{"id":"https://openalex.org/W4362664122","doi":"https://doi.org/10.1038/s42256-023-00637-1","title":"Linguistically inspired roadmap for building biologically reliable protein language models","display_name":"Linguistically inspired roadmap for building biologically reliable protein language models","publication_year":2023,"publication_date":"2023-04-06","ids":{"openalex":"https://openalex.org/W4362664122","doi":"https://doi.org/10.1038/s42256-023-00637-1"},"language":"en","primary_location":{"id":"doi:10.1038/s42256-023-00637-1","is_oa":false,"landing_page_url":"https://doi.org/10.1038/s42256-023-00637-1","pdf_url":null,"source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078756035","display_name":"Mai Ha Vu","orcid":"https://orcid.org/0000-0002-9702-226X"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Mai Ha Vu","raw_affiliation_strings":["Department of Linguistics and Scandinavian Studies, University of Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-9702-226X","affiliations":[{"raw_affiliation_string":"Department of Linguistics and Scandinavian Studies, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017929614","display_name":"Rahmad Akbar","orcid":"https://orcid.org/0000-0002-6692-0876"},"institutions":[{"id":"https://openalex.org/I1281400175","display_name":"Oslo University Hospital","ror":"https://ror.org/00j9c2840","country_code":"NO","type":"healthcare","lineage":["https://openalex.org/I1281400175"]},{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Rahmad Akbar","raw_affiliation_strings":["Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-6692-0876","affiliations":[{"raw_affiliation_string":"Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway","institution_ids":["https://openalex.org/I1281400175","https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000751357","display_name":"Philippe A. Robert","orcid":"https://orcid.org/0000-0003-1345-5015"},"institutions":[{"id":"https://openalex.org/I1281400175","display_name":"Oslo University Hospital","ror":"https://ror.org/00j9c2840","country_code":"NO","type":"healthcare","lineage":["https://openalex.org/I1281400175"]},{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Philippe A. Robert","raw_affiliation_strings":["Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0003-1345-5015","affiliations":[{"raw_affiliation_string":"Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway","institution_ids":["https://openalex.org/I1281400175","https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074531013","display_name":"Bart\u0142omiej \u015awi\u0105tczak","orcid":"https://orcid.org/0000-0001-6767-3064"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bartlomiej Swiatczak","raw_affiliation_strings":["Department of History of Science and Scientific Archeology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-6767-3064","affiliations":[{"raw_affiliation_string":"Department of History of Science and Scientific Archeology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054500587","display_name":"Geir Kjetil Sandve","orcid":"https://orcid.org/0000-0002-4959-1409"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Geir Kjetil Sandve","raw_affiliation_strings":["Department of Informatics, University of Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0002-4959-1409","affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089158926","display_name":"Victor Greiff","orcid":"https://orcid.org/0000-0003-2622-5032"},"institutions":[{"id":"https://openalex.org/I1281400175","display_name":"Oslo University Hospital","ror":"https://ror.org/00j9c2840","country_code":"NO","type":"healthcare","lineage":["https://openalex.org/I1281400175"]},{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Victor Greiff","raw_affiliation_strings":["Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0003-2622-5032","affiliations":[{"raw_affiliation_string":"Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway","institution_ids":["https://openalex.org/I1281400175","https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012620009","display_name":"Dag Haug","orcid":"https://orcid.org/0000-0001-5275-8073"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Dag Trygve Truslew Haug","raw_affiliation_strings":["Department of Linguistics and Scandinavian Studies, University of Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0001-5275-8073","affiliations":[{"raw_affiliation_string":"Department of Linguistics and Scandinavian Studies, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5012620009"],"corresponding_institution_ids":["https://openalex.org/I184942183"],"apc_list":{"value":9750,"currency":"EUR","value_usd":11690},"apc_paid":null,"fwci":8.9133,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.98412143,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"5","issue":"5","first_page":"485","last_page":"496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9965000152587891,"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":0.9965000152587891,"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":0.9932000041007996,"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":0.9876000285148621,"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":0.7003377079963684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5079286694526672},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5014452934265137},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.460647851228714},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4579026699066162},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33272993564605713},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11523163318634033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7003377079963684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5079286694526672},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5014452934265137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.460647851228714},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4579026699066162},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33272993564605713},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11523163318634033},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1038/s42256-023-00637-1","is_oa":false,"landing_page_url":"https://doi.org/10.1038/s42256-023-00637-1","pdf_url":null,"source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4530412850","display_name":null,"funder_award_id":"2019PG-T1D011","funder_id":"https://openalex.org/F4320309446","funder_display_name":"Leona