{"id":"https://openalex.org/W3177500196","doi":"https://doi.org/10.1109/tpami.2021.3095381","title":"ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning","display_name":"ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning","publication_year":2021,"publication_date":"2021-07-07","ids":{"openalex":"https://openalex.org/W3177500196","doi":"https://doi.org/10.1109/tpami.2021.3095381","mag":"3177500196","pmid":"https://pubmed.ncbi.nlm.nih.gov/34232869"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3095381","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3095381","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tpami.2021.3095381","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106730664","display_name":"Ahmed Elnaggar","orcid":"https://orcid.org/0000-0002-4998-312X"},"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":"Ahmed Elnaggar","raw_affiliation_strings":["Department of Informatics, Bioinformatics & Computational Biology - i12, Technical University of Munich (TUM), Garching/Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4998-312X","affiliations":[{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology - i12, Technical University of Munich (TUM), Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075726670","display_name":"Michael Heinzinger","orcid":"https://orcid.org/0000-0002-9601-3580"},"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":"Michael Heinzinger","raw_affiliation_strings":["Department of Informatics, Bioinformatics & Computational Biology - i12, Technical University of Munich (TUM), Garching/Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-9601-3580","affiliations":[{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology - i12, Technical University of Munich (TUM), Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088531553","display_name":"Christian Dallago","orcid":"https://orcid.org/0000-0003-4650-6181"},"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":"Christian Dallago","raw_affiliation_strings":["Department of Informatics, Bioinformatics & Computational Biology - i12, Technical University of Munich (TUM), Garching/Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4650-6181","affiliations":[{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology - i12, Technical University of Munich (TUM), Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017006282","display_name":"Ghalia Rehawi","orcid":"https://orcid.org/0000-0001-5115-8658"},"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":"Ghalia Rehawi","raw_affiliation_strings":["Department of Informatics, Bioinformatics & Computational Biology - i12, Technical University of Munich (TUM), Garching/Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5115-8658","affiliations":[{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology - i12, Technical University of Munich (TUM), Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053242621","display_name":"Yu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Med AI Technology (Wu Xi) Ltd., Wu Xi, Jiang Su, China"],"raw_orcid":"https://orcid.org/0000-0003-4976-9366","affiliations":[{"raw_affiliation_string":"Med AI Technology (Wu Xi) Ltd., Wu Xi, Jiang Su, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023448834","display_name":"Llion Jones","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Llion Jones","raw_affiliation_strings":["Google AI, Google, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google AI, Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069058332","display_name":"Tom Gibbs","orcid":"https://orcid.org/0000-0002-9196-5830"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Gibbs","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9196-5830","affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066682900","display_name":"T. Feh\u00e9r","orcid":"https://orcid.org/0000-0003-2095-4349"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamas Feher","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2095-4349","affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063763851","display_name":"Christoph Angerer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christoph Angerer","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019985343","display_name":"Martin Steinegger","orcid":"https://orcid.org/0000-0001-8781-9753"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Martin Steinegger","raw_affiliation_strings":["School of Biological Sciences, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biological Sciences, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032222900","display_name":"Debsindhu Bhowmik","orcid":"https://orcid.org/0000-0001-7770-9091"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debsindhu Bhowmik","raw_affiliation_strings":["Oak Ridge National Laboratory (ORNL), Oak Ridge, TN, USA"],"raw_orcid":"https://orcid.org/0000-0001-7770-9091","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory (ORNL), Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064905883","display_name":"Burkhard Rost","orcid":"https://orcid.org/0000-0003-0179-8424"},"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":"Burkhard