{"id":"https://openalex.org/W4385737488","doi":"https://doi.org/10.1038/s41588-023-01465-0","title":"Genome-wide prediction of disease variant effects with a deep protein language model","display_name":"Genome-wide prediction of disease variant effects with a deep protein language model","publication_year":2023,"publication_date":"2023-08-10","ids":{"openalex":"https://openalex.org/W4385737488","doi":"https://doi.org/10.1038/s41588-023-01465-0","pmid":"https://pubmed.ncbi.nlm.nih.gov/37563329","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/10484790"},"language":"en","primary_location":{"id":"doi:10.1038/s41588-023-01465-0","doi":"https://doi.org/10.1038/s41588-023-01465-0","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41588-023-01465-0","pdf_url":"https://www.nature.com/articles/s41588-023-01465-0.pdf","source":{"id":"https://openalex.org/S137905309","display_name":"Nature Genetics","issn_l":"1061-4036","issn":["1061-4036","1546-1718"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Genetics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.nature.com/articles/s41588-023-01465-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058480616","display_name":"Nadav Brandes","orcid":"https://orcid.org/0000-0002-0510-2546","observed_orcids":["https://orcid.org/0000-0002-0510-2546"]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nadav Brandes","raw_affiliation_strings":["Division of Rheumatology, Department of Medicine, University of California, San Francisco, San Francisco, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0510-2546","affiliations":[{"raw_affiliation_string":"Division of Rheumatology, Department of Medicine, University of California, San Francisco, San Francisco, CA, USA","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020140677","display_name":"Grant Goldman","orcid":"https://orcid.org/0000-0002-1158-6065","observed_orcids":["https://orcid.org/0000-0002-1158-6065"]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grant Goldman","raw_affiliation_strings":["Biological and Medical Informatics Graduate Program, University of California, San Francisco, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biological and Medical Informatics Graduate Program, University of California, San Francisco, San Francisco, CA, USA","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030725868","display_name":"Charlotte H. Wang","orcid":"https://orcid.org/0000-0001-7588-2077","observed_orcids":["https://orcid.org/0000-0001-7588-2077"]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charlotte H. Wang","raw_affiliation_strings":["Biomedical Sciences Graduate Program, University of California, San Francisco, San Francisco, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7588-2077","affiliations":[{"raw_affiliation_string":"Biomedical Sciences Graduate Program, University of California, San Francisco, San Francisco, CA, USA","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005819504","display_name":"Chun Ye","orcid":"https://orcid.org/0000-0001-6560-3783","observed_orcids":["https://orcid.org/0000-0001-6560-3783"]},"institutions":[{"id":"https://openalex.org/I1321430492","display_name":"Gladstone Institutes","ror":"https://ror.org/038321296","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1321430492"]},{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]},{"id":"https://openalex.org/I4210109986","display_name":"Parker Institute for Cancer Immunotherapy","ror":"https://ror.org/0184qbg02","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210109986"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chun Jimmie Ye","raw_affiliation_strings":["Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA, USA. jimmie.ye@ucsf.edu","Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, San Francisco, CA, USA. jimmie.ye@ucsf.edu","Department of Epidemiology & Biostatistics, University of California, San Francisco, San Francisco, CA, USA. jimmie.ye@ucsf.edu","Division of Rheumatology, Department of Medicine, University of California, San Francisco, San Francisco, CA, USA. jimmie.ye@ucsf.edu","Gladstone-UCSF Institute of Genomic Immunology, San Francisco, CA, USA. jimmie.ye@ucsf.edu","Institute for Human Genetics, University of California, San Francisco, San Francisco, CA, USA. jimmie.ye@ucsf.edu","Parker Institute for Cancer Immunotherapy, University of California, San Francisco, San Francisco, CA, USA. jimmie.ye@ucsf.edu","Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6560-3783","affiliations":[{"raw_affiliation_string":"Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA, USA. jimmie.ye@ucsf.edu","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, San Francisco, CA, USA. jimmie.ye@ucsf.edu","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"Department of Epidemiology & Biostatistics, University of California, San Francisco, San Francisco, CA, USA. jimmie.ye@ucsf.edu","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"Division of Rheumatology, Department of Medicine, University