{"id":"https://openalex.org/W4412884821","doi":"https://doi.org/10.1093/bib/bbaf384","title":"SARITA: a large language model for generating the S1 subunit of the SARS-CoV-2 spike protein","display_name":"SARITA: a large language model for generating the S1 subunit of the SARS-CoV-2 spike protein","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4412884821","doi":"https://doi.org/10.1093/bib/bbaf384","pmid":"https://pubmed.ncbi.nlm.nih.gov/40755284"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbaf384","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbaf384","pdf_url":"https://academic.oup.com/bib/article-pdf/26/4/bbaf384/63926290/bbaf384.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/26/4/bbaf384/63926290/bbaf384.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093116844","display_name":"Simone Rancati","orcid":"https://orcid.org/0009-0002-4405-1697"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]},{"id":"https://openalex.org/I2800717037","display_name":"University of Florida Health","ror":"https://ror.org/04tk2gy88","country_code":"US","type":"education","lineage":["https://openalex.org/I2800717037"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]},{"id":"https://openalex.org/I61515104","display_name":"University of Florida Health Science Center","ror":"https://ror.org/0419bgt07","country_code":"US","type":"education","lineage":["https://openalex.org/I61515104"]},{"id":"https://openalex.org/I94062374","display_name":"Florida College","ror":"https://ror.org/010bgev76","country_code":"US","type":"education","lineage":["https://openalex.org/I94062374"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Simone Rancati","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, University of Pavia , Via Adolfo Ferrata 5, Pavia, 27100 ,","Department of Epidemiology, College of Public Health and Health Professions, University of Florida , 2004 Mowry Road, Gainesville, FL 32610 ,","Emerging Pathogens Institute, University of Florida , 2055 Mowry Road, Gainesville, FL 32610 ,"],"raw_orcid":"https://orcid.org/0009-0002-4405-1697","affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, University of Pavia , Via Adolfo Ferrata 5, Pavia, 27100 ,","institution_ids":["https://openalex.org/I25217355"]},{"raw_affiliation_string":"Department of Epidemiology, College of Public Health and Health Professions, University of Florida , 2004 Mowry Road, Gainesville, FL 32610 ,","institution_ids":["https://openalex.org/I2800717037","https://openalex.org/I61515104","https://openalex.org/I94062374"]},{"raw_affiliation_string":"Emerging Pathogens Institute, University of Florida , 2055 Mowry Road, Gainesville, FL 32610 ,","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044714123","display_name":"Giovanna Nicora","orcid":"https://orcid.org/0000-0001-7007-0862"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanna Nicora","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, University of Pavia , Via Adolfo Ferrata 5, Pavia, 27100 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, University of Pavia , Via Adolfo Ferrata 5, Pavia, 27100 ,","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094282516","display_name":"Laura Bergomi","orcid":"https://orcid.org/0009-0006-0359-5128"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Laura Bergomi","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, University of Pavia , Via Adolfo Ferrata 5, Pavia, 27100 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, University of Pavia , Via Adolfo Ferrata 5, Pavia, 27100 ,","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046058191","display_name":"Tommaso Mario Buonocore","orcid":"https://orcid.org/0000-0002-2887-088X"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Tommaso Mario Buonocore","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, University of Pavia , Via Adolfo Ferrata 5, Pavia, 27100 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, University of Pavia , Via Adolfo Ferrata 5, Pavia, 27100 ,","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068650337","display_name":"Daniel M. Czy\u017c","orcid":"https://orcid.org/0000-0002-7491-5292"},"institutions":[{"id":"https://openalex.org/I1313142568","display_name":"Florida Museum of Natural History","ror":"https://ror.org/02pjdv450","country_code":"US","type":"archive","lineage":["https://openalex.org/I1313142568","https://openalex.org/I33213144"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel M Czyz","raw_affiliation_strings":["Department of Microbiology and Cell Science, University of Florida , 1355 Museum Dr, Gainesville, FL 32603 ,","Emerging Pathogens Institute, University of Florida , 2055 Mowry Road, Gainesville, FL 