{"id":"https://openalex.org/W4412454219","doi":"https://doi.org/10.1093/bioinformatics/btaf229","title":"MutBERT: probabilistic genome representation improves genomics foundation models","display_name":"MutBERT: probabilistic genome representation improves genomics foundation models","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4412454219","doi":"https://doi.org/10.1093/bioinformatics/btaf229","pmid":"https://pubmed.ncbi.nlm.nih.gov/40662829"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf229","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf229","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/Supplement_1/i294/63745665/btaf229.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"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/bioinformatics/article-pdf/41/Supplement_1/i294/63745665/btaf229.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042658211","display_name":"Wen Hui Long","orcid":"https://orcid.org/0000-0002-3245-765X"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Weicai Long","raw_affiliation_strings":["Data Science and Analytics Thrust, Hong Kong University of Science and Technology (Guangzhou) , Guangzhou, 511453,"],"affiliations":[{"raw_affiliation_string":"Data Science and Analytics Thrust, Hong Kong University of Science and Technology (Guangzhou) , Guangzhou, 511453,","institution_ids":["https://openalex.org/I37987034","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111219297","display_name":"Houcheng Su","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Houcheng Su","raw_affiliation_strings":["Data Science and Analytics Thrust, Hong Kong University of Science and Technology (Guangzhou) , Guangzhou, 511453,"],"affiliations":[{"raw_affiliation_string":"Data Science and Analytics Thrust, Hong Kong University of Science and Technology (Guangzhou) , Guangzhou, 511453,","institution_ids":["https://openalex.org/I37987034","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081800971","display_name":"Jiaqi Xiong","orcid":"https://orcid.org/0000-0003-0455-4716"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Jiaqi Xiong","raw_affiliation_strings":["Data Science and Analytics Thrust, Hong Kong University of Science and Technology (Guangzhou) , Guangzhou, 511453,"],"affiliations":[{"raw_affiliation_string":"Data Science and Analytics Thrust, Hong Kong University of Science and Technology (Guangzhou) , Guangzhou, 511453,","institution_ids":["https://openalex.org/I37987034","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100424688","display_name":"Yanlin Zhang","orcid":"https://orcid.org/0000-0003-4002-443X"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yanlin Zhang","raw_affiliation_strings":["Data Science and Analytics Thrust, Hong Kong University of Science and Technology (Guangzhou) , Guangzhou, 511453,"],"affiliations":[{"raw_affiliation_string":"Data Science and Analytics Thrust, Hong Kong University of Science and Technology (Guangzhou) , Guangzhou, 511453,","institution_ids":["https://openalex.org/I37987034","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042658211"],"corresponding_institution_ids":["https://openalex.org/I37987034","https://openalex.org/I889458895"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":3.4971,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9249866,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"41","issue":"Supplement_1","first_page":"i294","last_page":"i303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11642","display_name":"Genomics and Rare Diseases","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9988999962806702,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9983000159263611,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.5808877944946289},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.5712803602218628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5532363653182983},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4799485504627228},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4776262640953064},{"id":"https://openalex.org/keywords/1000-genomes-project","display_name":"1000 Genomes Project","score":0.46057748794555664},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.45513617992401123},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.44355547428131104},{"id":"https://openalex.org/keywords/single-nucleotide-polymorphism","display_name":"Single-nucleotide polymorphism","score":0.44030168652534485},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3288516104221344},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.30604439973831177},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.28639161586761475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2849077582359314},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09201943874359131},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.07526373863220215}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5808877944946289},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.5712803602218628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5532363653182983},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4799485504627228},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4776262640953064},{"id":"https://openalex.org/C97425143","wikidata":"https://www.wikidata.org/wiki/Q164786","display_name":"1000 Genomes Project","level":5,"score":0.46057748794555664},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.45513617992401123},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.44355547428131104},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.44030168652534485},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3288516104221344},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30604439973831177},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.28639161586761475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2849077582359314},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09201943874359131},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.07526373863220215},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005787","descriptor_name":"Gene Frequency","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005787","descriptor_name":"Gene Frequency","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005787","descriptor_name":"Gene Frequency","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005787","descriptor_name":"Gene Frequency","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":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaf229","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf229","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/Supplement_1/i294/63745665/btaf229.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40662829","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40662829","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12261424","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12261424","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaf229","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf229","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/Supplement_1/i294/63745665/btaf229.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412454219.pdf","grobid_xml":"https://content.openalex.org/works/W4412454219.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1988301066","https://openalex.org/W2112132489","https://openalex.org/W2979826702","https://openalex.org/W3029661147","https://openalex.org/W3127238141","https://openalex.org/W3203588026","https://openalex.org/W4281758439","https://openalex.org/W4294012180","https://openalex.org/W4295312788","https://openalex.org/W4382603228","https://openalex.org/W4385245566","https://openalex.org/W4387966979","https://openalex.org/W4388979610","https://openalex.org/W4392575276","https://openalex.org/W4400921533","https://openalex.org/W4401103147","https://openalex.org/W4404821554","https://openalex.org/W4405995672","https://openalex.org/W6739901393","https://openalex.org/W6766978945","https://openalex.org/W6838322825","https://openalex.org/W6849916264","https://openalex.org/W6853816692"],"related_works":["https://openalex.org/W2095322240","https://openalex.org/W2383248267","https://openalex.org/W1997337693","https://openalex.org/W2364503270","https://openalex.org/W2409743480","https://openalex.org/W2160515792","https://openalex.org/W2156272823","https://openalex.org/W2227014354","https://openalex.org/W2784408333","https://openalex.org/W3096600795"],"abstract_inverted_index":{"https://github.com/ai4nucleome/mutBERT.":[0]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}
