{"id":"https://openalex.org/W4392112958","doi":"https://doi.org/10.1093/bib/bbae047","title":"Continually adapting pre-trained language model to universal annotation of single-cell RNA-seq data","display_name":"Continually adapting pre-trained language model to universal annotation of single-cell RNA-seq data","publication_year":2024,"publication_date":"2024-01-22","ids":{"openalex":"https://openalex.org/W4392112958","doi":"https://doi.org/10.1093/bib/bbae047","pmid":"https://pubmed.ncbi.nlm.nih.gov/38388681"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbae047","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbae047","pdf_url":"https://academic.oup.com/bib/article-pdf/25/2/bbae047/56742389/bbae047.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bib/article-pdf/25/2/bbae047/56742389/bbae047.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015679423","display_name":"Hui Wan","orcid":"https://orcid.org/0000-0003-4217-6250"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wan","raw_affiliation_strings":["School of Mathematical Sciences, Peking University , Beijing, China, 100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Peking University , Beijing, China, 100871","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064410034","display_name":"Musu Yuan","orcid":"https://orcid.org/0000-0002-5674-1639"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Musu Yuan","raw_affiliation_strings":["Center for Quantitative Biology, Peking University , Beijing, China, 100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Quantitative Biology, Peking University , Beijing, China, 100871","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102619439","display_name":"Yiwei Fu","orcid":"https://orcid.org/0009-0000-1637-6764"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Fu","raw_affiliation_strings":["School of Mathematical Sciences, Peking University , Beijing, China, 100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Peking University , Beijing, China, 100871","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091013880","display_name":"Minghua Deng","orcid":"https://orcid.org/0000-0002-9143-1898"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Minghua Deng","raw_affiliation_strings":["Center for Quantitative Biology, Peking University , Beijing, China, 100871","Center for Statistical Science, Peking university , Beijing, China, 100871","School of Mathematical Sciences, Peking University , Beijing, China, 100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Quantitative Biology, Peking University , Beijing, China, 100871","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Center for Statistical Science, Peking university , Beijing, China, 100871","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Mathematical Sciences, Peking University , Beijing, China, 100871","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5091013880"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":{"value":4011,"currency":"USD","value_usd":4011},"fwci":1.8662,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84845578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"25","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9915000200271606,"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":0.9915000200271606,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0034000000450760126,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.0012000000569969416,"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":0.7920970916748047},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.783250093460083},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.5384829044342041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5182763934135437},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4656893014907837},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37912851572036743},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36306095123291016}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7920970916748047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.783250093460083},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.5384829044342041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5182763934135437},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4656893014907837},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37912851572036743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36306095123291016}],"mesh":[{"descriptor_ui":"D000092386","descriptor_name":"Single-Cell Gene Expression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000092386","descriptor_name":"Single-Cell Gene Expression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000092386","descriptor_name":"Single-Cell Gene Expression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000092386","descriptor_name":"Single-Cell Gene Expression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbae047","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbae047","pdf_url":"https://academic.oup.com/bib/article-pdf/25/2/bbae047/56742389/bbae047.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:38388681","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38388681","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10883808","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10883808","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10883808/pdf/bbae047.