{"id":"https://openalex.org/W4296780589","doi":"https://doi.org/10.1093/bioinformatics/btac474","title":"DistilProtBert: a distilled protein language model used to distinguish between real proteins and their randomly shuffled counterparts","display_name":"DistilProtBert: a distilled protein language model used to distinguish between real proteins and their randomly shuffled counterparts","publication_year":2022,"publication_date":"2022-08-24","ids":{"openalex":"https://openalex.org/W4296780589","doi":"https://doi.org/10.1093/bioinformatics/btac474","pmid":"https://pubmed.ncbi.nlm.nih.gov/36124789"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac474","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac474","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/Supplement_2/ii95/50485222/btac474.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"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":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/38/Supplement_2/ii95/50485222/btac474.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073641828","display_name":"Yaron Geffen","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Yaron Geffen","raw_affiliation_strings":["The Mina & Everard Goodman Faculty of Life Sciences, Bar-Ilan University , Ramat-Gan 5290002, Israel"],"affiliations":[{"raw_affiliation_string":"The Mina & Everard Goodman Faculty of Life Sciences, Bar-Ilan University , Ramat-Gan 5290002, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078975856","display_name":"Yanay Ofran","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yanay Ofran","raw_affiliation_strings":["The Mina & Everard Goodman Faculty of Life Sciences, Bar-Ilan University , Ramat-Gan 5290002, Israel"],"affiliations":[{"raw_affiliation_string":"The Mina & Everard Goodman Faculty of Life Sciences, Bar-Ilan University , Ramat-Gan 5290002, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056692823","display_name":"Ron Unger","orcid":"https://orcid.org/0000-0003-4153-3922"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ron Unger","raw_affiliation_strings":["The Mina & Everard Goodman Faculty of Life Sciences, Bar-Ilan University , Ramat-Gan 5290002, Israel"],"affiliations":[{"raw_affiliation_string":"The Mina & Everard Goodman Faculty of Life Sciences, Bar-Ilan University , Ramat-Gan 5290002, Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073641828"],"corresponding_institution_ids":["https://openalex.org/I13955877"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":3.033,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.92667343,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"38","issue":"Supplement_2","first_page":"ii95","last_page":"ii98"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9986000061035156,"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":0.996999979019165,"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/shuffling","display_name":"Shuffling","score":0.7337364554405212},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6363542079925537},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5821839570999146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5217786431312561},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.5124645829200745},{"id":"https://openalex.org/keywords/proteome","display_name":"Proteome","score":0.5044797658920288},{"id":"https://openalex.org/keywords/amino-acid","display_name":"Amino acid","score":0.44919395446777344},{"id":"https://openalex.org/keywords/distilled-water","display_name":"Distilled water","score":0.44617655873298645},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43395617604255676},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3930933177471161},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36208808422088623},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3280676007270813},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3274851441383362},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.25183814764022827},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2272261083126068},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.22586724162101746},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.18377536535263062},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.12080872058868408},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10293340682983398}],"concepts":[{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.7337364554405212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6363542079925537},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5821839570999146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5217786431312561},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.5124645829200745},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.5044797658920288},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.44919395446777344},{"id":"https://openalex.org/C2779429693","wikidata":"https://www.wikidata.org/wiki/Q274959","display_name":"Distilled water","level":2,"score":0.44617655873298645},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43395617604255676},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3930933177471161},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36208808422088623},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3280676007270813},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3274851441383362},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.25183814764022827},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2272261083126068},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.22586724162101746},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.18377536535263062},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.12080872058868408},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10293340682983398},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","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":"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":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btac474","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac474","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/Supplement_2/ii95/50485222/btac474.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36124789","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36124789","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}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac474","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac474","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/Supplement_2/ii95/50485222/btac474.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321449","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495"},{"id":"https://openalex.org/F4320334233","display_name":"Data Science Institute, Columbia University","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296780589.pdf","grobid_xml":"https://content.openalex.org/works/W4296780589.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2001335546","https://openalex.org/W2013460486","https://openalex.org/W2058832897","https://openalex.org/W2076048958","https://openalex.org/W2104972430","https://openalex.org/W2567587907","https://openalex.org/W2730472814","https://openalex.org/W2767444993","https://openalex.org/W2896457183","https://openalex.org/W2950374603","https://openalex.org/W2951433247","https://openalex.org/W2965373594","https://openalex.org/W2978017171","https://openalex.org/W2980282514","https://openalex.org/W2980789587","https://openalex.org/W2996428491","https://openalex.org/W2997234557","https://openalex.org/W3034457371","https://openalex.org/W3037888463","https://openalex.org/W3105966348","https://openalex.org/W3144701084","https://openalex.org/W3146944767","https://openalex.org/W3175054838","https://openalex.org/W3175463116","https://openalex.org/W3177828909","https://openalex.org/W3186179742","https://openalex.org/W3198971594","https://openalex.org/W4205773061","https://openalex.org/W4206275111","https://openalex.org/W4287724045","https://openalex.org/W4385245566","https://openalex.org/W6638523607","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6763868836","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6768086466","https://openalex.org/W6768817161","https://openalex.org/W6768851824","https://openalex.org/W6776322294","https://openalex.org/W6780110802","https://openalex.org/W6780145172","https://openalex.org/W6797484841","https://openalex.org/W6797492301"],"related_works":["https://openalex.org/W4213239787","https://openalex.org/W4377131110","https://openalex.org/W2045745654","https://openalex.org/W2114337652","https://openalex.org/W4388857216","https://openalex.org/W2046590706","https://openalex.org/W4390419005","https://openalex.org/W1587991081","https://openalex.org/W2949444602","https://openalex.org/W2120641958"],"abstract_inverted_index":{"https://github.com/yarongef/DistilProtBert.":[0]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}