of California, San Francisco, San Francisco, CA, USA. jimmie.ye@ucsf.edu","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"Gladstone-UCSF Institute of Genomic Immunology, San Francisco, CA, USA. jimmie.ye@ucsf.edu","institution_ids":["https://openalex.org/I1321430492","https://openalex.org/I180670191"]},{"raw_affiliation_string":"Institute for Human Genetics, University of California, San Francisco, San Francisco, CA, USA. jimmie.ye@ucsf.edu","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"Parker Institute for Cancer Immunotherapy, University of California, San Francisco, San Francisco, CA, USA. jimmie.ye@ucsf.edu","institution_ids":["https://openalex.org/I180670191","https://openalex.org/I4210109986"]},{"raw_affiliation_string":"Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA, USA","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032880246","display_name":"Vasilis Ntranos","orcid":"https://orcid.org/0000-0002-2477-0670","observed_orcids":["https://orcid.org/0000-0002-2477-0670"]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vasilis Ntranos","raw_affiliation_strings":["Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA, USA. vasilis.ntranos@ucsf.edu","Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, San Francisco, CA, USA. vasilis.ntranos@ucsf.edu","Department of Epidemiology & Biostatistics, University of California, San Francisco, San Francisco, CA, USA. vasilis.ntranos@ucsf.edu","Diabetes Center, University of California, San Francisco, San Francisco, CA, USA. vasilis.ntranos@ucsf.edu","Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2477-0670","affiliations":[{"raw_affiliation_string":"Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA, USA. vasilis.ntranos@ucsf.edu","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, San Francisco, CA, USA. vasilis.ntranos@ucsf.edu","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"Department of Epidemiology & Biostatistics, University of California, San Francisco, San Francisco, CA, USA. vasilis.ntranos@ucsf.edu","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"Diabetes Center, University of California, San Francisco, San Francisco, CA, USA. vasilis.ntranos@ucsf.edu","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA, USA","institution_ids":["https://openalex.org/I180670191"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005819504","https://openalex.org/A5032880246"],"corresponding_institution_ids":["https://openalex.org/I1321430492","https://openalex.org/I180670191","https://openalex.org/I4210109986"],"apc_list":{"value":11690,"currency":"USD","value_usd":11690},"apc_paid":{"value":11690,"currency":"USD","value_usd":11690},"fwci":59.1853,"has_fulltext":true,"cited_by_count":476,"citation_normalized_percentile":{"value":0.99968946,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":"55","issue":"9","first_page":"1512","last_page":"1522"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.9984999895095825,"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":0.9984999895095825,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pathogenicity-classification","display_name":"pathogenicity classification","score":0.6830000281333923},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.9539999961853027},{"id":"https://openalex.org/keywords/deep-mutational-scanning","display_name":"deep mutational scanning","score":0.7120000123977661},{"id":"https://openalex.org/keywords/alternative-splicing","display_name":"alternative splicing","score":0.7549999952316284},{"id":"https://openalex.org/keywords/protein-isoforms","display_name":"protein isoforms","score":0.972000002861023},{"id":"https://openalex.org/keywords/clinvar","display_name":"ClinVar","score":0.8479999899864197},{"id":"https://openalex.org/keywords/human-gene-mutation-database","display_name":"HGMD","score":0.7960000038146973},{"id":"https://openalex.org/keywords/protein-engineering","display_name":"protein engineering","score":0.32899999618530273}],"concepts":[{"id":"https://openalex.org/C75563809","wikidata":"https://www.wikidata.org/wiki/Q2656896","display_name":"Missense mutation","level":4,"score":0.6533437967300415},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6092719435691833},{"id":"https://openalex.org/C119054055","wikidata":"https://www.wikidata.org/wiki/Q1576681","display_name":"Indel","level":5,"score":0.6092413067817688},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5509089231491089},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5480870604515076},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5233794450759888},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5043963193893433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5042997598648071},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4841461777687073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42264240980148315},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3924505412578583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37100356817245483},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2643928825855255},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.2631409168243408},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.16848623752593994},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020125","descriptor_name":"Mutation, Missense","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1038/s41588-023-01465-0","doi":"https://doi.org/10.1038/s41588-023-01465-0","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41588-023-01465-0","pdf_url":"https://www.nature.com/articles/s41588-023-01465-0.pdf","source":{"id":"https://openalex.org/S137905309","display_name":"Nature