{"id":"https://openalex.org/W4394763992","doi":"https://doi.org/10.1093/bib/bbae163","title":"Self-supervised learning on millions of primary RNA sequences from 72 vertebrates improves sequence-based RNA splicing prediction","display_name":"Self-supervised learning on millions of primary RNA sequences from 72 vertebrates improves sequence-based RNA splicing prediction","publication_year":2024,"publication_date":"2024-03-27","ids":{"openalex":"https://openalex.org/W4394763992","doi":"https://doi.org/10.1093/bib/bbae163","pmid":"https://pubmed.ncbi.nlm.nih.gov/38605640"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbae163","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbae163","pdf_url":"https://academic.oup.com/bib/article-pdf/25/3/bbae163/57215917/bbae163.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","license_id":"https://openalex.org/licenses/cc-by","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/25/3/bbae163/57215917/bbae163.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100420334","display_name":"Ken Chen","orcid":"https://orcid.org/0000-0001-5701-1438"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ken Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou , China"],"raw_orcid":"https://orcid.org/0000-0001-5701-1438","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou , China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023986915","display_name":"Yue Zhou","orcid":"https://orcid.org/0000-0003-2771-0144"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhou","raw_affiliation_strings":["Peng Cheng Laboratory , Shenzhen , China"],"raw_orcid":"https://orcid.org/0000-0003-2771-0144","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory , Shenzhen , China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078518917","display_name":"Maolin Ding","orcid":"https://orcid.org/0009-0007-2837-9533"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maolin Ding","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou , China"],"raw_orcid":"https://orcid.org/0009-0007-2837-9533","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou , China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053242621","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0003-4976-9366"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Peng Cheng Laboratory , Shenzhen , China"],"raw_orcid":"https://orcid.org/0000-0003-4976-9366","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory , Shenzhen , China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070028902","display_name":"Zhixiang Ren","orcid":"https://orcid.org/0000-0002-4104-3790"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhixiang Ren","raw_affiliation_strings":["Peng Cheng Laboratory , Shenzhen , China"],"raw_orcid":"https://orcid.org/0000-0002-4104-3790","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory , Shenzhen , China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023539493","display_name":"Yuedong Yang","orcid":"https://orcid.org/0000-0002-6782-2813"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuedong Yang","raw_affiliation_strings":["Key Laboratory of Machine Intelligence and Advanced Computing (Sun Yat-sen University), Ministry of Education , China","School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou , China"],"raw_orcid":"https://orcid.org/0000-0002-6782-2813","affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Intelligence and Advanced Computing (Sun Yat-sen University), Ministry of Education , China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University , Guangzhou , China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5023539493","https://openalex.org/A5070028902"],"corresponding_institution_ids":["https://openalex.org/I157773358","https://openalex.org/I4210136793"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":{"value":4011,"currency":"USD","value_usd":4011},"fwci":13.2946,"has_fulltext":true,"cited_by_count":63,"citation_normalized_percentile":{"value":0.99360938,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"25","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","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/T10521","display_name":"RNA and protein synthesis mechanisms","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/T10604","display_name":"RNA Research and Splicing","score":0.9997000098228455,"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/T11482","display_name":"RNA modifications and cancer","score":0.9994999766349792,"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/rna-splicing","display_name":"RNA