32610 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Microbiology and Cell Science, University of Florida , 1355 Museum Dr, Gainesville, FL 32603 ,","institution_ids":["https://openalex.org/I1313142568"]},{"raw_affiliation_string":"Emerging Pathogens Institute, University of Florida , 2055 Mowry Road, Gainesville, FL 32610 ,","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090028219","display_name":"Enea Parimbelli","orcid":"https://orcid.org/0000-0003-0679-828X"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Enea Parimbelli","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, University of Pavia , Via Adolfo Ferrata 5, Pavia, 27100 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, University of Pavia , Via Adolfo Ferrata 5, Pavia, 27100 ,","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050932220","display_name":"Riccardo Bellazzi","orcid":"https://orcid.org/0000-0002-6974-9808"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Riccardo Bellazzi","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, University of Pavia , Via Adolfo Ferrata 5, Pavia, 27100 ,"],"raw_orcid":"https://orcid.org/0000-0002-6974-9808","affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, University of Pavia , Via Adolfo Ferrata 5, Pavia, 27100 ,","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030387965","display_name":"Marco Salemi","orcid":"https://orcid.org/0000-0003-0136-2102"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]},{"id":"https://openalex.org/I94062374","display_name":"Florida College","ror":"https://ror.org/010bgev76","country_code":"US","type":"education","lineage":["https://openalex.org/I94062374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Salemi","raw_affiliation_strings":["Department of Pathology, Immunology and Laboratory Medicine, College of Medicine, University of Florida , 1600 SW Archer Road, Gainesville, FL 32610 ,","Emerging Pathogens Institute, University of Florida , 2055 Mowry Road, Gainesville, FL 32610 ,"],"raw_orcid":"https://orcid.org/0000-0003-0136-2102","affiliations":[{"raw_affiliation_string":"Department of Pathology, Immunology and Laboratory Medicine, College of Medicine, University of Florida , 1600 SW Archer Road, Gainesville, FL 32610 ,","institution_ids":["https://openalex.org/I94062374"]},{"raw_affiliation_string":"Emerging Pathogens Institute, University of Florida , 2055 Mowry Road, Gainesville, FL 32610 ,","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039419132","display_name":"Mattia Prosperi","orcid":"https://orcid.org/0000-0002-9021-5595"},"institutions":[{"id":"https://openalex.org/I2800717037","display_name":"University of Florida Health","ror":"https://ror.org/04tk2gy88","country_code":"US","type":"education","lineage":["https://openalex.org/I2800717037"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]},{"id":"https://openalex.org/I61515104","display_name":"University of Florida Health Science Center","ror":"https://ror.org/0419bgt07","country_code":"US","type":"education","lineage":["https://openalex.org/I61515104"]},{"id":"https://openalex.org/I94062374","display_name":"Florida College","ror":"https://ror.org/010bgev76","country_code":"US","type":"education","lineage":["https://openalex.org/I94062374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mattia Prosperi","raw_affiliation_strings":["Department of Epidemiology, College of Public Health and Health Professions, University of Florida , 2004 Mowry Road, Gainesville, FL 32610 ,","Emerging Pathogens Institute, University of Florida , 2055 Mowry Road, Gainesville, FL 32610 ,"],"raw_orcid":"https://orcid.org/0000-0002-9021-5595","affiliations":[{"raw_affiliation_string":"Department of Epidemiology, College of Public Health and Health Professions, University of Florida , 2004 Mowry Road, Gainesville, FL 32610 ,","institution_ids":["https://openalex.org/I2800717037","https://openalex.org/I61515104","https://openalex.org/I94062374"]},{"raw_affiliation_string":"Emerging Pathogens Institute, University of Florida , 2055 Mowry Road, Gainesville, FL 32610 ,","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004394877","display_name":"Simone Marini","orcid":"https://orcid.org/0000-0002-5704-3533"},"institutions":[{"id":"https://openalex.org/I2800717037","display_name":"University of Florida Health","ror":"https://ror.org/04tk2gy88","country_code":"US","type":"education","lineage":["https://openalex.org/I2800717037"]},{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]},{"id":"https://openalex.org/I61515104","display_name":"University of Florida Health Science Center","ror":"https://ror.org/0419bgt07","country_code":"US","type":"education","lineage":["https://openalex.org/I61515104"]},{"id":"https://openalex.org/I94062374","display_name":"Florida