{"id":"https://openalex.org/W4404633904","doi":"https://doi.org/10.1093/bioinformatics/btae621","title":"Expert-guided protein language models enable accurate and blazingly fast fitness prediction","display_name":"Expert-guided protein language models enable accurate and blazingly fast fitness prediction","publication_year":2024,"publication_date":"2024-11-01","ids":{"openalex":"https://openalex.org/W4404633904","doi":"https://doi.org/10.1093/bioinformatics/btae621","pmid":"https://pubmed.ncbi.nlm.nih.gov/39576695"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae621","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae621","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae621/60791521/btae621.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/advance-article-pdf/doi/10.1093/bioinformatics/btae621/60791521/btae621.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005408973","display_name":"C\u00e9line Marquet","orcid":"https://orcid.org/0000-0002-8691-5791"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"C\u00e9line Marquet","raw_affiliation_strings":["School of Computation, Information, and Technology, Department of Informatics, Bioinformatics and Computational Biology, Technical University of Munich , Garching/Munich 85748,","Information and Technology","TUM School of Computation, Garching/Munich, 85748, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computation, Information, and Technology, Department of Informatics, Bioinformatics and Computational Biology, Technical University of Munich , Garching/Munich 85748,","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Information and Technology","institution_ids":[]},{"raw_affiliation_string":"TUM School of Computation, Garching/Munich, 85748, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095925073","display_name":"Julius Schlensok","orcid":"https://orcid.org/0009-0003-5106-7002"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julius Schlensok","raw_affiliation_strings":["School of Computation, Information, and Technology, Department of Informatics, Bioinformatics and Computational Biology, Technical University of Munich , Garching/Munich 85748,","TUM School of Computation, Garching/Munich, 85748, Germany","Information and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computation, Information, and Technology, Department of Informatics, Bioinformatics and Computational Biology, Technical University of Munich , Garching/Munich 85748,","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"TUM School of Computation, Garching/Munich, 85748, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Information and Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082179193","display_name":"Marina Abakarova","orcid":"https://orcid.org/0000-0002-4686-167X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]},{"id":"https://openalex.org/I4210097156","display_name":"Biologie Computationnelle, Quantitative et Synth\u00e9tique","ror":"https://ror.org/00pcqj134","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210096427","https://openalex.org/I4210097156"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marina Abakarova","raw_affiliation_strings":["Laboratory of Computational and Quantitative Biology, UMR 7238, Sorbonne Universit\u00e9, CNRS, IBPS , Paris 75005,","UMR U1284, Universite Paris Cit\u00e9, INSERM , Paris 75004,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Computational and Quantitative Biology, UMR 7238, Sorbonne Universit\u00e9, CNRS, IBPS , Paris 75005,","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210097156"]},{"raw_affiliation_string":"UMR U1284, Universite Paris Cit\u00e9, INSERM , Paris 75004,","institution_ids":["https://openalex.org/I154526488","https://openalex.org/I204730241","https://openalex.org/I4210091437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064905883","display_name":"Burkhard Rost","orcid":"https://orcid.org/0000-0003-0179-8424"},"institutions":[{"id":"https://openalex.org/I4210137766","display_name":"Institute for Advanced Study","ror":"https://ror.org/03xg85719","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210137766"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Burkhard Rost","raw_affiliation_strings":["School of Computation, Information, and Technology, Department of Informatics, Bioinformatics and Computational Biology, Technical University of Munich , Garching/Munich 85748,","School of Life Sciences Weihenstephan, Technical University of Munich , Freising,","Institute for Advanced Study (TUM-IAS), Garching/Munich, 85748, Germany","TUM School of Computation, Garching/Munich, 85748, Germany","Information and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computation, Information, and Technology, Department of Informatics, Bioinformatics and Computational Biology, Technical University of Munich , Garching/Munich 85748,","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"School of Life Sciences Weihenstephan, Technical University of Munich , Freising,","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Advanced Study (TUM-IAS), Garching/Munich, 85748, Germany","institution_ids":["https://openalex.org/I4210137766"]},{"raw_affiliation_string":"TUM School of Computation, Garching/Munich, 