Rost","raw_affiliation_strings":["Department of Informatics, Bioinformatics & Computational Biology - i12, Technical University of Munich (TUM), Garching/Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0179-8424","affiliations":[{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology - i12, Technical University of Munich (TUM), Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5106730664"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":153.7784,"has_fulltext":false,"cited_by_count":2164,"citation_normalized_percentile":{"value":0.99981821,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"44","issue":"10","first_page":"7112","last_page":"7127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10636","display_name":"Innovative Teaching and Learning Methods","score":0.9592999815940857,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6717120409011841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6226099133491516},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48765242099761963},{"id":"https://openalex.org/keywords/language-acquisition","display_name":"Language acquisition","score":0.4746846854686737},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4733840525150299},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23046717047691345},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.12602201104164124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6717120409011841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6226099133491516},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48765242099761963},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.4746846854686737},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4733840525150299},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23046717047691345},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.12602201104164124}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"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}],"locations_count":5,"locations":[{"id":"doi:10.1109/tpami.2021.3095381","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3095381","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:34232869","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34232869","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":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:mediatum.ub.tum.de:node/1772683","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1772683","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"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":null,"raw_type":"article"},{"id":"pmh:oai:osti.gov:1968363","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1968363","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:osti.gov:1968366","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1968366","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1109/tpami.2021.3095381","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3095381","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G2088101978","display_name":null,"funder_award_id":"2019R1A6A1A10073437","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8877558626","display_name":null,"funder_award_id":"NRF-2020M3A9G7103933","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":123,"referenced_works":["https://openalex.org/W93532817","https://openalex.org/W1499450468","https://openalex.org/W1501531009","https://openalex.org/W1982825626","https://openalex.org/W1985818354","https://openalex.org/W1996073320","https://openalex.org/W2013136212","https://openalex.org/W2029476353","https://openalex.org/W2030395559","https://openalex.org/W2051545676","https://openalex.org/W2057820165","https://openalex.org/W2061042699","https://openalex.org/W2084620575","https://openalex.org/W2089999388","https://openalex.org/W2102461176","https://openalex.org/W2104972430","https://openalex.org/W2110510374","https://openalex.org/W2111973517","https://openalex.org/W2120671490","https://openalex.org/W2121085676","https://openalex.org/W2130479394","https://openalex.org/W2143210482","https://openalex.org/W2147717514","https://openalex.org/W2153153865","https://openalex.org/W2165795960","https://openalex.org/W2168970921","https://openalex.org/W2173591891","https://openalex.org/W2187089797","https://openalex.org/W2271840356","https://openalex.org/W2342838938","https://openalex.org/W2491528959","https://openalex.org/W2517405041","https://openalex.org/W2546302380","https://openalex.org/W2567587907","https://openalex.org/W2606722458","https://openalex.org/W2607268717","https://openalex.org/W2611669587","https://openalex.org/W2730472814","https://openalex.org/W2769882797","https://openalex.org/W2809901035","https://openalex.org/W2883004550","https://openalex.org/W2896457183","https://openalex.org/W2897944569","https://openalex.org/W2902353954","https://openalex.org/W2909727437","https://openalex.org/W2913820882","https://openalex.org/W2943495267","https://openalex.org/W2949342052","https://openalex.org/W2950374603","https://openalex.org/W2950784811","https://openalex.org/W2950954328","https://openalex.org/W2951433247","https://openalex.org/W2952209472","https://openalex.org/W2952317511","https://openalex.org/W2953008