College","ror":"https://ror.org/010bgev76","country_code":"US","type":"education","lineage":["https://openalex.org/I94062374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simone Marini","raw_affiliation_strings":["Department of Epidemiology, College of Public Health and Health Professions, University of Florida , 2004 Mowry Road, Gainesville, FL 32610 ,","Emerging Pathogens Institute, University of Florida , 2055 Mowry Road, Gainesville, FL 32610 ,"],"raw_orcid":"https://orcid.org/0000-0002-5704-3533","affiliations":[{"raw_affiliation_string":"Department of Epidemiology, College of Public Health and Health Professions, University of Florida , 2004 Mowry Road, Gainesville, FL 32610 ,","institution_ids":["https://openalex.org/I2800717037","https://openalex.org/I61515104","https://openalex.org/I94062374"]},{"raw_affiliation_string":"Emerging Pathogens Institute, University of Florida , 2055 Mowry Road, Gainesville, FL 32610 ,","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":{"value":4011,"currency":"USD","value_usd":4011},"fwci":7.055,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.97561511,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"26","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10118","display_name":"SARS-CoV-2 and COVID-19 Research","score":0.4275999963283539,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10118","display_name":"SARS-CoV-2 and COVID-19 Research","score":0.4275999963283539,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.29510000348091125,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.04470000043511391,"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/spike","display_name":"Spike (software development)","score":0.6506766676902771},{"id":"https://openalex.org/keywords/protein-subunit","display_name":"Protein subunit","score":0.5566130876541138},{"id":"https://openalex.org/keywords/severe-acute-respiratory-syndrome-coronavirus-2","display_name":"Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)","score":0.5478968620300293},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5061902403831482},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4609556496143341},{"id":"https://openalex.org/keywords/mutation","display_name":"Mutation","score":0.4309884011745453},{"id":"https://openalex.org/keywords/virology","display_name":"Virology","score":0.4162783920764923},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4153820872306824},{"id":"https://openalex.org/keywords/coronavirus-disease-2019","display_name":"Coronavirus disease 2019 (COVID-19)","score":0.38135141134262085},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.37269335985183716},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3589133024215698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34715619683265686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3435271084308624},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.26211023330688477},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.24650731682777405}],"concepts":[{"id":"https://openalex.org/C2781390188","wikidata":"https://www.wikidata.org/wiki/Q25203449","display_name":"Spike (software development)","level":2,"score":0.6506766676902771},{"id":"https://openalex.org/C104292427","wikidata":"https://www.wikidata.org/wiki/Q899781","display_name":"Protein subunit","level":3,"score":0.5566130876541138},{"id":"https://openalex.org/C3007834351","wikidata":"https://www.wikidata.org/wiki/Q82069695","display_name":"Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)","level":5,"score":0.5478968620300293},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5061902403831482},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4609556496143341},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.4309884011745453},{"id":"https://openalex.org/C159047783","wikidata":"https://www.wikidata.org/wiki/Q7215","display_name":"Virology","level":1,"score":0.4162783920764923},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4153820872306824},{"id":"https://openalex.org/C3008058167","wikidata":"https://www.wikidata.org/wiki/Q84263196","display_name":"Coronavirus disease 2019 (COVID-19)","level":4,"score":0.38135141134262085},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.37269335985183716},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3589133024215698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34715619683265686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3435271084308624},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.26211023330688477},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.24650731682777405},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C524204448","wikidata":"https://www.wikidata.org/wiki/Q788926","display_name":"Infectious