{"id":"https://openalex.org/W7223092091","doi":"https://doi.org/10.64898/2026.10.20.760448","title":"Carbon-A: Unified Genome Annotation across Eukaryotic Diversity","display_name":"Carbon-A: Unified Genome Annotation across Eukaryotic Diversity","publication_year":2026,"publication_date":"2026-10-21","ids":{"openalex":"https://openalex.org/W7223092091","doi":"https://doi.org/10.64898/2026.10.20.760448"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.20.760448","doi":"https://doi.org/10.64898/2026.10.20.760448","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.20.760448","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/21/2026.10.20.760448.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":"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/2026/10/21/2026.10.20.760448.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048205675","display_name":"Georgia Channing","orcid":"https://orcid.org/0009-0001-6354-7527","observed_orcids":["https://orcid.org/0009-0001-6354-7527"]},"institutions":[{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":"US","type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georgia Channing","raw_affiliation_strings":["Hugging Face"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hugging Face","institution_ids":["https://openalex.org/I4387154989"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124401516","display_name":"Zhenghang Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405263327","display_name":"The Affiliated High School of Peking University","ror":"https://ror.org/05a2mmm74","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570","https://openalex.org/I4405263327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenghang Shi","raw_affiliation_strings":["The Affiliated High School of Peking University, Beijing, China","Zhongguancun Academy, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Affiliated High School of Peking University, Beijing, China","institution_ids":["https://openalex.org/I4405263327"]},{"raw_affiliation_string":"Zhongguancun Academy, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159177646","display_name":"Xiaoxing Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391768054","display_name":"State Key Laboratory of Membrane Biology","ror":"https://ror.org/03mq8q210","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I20231570","https://openalex.org/I4210167311","https://openalex.org/I4391768054","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxing Zhang","raw_affiliation_strings":["State Key Laboratory of Membrane Biology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Membrane Biology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I4391768054","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021973692","display_name":"Mathieu Morlon","orcid":"https://orcid.org/0009-0003-1899-3522","observed_orcids":["https://orcid.org/0009-0003-1899-3522"]},"institutions":[{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":"US","type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mathieu Morlon","raw_affiliation_strings":["Hugging Face"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hugging Face","institution_ids":["https://openalex.org/I4387154989"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075846365","display_name":"Kashif Rasul","orcid":"https://orcid.org/0000-0003-3016-5386","observed_orcids":["https://orcid.org/0000-0003-3016-5386"]},"institutions":[{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":"US","type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kashif Rasul","raw_affiliation_strings":["Hugging Face"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hugging Face","institution_ids":["https://openalex.org/I4387154989"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021606126","display_name":"Anton Lozhkov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":"US","type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anton Lozhkov","raw_affiliation_strings":["Hugging Face"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hugging Face","institution_ids":["https://openalex.org/I4387154989"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095102135","display_name":"Shikun Feng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikun Feng","raw_affiliation_strings":["Zhongguancun Academy, Beijing, China","Zhongguancun Institute of Artificial Intelligence, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhongguancun Academy, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Zhongguancun Institute of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027903849","display_name":"J Li","orcid":"https://orcid.org/0000-0002-0032-1758","observed_orcids":["https://orcid.org/0000-0002-0032-1758"]},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaoyang Li","raw_affiliation_strings":["Zhongguancun Academy, Beijing, China","Zhongguancun Institute of Artificial Intelligence, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhongguancun Academy, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Zhongguancun Institute of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159163946","display_name":"Haiguang Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiguang Liu","raw_affiliation_strings":["Zhongguancun Academy, Beijing, China","Zhongguancun Institute of Artificial Intelligence, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhongguancun Academy, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Zhongguancun Institute of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001896455","display_name":"Diego di