splicing","score":0.8099740743637085},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7272600531578064},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.7050371170043945},{"id":"https://openalex.org/keywords/rna","display_name":"RNA","score":0.5689435005187988},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.522646427154541},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5114783048629761},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4941733181476593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4876011908054352},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.47261929512023926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4398965537548065},{"id":"https://openalex.org/keywords/splice","display_name":"splice","score":0.4389364421367645},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.41327041387557983},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4100803732872009},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3924409747123718},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3553662896156311},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.27105510234832764},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.10617932677268982}],"concepts":[{"id":"https://openalex.org/C54458228","wikidata":"https://www.wikidata.org/wiki/Q237218","display_name":"RNA splicing","level":4,"score":0.8099740743637085},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7272600531578064},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.7050371170043945},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.5689435005187988},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.522646427154541},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5114783048629761},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4941733181476593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4876011908054352},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.47261929512023926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4398965537548065},{"id":"https://openalex.org/C2780989783","wikidata":"https://www.wikidata.org/wiki/Q7578557","display_name":"splice","level":3,"score":0.4389364421367645},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.41327041387557983},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4100803732872009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3924409747123718},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3553662896156311},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.27105510234832764},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.10617932677268982}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012326","descriptor_name":"RNA Splicing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012326","descriptor_name":"RNA Splicing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012326","descriptor_name":"RNA Splicing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012326","descriptor_name":"RNA Splicing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014714","descriptor_name":"Vertebrates","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D014714","descriptor_name":"Vertebrates","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D014714","descriptor_name":"Vertebrates","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D014714","descriptor_name":"Vertebrates","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bib/bbae163","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbae163","pdf_url":"https://academic.oup.com/bib/article-pdf/25/3/bbae163/57215917/bbae163.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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:38605640","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38605640","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:11009468","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11009468","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11009468/pdf/bbae163.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"},{"id":"pmh:oai:research-repository.griffith.edu.au:10072/430585","is_oa":true,"landing_page_url":"https://hdl.handle.net/10072/430585","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal article"}],"best_oa_location":{"id":"doi:10.1093/bib/bbae163","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbae163","pdf_url":"https://academic.oup.com/bib/article-pdf/25/3/bbae163/57215917/bbae163.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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G2670027177","display_name":null,"funder_award_id":"PCL2021A09","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2829389921","display_name":null,"funder_award_id":"T2394502","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3428819714","display_name":null,"funder_award_id":"PCL2021A09","funder_id":"https://openalex.org/F4320318558","funder_display_name":"Peng Cheng Laboratory"},{"id":"https://openalex.org/G4642882069","display_name":null,"funder_award_id":"2022YFF1203100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4877307238","display_name":null,"funder_award_id":"2022YFF1203100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5150481254","display_name":null,"funder_award_id":"PCL2021A13","funder_id":"https://openalex.org/F4320318558","funder_display_name":"Peng Cheng