{"id":"https://openalex.org/W4297243391","doi":"https://doi.org/10.1038/s42256-022-00534-z","title":"scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data","display_name":"scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data","publication_year":2022,"publication_date":"2022-09-26","ids":{"openalex":"https://openalex.org/W4297243391","doi":"https://doi.org/10.1038/s42256-022-00534-z"},"language":"en","primary_location":{"id":"doi:10.1038/s42256-022-00534-z","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-022-00534-z","pdf_url":"https://www.nature.com/articles/s42256-022-00534-z.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.nature.com/articles/s42256-022-00534-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089823903","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0002-1245-1197"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I4210116091","display_name":"Department of Physics, Mathematics and Informatics","ror":"https://ror.org/023sm4k53","country_code":"BY","type":"facility","lineage":["https://openalex.org/I151823869","https://openalex.org/I4210116091"]}],"countries":["BY","CN"],"is_corresponding":true,"raw_author_name":"Fan Yang","raw_affiliation_strings":[", , , . and of ","AI Lab, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":", , , . and of ","institution_ids":["https://openalex.org/I4210116091"]},{"raw_affiliation_string":"AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074094490","display_name":"Wenchuan Wang","orcid":"https://orcid.org/0000-0003-1367-5886"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I4210116091","display_name":"Department of Physics, Mathematics and Informatics","ror":"https://ror.org/023sm4k53","country_code":"BY","type":"facility","lineage":["https://openalex.org/I151823869","https://openalex.org/I4210116091"]}],"countries":["BY","CN"],"is_corresponding":false,"raw_author_name":"Wenchuan Wang","raw_affiliation_strings":[", , , . and of ","AI Lab, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":", , , . and of ","institution_ids":["https://openalex.org/I4210116091"]},{"raw_affiliation_string":"AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100321391","display_name":"Fang Wang","orcid":"https://orcid.org/0000-0002-1491-5207"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I4210116091","display_name":"Department of Physics, Mathematics and Informatics","ror":"https://ror.org/023sm4k53","country_code":"BY","type":"facility","lineage":["https://openalex.org/I151823869","https://openalex.org/I4210116091"]}],"countries":["BY","CN"],"is_corresponding":false,"raw_author_name":"Fang Wang","raw_affiliation_strings":[", , , . and of ","AI Lab, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":", , , . and of ","institution_ids":["https://openalex.org/I4210116091"]},{"raw_affiliation_string":"AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102867157","display_name":"Yuan Fang","orcid":"https://orcid.org/0009-0000-6551-0245"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I4210116091","display_name":"Department of Physics, Mathematics and Informatics","ror":"https://ror.org/023sm4k53","country_code":"BY","type":"facility","lineage":["https://openalex.org/I151823869","https://openalex.org/I4210116091"]}],"countries":["BY","CN"],"is_corresponding":false,"raw_author_name":"Yuan Fang","raw_affiliation_strings":[", , , . and of ","AI Lab, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":", , , . and of ","institution_ids":["https://openalex.org/I4210116091"]},{"raw_affiliation_string":"AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110628758","display_name":"Duyu Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I4210116091","display_name":"Department of Physics, Mathematics and Informatics","ror":"https://ror.org/023sm4k53","country_code":"BY","type":"facility","lineage":["https://openalex.org/I151823869","https://openalex.org/I4210116091"]}],"countries":["BY","CN"],"is_corresponding":false,"raw_author_name":"Duyu Tang","raw_affiliation_strings":[", , , . and of ","AI Lab, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":", , , . and of ","institution_ids":["https://openalex.org/I4210116091"]},{"raw_affiliation_string":"AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068865316","display_name":"Junzhou Huang","orcid":"https://orcid.org/0000-0002-9548-1227"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]},{"id":"https://openalex.org/I4210116091","display_name":"Department of Physics, Mathematics and Informatics","ror":"https://ror.org/023sm4k53","country_code":"BY","type":"facility","lineage":["https://openalex.org/I151823869","https://openalex.org/I4210116091"]}],"countries":["BY","US"],"is_corresponding":false,"raw_author_name":"Junzhou Huang","raw_affiliation_strings":[", , , . and of ","Department of Computer Science and Engineering, the University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":", , , . and of ","institution_ids":["https://openalex.org/I4210116091"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, the University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716955","display_name":"Hui L\u00fc","orcid":"https://orcid.org/0000-0001-8347-0830"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210116091","display_name":"Department of Physics, Mathematics and Informatics","ror":"https://ror.org/023sm4k53","country_code":"BY","type":"facility","lineage":["https://openalex.org/I151823869","https://openalex.org/I4210116091"]}],"countries":["BY","CN"],"is_corresponding":false,"raw_author_name":"Hui Lu","raw_affiliation_strings":[", , , . and of ","SJTU-Yale Joint Center for Biostatistics and Data Science, School of Life Sciences and Biotechnology, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":", , , . and of ","institution_ids":["https://openalex.org/I4210116091"]},{"raw_affiliation_string":"SJTU-Yale Joint Center for Biostatistics and Data Science, School of Life Sciences and Biotechnology, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100695406","display_name":"Jianhua Yao","orcid":"https://orcid.org/0000-0001-9157-9596"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I4210116091","display_name":"Department of Physics, Mathematics and Informatics","ror":"https://ror.org/023sm4k53","country_code":"BY","type":"facility","lineage":["https://openalex.org/I151823869","https://openalex.org/I4210116091"]}],"countries":["BY","CN"],"is_corresponding":false,"raw_author_name":"Jianhua