85748, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Information and Technology","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453514","display_name":"\u00c9lodie Laine","orcid":"https://orcid.org/0000-0003-4870-6304"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I185839726","display_name":"Institut Universitaire de France","ror":"https://ror.org/055khg266","country_code":"FR","type":"education","lineage":["https://openalex.org/I185839726"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210097156","display_name":"Biologie Computationnelle, Quantitative et Synth\u00e9tique","ror":"https://ror.org/00pcqj134","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210096427","https://openalex.org/I4210097156"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Elodie Laine","raw_affiliation_strings":["Institut Universitaire de France , Paris 75005,","Laboratory of Computational and Quantitative Biology, UMR 7238, Sorbonne Universit\u00e9, CNRS, IBPS , Paris 75005,"],"raw_orcid":"https://orcid.org/0000-0003-4870-6304","affiliations":[{"raw_affiliation_string":"Institut Universitaire de France , Paris 75005,","institution_ids":["https://openalex.org/I185839726"]},{"raw_affiliation_string":"Laboratory of Computational and Quantitative Biology, UMR 7238, Sorbonne Universit\u00e9, CNRS, IBPS , Paris 75005,","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210097156"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5005408973","https://openalex.org/A5076453514"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I185839726","https://openalex.org/I39804081","https://openalex.org/I4210097156","https://openalex.org/I62916508"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":12.1819,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.99036151,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"40","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.6276000142097473,"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":0.6276000142097473,"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":0.11190000176429749,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.04729999974370003,"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/computer-science","display_name":"Computer science","score":0.720770537853241},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4841483235359192},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46364250779151917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35544294118881226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.720770537853241},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4841483235359192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46364250779151917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35544294118881226}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004331","descriptor_name":"Drosophila melanogaster","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004331","descriptor_name":"Drosophila melanogaster","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004331","descriptor_name":"Drosophila melanogaster","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004331","descriptor_name":"Drosophila melanogaster","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004331","descriptor_name":"Drosophila melanogaster","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004331","descriptor_name":"Drosophila melanogaster","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004331","descriptor_name":"Drosophila melanogaster","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020125","descriptor_name":"Mutation, Missense","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020125","descriptor_name":"Mutation, Missense","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020125","descriptor_name":"Mutation, Missense","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020125","descriptor_name":"Mutation, Missense","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020125","descriptor_name":"Mutation, Missense","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020125","descriptor_name":"Mutation, Missense","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020125","descriptor_name":"Mutation, Missense","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btae621","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae621","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae621/60791521/btae621.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:39576695","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39576695","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:HAL:hal-04801953v1","is_oa":true,"landing_page_url":"https://hal.sorbonne-universite.fr/hal-04801953","pdf_url":"https://hal.sorbonne-universite.fr/hal-04801953/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Bioinformatics, 2024, &#x27E8;10.1093/bioinformatics/btae621&#x27E9;","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11588025","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11588025","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11588025/pdf/btae621.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btae621","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae621","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae621/60791521/btae621.