Laboratory"}],"funders":[{"id":"https://openalex.org/F4320318558","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06"},{"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/W4394763992.pdf"},"referenced_works_count":76,"referenced_works":["https://openalex.org/W1019830208","https://openalex.org/W1968569455","https://openalex.org/W2034691490","https://openalex.org/W2079699077","https://openalex.org/W2088338354","https://openalex.org/W2089891619","https://openalex.org/W2096237610","https://openalex.org/W2102619694","https://openalex.org/W2103534177","https://openalex.org/W2107026277","https://openalex.org/W2112814753","https://openalex.org/W2129682060","https://openalex.org/W2132123037","https://openalex.org/W2141458291","https://openalex.org/W2145191876","https://openalex.org/W2169456326","https://openalex.org/W2198606573","https://openalex.org/W2582377823","https://openalex.org/W2671644384","https://openalex.org/W2765584677","https://openalex.org/W2774883395","https://openalex.org/W2786672974","https://openalex.org/W2800392236","https://openalex.org/W2806983385","https://openalex.org/W2897249806","https://openalex.org/W2899616402","https://openalex.org/W2902014603","https://openalex.org/W2908510526","https://openalex.org/W2909194804","https://openalex.org/W2913668833","https://openalex.org/W2918497364","https://openalex.org/W2951195117","https://openalex.org/W2951364430","https://openalex.org/W2952713926","https://openalex.org/W2960193069","https://openalex.org/W3001279689","https://openalex.org/W3013690547","https://openalex.org/W3091921516","https://openalex.org/W3106188259","https://openalex.org/W3118485687","https://openalex.org/W3127238141","https://openalex.org/W3144227021","https://openalex.org/W3146944767","https://openalex.org/W3153385703","https://openalex.org/W3160208824","https://openalex.org/W3177500196","https://openalex.org/W3179485843","https://openalex.org/W3203588026","https://openalex.org/W3217274194","https://openalex.org/W4205731547","https://openalex.org/W4226065462","https://openalex.org/W4280524269","https://openalex.org/W4280594315","https://openalex.org/W4281758439","https://openalex.org/W4285172194","https://openalex.org/W4287724045","https://openalex.org/W4290546063","https://openalex.org/W4294170691","https://openalex.org/W4304607335","https://openalex.org/W4307475440","https://openalex.org/W4308239184","https://openalex.org/W4309793872","https://openalex.org/W4378976294","https://openalex.org/W4385245566","https://openalex.org/W4385945347","https://openalex.org/W4387966979","https://openalex.org/W4389132733","https://openalex.org/W4392302569","https://openalex.org/W6682691769","https://openalex.org/W6732702628","https://openalex.org/W6739901393","https://openalex.org/W6748816842","https://openalex.org/W6780145172","https://openalex.org/W6783944145","https://openalex.org/W6798272402","https://openalex.org/W6858273633"],"related_works":["https://openalex.org/W2029220916","https://openalex.org/W2274928342","https://openalex.org/W4247092347","https://openalex.org/W1943031701","https://openalex.org/W3129862691","https://openalex.org/W1993348797","https://openalex.org/W3006402873","https://openalex.org/W2887346131","https://openalex.org/W2008832338","https://openalex.org/W2014791263"],"abstract_inverted_index":{"Language":[0],"models":[1,17,39,144],"pretrained":[2,55],"by":[3,65],"self-supervised":[4],"learning":[5],"(SSL)":[6],"have":[7,49],"been":[8],"widely":[9],"utilized":[10],"to":[11,26,30,72,159],"study":[12,136],"protein":[13],"sequences,":[14],"while":[15],"few":[16],"were":[18,24],"developed":[19,50],"for":[20],"genomic":[21,142,168],"sequences":[22,61],"and":[23,69,95,129,151],"limited":[25],"single":[27],"species.":[28],"Due":[29],"the":[31,91,100,138,164],"lack":[32],"of":[33,75,86,103,119,125,132,140,149,163],"genomes":[34],"from":[35,62],"different":[36],"species,":[37],"these":[38],"cannot":[40],"effectively":[41],"leverage":[42],"evolutionary":[43],"information.":[44],"In":[45],"this":[46],"study,":[47],"we":[48],"SpliceBERT,":[51],"a":[52,107,146,156],"language":[53,67,143],"model":[54],"on":[56,80,113,122,145],"primary":[57],"ribonucleic":[58],"acids":[59],"(RNA)":[60],"72":[63],"vertebrates":[64],"masked":[66],"modeling,":[68],"applied":[70],"it":[71],"sequence-based":[73],"modeling":[74],"RNA":[76],"splicing.":[77],"Pretraining":[78],"SpliceBERT":[79,109],"diverse":[81,147],"species":[82,150],"enables":[83],"effective":[84,112],"identification":[85],"evolutionarily":[87],"conserved":[88],"elements.":[89],"Meanwhile,":[90],"learned":[92],"hidden":[93],"states":[94],"attention":[96],"weights":[97],"can":[98],"characterize":[99],"biological":[101],"properties":[102],"splice":[104,133],"sites.":[105,134],"As":[106],"result,":[108],"was":[110],"shown":[111],"several":[114],"downstream":[115],"tasks:":[116],"zero-shot":[117],"prediction":[118,124,131],"variant":[120],"effects":[121],"splicing,":[123],"branchpoints":[126],"in":[127],"humans,":[128],"cross-species":[130],"Our":[135],"highlighted":[137],"importance":[139],"pretraining":[141],"range":[148],"suggested":[152],"that":[153],"SSL":[154],"is":[155],"promising":[157],"approach":[158],"enhance":[160],"our":[161],"understanding":[162],"regulatory":[165],"logic":[166],"underlying":[167],"sequences.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":37},{"year":2024,"cited_by_count":16}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