M. and Harry B. Helmsley Charitable Trust"},{"id":"https://openalex.org/G512131340","display_name":null,"funder_award_id":"311341","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"},{"id":"https://openalex.org/G5476840626","display_name":null,"funder_award_id":"215817","funder_id":"https://openalex.org/F4320310758","funder_display_name":"Kreftforeningen"},{"id":"https://openalex.org/G7508303142","display_name":null,"funder_award_id":"825821","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G7694509137","display_name":null,"funder_award_id":"300740","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"}],"funders":[{"id":"https://openalex.org/F4320309446","display_name":"Leona M. and Harry B. Helmsley Charitable Trust","ror":"https://ror.org/011x6n313"},{"id":"https://openalex.org/F4320310082","display_name":"Stiftelsen Kristian Gerhard Jebsen","ror":"https://ror.org/021g6tq38"},{"id":"https://openalex.org/F4320310758","display_name":"Kreftforeningen","ror":"https://ror.org/01925vb10"},{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335409","display_name":"Livsvitenskap, Universitetet i Oslo","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":110,"referenced_works":["https://openalex.org/W1501531009","https://openalex.org/W1969005071","https://openalex.org/W1971784866","https://openalex.org/W1972177221","https://openalex.org/W1989445634","https://openalex.org/W2018198423","https://openalex.org/W2066757437","https://openalex.org/W2079145130","https://openalex.org/W2171634310","https://openalex.org/W2211953232","https://openalex.org/W2402268235","https://openalex.org/W2549835527","https://openalex.org/W2616207459","https://openalex.org/W2736287575","https://openalex.org/W2742030900","https://openalex.org/W2771330107","https://openalex.org/W2775363893","https://openalex.org/W2791796577","https://openalex.org/W2803176955","https://openalex.org/W2804639187","https://openalex.org/W2811364409","https://openalex.org/W2911489562","https://openalex.org/W2911930496","https://openalex.org/W2916562859","https://openalex.org/W2945976633","https://openalex.org/W2946417913","https://openalex.org/W2951286828","https://openalex.org/W2952209472","https://openalex.org/W2952984539","https://openalex.org/W2962739339","https://openalex.org/W2963355447","https://openalex.org/W2965373594","https://openalex.org/W2972324944","https://openalex.org/W2980789587","https://openalex.org/W2990241049","https://openalex.org/W2995514860","https://openalex.org/W2998280981","https://openalex.org/W3001279689","https://openalex.org/W3004346089","https://openalex.org/W3011574394","https://openalex.org/W3011885318","https://openalex.org/W3014415613","https://openalex.org/W3016562905","https://openalex.org/W3018526736","https://openalex.org/W3024787440","https://openalex.org/W3034510440","https://openalex.org/W3034830866","https://openalex.org/W3035390927","https://openalex.org/W3037888463","https://openalex.org/W3049692992","https://openalex.org/W3088409176","https://openalex.org/W3098666169","https://openalex.org/W3098865414","https://openalex.org/W3100198908","https://openalex.org/W3102596196","https://openalex.org/W3104685001","https://openalex.org/W3107527779","https://openalex.org/W3118485687","https://openalex.org/W3118936575","https://openalex.org/W3121000782","https://openalex.org/W3125294413","https://openalex.org/W3133702157","https://openalex.org/W3136270197","https://openalex.org/W3138783506","https://openalex.org/W3144701084","https://openalex.org/W3146944767","https://openalex.org/W3154046803","https://openalex.org/W3155101735","https://openalex.org/W3166142427","https://openalex.org/W3175170601","https://openalex.org/W3175212568","https://openalex.org/W3176893837","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3179485843","https://openalex.org/W3184997006","https://openalex.org/W3186612807","https://openalex.org/W3201490875","https://openalex.org/W3206187363","https://openalex.org/W3211728297","https://openalex.org/W4200079908","https://openalex.org/W4205773061","https://openalex.org/W4210494137","https://openalex.org/W4220959747","https://openalex.org/W4220991280","https://openalex.org/W4223473836","https://openalex.org/W4223644783","https://openalex.org/W4225156065","https://openalex.org/W4226108318","https://openalex.org/W4226146865","https://openalex.org/W4226271314","https://openalex.org/W4234216897","https://openalex.org/W4280625391","https://openalex.org/W4281719345","https://openalex.org/W4283068487","https://openalex.org/W4283390570","https://openalex.org/W4283716699","https://openalex.org/W4283733033","https://openalex.org/W4285157756","https://openalex.org/W4285267582","https://openalex.org/W4288066876","https://openalex.org/W4288631803","https://openalex.org/W4294956060","https://openalex.org/W4306955484","https://openalex.org/W4307106501","https://openalex.org/W4313430583","https://openalex.org/W4319915529","https://openalex.org/W4327550249","https://openalex.org/W6763868836","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":14}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}