{"id":"https://openalex.org/W2995514860","doi":"https://doi.org/10.1186/s12859-019-3220-8","title":"Modeling aspects of the language of life through transfer-learning protein sequences","display_name":"Modeling aspects of the language of life through transfer-learning protein sequences","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2995514860","doi":"https://doi.org/10.1186/s12859-019-3220-8","mag":"2995514860","pmid":"https://pubmed.ncbi.nlm.nih.gov/31847804"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-019-3220-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-3220-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-3220-8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-3220-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Michael Heinzinger","raw_affiliation_strings":["Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany. mheinzinger@rostlab.org","TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany. mheinzinger@rostlab.org","Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-9601-3580","affiliations":[{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany. mheinzinger@rostlab.org","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany. mheinzinger@rostlab.org","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","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":false,"raw_author_name":"Ahmed Elnaggar","raw_affiliation_strings":["Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany","TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053242621","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0003-4976-9366"},"institutions":[{"id":"https://openalex.org/I4210163716","display_name":"Leibniz Supercomputing Centre","ror":"https://ror.org/05558nw16","country_code":"DE","type":"facility","lineage":["https://openalex.org/I109144446","https://openalex.org/I4210163716"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Leibniz Supercomputing Centre, Boltzmannstr. 1, 85748, Garching/Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz Supercomputing Centre, Boltzmannstr. 1, 85748, Garching/Munich, Germany","institution_ids":["https://openalex.org/I4210163716"]}]},{"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, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany","TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090410765","display_name":"Dmitrii Nechaev","orcid":null},"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":"Dmitrii Nechaev","raw_affiliation_strings":["Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany","TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022973212","display_name":"Florian Matthes","orcid":"https://orcid.org/0000-0002-6667-5452"},"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":"Florian Matthes","raw_affiliation_strings":["TUM Department of Informatics, Software Engineering and Business Information Systems, Boltzmannstr. 1, 85748, Garching/Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TUM Department of Informatics, Software Engineering and Business Information Systems, Boltzmannstr. 1, 85748, Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"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/I4210137766","display_name":"Institute for Advanced Study","ror":"https://ror.org/03xg85719","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210137766"]},{"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"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Burkhard Rost","raw_affiliation_strings":["Department of Biochemistry and Molecular Biophysics & New York Consortium on Membrane Protein Structure (NYCOMPS), Columbia University, 701 West, 168th Street, New York, NY, 10032, USA","Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany","Institute for Advanced Study (TUM-IAS), Lichtenbergstr. 2a, 85748, Garching/Munich, Germany","TUM School of Life Sciences Weihenstephan (WZW), Alte Akademie 8, Freising, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biophysics & New York Consortium on Membrane Protein Structure (NYCOMPS), Columbia University, 701 West, 168th Street, New York, NY, 10032, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Advanced Study (TUM-IAS), Lichtenbergstr. 