomes,":[231],"catalogues.":[235]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-21T00:00:00"}