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bib/bbae047","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbae047","pdf_url":"https://academic.oup.com/bib/article-pdf/25/2/bbae047/56742389/bbae047.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G4089423392","display_name":null,"funder_award_id":"2021YFF1200902","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5690750078","display_name":null,"funder_award_id":"31871342","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392112958.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2011787586","https://openalex.org/W2146288698","https://openalex.org/W2523369352","https://openalex.org/W2523620612","https://openalex.org/W2526262591","https://openalex.org/W2758815122","https://openalex.org/W2781528640","https://openalex.org/W2788388592","https://openalex.org/W2894687190","https://openalex.org/W2931036699","https://openalex.org/W2948469692","https://openalex.org/W2951506174","https://openalex.org/W2964189064","https://openalex.org/W3003725832","https://openalex.org/W3093900604","https://openalex.org/W3121168830","https://openalex.org/W3125116114","https://openalex.org/W3154039181","https://openalex.org/W3177545502","https://openalex.org/W3196650609","https://openalex.org/W4205916264","https://openalex.org/W4225598893","https://openalex.org/W4297243391","https://openalex.org/W4306391398","https://openalex.org/W4307432965","https://openalex.org/W4313529882","https://openalex.org/W4316096017","https://openalex.org/W6755207826","https://openalex.org/W6849445909"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W1986582023","https://openalex.org/W2966829450","https://openalex.org/W4315864862"],"abstract_inverted_index":{"MOTIVATION:":[0],"Cell-type":[1],"annotation":[2,18,55,94,105,231,252],"of":[3,11,25,47,63,85,121,135,141,193,221,236,291,296],"single-cell":[4,78],"RNA-sequencing":[5],"(scRNA-seq)":[6],"data":[7,128,278,307],"is":[8,96,166,181,298],"a":[9,52,102,112,118,169,174],"hallmark":[10],"biomedical":[12],"research":[13],"and":[14,66,88,144,183,214,243,287],"clinical":[15],"application.":[16],"Current":[17],"tools":[19,40],"usually":[20],"assume":[21],"the":[22,30,44,82,133,191,210,219,234,241,250,285],"simultaneous":[23],"acquisition":[24],"well-annotated":[26,262],"data,":[27,49,124],"but":[28],"without":[29],"ability":[31,62],"to":[32,75,208],"expand":[33,249],"knowledge":[34,206,222],"from":[35,224,259,300],"new":[36,126,237,256],"data.":[37],"Yet,":[38],"such":[39],"are":[41,308],"inconsistent":[42],"with":[43,173,196,277],"continuous":[45,53],"emergence":[46],"scRNA-seq":[48,123],"calling":[50],"for":[51,92],"cell-type":[54,93,104,251],"model.":[56],"In":[57],"addition,":[58],"by":[59,254],"their":[60],"powerful":[61],"information":[64],"integration":[65],"model":[67,115,142,147,201,289],"interpretability,":[68],"transformer-based":[69],"pre-trained":[70,89,113],"language":[71,90,114],"models":[72,91],"have":[73],"led":[74],"breakthroughs":[76],"in":[77,139,161,185,218,272],"biology":[79],"research.":[80],"Therefore,":[81],"systematic":[83],"combining":[84],"continual":[86],"learning":[87],"tasks":[95],"inevitable.":[97],"RESULTS:":[98],"We":[99,246],"herein":[100],"propose":[101],"universal":[103,230],"tool,":[106],"called":[107],"CANAL,":[108],"that":[109,155],"continuously":[110,248],"fine-tunes":[111],"trained":[116],"on":[117],"large":[119],"amount":[120],"unlabeled":[122,273],"as":[125,265,267],"well-labeled":[127],"emerges.":[129],"CANAL":[130,297],"essentially":[131],"alleviates":[132],"dilemma":[134],"catastrophic":[136],"forgetting,":[137],"both":[138],"terms":[140],"inputs":[143],"outputs.":[145],"For":[146,200],"inputs,":[148],"we":[149,203],"introduce":[150],"an":[151],"experience":[152],"replay":[153],"schema":[154],"repeatedly":[156],"reviews":[157],"previous":[158,213],"vital":[159],"examples":[160],"current":[162,215],"training":[163,226,263],"stages.":[164,227,245],"This":[165],"achieved":[167],"through":[168],"dynamic":[170],"example":[171,179],"bank":[172,180],"fixed":[175],"buffer":[176],"size.":[177],"The":[178],"class-balanced":[182],"proficient":[184],"retaining":[186],"cell-type-specific":[187],"information,":[188],"particularly":[189],"facilitating":[190],"consolidation":[192],"patterns":[194],"associated":[195],"rare":[197],"cell":[198,238,257],"types.":[199],"outputs,":[202],"utilize":[204],"representation":[205],"distillation":[207],"regularize":[209],"divergence":[211],"between":[212],"models,":[216],"resulting":[217],"preservation":[220],"learned":[223],"past":[225],"Moreover,":[228],"our":[229],"framework":[232],"considers":[233],"inclusion":[235],"types":[239,258],"throughout":[240],"fine-tuning":[242],"testing":[244],"can":[247],"library":[253],"absorbing":[255],"newly":[260],"arrived,":[261],"datasets,":[264],"well":[266],"automatically":[268],"identify":[269],"novel":[270],"cells":[271],"datasets.":[274],"Comprehensive":[275],"experiments":[276],"streams":[279],"under":[280],"various":[281],"biological":[282],"scenarios":[283],"demonstrate":[284],"versatility":[286],"high":[288],"interpretability":[290],"CANAL.":[292],"AVAILABILITY:":[293],"An":[294],"implementation":[295],"available":[299,309],"https://github.com/aster-ww/CANAL-torch.":[301],"CONTACT:":[302],"dengmh@pku.edu.cn.":[303],"SUPPLEMENTARY":[304],"INFORMATION:":[305],"Supplementary":[306],"at":[310],"Journal":[311],"Name":[312],"online.":[313]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}