{"id":"https://openalex.org/W3161612534","doi":"https://doi.org/10.1093/bioinformatics/btab371","title":"Clustering FunFams using sequence embeddings improves EC purity","display_name":"Clustering FunFams using sequence embeddings improves EC purity","publication_year":2021,"publication_date":"2021-05-11","ids":{"openalex":"https://openalex.org/W3161612534","doi":"https://doi.org/10.1093/bioinformatics/btab371","mag":"3161612534","pmid":"https://pubmed.ncbi.nlm.nih.gov/33978744"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab371","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab371","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/20/3449/40854265/btab371.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/37/20/3449/40854265/btab371.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025018140","display_name":"Maria Littmann","orcid":"https://orcid.org/0000-0001-8533-8163"},"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":"Maria Littmann","raw_affiliation_strings":["Center for Doctoral Studies in Informatics and its Applications (CeDoSIA), TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA) , 85748 Garching/Munich, Germany","Department of Informatics, Bioinformatics & Computational Biology\u2014i12, TUM (Technical University of Munich) , 85748 Garching/Munich, Germany","Center for Doctoral Studies in Informatics and its Applications (CeDoSIA), TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), 85748 Garching/Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8533-8163","affiliations":[{"raw_affiliation_string":"Center for Doctoral Studies in Informatics and its Applications (CeDoSIA), TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA) , 85748 Garching/Munich, Germany","institution_ids":[]},{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology\u2014i12, TUM (Technical University of Munich) , 85748 Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Center for Doctoral Studies in Informatics and its Applications (CeDoSIA), TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), 85748 Garching/Munich, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038645988","display_name":"Nicola Bordin","orcid":"https://orcid.org/0000-0002-6568-9035"},"institutions":[{"id":"https://openalex.org/I4210157240","display_name":"Institute of Structural and Molecular Biology","ror":"https://ror.org/05wsetc54","country_code":"GB","type":"facility","lineage":["https://openalex.org/I124357947","https://openalex.org/I124357947","https://openalex.org/I4210157240","https://openalex.org/I45129253","https://openalex.org/I98259816"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nicola Bordin","raw_affiliation_strings":["Institute of Structural and Molecular Biology, University College London , London WC1E 6BT, UK"],"raw_orcid":"https://orcid.org/0000-0002-6568-9035","affiliations":[{"raw_affiliation_string":"Institute of Structural and Molecular Biology, University College London , London WC1E 6BT, UK","institution_ids":["https://openalex.org/I4210157240","https://openalex.org/I45129253"]}]},{"author_position":"middle","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":false,"raw_author_name":"Michael Heinzinger","raw_affiliation_strings":["Center for Doctoral Studies in Informatics and its Applications (CeDoSIA), TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA) , 85748 Garching/Munich, Germany","Department of Informatics, Bioinformatics & Computational Biology\u2014i12, TUM (Technical University of Munich) , 85748 Garching/Munich, Germany","Center for Doctoral Studies in Informatics and its Applications (CeDoSIA), TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), 85748 Garching/Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Doctoral Studies in Informatics and its Applications (CeDoSIA), TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA) , 85748 Garching/Munich, Germany","institution_ids":[]},{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology\u2014i12, TUM (Technical University of Munich) , 85748 Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Center for Doctoral Studies in Informatics and its Applications (CeDoSIA), TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), 85748 Garching/Munich, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062361890","display_name":"Konstantin Sch\u00fctze","orcid":"https://orcid.org/0000-0002-3957-412X"},"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":"Konstantin Sch\u00fctze","raw_affiliation_strings":["Department of Informatics, Bioinformatics & Computational Biology\u2014i12, TUM (Technical University of Munich) , 85748 Garching/Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology\u2014i12, TUM (Technical University of Munich) , 85748 Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"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":["Center for Doctoral Studies in Informatics and its Applications (CeDoSIA), TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA) , 85748 Garching/Munich, Germany","Department of Informatics, Bioinformatics & Computational Biology\u2014i12, TUM (Technical University of Munich) , 85748 Garching/Munich, Germany","Center for Doctoral Studies in Informatics and its Applications (CeDoSIA), TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), 85748 Garching/Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4650-6181","affiliations":[{"raw_affiliation_string":"Center for Doctoral Studies in Informatics and its Applications (CeDoSIA), TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA) , 85748 Garching/Munich, Germany","institution_ids":[]},{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology\u2014i12, TUM (Technical University of Munich) , 85748 Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Center for Doctoral Studies in Informatics and its Applications (CeDoSIA), TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), 85748 Garching/Munich, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081250379","display_name":"Christine Orengo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210157240","display_name":"Institute of Structural and Molecular Biology","ror":"https://ror.org/05wsetc54","country_code":"GB","type":"facility","lineage":["https://openalex.org/I124357947","https://openalex.org/I124357947","https://openalex.org/I4210157240","https://openalex.org/I45129253","https://openalex.org/I98259816"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Christine Orengo","raw_affiliation_strings":["Institute of Structural and Molecular Biology, University College London , London WC1E 6BT, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Structural and Molecular Biology, University College London , London WC1E 6BT, UK","institution_ids":["https://openalex.org/I4210157240","https://openalex.org/I45129253"]}]},{"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/I309496635","display_name":"Weihenstephan-Triesdorf University of Applied