Genetics","issn_l":"1061-4036","issn":["1061-4036","1546-1718"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Genetics","raw_type":"journal-article"},{"id":"doi:10.1101/2022.08.25.505311","doi":"https://doi.org/10.1101/2022.08.25.505311","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2022.08.25.505311","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2022/08/26/2022.08.25.505311.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:10484790","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10484790","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10484790/pdf/41588_2023_Article_1465.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,"listed_in":[],"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":"Nat Genet","raw_type":"Text"},{"id":"pmid:37563329","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37563329","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,"listed_in":[],"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":"Nature genetics","raw_type":"Journal Article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt95r4c6c6","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/95r4c6c6","pdf_url":"https://escholarship.org/content/qt95r4c6c6/qt95r4c6c6.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"Nature Genetics, vol 55, iss 9","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1038/s41588-023-01465-0","doi":"https://doi.org/10.1038/s41588-023-01465-0","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41588-023-01465-0","pdf_url":"https://www.nature.com/articles/s41588-023-01465-0.pdf","source":{"id":"https://openalex.org/S137905309","display_name":"Nature Genetics","issn_l":"1061-4036","issn":["1061-4036","1546-1718"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Genetics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.6240000128746033,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1369814150","display_name":"Fine mapping rheumatic disease variants using functional genomic sequencing","funder_award_id":"R01AR071522","funder_id":"https://openalex.org/F4320337362","funder_display_name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases"},{"id":"https://openalex.org/G2384146834","display_name":"Fine mapping rheumatic disease variants using functional genomic sequencing","funder_award_id":"U01HG012192","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G5062866998","display_name":"BMI Bioinformatics Training Grant","funder_award_id":"T32GM067547","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G518370680","display_name":null,"funder_award_id":"CRI4499","funder_id":"https://openalex.org/F4320306155","funder_display_name":"Cancer Research Institute"},{"id":"https://openalex.org/G5387445677","display_name":"Genetic regulation and immunological function of ERAP2 haplotypes","funder_award_id":"R01AI136972","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"},{"id":"https://openalex.org/G6551126045","display_name":"Mapping gene-by-environment interactions using multiplexed single cell RNA-sequencing","funder_award_id":"R01HG011239","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320306155","display_name":"Cancer Research Institute","ror":"https://ror.org/02f3xk561"},{"id":"https://openalex.org/F4320315119","display_name":"Parker Institute for Cancer Immunotherapy","ror":"https://ror.org/0184qbg02"},{"id":"https://openalex.org/F4320315474","display_name":"Chan Zuckerberg Initiative","ror":"https://ror.org/02qenvm24"},{"id":"https://openalex.org/F4320320350","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"},{"id":"https://openalex.org/F4320337362","display_name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","ror":"https://ror.org/006zn3t30"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385737488.pdf","grobid_xml":"https://content.openalex.org/works/W4385737488.