Bernardo","orcid":"https://orcid.org/0000-0002-1911-7407","observed_orcids":["https://orcid.org/0000-0002-1911-7407"]},"institutions":[{"id":"https://openalex.org/I4210152213","display_name":"Telethon Institute Of Genetics And Medicine","ror":"https://ror.org/04xfdsg27","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210152213","https://openalex.org/I4210154366"]},{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Diego di Bernardo","raw_affiliation_strings":["Telethon Institute of Genetics and Medicine (TIGEM), Pozzuoli, Napoli, Italy","University of Naples Federico II, Naples, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Telethon Institute of Genetics and Medicine (TIGEM), Pozzuoli, Napoli, Italy","institution_ids":["https://openalex.org/I4210152213"]},{"raw_affiliation_string":"University of Naples Federico II, Naples, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044192296","display_name":"Nieng Yan","orcid":"https://orcid.org/0000-0003-4829-7416","observed_orcids":["https://orcid.org/0000-0003-4829-7416"]},"institutions":[{"id":"https://openalex.org/I4391768054","display_name":"State Key Laboratory of Membrane Biology","ror":"https://ror.org/03mq8q210","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I20231570","https://openalex.org/I4210167311","https://openalex.org/I4391768054","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nieng Yan","raw_affiliation_strings":["Institute of Bio-Architecture and Bio-Interactions (IBABI), Shenzhen, Guangdong, China","State Key Laboratory of Membrane Biology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Bio-Architecture and Bio-Interactions (IBABI), Shenzhen, Guangdong, China","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Membrane Biology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I4391768054","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124421726","display_name":"Tao Qin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qin","raw_affiliation_strings":["Zhongguancun Academy, Beijing, China","Zhongguancun Institute of Artificial Intelligence, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhongguancun Academy, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Zhongguancun Institute of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5156391379","display_name":"Thomas Wolf","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":"US","type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Wolf","raw_affiliation_strings":["Hugging Face"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hugging Face","institution_ids":["https://openalex.org/I4387154989"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008355834","display_name":"Leandro von Werra","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":"US","type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leandro von Werra","raw_affiliation_strings":["Hugging Face"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hugging Face","institution_ids":["https://openalex.org/I4387154989"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032831634","display_name":"Qiuyi Li","orcid":"https://orcid.org/0000-0002-6856-6831","observed_orcids":["https://orcid.org/0000-0002-6856-6831"]},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiuyi Li","raw_affiliation_strings":["Zhongguancun Academy, Beijing, China","Zhongguancun Institute of Artificial Intelligence, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6856-6831","affiliations":[{"raw_affiliation_string":"Zhongguancun Academy, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Zhongguancun Institute of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5032831634"],"corresponding_institution_ids":["https://openalex.org/I4210100255"],"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":0.9961000084877014,"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":0.9961000084877014,"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":0.0017999999690800905,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0003000000142492354,"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-coding-gene-prediction","display_name":"protein-coding gene prediction","score":0.8730000257492065},{"id":"https://openalex.org/keywords/eukaryotic-genome-annotation","display_name":"eukaryotic genome annotation","score":0.6430000066757202},{"id":"https://openalex.org/keywords/cross-domain-prediction","display_name":"cross-domain prediction","score":0.5979999899864197},{"id":"https://openalex.org/keywords/gene-discovery","display_name":"gene discovery","score":0.6899999976158142},{"id":"https://openalex.org/keywords/genomic-language-models","display_name":"genomic language models","score":0.6800000071525574},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.5770000219345093}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8267999887466431},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.6165000200271606},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6039000153541565},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6021000146865845},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.597100019454956},{"id":"https://openalex.org/C79029880","wikidata":"https://www.wikidata.org/wiki/Q901755","display_name":"GenBank","level":3,"score":0.5687000155448914},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.525600016117096},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.5232999920845032},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C89566754","wikidata":"https://www.wikidata.org/wiki/Q2273828","display_name":"Genome