2a, 85748, Garching/Munich, Germany","institution_ids":["https://openalex.org/I4210137766"]},{"raw_affiliation_string":"TUM School of Life Sciences Weihenstephan (WZW), Alte Akademie 8, Freising, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5075726670"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":1608,"currency":"EUR","value_usd":1734},"fwci":17.9792,"has_fulltext":true,"cited_by_count":646,"citation_normalized_percentile":{"value":0.99623932,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"20","issue":"1","first_page":"723","last_page":"723"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9678999781608582,"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":0.9678999781608582,"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":0.009100000374019146,"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":0.0024999999441206455,"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":0.6561181545257568},{"id":"https://openalex.org/keywords/human-proteome-project","display_name":"Human proteome project","score":0.5259706377983093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5225260257720947},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.512712836265564},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.48212766647338867},{"id":"https://openalex.org/keywords/proteome","display_name":"Proteome","score":0.4420834183692932},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.4390898048877716},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.430581271648407},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41625869274139404},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37020984292030334},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35344260931015015},{"id":"https://openalex.org/keywords/proteomics","display_name":"Proteomics","score":0.3222426772117615},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.2854289412498474},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.27320992946624756},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.22516494989395142},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.1962217390537262},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.19044476747512817},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.1781333088874817},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.144578218460083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6561181545257568},{"id":"https://openalex.org/C94795543","wikidata":"https://www.wikidata.org/wiki/Q3813754","display_name":"Human proteome project","level":4,"score":0.5259706377983093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5225260257720947},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.512712836265564},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.48212766647338867},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.4420834183692932},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.4390898048877716},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.430581271648407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41625869274139404},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37020984292030334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35344260931015015},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.3222426772117615},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2854289412498474},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.27320992946624756},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.22516494989395142},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.1962217390537262},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.19044476747512817},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.1781333088874817},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.144578218460083}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"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},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1186/s12859-019-3220-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-3220-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-3220-8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:31847804","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31847804","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:53c4efcb1fe04a0e8cc7ce845b681905","is_oa":true,"landing_page_url":"https://doaj.org/article/53c4efcb1fe04a0e8cc7ce845b681905","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 20, Iss 1, Pp 1-17 (2019)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:5874805","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6918593","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1543610","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1543610","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":"","raw_type":"article"},{"id":"doi:10.7916/tt83-bq62","is_oa":true,"landing_page_url":"https://doi.org/10.7916/tt83-bq62","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1186/s12859-019-3220-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-019-3220-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-3220-8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1270295441","display_name":null,"funder_award_id":"DFG-GZ: