{"id":"https://openalex.org/W4287629316","doi":"https://doi.org/10.5281/zenodo.5795849","title":"Learning Functional Properties of Proteins with Language Models","display_name":"Learning Functional Properties of Proteins with Language Models","publication_year":2020,"publication_date":"2020-10-28","ids":{"openalex":"https://openalex.org/W4287629316","doi":"https://doi.org/10.5281/zenodo.5795849"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:5795850","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/5795850","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/article"},"volume":null,"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/5795850","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025046599","display_name":"Serb\u00fclent \u00dcnsal","orcid":"https://orcid.org/0000-0002-1986-3485","observed_orcids":["https://orcid.org/0000-0002-1986-3485"]},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Serbulent, Unsal","raw_affiliation_strings":["Cancer Systems Biology Laboratory (KanSiL), Graduate School of Informatics, Middle East Technical University, Ankara, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-1986-3485","affiliations":[{"raw_affiliation_string":"Cancer Systems Biology Laboratory (KanSiL), Graduate School of Informatics, Middle East Technical University, Ankara, Turkey","institution_ids":["https://openalex.org/I201799495"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054058101","display_name":"Heval Ata\u015f","orcid":"https://orcid.org/0000-0003-3180-7010","observed_orcids":["https://orcid.org/0000-0003-3180-7010"]},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ata\u015f, Heval","raw_affiliation_strings":["Cancer Systems Biology Laboratory (KanSiL), Graduate School of Informatics, Middle East Technical University, Ankara, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cancer Systems Biology Laboratory (KanSiL), Graduate School of Informatics, Middle East Technical University, Ankara, Turkey","institution_ids":["https://openalex.org/I201799495"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089498016","display_name":"Muammer Albayrak","orcid":"https://orcid.org/0000-0002-5946-6310","observed_orcids":["https://orcid.org/0000-0002-5946-6310"]},"institutions":[{"id":"https://openalex.org/I162720556","display_name":"Karadeniz Technical University","ror":"https://ror.org/03z8fyr40","country_code":"TR","type":"education","lineage":["https://openalex.org/I162720556"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Albayrak, Muammer","raw_affiliation_strings":["Department of Biostatistics and Computer Sciences, Karadeniz Technical University, Trabzon, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Computer Sciences, Karadeniz Technical University, Trabzon, Turkey","institution_ids":["https://openalex.org/I162720556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005115875","display_name":"Kemal Turhan","orcid":"https://orcid.org/0000-0001-7871-3025","observed_orcids":["https://orcid.org/0000-0001-7871-3025"]},"institutions":[{"id":"https://openalex.org/I162720556","display_name":"Karadeniz Technical University","ror":"https://ror.org/03z8fyr40","country_code":"TR","type":"education","lineage":["https://openalex.org/I162720556"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Turhan, Kemal","raw_affiliation_strings":["Department of Biostatistics and Computer Sciences, Karadeniz Technical University, Trabzon, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Computer Sciences, Karadeniz Technical University, Trabzon, Turkey","institution_ids":["https://openalex.org/I162720556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037079774","display_name":"Aybar C. Acar","orcid":"https://orcid.org/0000-0001-5694-8675","observed_orcids":["https://orcid.org/0000-0001-5694-8675"]},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Acar, Aybar C.","raw_affiliation_strings":["Cancer Systems Biology Laboratory (KanSiL), Graduate School of Informatics, Middle East Technical University, Ankara, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-5694-8675","affiliations":[{"raw_affiliation_string":"Cancer Systems Biology Laboratory (KanSiL), Graduate School of Informatics, Middle East Technical University, Ankara, Turkey","institution_ids":["https://openalex.org/I201799495"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003981652","display_name":"Tunca Do\u011fan","orcid":"https://orcid.org/0000-0002-1298-9763","observed_orcids":["https://orcid.org/0000-0002-1298-9763"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Do\u011fan, Tunca","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1298-9763","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0811,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37970725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9404000043869019,"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":0.9404000043869019,"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":0.05209999904036522,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/protein-functional-properties","display_name":"protein functional properties","score":0.7170000076293945},{"id":"https://openalex.org/keywords/protein-embeddings","display_name":"protein embeddings","score":0.7149999737739563},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.7960000038146973},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"multiple sequence alignment","score":0.8999999761581421},{"id":"https://openalex.org/keywords/human-protein","display_name":"human protein","score":0.7919999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44835928082466125},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3822299540042877},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3688891530036926},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.36737003922462463},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3212229013442993},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26855218410491943},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.21617954969406128},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.129184752702713}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:zenodo.org:5795850","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/5795850","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.5281/zenodo.5795849","doi":"https://doi.org/10.5281/zenodo.5795849","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5795849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"doi:10.5281/zenodo.5795850","doi":"https://doi.org/10.5281/zenodo.5795850","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5795850","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:5795850","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/5795850","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7164941025","https://openalex.org/W4416260672","https://openalex.org/W4410698941","https://openalex.org/W7131765305","https://openalex.org/W7161497838","https://openalex.org/W4399911287","https://openalex.org/W7206398842","https://openalex.org/W7169650668","https://openalex.org/W7160519685","https://openalex.org/W6950292117"],"abstract_inverted_index":{"This":[0],"dataset":[1,21,57],"includes;":[2],"-":[3,15,27,49,50],"Precomputed":[4,16],"representation":[5,17],"vectors":[6,18],"of":[7,19,29,52,55],"human":[8,30],"proteins":[9,31],"with":[10,22,33,59],"various":[11,23],"protein":[12,24,53],"embedding":[13,25],"models.":[14,26],"SKEMPI":[20,56],"MSAs":[28,51],"calculated":[32,58],"HHBlits.":[34,60],"--":[35],"Splitted":[36],"tar.gz":[37],"files":[38],"can":[39],"be":[40],"opened":[41],"by":[42],"command;":[43],"cat":[44],"human_protein_msa.tar.gz.*":[45],"|":[46],"tar":[47],"xzvf":[48],"sequences":[54]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2022-07-25T00:00:00"}