project","level":4,"score":0.4108999967575073},{"id":"https://openalex.org/C105176652","wikidata":"https://www.wikidata.org/wiki/Q1147112","display_name":"Comparative genomics","level":5,"score":0.38499999046325684},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3840000033378601},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.3767000138759613},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35030001401901245},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.3294999897480011},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.31520000100135803},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.2976999878883362},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.287200003862381},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.2515999972820282},{"id":"https://openalex.org/C149034497","wikidata":"https://www.wikidata.org/wiki/Q1384835","display_name":"Expressed sequence tag","level":4,"score":0.2513999938964844},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.20.760448","doi":"https://doi.org/10.64898/2026.10.20.760448","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.20.760448","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/21/2026.10.20.760448.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.20.760448","doi":"https://doi.org/10.64898/2026.10.20.760448","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.20.760448","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/21/2026.10.20.760448.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223092091.pdf","grobid_xml":"https://content.openalex.org/works/W7223092091.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1978683904","https://openalex.org/W2129161084","https://openalex.org/W2135230723","https://openalex.org/W3162875552","https://openalex.org/W3177828909","https://openalex.org/W3195577433","https://openalex.org/W4327550249","https://openalex.org/W4396721167","https://openalex.org/W4404458588","https://openalex.org/W4405231264","https://openalex.org/W4407424297","https://openalex.org/W7162319355"],"related_works":["https://openalex.org/W7160064876","https://openalex.org/W4385446919","https://openalex.org/W3119984181","https://openalex.org/W7124993521","https://openalex.org/W4384405844","https://openalex.org/W7125483477","https://openalex.org/W2078942911","https://openalex.org/W4380320469","https://openalex.org/W2896066313","https://openalex.org/W7160152549"],"abstract_inverted_index":{"Abstract":[0],"Structural":[1],"genome":[2,123],"annotation":[3,220],"remains":[4,95],"a":[5,42,48,218,227,233],"bottleneck":[6],"in":[7,97,125],"eukaryotic":[8,63,122],"genomics":[9],"as":[10,164,170,173],"conventional":[11],"methods":[12],"depend":[13],"on":[14],"external":[15],"evidence":[16,191],"that":[17,46],"is":[18],"unevenly":[19],"available":[20],"across":[21,59],"the":[22,60,80,90,129],"tree":[23],"of":[24,62,145],"life,":[25],"and":[26,72,85,99,104,142,154,167,215,232,239],"existing":[27],"ab":[28],"initio":[29],"predictors":[30],"are":[31],"typically":[32],"specialized":[33],"for":[34,109,192,222,229,236],"particular":[35],"taxonomic":[36],"groups.":[37],"We":[38],"introduce":[39],"Carbon-Annotator":[40],"(Carbon-A),":[41],"1.2-billion-parameter":[43],"encoder":[44],"model":[45],"uses":[47],"single":[49],"checkpoint":[50],"to":[51,120,127,204],"annotate":[52],"protein-coding":[53,152],"genes":[54],"directly":[55],"from":[56,185,197],"genomic":[57,146,238],"sequences":[58],"breadth":[61],"diversity,":[64],"including":[65],"mammals,":[66],"other":[67],"vertebrates,":[68],"invertebrates,":[69],"plants,":[70],"fungi,":[71],"protozoa.":[73],"Across":[74],"42":[75],"benchmark":[76,177],"genomes,":[77],"Carbon-A":[78,119,193,214],"achieves":[79],"highest":[81],"overall":[82],"nucleotide-,":[83],"exon-,":[84],"gene-level":[86],"F1":[87],"scores":[88,108],"among":[89],"evaluated":[91],"models.":[92,242],"It":[93],"also":[94],"robust":[96],"cross-domain":[98],"nonstandard":[100],"genetic":[101],"code":[102],"evaluations":[103],"provides":[105],"per-gene":[106],"confidence":[107],"ranking":[110],"prediction":[111],"reliability.":[112],"Given":[113],"its":[114,202],"demonstrated":[115],"performance,":[116],"we":[117,179],"apply":[118],"all":[121],"assemblies":[124,138],"GenBank":[126],"build":[128],"Carbon":[130],"Annotation":[131],"Database":[132],"(CADB),":[133],"which":[134],"currently":[135],"contains":[136],"48,167":[137],"representing":[139],"22,617":[140],"taxa":[141,172],"27.18":[143],"Tbp":[144],"sequence,":[147],"with":[148],"566.34":[149],"million":[150],"predicted":[151],"loci":[153],"their":[155],"translated":[156],"protein":[157,240],"sequences.":[158],"This":[159],"represents":[160],"approximately":[161],"nine":[162],"times":[163,169],"much":[165],"sequence":[166],"eleven":[168],"many":[171],"RefSeq.":[174,198],"Beyond":[175],"standard":[176],"evaluation,":[178],"generated":[180],"full-length":[181],"PacBio":[182],"Iso-Seq":[183],"transcriptomes":[184],"four":[186],"species,":[187],"providing":[188],"independent":[189],"experimental":[190],"gene":[194,211,230],"candidates":[195],"absent":[196],"These":[199],"findings":[200],"demonstrate":[201],"potential":[203],"complement":[205],"established":[206],"reference":[207],"annotations":[208],"through":[209],"new":[210],"discovery.":[212],"Together,":[213],"CADB":[216],"provide":[217],"consistent":[219],"resource":[221],"species":[223],"lacking":[224],"curated":[225],"annotations,":[226],"foundation":[228],"discovery,":[231],"large":[234],"corpus":[235],"training":[237],"language":[241]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-10-22T00:00:00"}
