{"id":"https://openalex.org/W4410698941","doi":"https://doi.org/10.1039/d4dd00195h","title":"Reprogramming pretrained language models for protein sequence representation learning","display_name":"Reprogramming pretrained language models for protein sequence representation learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410698941","doi":"https://doi.org/10.1039/d4dd00195h"},"language":"en","primary_location":{"id":"doi:10.1039/d4dd00195h","doi":"https://doi.org/10.1039/d4dd00195h","is_oa":true,"landing_page_url":"https://doi.org/10.1039/d4dd00195h","pdf_url":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d4dd00195h","source":{"id":"https://openalex.org/S4210202120","display_name":"Digital Discovery","issn_l":"2635-098X","issn":["2635-098X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","ki-jl-1","norway-1"],"host_organization":"https://openalex.org/P4310320556","host_organization_name":"Royal Society of Chemistry","host_organization_lineage":["https://openalex.org/P4310320556"],"host_organization_lineage_names":["Royal Society of Chemistry"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Discovery","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d4dd00195h","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015655299","display_name":"Ria Vinod","orcid":"https://orcid.org/0000-0002-6282-9741","observed_orcids":["https://orcid.org/0000-0002-6282-9741"]},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ria Vinod","raw_affiliation_strings":["Department of Computational and Molecular Biology, Brown University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational and Molecular Biology, Brown University, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050344371","display_name":"Pin\u2010Yu Chen","orcid":"https://orcid.org/0000-0003-1039-8369","observed_orcids":["https://orcid.org/0000-0003-1039-8369","https://orcid.org/0009-0008-1182-583X"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pin-Yu Chen","raw_affiliation_strings":["IBM Research, USA"],"raw_orcid":"https://orcid.org/0000-0003-1039-8369","affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064335115","display_name":"Payel Das","orcid":"https://orcid.org/0000-0002-7288-0516","observed_orcids":["https://orcid.org/0000-0002-7288-0516","https://orcid.org/0000-0002-3239-4222"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Payel Das","raw_affiliation_strings":["IBM Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050344371","https://openalex.org/A5064335115"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":1.0193,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72715933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"4","issue":"6","first_page":"1591","last_page":"1601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9829000234603882,"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":0.9829000234603882,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0044999998062849045,"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":0.003800000064074993,"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/pre-trained-language-models","display_name":"pre-trained language models","score":0.8029999732971191},{"id":"https://openalex.org/keywords/dictionary-learning","display_name":"dictionary learning","score":0.9819999933242798},{"id":"https://openalex.org/keywords/protein-embeddings","display_name":"protein embeddings","score":0.7070000171661377}],"concepts":[{"id":"https://openalex.org/C77255625","wikidata":"https://www.wikidata.org/wiki/Q402093","display_name":"Reprogramming","level":3,"score":0.7986339330673218},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6537009477615356},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6510111093521118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5887126922607422},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4994771480560303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47925496101379395},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.465383917093277},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.28868502378463745},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0998833179473877},{"id":"https://openalex.org/C1491633281","wikidata":"https://www.wikidata.org/wiki/Q7868","display_name":"Cell","level":2,"score":0.06924515962600708},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1039/d4dd00195h","doi":"https://doi.org/10.1039/d4dd00195h","is_oa":true,"landing_page_url":"https://doi.org/10.1039/d4dd00195h","pdf_url":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d4dd00195h","source":{"id":"https://openalex.org/S4210202120","display_name":"Digital Discovery","issn_l":"2635-098X","issn":["2635-098X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","ki-jl-1","norway-1"],"host_organization":"https://openalex.org/P4310320556","host_organization_name":"Royal Society of Chemistry","host_organization_lineage":["https://openalex.org/P4310320556"],"host_organization_lineage_names":["Royal Society of Chemistry"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Discovery","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1039/d4dd00195h","doi":"https://doi.org/10.1039/d4dd00195h","is_oa":true,"landing_page_url":"https://doi.org/10.1039/d4dd00195h","pdf_url":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d4dd00195h","source":{"id":"https://openalex.org/S4210202120","display_name":"Digital Discovery","issn_l":"2635-098X","issn":["2635-098X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","ki-jl-1","norway-1"],"host_organization":"https://openalex.org/P4310320556","host_organization_name":"Royal Society of Chemistry","host_organization_lineage":["https://openalex.org/P4310320556"],"host_organization_lineage_names":["Royal Society of Chemistry"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Discovery","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410698941.pdf","grobid_xml":"https://content.openalex.org/works/W4410698941.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1607035479","https://openalex.org/W2076048958","https://openalex.org/W2160547390","https://openalex.org/W2730472814","https://openalex.org/W2735621019","https://openalex.org/W2889498145","https://openalex.org/W2898402099","https://openalex.org/W2949952216","https://openalex.org/W2950374603","https://openalex.org/W2950627632","https://openalex.org/W2980789587","https://openalex.org/W2997234557","https://openalex.org/W3027325047","https://openalex.org/W3041133507","https://openalex.org/W3096418018","https://openalex.org/W3135156311","https://openalex.org/W3136918052","https://openalex.org/W3146944767","https://openalex.org/W3166142427","https://openalex.org/W3177828909","https://openalex.org/W3186179742","https://openalex.org/W3215514970","https://openalex.org/W4205773061","https://openalex.org/W4317369987","https://openalex.org/W4320301318","https://openalex.org/W4379932151","https://openalex.org/W4385743368","https://openalex.org/W4388024559","https://openalex.org/W4414747430","https://openalex.org/W6600448047"],"related_works":["https://openalex.org/W1631979401","https://openalex.org/W2395945797","https://openalex.org/W1497716427","https://openalex.org/W2129470469","https://openalex.org/W2368295610","https://openalex.org/W1543102035","https://openalex.org/W2946692299","https://openalex.org/W3014941007","https://openalex.org/W2183075003","https://openalex.org/W2990520546"],"abstract_inverted_index":{"The":[0],"representation":[1],"reprogramming":[2],"via":[3],"dictionary":[4],"learning":[5,21],"framework":[6],"reprograms":[7],"a":[8,22],"pretrained":[9],"English":[10,27],"language":[11],"model":[12],"to":[13],"learn":[14],"the":[15],"embeddings":[16],"of":[17],"protein":[18,29],"sequences":[19],"by":[20],"sparse":[23],"linear":[24],"mapping":[25],"between":[26],"and":[28],"vocabulary":[30],"embeddings.":[31]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}