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":[{"id":"https://openalex.org/G1270295441","display_name":null,"funder_award_id":"DFG-GZ: RO1320/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G272277265","display_name":null,"funder_award_id":"101087830","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4565363061","display_name":"Ageing and Natural DeAth GenetIc cOntrollers","funder_award_id":"ANR-20-CE44-0010","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G7542597935","display_name":null,"funder_award_id":"RO1320/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320308269","display_name":"Alexander von Humboldt-Stiftung","ror":"https://ror.org/012kf4317"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320330232","display_name":"Sorbonne Universit\u00e9","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404633904.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1563940013","https://openalex.org/W1683278196","https://openalex.org/W2035991134","https://openalex.org/W2060588922","https://openalex.org/W2066001051","https://openalex.org/W2094223039","https://openalex.org/W2143238378","https://openalex.org/W2245592118","https://openalex.org/W2344038501","https://openalex.org/W2521967673","https://openalex.org/W2611293415","https://openalex.org/W2774216375","https://openalex.org/W2884968852","https://openalex.org/W2914213386","https://openalex.org/W2919115771","https://openalex.org/W2950954328","https://openalex.org/W2967474035","https://openalex.org/W2980282514","https://openalex.org/W2997234557","https://openalex.org/W3010879523","https://openalex.org/W3134186384","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3179485843","https://openalex.org/W3209435229","https://openalex.org/W3211728297","https://openalex.org/W3216341763","https://openalex.org/W4225868104","https://openalex.org/W4281648132","https://openalex.org/W4281790889","https://openalex.org/W4285098076","https://openalex.org/W4300594491","https://openalex.org/W4309506674","https://openalex.org/W4309958141","https://openalex.org/W4313291879","https://openalex.org/W4313500062","https://openalex.org/W4313530868","https://openalex.org/W4327550249","https://openalex.org/W4360612265","https://openalex.org/W4367055489","https://openalex.org/W4376612841","https://openalex.org/W4380422659","https://openalex.org/W4380551121","https://openalex.org/W4384200881","https://openalex.org/W4384820649","https://openalex.org/W4386861232","https://openalex.org/W4387303685","https://openalex.org/W4388024559","https://openalex.org/W4388486405","https://openalex.org/W4389472984","https://openalex.org/W4392686654","https://openalex.org/W4394946907","https://openalex.org/W6633589378"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"MOTIVATION:":[0],"Exhaustive":[1],"experimental":[2,55],"annotation":[3],"of":[4,7,54,62,111,123,139,142,149],"the":[5,17,52,70,74,91,105,132,137],"effect":[6,21,33,78],"all":[8,146,150],"known":[9],"protein":[10,36],"variants":[11,68],"remains":[12],"daunting":[13],"and":[14,94,187],"expensive,":[15],"stressing":[16],"need":[18],"for":[19],"scalable":[20],"predictions.":[22],"We":[23],"introduce":[24],"VespaG,":[25],"a":[26,44,60,82,119,166],"blazingly":[27],"fast":[28],"missense":[29],"amino":[30,66],"acid":[31,67],"variant":[32,112],"predictor,":[34],"leveraging":[35],"language":[37],"model":[38],"(pLM)":[39],"embeddings":[40],"as":[41,81,155],"input":[42],"to":[43,90],"minimal":[45],"deep":[46],"learning":[47],"model.":[48],"RESULTS:":[49],"To":[50],"overcome":[51],"sparsity":[53],"training":[56,185],"data,":[57],"we":[58],"created":[59],"dataset":[61],"39":[63],"million":[64,115],"single":[65],"from":[69],"human":[71],"proteome":[72],"applying":[73],"multiple":[75],"sequence":[76],"alignment-based":[77],"predictor":[79],"GEMME":[80],"pseudo":[83],"standard-of-truth.":[84],"This":[85],"setup":[86],"increases":[87],"interpretability":[88],"compared":[89],"baseline":[92],"pLM":[93],"is":[95,178],"easily":[96],"retrainable":[97],"with":[98],"novel":[99],"or":[100,158],"updated":[101],"pLMs.":[102],"Assessed":[103],"against":[104],"ProteinGym":[106],"benchmark":[107],"(217":[108],"multiplex":[109],"assays":[110],"effect-MAVE-with":[113],"2.5":[114],"variants),":[116],"VespaG":[117,135,177],"achieved":[118],"mean":[120],"Spearman":[121],"correlation":[122],"0.48":[124],"\u00b1":[125],"0.02,":[126],"matching":[127],"top-performing":[128],"methods":[129],"evaluated":[130],"on":[131,165],"same":[133],"data.":[134],"has":[136],"advantage":[138],"being":[140],"orders":[141],"magnitude":[143],"faster,":[144],"predicting":[145],"mutational":[147],"landscapes":[148],"proteins":[151],"in":[152,161],"proteomes":[153],"such":[154],"Homo":[156],"sapiens":[157],"Drosophila":[159],"melanogaster":[160],"under":[162],"30":[163],"min":[164],"consumer":[167],"laptop":[168],"(12-core":[169],"CPU,":[170],"16":[171],"GB":[172],"RAM).":[173],"AVAILABILITY":[174],"AND":[175],"IMPLEMENTATION:":[176],"available":[179,190],"freely":[180],"at":[181,191],"https://github.com/jschlensok/vespag.":[182],"The":[183],"associated":[184],"data":[186],"predictions":[188],"are":[189],"https://doi.org/10.5281/zenodo.11085958.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}