disease (medical specialty)","level":3,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000085962","descriptor_name":"Angiotensin-Converting Enzyme 2","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D000085962","descriptor_name":"Angiotensin-Converting Enzyme 2","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D000085962","descriptor_name":"Angiotensin-Converting Enzyme 2","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D000085962","descriptor_name":"Angiotensin-Converting Enzyme 2","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D000085962","descriptor_name":"Angiotensin-Converting Enzyme 2","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021122","descriptor_name":"Protein Subunits","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D021122","descriptor_name":"Protein Subunits","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D021122","descriptor_name":"Protein Subunits","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D021122","descriptor_name":"Protein Subunits","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D021122","descriptor_name":"Protein Subunits","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D021122","descriptor_name":"Protein Subunits","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D021122","descriptor_name":"Protein Subunits","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D021122","descriptor_name":"Protein Subunits","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D021122","descriptor_name":"Protein Subunits","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D021122","descriptor_name":"Protein Subunits","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbaf384","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbaf384","pdf_url":"https://academic.oup.com/bib/article-pdf/26/4/bbaf384/63926290/bbaf384.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:40755284","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40755284","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:12319310","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12319310","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bib/bbaf384","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbaf384","pdf_url":"https://academic.oup.com/bib/article-pdf/26/4/bbaf384/63926290/bbaf384.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":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"awards":[{"id":"https://openalex.org/G4900885053","display_name":null,"funder_award_id":"NIAID R01 AI170187","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5972039082","display_name":null,"funder_award_id":"R01 AI170187","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"},{"id":"https://openalex.org/G8956794174","display_name":null,"funder_award_id":"NIAID R01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412884821.pdf","grobid_xml":"https://content.openalex.org/works/W4412884821.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W2003503754","https://openalex.org/W2076048958","https://openalex.org/W2296045491","https://openalex.org/W2568617656","https://openalex.org/W2605343262","https://openalex.org/W2953008890","https://openalex.org/W2984894304","https://openalex.org/W3013800395","https://openalex.org/W3016636971","https://openalex.org/W3046463683","https://openalex.org/W3080773980","https://openalex.org/W3108980364","https://openalex.org/W3121000782","https://openalex.org/W3154495123","https://openalex.org/W3155806510","https://openalex.org/W3193589100","https://openalex.org/W3196710831","https://openalex.org/W3198423708","https://openalex.org/W3206756402","https://openalex.org/W3216019834","https://openalex.org/W4206912062","https://openalex.org/W4210831523","https://openalex.org/W4220807057","https://openalex.org/W4220886953","https://openalex.org/W4225492776","https://openalex.org/W4225591000","https://openalex.org/W4225851399","https://openalex.org/W4280491725","https://openalex.org/W4288066876","https://openalex.org/W4292779060","https://openalex.org/W4302293779","https://openalex.org/W4309486879","https://openalex.org/W4310557809","https://openalex.org/W4313488627","https://openalex.org/W4317376568","https://openalex.org/W4361213606","https://openalex.org/W4378470295","https://openalex.org/W4385245566","https://openalex.org/W4387540805","https://openalex.org/W4388024559","https://openalex.org/W4391018438","https://openalex.org/W4395451981","https://openalex.org/W4403731275","https://openalex.org/W4406261422","https://openalex.org/W4410325217"],"related_works":["https