Yao","raw_affiliation_strings":[", , , . and of ","AI Lab, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":", , , . and of ","institution_ids":["https://openalex.org/I4210116091"]},{"raw_affiliation_string":"AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5089823903"],"corresponding_institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210116091"],"apc_list":{"value":9750,"currency":"EUR","value_usd":11690},"apc_paid":null,"fwci":43.4867,"has_fulltext":true,"cited_by_count":541,"citation_normalized_percentile":{"value":0.99932257,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"4","issue":"10","first_page":"852","last_page":"866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":1.0,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":1.0,"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/T10773","display_name":"Extracellular vesicles in disease","score":0.9914000034332275,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/annotation","display_name":"Annotation","score":0.7560690641403198},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7305411100387573},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6036174297332764},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6032248735427856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5661482810974121},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5613972544670105},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45246338844299316},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44465214014053345},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.44379156827926636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44018417596817017},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3319190740585327},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2720916271209717},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.23954474925994873},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.16972589492797852},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.07571911811828613}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7560690641403198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7305411100387573},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6036174297332764},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6032248735427856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5661482810974121},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5613972544670105},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45246338844299316},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44465214014053345},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.44379156827926636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44018417596817017},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3319190740585327},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2720916271209717},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.23954474925994873},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16972589492797852},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.07571911811828613},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1038/s42256-022-00534-z","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-022-00534-z","pdf_url":"https://www.nature.com/articles/s42256-022-00534-z.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1038/s42256-022-00534-z","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-022-00534-z","pdf_url":"https://www.nature.com/articles/s42256-022-00534-z.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308380","display_name":"Yale University","ror":"https://ror.org/03v76x132"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297243391.pdf","grobid_xml":"https://content.openalex.org/works/W4297243391.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1967327758","https://openalex.org/W1980867644","https://openalex.org/W2114055879","https://openalex.org/W2137460766","https://openalex.org/W2523369352","https://openalex.org/W2523419694","https://openalex.org/W2523620612","https://openalex.org/W2526262591","https://openalex.org/W2763420753","https://openalex.org/W2790756470","https://openalex.org/W2794521141","https://openalex.org/W2796170779","https://openalex.org/W2801443765","https://openalex.org/W2894662039","https://openalex.org/W2894687190","https://openalex.org/W2895456557","https://openalex.org/W2896518632","https://openalex.org/W2899224111","https://openalex.org/W2899728356","https://openalex.org/W2907514116","https://openalex.org/W2916020270","https://openalex.org/W2931036699","https://openalex.org/W2950813464","https://openalex.org/W2951506174","https://openalex.org/W2951737297","https://openalex.org/W2952631022","https://openalex.org/W2959295202","https://openalex.org/W2964643116","https://openalex.org/W2968352143","https://openalex.org/W2971398276","https://openalex.org/W2971653850","https://openalex.org/W2984629040","https://openalex.org/W2995410603","https://openalex.org/W2998840182","https://openalex.org/W3002417351","https://openalex.org/W3009609875","https://openalex.org/W3015134137","https://openalex.org/W3021135130","https://openalex.org/W3024842005","https://openalex.org/W3025989739","https://openalex.org/W3035231859","https://openalex.org/W3041129226","https://openalex.org/W3044352330","https://openalex.org/W3088401235","https://openalex.org/W3105982350","https://openalex.org/W3112976705","https://openalex.org/W3117771127","https://openalex.org/W3119774682","https://openalex.org/W3124814274","https://openalex.org/W3130453114","https://openalex.org/W3132715010","https://openalex.org/W3157103618","https://openalex.org/W3164692211","https://openalex.org/W4210984920","https://openalex.org/W4283726509","https://openalex.org/W6763509872","https://openalex.org/W6783944145","https://openalex.org/W6931347251"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W2905433371","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4390569940","https://openalex.org/W4281702477","https://openalex.org/W2888392564","https://openalex.org/W3124814274"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":42},{"year":2025,"cited_by_count":254},{"year":2024,"cited_by_count":178},{"year":2023,"cited_by_count":65},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}