RO1320/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G4722347315","display_name":null,"funder_award_id":"DFG\u2013GZ: RO1320/4\u20131","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7542597935","display_name":null,"funder_award_id":"RO1320/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320308269","display_name":"Alexander von Humboldt-Stiftung","ror":"https://ror.org/012kf4317"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320334763","display_name":"Leibniz-Gemeinschaft","ror":"https://ror.org/01n6r0e97"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2995514860.pdf","grobid_xml":"https://content.openalex.org/works/W2995514860.grobid-xml"},"referenced_works_count":106,"referenced_works":["https://openalex.org/W1501531009","https://openalex.org/W1526754730","https://openalex.org/W1834070694","https://openalex.org/W1938755728","https://openalex.org/W1965540415","https://openalex.org/W1968544966","https://openalex.org/W1973253766","https://openalex.org/W1982228765","https://openalex.org/W1982289655","https://openalex.org/W1982583124","https://openalex.org/W1985222378","https://openalex.org/W1985818354","https://openalex.org/W1995918845","https://openalex.org/W1996073320","https://openalex.org/W1997967533","https://openalex.org/W2006211612","https://openalex.org/W2008545402","https://openalex.org/W2008708467","https://openalex.org/W2013136212","https://openalex.org/W2025630031","https://openalex.org/W2029476353","https://openalex.org/W2045777307","https://openalex.org/W2050625197","https://openalex.org/W2051210555","https://openalex.org/W2059145105","https://openalex.org/W2059185913","https://openalex.org/W2061042699","https://openalex.org/W2064675550","https://openalex.org/W2070126374","https://openalex.org/W2079882489","https://openalex.org/W2085789739","https://openalex.org/W2094005653","https://openalex.org/W2095222655","https://openalex.org/W2095705004","https://openalex.org/W2099302461","https://openalex.org/W2099589970","https://openalex.org/W2100063856","https://openalex.org/W2102461176","https://openalex.org/W2103485392","https://openalex.org/W2104972430","https://openalex.org/W2107725114","https://openalex.org/W2108206279","https://openalex.org/W2109553965","https://openalex.org/W2111973517","https://openalex.org/W2115453442","https://openalex.org/W2120401481","https://openalex.org/W2120671490","https://openalex.org/W2121651202","https://openalex.org/W2123969230","https://openalex.org/W2126871981","https://openalex.org/W2130479394","https://openalex.org/W2131204071","https://openalex.org/W2141803423","https://openalex.org/W2141920771","https://openalex.org/W2143210482","https://openalex.org/W2146396614","https://openalex.org/W2149822709","https://openalex.org/W2153153865","https://openalex.org/W2153187042","https://openalex.org/W2156125289","https://openalex.org/W2157009395","https://openalex.org/W2158173168","https://openalex.org/W2158714788","https://openalex.org/W2161072217","https://openalex.org/W2161922860","https://openalex.org/W2168970921","https://openalex.org/W2169317607","https://openalex.org/W2170463736","https://openalex.org/W2170747616","https://openalex.org/W2170960297","https://openalex.org/W2173591891","https://openalex.org/W2187089797","https://openalex.org/W2250539671","https://openalex.org/W2342838938","https://openalex.org/W2398638460","https://openalex.org/W2468915207","https://openalex.org/W2472351724","https://openalex.org/W2493916176","https://openalex.org/W2567587907","https://openalex.org/W2607268717","https://openalex.org/W2730472814","https://openalex.org/W2754054476","https://openalex.org/W2769882797","https://openalex.org/W2799163714","https://openalex.org/W2800388620","https://openalex.org/W2806449887","https://openalex.org/W2887766567","https://openalex.org/W2896457183","https://openalex.org/W2897944569","https://openalex.org/W2913820882","https://openalex.org/W2943495267","https://openalex.org/W2949117887","https://openalex.org/W2950374603","https://openalex.org/W2950577311","https://openalex.org/W2950813464","https://openalex.org/W2950954328","https://openalex.org/W2951559648","https://openalex.org/W2951651062","https://openalex.org/W2952209472","https://openalex.org/W2962739339","https://openalex.org/W2963457143","https://openalex.org/W2964110616","https://openalex.org/W2972411752","https://openalex.org/W3146944767","https://openalex.org/W4252944911","https://openalex.org/W6600135713"],"related_works":["https://openalex.org/W3092794487","https://openalex.org/W2094752534","https://openalex.org/W2885268310","https://