://openalex.org/W2174331923","https://openalex.org/W2050175337","https://openalex.org/W4408447381","https://openalex.org/W2329992713","https://openalex.org/W3050304047","https://openalex.org/W2317338006","https://openalex.org/W2385487847","https://openalex.org/W2062974934","https://openalex.org/W2385476654","https://openalex.org/W2904960904"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,45],"COVID-19":[2],"pandemic":[3],"has":[4,30],"caused":[5],"over":[6,224],"776":[7],"million":[8,12],"infections":[9],"and":[10,18,37,59,66,87,109,181,192,194,203,213,234,259,275,295,303,308,352],"7":[11],"deaths":[13],"globally":[14],"between":[15,178],"December":[16],"2019":[17],"November":[19,182],"2024.":[20],"Since":[21],"the":[22,25,42,50,70,131,265,280,306,334,347],"emergence":[23],"of":[24,186,196,208,226,252,283,311,336,349],"original":[26],"Wuhan":[27],"strain,":[28],"SARS-CoV-2":[29,140,152,341],"evolved":[31],"into":[32],"multiple":[33],"variants-including":[34],"Alpha,":[35],"Delta,":[36],"Omicron-primarily":[38],"through":[39],"mutations":[40,80,250,302,312],"in":[41,64,98,206,223,264,271,314,346],"Spike":[43,141,153],"glycoprotein.":[44],"S1":[46,154,165,342],"subunit,":[47],"which":[48],"binds":[49],"human":[51],"angiotensin-converting":[52],"enzyme":[53],"2":[54],"(ACE2)":[55],"receptor,":[56],"mutates":[57],"frequently":[58],"plays":[60],"a":[61,117,169,324],"key":[62,249],"role":[63],"infectivity":[65],"immune":[67],"escape,":[68],"while":[69],"more":[71],"conserved":[72],"S2":[73],"subunit":[74],"mediates":[75],"membrane":[76],"fusion.":[77],"Anticipating":[78],"future":[79,253,340],"is":[81,158],"essential":[82],"for":[83,293,327],"guiding":[84],"vaccine":[85],"design":[86],"therapeutic":[88],"strategies.":[89],"Generative":[90],"Large":[91],"Language":[92],"Models":[93],"(LLMs)":[94],"have":[95],"shown":[96],"promise":[97],"protein":[99,132],"sequence":[100,209],"modeling":[101],"due":[102],"to":[103,106,122,144,148,160,215,242,338],"their":[104],"capacity":[105],"produce":[107],"realistic":[108],"functional":[110,281],"synthetic":[111,151,164],"sequences.":[112],"Here,":[113],"we":[114],"introduce":[115],"SARITA,":[116],"GPT-3-based":[118],"LLM":[119],"with":[120,228,286],"up":[121],"1.2":[123],"billion":[124],"parameters,":[125],"fine-tuned":[126],"via":[127],"continual":[128],"learning":[129],"on":[130,136,174],"model":[133],"RITA":[134],"trained":[135],"107":[137],"017":[138],"high-quality":[139,150,221],"sequences":[142,176,222],"(up":[143],"March":[145,179,316],"1st":[146,317],"2021)":[147],"generate":[149,161],"subunits.":[155],"RESULTS:":[156],"SARITA":[157,219,299,337],"able":[159],"realistic,":[162],"full-length":[163],"subunits":[166],"starting":[167],"from":[168],"14-amino-acid":[170],"prompt.":[171],"When":[172],"evaluated":[173],"unseen":[175],"collected":[177],"2021":[180,318],"2023-including":[183],"major":[184],"Variants":[185,195],"Concern":[187],"(VOCs)":[188],"such":[189,198],"as":[190,199,255,323],"Delta":[191],"Omicron,":[193],"Interest":[197],"Iota-SARITA":[200],"outperforms":[201],"baseline":[202],"state-of-the-art":[204],"LLMs":[205],"terms":[207],"quality,":[210],"biological":[211],"plausibility,":[212],"similarity":[214,236],"real-world":[216],"viral":[217,328],"evolution.":[218,329],"generates":[220],"97%":[225],"cases,":[227],"markedly":[229],"lower":[230],"False":[231],"Mutation":[232],"Rate":[233],"higher":[235],"scores":[237],"(PAM30,":[238],"Levenshtein":[239],"distance)":[240],"compared":[241],"alternative":[243],"approaches.":[244],"It":[245],"also":[246],"accurately":[247,304],"reproduces":[248],"characteristic":[251],"variants-such":[254],"L212I,":[256],"R158L,":[257],"T95P,":[258],"E406K-which":[260],"were":[261],"not":[262],"present":[263],"training":[266],"data":[267],"but":[268],"emerged":[269],"later":[270],"VOCs":[272],"like":[273],"Omicron":[274],"Delta.":[276],"Structure-based":[277],"analysis":[278],"confirms":[279],"plausibility":[282],"these":[284],"substitutions,":[285],"\u0394\u0394G":[287],"values":[288],"within":[289],"experimentally":[290],"supported":[291],"thresholds":[292],"ACE2":[294],"antibody":[296],"binding.":[297],"Furthermore,":[298],"anticipates":[300],"immune-evasive":[301],"captures":[305],"positional":[307],"statistical":[309],"distribution":[310],"found":[313],"post-":[315],"variants,":[319],"highlighting":[320],"its":[321],"potential":[322,335],"predictive":[325],"tool":[326],"CONCLUSION:":[330],"These":[331],"results":[332],"indicate":[333],"predict":[339],"evolution,":[343],"potentially":[344],"aiding":[345],"development":[348],"adaptable":[350],"vaccines":[351],"treatments.":[353]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
