{"id":"https://openalex.org/W3146944767","doi":"https://doi.org/10.1073/pnas.2016239118","title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","display_name":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","publication_year":2021,"publication_date":"2021-04-05","ids":{"openalex":"https://openalex.org/W3146944767","doi":"https://doi.org/10.1073/pnas.2016239118","mag":"3146944767","pmid":"https://pubmed.ncbi.nlm.nih.gov/33876751"},"language":"en","primary_location":{"id":"doi:10.1073/pnas.2016239118","is_oa":true,"landing_page_url":"https://doi.org/10.1073/pnas.2016239118","pdf_url":"https://www.pnas.org/content/pnas/118/15/e2016239118.full.pdf","source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.pnas.org/content/pnas/118/15/e2016239118.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029063409","display_name":"Alexander Rives","orcid":"https://orcid.org/0000-0003-2208-0796"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alexander Rives","raw_affiliation_strings":["Department of Computer Science, New York University, New York, NY 10012;","Facebook AI Research, New York, NY 10003;"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, New York University, New York, NY 10012;","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Facebook AI Research, New York, NY 10003;","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013933539","display_name":"Joshua Meier","orcid":"https://orcid.org/0000-0001-5934-2097"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Meier","raw_affiliation_strings":["Facebook AI Research, New York, NY 10003;"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, New York, NY 10003;","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006044037","display_name":"Tom Sercu","orcid":"https://orcid.org/0000-0003-2947-6064"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Sercu","raw_affiliation_strings":["Facebook AI Research, New York, NY 10003;"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, New York, NY 10003;","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109633499","display_name":"Siddharth Goyal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Goyal","raw_affiliation_strings":["Facebook AI Research, New York, NY 10003;"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, New York, NY 10003;","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101484037","display_name":"Zeming Lin","orcid":"https://orcid.org/0000-0002-0883-1373"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeming Lin","raw_affiliation_strings":["Department of Computer Science, New York University, New York, NY 10012;"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, New York University, New York, NY 10012;","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101968034","display_name":"Jason Liu","orcid":"https://orcid.org/0000-0001-7197-7319"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Liu","raw_affiliation_strings":["Facebook AI Research, New York, NY 10003;"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, New York, NY 10003;","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049260750","display_name":"Demi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Demi Guo","raw_affiliation_strings":["Harvard University, Cambridge, MA 02138;"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA 02138;","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076248976","display_name":"Myle Ott","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Myle Ott","raw_affiliation_strings":["Facebook AI Research, New York, NY 10003;"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, New York, NY 10003;","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058450549","display_name":"C. Lawrence Zitnick","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lawrence Zitnick","raw_affiliation_strings":["Facebook AI Research, New York, NY 10003;"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, New York, NY 10003;","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101481224","display_name":"Jerry Ma","orcid":"https://orcid.org/0000-0003-4853-0724"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jerry Ma","raw_affiliation_strings":["Booth School of Business, University of Chicago, Chicago, IL 60637;","Yale Law School, New Haven, CT 06511"],"affiliations":[{"raw_affiliation_string":"Booth School of Business, University of Chicago, Chicago, IL 60637;","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"Yale Law School, New Haven, CT 06511","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089960673","display_name":"Rob Fergus","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Fergus","raw_affiliation_strings":["Department of Computer Science, New York University, New York, NY 10012;"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, New York University, New York, NY 10012;","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5029063409"],"corresponding_institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":148.5266,"has_fulltext":false,"cited_by_count":2916,"citation_normalized_percentile":{"value":0.99990671,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"118","issue":"15","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9991999864578247,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9966999888420105,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6409164071083069},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.545437753200531},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5281438827514648},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5140217542648315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49223676323890686},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47371500730514526},{"id":"https://openalex.org/keywords/protein-secondary-structure","display_name":"Protein secondary structure","score":0.4280596971511841},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.21848905086517334}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6409164071083069},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.545437753200531},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5281438827514648},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5140217542648315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49223676323890686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47371500730514526},{"id":"https://openalex.org/C62614982","wikidata":"https://www.wikidata.org/wiki/Q904984","display_name":"Protein secondary structure","level":2,"score":0.4280596971511841},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.21848905086517334},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1073/pnas.2016239118","is_oa":true,"landing_page_url":"https://doi.org/10.1073/pnas.2016239118","pdf_url":"https://www.pnas.org/content/pnas/118/15/e2016239118.full.pdf","source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},{"id":"pmid:33876751","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33876751","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":"Proceedings