openalex.org/W2025055488","https://openalex.org/W2575115220","https://openalex.org/W2580329791","https://openalex.org/W2909412621","https://openalex.org/W3032536091","https://openalex.org/W2145037531","https://openalex.org/W1975345997"],"abstract_inverted_index":{"BACKGROUND:":[0],"Predicting":[1],"protein":[2,73,92,248,327,340],"function":[3],"and":[4,24,119,148,186,230,349],"structure":[5,137],"from":[6,50,86,105,190,205,320],"sequence":[7,293,322],"is":[8,34,41,254,286,354,360],"one":[9],"important":[10,252],"challenge":[11],"for":[12,28,44,48,128,231,271,301,325],"computational":[13],"biology.":[14],"For":[15],"26":[16],"years,":[17],"most":[18],"state-of-the-art":[19],"approaches":[20],"combined":[21],"machine":[22],"learning":[23],"evolutionary":[25,39,217,228,269,355],"information.":[26,218],"However,":[27],"some":[29,224,232],"applications":[30],"retrieving":[31],"related":[32],"proteins":[33,49,192,233],"becoming":[35],"too":[36],"time-consuming.":[37],"Additionally,":[38],"information":[40,229,270,319,359],"less":[42],"powerful":[43],"small":[45],"families,":[46],"e.g.":[47],"the":[51,60,81,97,101,133,171,202,212,237,244,251,257,268,289,302,332,337,364],"Dark":[52],"Proteome.":[53],"Both":[54],"these":[55,113],"problems":[56],"are":[57],"addressed":[58],"by":[59,79,123,347],"new":[61,114],"methodology":[62],"introduced":[63,67],"here.":[64],"RESULTS:":[65],"We":[66,110],"a":[68,272,297,367],"novel":[69],"way":[70],"to":[71,112,242,266,317],"represent":[72],"sequences":[74,341],"as":[75,116],"continuous":[76],"vectors":[77],"(embeddings)":[78],"using":[80,216,227],"language":[82,88,102,333],"model":[83],"ELMo":[84,94],"taken":[85],"natural":[87],"processing.":[89],"By":[90],"modeling":[91],"sequences,":[93,207],"effectively":[95],"captured":[96],"biophysical":[98],"properties":[99],"of":[100,103,247,288,291,304,334,366],"life":[104],"unlabeled":[106,321],"big":[107,305],"data":[108,306],"(UniRef50).":[109],"refer":[111],"embeddings":[115,200,277],"SeqVec":[117,199,275,295,330],"(Sequence-to-Vector)":[118],"demonstrate":[120],"their":[121],"effectiveness":[122],"training":[124],"simple":[125],"neural":[126],"networks":[127],"two":[129,264],"different":[130],"tasks.":[131,329],"At":[132,170],"per-residue":[134],"level,":[135,173],"secondary":[136],"(Q3":[138],"=":[139,144,154,182,194],"79%":[140],"\u00b1":[141,146,156,184,196],"1,":[142],"Q8":[143],"68%":[145,183],"1)":[147,185],"regions":[149],"with":[150],"intrinsic":[151],"disorder":[152],"(MCC":[153],"0.59":[155],"0.03)":[157],"were":[158,188],"predicted":[159,177],"significantly":[160],"better":[161,342],"than":[162,343],"through":[163,167],"one-hot":[164],"encoding":[165],"or":[166,311],"Word2vec-like":[168],"approaches.":[169],"per-protein":[172],"subcellular":[174],"localization":[175],"was":[176],"in":[178,280,307],"ten":[179],"classes":[180],"(Q10":[181],"membrane-bound":[187],"distinguished":[189],"water-soluble":[191],"(Q2":[193],"87%":[195],"1).":[197],"Although":[198],"generated":[201],"best":[203,213],"predictions":[204],"single":[206,368],"no":[208],"solution":[209],"improved":[210,222],"over":[211,223],"existing":[214],"method":[215],"Nevertheless,":[219],"our":[220],"approach":[221,300],"popular":[225],"methods":[226],"even":[234],"did":[235],"beat":[236],"best.":[238],"Thus,":[239],"they":[240],"prove":[241],"condense":[243],"underlying":[245,339],"principles":[246,338],"sequences.":[249],"Overall,":[250],"novelty":[253],"speed:":[255],"where":[256],"lightning-fast":[258],"HHblits":[259],"needed":[260],"on":[261,278,363],"average":[262,279],"about":[263],"minutes":[265],"generate":[267],"target":[273],"protein,":[274],"created":[276],"0.03":[281],"s.":[282],"As":[283],"this":[284],"speed-up":[285],"independent":[287],"size":[290],"growing":[292],"databases,":[294],"provides":[296],"highly":[298],"scalable":[299],"analysis":[303],"proteomics,":[308],"i.e.":[309],"microbiome":[310],"metaproteome":[312],"analysis.":[313],"CONCLUSION:":[314],"Transfer-learning":[315],"succeeded":[316],"extract":[318],"databases":[323],"relevant":[324],"various":[326],"prediction":[328,350],"modeled":[331],"life,":[335],"namely":[336],"any":[344],"features":[345],"suggested":[346],"textbooks":[348],"methods.":[351],"The":[352],"exception":[353],"information,":[356],"however,":[357],"that":[358],"not":[361],"available":[362],"level":[365],"sequence.":[369]},"counts_by_year":[{"year":2026,"cited_by_count":44},{"year":2025,"cited_by_count":105},{"year":2024,"cited_by_count":128},{"year":2023,"cited_by_count":132},{"year":2022,"cited_by_count":106},{"year":2021,"cited_by_count":96},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}