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W966012335","https://openalex.org/W1502061430","https://openalex.org/W1563940013","https://openalex.org/W1585895556","https://openalex.org/W1844405070","https://openalex.org/W1965092590","https://openalex.org/W1999260084","https://openalex.org/W2010595044","https://openalex.org/W2017730572","https://openalex.org/W2025570007","https://openalex.org/W2036681136","https://openalex.org/W2043416934","https://openalex.org/W2051978340","https://openalex.org/W2055996155","https://openalex.org/W2078663610","https://openalex.org/W2101234009","https://openalex.org/W2110646848","https://openalex.org/W2112001822","https://openalex.org/W2114850508","https://openalex.org/W2119412782","https://openalex.org/W2143210482","https://openalex.org/W2143238378","https://openalex.org/W2144761225","https://openalex.org/W2155570392","https://openalex.org/W2161317138","https://openalex.org/W2174602966","https://openalex.org/W2245592118","https://openalex.org/W2279930231","https://openalex.org/W2320983896","https://openalex.org/W2331911623","https://openalex.org/W2472351724","https://openalex.org/W2570257422","https://openalex.org/W2727251566","https://openalex.org/W2781028774","https://openalex.org/W2781534540","https://openalex.org/W2890179300","https://openalex.org/W2901303766","https://openalex.org/W2905452503","https://openalex.org/W2951599627","https://openalex.org/W2980789587","https://openalex.org/W2982247245","https://openalex.org/W2987965949","https://openalex.org/W2999481648","https://openalex.org/W3009209436","https://openalex.org/W3010305620","https://openalex.org/W3012384638","https://openalex.org/W3031073114","https://openalex.org/W3040739508","https://openalex.org/W3045929934","https://openalex.org/W3107322429","https://openalex.org/W3144701084","https://openalex.org/W3146944767","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3179485843","https://openalex.org/W3184953764","https://openalex.org/W3185808000","https://openalex.org/W3195230255","https://openalex.org/W3199639770","https://openalex.org/W3201689665","https://openalex.org/W3209435229","https://openalex.org/W4205773061","https://openalex.org/W4206229719","https://openalex.org/W4213097893","https://openalex.org/W4226399820","https://openalex.org/W4281648132","https://openalex.org/W4313291879","https://openalex.org/W4360836968","https://openalex.org/W4366823175","https://openalex.org/W4376133226","https://openalex.org/W4380422659","https://openalex.org/W4388024559","https://openalex.org/W6969286641"],"related_works":["https://openalex.org/W4293530896","https://openalex.org/W4385741267","https://openalex.org/W4404633904","https://openalex.org/W4394063194","https://openalex.org/W7203959501","https://openalex.org/W4396912951","https://openalex.org/W7130857691","https://openalex.org/W7208404620","https://openalex.org/W4405995672","https://openalex.org/W4411097524"],"abstract_inverted_index":{"Abstract":[0],"Distinguishing":[1],"between":[2,124],"damaging":[3,168],"and":[4,23,97,126,135],"neutral":[5,174],"missense":[6,51,116],"variants":[7,35,128,131,162],"is":[8,195],"an":[9],"ongoing":[10],"challenge":[11],"in":[12,33,105,110,133,169,175],"human":[13,81,107],"genetics,":[14],"with":[15],"profound":[16],"implications":[17],"for":[18,99,112],"clinical":[19],"diagnosis,":[20],"genetic":[21],"studies":[22],"protein":[24,59,72,171],"engineering.":[25],"Recently,":[26],"deep-learning":[27],"models":[28,42],"have":[29],"achieved":[30],"state-of-the-art":[31,139],"performance":[32],"classifying":[34],"as":[36,167],"pathogenic":[37,125],"or":[38,61],"benign.":[39],"However,":[40],"these":[41],"are":[43],"currently":[44],"unable":[45],"to":[46,63,75,122],"provide":[47],"predictions":[48,111,194],"over":[49],"all":[50,103,113,182],"variants,":[52],"either":[53],"because":[54],"of":[55,80,146,154,180,191],"dependency":[56],"on":[57],"close":[58],"homologs":[60],"due":[62],"software":[64],"limitations.":[65],"Here":[66],"we":[67,91],"leveraged":[68],"ESM1b,":[69],"a":[70,93],"650M-parameter":[71],"language":[73],"model,":[74],"predict":[76],"the":[77,100,106,144,147,151,178],"functional":[78],"impact":[79],"coding":[82],"variation":[83],"at":[84,149],"scale.":[85],"To":[86],"overcome":[87],"existing":[88,138],"technical":[89],"limitations,":[90],"developed":[92],"modified":[94],"ESM1b":[95,119,141],"workflow":[96],"functionalized,":[98],"first":[101],"time,":[102],"proteins":[104],"genome,":[108],"resulting":[109],"\u223c450M":[114],"possible":[115],"variant":[117,186,192],"effects.":[118,187],"was":[120],"able":[121],"distinguish":[123],"benign":[127],"across":[129,163],"\u223c150K":[130],"annotated":[132,160],"ClinVar":[134],"HGMD,":[136],"outperforming":[137],"methods.":[140],"also":[142],"exceeded":[143],"state":[145],"art":[148],"predicting":[150],"experimental":[152],"results":[153],"deep":[155],"mutational":[156],"scans.":[157],"We":[158],"further":[159],"\u223c2M":[161],"\u223c9K":[164],"alternatively-spliced":[165],"genes":[166],"certain":[170],"isoforms":[172,183],"while":[173],"others,":[176],"demonstrating":[177],"importance":[179],"considering":[181],"when":[184],"functionalizing":[185],"The":[188],"complete":[189],"catalog":[190],"effect":[193],"available":[196],"at:":[197],"https://huggingface.co/spaces/ntranoslab/esm_variants":[198],".":[199]},"counts_by_year":[{"year":2026,"cited_by_count":159},{"year":2025,"cited_by_count":171},{"year":2024,"cited_by_count":115},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2023-08-11T00:00:00"}