of the National Academy of Sciences of the United States of America","raw_type":null},{"id":"pmh:oai:uchicago.tind.io:9666","is_oa":true,"landing_page_url":"http://knowledge.uchicago.edu/record/9666","pdf_url":null,"source":{"id":"https://openalex.org/S4306402460","display_name":"Knowledge@UChicago (University of Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40347166","host_organization_name":"University of Chicago","host_organization_lineage":["https://openalex.org/I40347166"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://knowledge.uchicago.edu/record/9666","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8053943","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8053943","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Natl Acad Sci U S A","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1073/pnas.2016239118","is_oa":true,"landing_page_url":"https://doi.org/10.1073/pnas.2016239118","pdf_url":"https://www.pnas.org/content/pnas/118/15/e2016239118.full.pdf","source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7162472935","display_name":null,"funder_award_id":"1339362","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3146944767.pdf","grobid_xml":"https://content.openalex.org/works/W3146944767.grobid-xml"},"referenced_works_count":92,"referenced_works":["https://openalex.org/W1514077080","https://openalex.org/W1861406683","https://openalex.org/W1936034247","https://openalex.org/W1936662467","https://openalex.org/W1971896762","https://openalex.org/W1976666280","https://openalex.org/W1979762151","https://openalex.org/W1985471077","https://openalex.org/W2008545402","https://openalex.org/W2021312899","https://openalex.org/W2051210555","https://openalex.org/W2055043387","https://openalex.org/W2059117301","https://openalex.org/W2060300932","https://openalex.org/W2060588922","https://openalex.org/W2061042699","https://openalex.org/W2076048958","https://openalex.org/W2102461176","https://openalex.org/W2104972430","https://openalex.org/W2106694138","https://openalex.org/W2112837356","https://openalex.org/W2114340287","https://openalex.org/W2117130368","https://openalex.org/W2118756701","https://openalex.org/W2124343374","https://openalex.org/W2137566700","https://openalex.org/W2147526198","https://openalex.org/W2150853465","https://openalex.org/W2151831732","https://openalex.org/W2161062388","https://openalex.org/W2161072217","https://openalex.org/W2166701319","https://openalex.org/W2169478909","https://openalex.org/W2170973209","https://openalex.org/W2171641243","https://openalex.org/W2187089797","https://openalex.org/W2245592118","https://openalex.org/W2385735394","https://openalex.org/W2546302380","https://openalex.org/W2557595285","https://openalex.org/W2559655401","https://openalex.org/W2593864460","https://openalex.org/W2612690371","https://openalex.org/W2742834898","https://openalex.org/W2774216375","https://openalex.org/W2791796577","https://openalex.org/W2801109052","https://openalex.org/W2882319491","https://openalex.org/W2890223884","https://openalex.org/W2900065283","https://openalex.org/W2900092738","https://openalex.org/W2900629010","https://openalex.org/W2909727437","https://openalex.org/W2943495267","https://openalex.org/W2949867299","https://openalex.org/W2950374603","https://openalex.org/W2950577311","https://openalex.org/W2951433247","https://openalex.org/W2956569764","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W2967606876","https://openalex.org/W2970119519","https://openalex.org/W2971227267","https://openalex.org/W2971803505","https://openalex.org/W2977684889","https://openalex.org/W2980789587","https://openalex.org/W2993794083","https://openalex.org/W2995514860","https://openalex.org/W2996378307","https://openalex.org/W2998704965","https://openalex.org/W2998737920","https://openalex.org/W2999044305","https://openalex.org/W2999481648","https://openalex.org/W3010387158","https://openalex.org/W3015572436","https://openalex.org/W3015700791","https://openalex.org/W3037888463","https://openalex.org/W3088059392","https://openalex.org/W3102341076","https://openalex.org/W3132323068","https://openalex.org/W3146944767","https://openalex.org/W3163435021","https://openalex.org/W3198971594","https://openalex.org/W3199799076","https://openalex.org/W4211054902","https://openalex.org/W4249478743","https://openalex.org/W4285719527","https://openalex.org/W6640598943","https://openalex.org/W6680532216","https://openalex.org/W6685158001","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"In":[0,30],"the":[1,31,34,50,123,145],"field":[2],"of":[3,8,37,52,125,128,134,163,169],"artificial":[4,62],"intelligence,":[5],"a":[6,55,75,117,161],"combination":[7],"scale":[9,51],"in":[10,24,101,144],"data":[11,41,110],"and":[12,27,60,139,147,172,175],"model":[13,79,95],"capacity":[14],"enabled":[15],"by":[16,151],"unsupervised":[17,71],"learning":[18,26,72,155],"has":[19,116],"led":[20],"to":[21,73,131],"major":[22],"advances":[23],"representation":[25,114],"statistical":[28],"generation.":[29],"life":[32],"sciences,":[33],"anticipated":[35],"growth":[36],"sequencing":[38],"promises":[39],"unprecedented":[40],"on":[42,80],"natural":[43],"sequence":[44,109],"diversity.":[45,92],"Protein":[46],"language":[47,78],"modeling":[48],"at":[49],"evolution":[53],"is":[54,142],"logical":[56],"step":[57],"toward":[58],"predictive":[59],"generative":[61],"intelligence":[63],"for":[64,179],"biology.":[65],"To":[66],"this":[67],"end,":[68],"we":[69],"use":[70],"train":[74],"deep":[76],"contextual":[77],"86":[81],"billion":[82],"amino":[83,129],"acids":[84,130],"across":[85,160],"250":[86],"million":[87],"protein":[88],"sequences":[89],"spanning":[90],"evolutionary":[91],"The":[93,104,112],"resulting":[94],"contains":[96],"information":[97],"about":[98,137],"biological":[99],"properties":[100,127],"its":[102],"representations.":[103],"representations":[105,146],"are":[106],"learned":[107,113],"from":[108,122],"alone.":[111],"space":[115],"multiscale":[118],"organization":[119],"reflecting":[120],"structure":[121,141,174],"level":[124],"biochemical":[126],"remote":[132],"homology":[133],"proteins.":[135],"Information":[136],"secondary":[138,173],"tertiary":[140],"encoded":[143],"can":[148],"be":[149],"identified":[150],"linear":[152],"projections.":[153],"Representation":[154],"produces":[156],"features":[157,178],"that":[158],"generalize":[159],"range":[162],"applications,":[164],"enabling":[165],"state-of-the-art":[166,177],"supervised":[167],"prediction":[168],"mutational":[170],"effect":[171],"improving":[176],"long-range":[180],"contact":[181],"prediction.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":206},{"year":2025,"cited_by_count":839},{"year":2024,"cited_by_count":774},{"year":2023,"cited_by_count":530},{"year":2022,"cited_by_count":339},{"year":2021,"cited_by_count":174},{"year":2020,"cited_by_count":41},{"year":2019,"cited_by_count":11},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2025-10-10T00:00:00"}