890","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2963457143","https://openalex.org/W2964110616","https://openalex.org/W2964308564","https://openalex.org/W2970597249","https://openalex.org/W2973727699","https://openalex.org/W2976222273","https://openalex.org/W2977720775","https://openalex.org/W2980789587","https://openalex.org/W2994687354","https://openalex.org/W2995435108","https://openalex.org/W2995514860","https://openalex.org/W2996428491","https://openalex.org/W2997234557","https://openalex.org/W3010387158","https://openalex.org/W3101509328","https://openalex.org/W3111174583","https://openalex.org/W3118936575","https://openalex.org/W3136918052","https://openalex.org/W3163595068","https://openalex.org/W3197123494","https://openalex.org/W4225868104","https://openalex.org/W4242716081","https://openalex.org/W4242765109","https://openalex.org/W4287704453","https://openalex.org/W4287824654","https://openalex.org/W4288089799","https://openalex.org/W4288103164","https://openalex.org/W4292779060","https://openalex.org/W4294170691","https://openalex.org/W4295312788","https://openalex.org/W4295838474","https://openalex.org/W4301239768","https://openalex.org/W4301425111","https://openalex.org/W4323654151","https://openalex.org/W4385245566","https://openalex.org/W6679434410","https://openalex.org/W6682691769","https://openalex.org/W6694517276","https://openalex.org/W6723244650","https://openalex.org/W6726568470","https://openalex.org/W6731867162","https://openalex.org/W6739901393","https://openalex.org/W6748645090","https://openalex.org/W6752790953","https://openalex.org/W6755207826","https://openalex.org/W6758485811","https://openalex.org/W6761628794","https://openalex.org/W6762287338","https://openalex.org/W6762363781","https://openalex.org/W6763701032","https://openalex.org/W6763868836","https://openalex.org/W6766978945","https://openalex.org/W6767868144","https://openalex.org/W6767997687","https://openalex.org/W6768021236","https://openalex.org/W6768317493","https://openalex.org/W6768580128","https://openalex.org/W6769627184","https://openalex.org/W6771265304","https://openalex.org/W6771626834","https://openalex.org/W6771917389","https://openalex.org/W6778883912","https://openalex.org/W6780043775","https://openalex.org/W6781533629","https://openalex.org/W6787324736","https://openalex.org/W6791955017"],"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":{"Computational":[0],"biology":[1],"and":[2,41,53,75,136],"bioinformatics":[3],"provide":[4],"vast":[5],"data":[6,50,90],"gold-mines":[7],"from":[8,17,51,88],"protein":[9,63,96,119,130],"sequences,":[10],"ideal":[11],"for":[12,25,109,151],"Language":[13,19],"Models":[14],"(LMs)":[15],"taken":[16],"Natural":[18],"Processing":[20],"(NLP).":[21],"These":[22],"LMs":[23,64],"reach":[24],"new":[26],"prediction":[27,117],"frontiers":[28],"at":[29],"low":[30],"inference":[31],"costs.":[32],"Here,":[33],"we":[34],"trained":[35,67],"two":[36],"auto-regressive":[37],"models":[38,44,190],"(Transformer-XL,":[39],"XLNet)":[40],"four":[42],"auto-encoder":[43],"(BERT,":[45],"Albert,":[46],"Electra,":[47],"T5)":[48],"on":[49,68],"UniRef":[52],"BFD":[54],"containing":[55],"up":[56],"to":[57],"393":[58],"billion":[59],"amino":[60],"acids.":[61],"The":[62],"(pLMs)":[65],"were":[66],"the":[69,85,100,104,146,152,156,173,181,184],"Summit":[70],"supercomputer":[71],"using":[72,103],"5616":[73],"GPUs":[74],"TPU":[76],"Pod":[77],"up-to":[78],"1024":[79],"cores.":[80],"Dimensionality":[81],"reduction":[82],"revealed":[83],"that":[84,176],"raw":[86],"pLM-embeddings":[87],"unlabeled":[89],"captured":[91],"some":[92,179],"biophysical":[93],"features":[94],"of":[95,102,118,129,180,183,186],"sequences.":[97],"We":[98],"validated":[99],"advantage":[101],"embeddings":[105,149],"as":[106],"exclusive":[107],"input":[108],"several":[110],"subsequent":[111],"tasks:":[112],"(1)":[113],"a":[114],"per-residue":[115],"(per-token)":[116],"secondary":[120,144],"structure":[121],"(3-state":[122],"accuracy":[123,141],"Q3=81%-87%);":[124],"(2)":[125],"per-protein":[126],"(pooling)":[127],"predictions":[128],"sub-cellular":[131],"location":[132],"(ten-state":[133],"accuracy:":[134],"Q10=81%)":[135],"membrane":[137],"versus":[138],"water-soluble":[139],"(2-state":[140],"Q2=91%).":[142],"For":[143],"structure,":[145],"most":[147],"informative":[148],"(ProtT5)":[150],"first":[153],"time":[154],"outperformed":[155],"state-of-the-art":[157],"without":[158],"multiple":[159],"sequence":[160],"alignments":[161],"(MSAs)":[162],"or":[163],"evolutionary":[164],"information":[165],"thereby":[166],"bypassing":[167],"expensive":[168],"database":[169],"searches.":[170],"Taken":[171],"together,":[172],"results":[174],"implied":[175],"pLMs":[177],"learned":[178],"grammar":[182],"language":[185],"life.":[187],"All":[188],"our":[189],"are":[191],"available":[192],"through":[193],"https://github.com/agemagician/ProtTrans.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":252},{"year":2025,"cited_by_count":813},{"year":2024,"cited_by_count":629},{"year":2023,"cited_by_count":316},{"year":2022,"cited_by_count":121},{"year":2021,"cited_by_count":33}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}