Sciences","ror":"https://ror.org/00gzkxz88","country_code":"DE","type":"education","lineage":["https://openalex.org/I309496635"]},{"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"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Burkhard Rost","raw_affiliation_strings":["Department of Informatics, Bioinformatics & Computational Biology\u2014i12, TUM (Technical University of Munich) , 85748 Garching/Munich, Germany","Institute for Advanced Study (TUM-IAS) , 85748 Garching/Munich, Germany","TUM School of Life Sciences Weihenstephan (WZW) , 85354 Freising, Germany","TUM School of Life Sciences Weihenstephan (WZW), 85354 Freising, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Bioinformatics & Computational Biology\u2014i12, TUM (Technical University of Munich) , 85748 Garching/Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Advanced Study (TUM-IAS) , 85748 Garching/Munich, Germany","institution_ids":["https://openalex.org/I4210137766"]},{"raw_affiliation_string":"TUM School of Life Sciences Weihenstephan (WZW) , 85354 Freising, Germany","institution_ids":["https://openalex.org/I309496635"]},{"raw_affiliation_string":"TUM School of Life Sciences Weihenstephan (WZW), 85354 Freising, Germany","institution_ids":["https://openalex.org/I309496635"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025018140","https://openalex.org/A5064905883","https://openalex.org/A5081250379"],"corresponding_institution_ids":["https://openalex.org/I309496635","https://openalex.org/I4210137766","https://openalex.org/I4210157240","https://openalex.org/I45129253","https://openalex.org/I62916508"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.5376,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.90634663,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"37","issue":"20","first_page":"3449","last_page":"3455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9157999753952026,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9157999753952026,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.01889999955892563,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.016699999570846558,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6684889793395996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6524308919906616},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6188929080963135},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5861594676971436},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5820134282112122},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.569158673286438},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5619649887084961},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5104264616966248},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.49419930577278137},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.49078306555747986},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.46184462308883667},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4593191146850586},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4145115911960602},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32088321447372437},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2808411121368408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2665761113166809},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.24721887707710266},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1416836977005005}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6684889793395996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6524308919906616},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6188929080963135},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5861594676971436},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5820134282112122},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.569158673286438},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5619649887084961},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5104264616966248},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.49419930577278137},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.49078306555747986},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.46184462308883667},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4593191146850586},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4145115911960602},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32088321447372437},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2808411121368408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2665761113166809},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24721887707710266},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1416836977005005},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/btab371","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab371","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/20/3449/40854265/btab371.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:33978744","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33978744","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},{"id":"pmh:oai:europepmc.org:7434652","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC8545299","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8545299","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8545299","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:www.research.unipd.it:11577/3597638","is_oa":true,"landing_page_url":"https://hdl.handle.net/11577/3597638","pdf_url":null,"source":{"id":"https://openalex.org/S4377196283","display_name":"Research Padua  Archive (University of Padua)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btab371","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab371","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/20/3449/40854265/btab371.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"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/G1305978807","display_name":"Leveraging functional profiling datasets with machine learning to uncover proteins and cellular processes important for ageing","funder_award_id":"BB/R009597/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"},{"id":"https://openalex.org/G2420487338","display_name":null,"funder_award_id":"BB/K020013/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"},{"id":"https://openalex.org/G3068706553","display_name":null,"funder_award_id":"RO1320/4\u20131","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G3957071345","display_name":null,"funder_award_id":"BB/R009597/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"},{"id":"https://openalex.org/G5931231857","display_name":null,"funder_award_id":"01IS17049","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"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"},{"id":"https://openalex.org/G8104252070","display_name":null,"funder_award_id":"031L0168","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G8904207333","display_name":"An Greatly Expanded CATH-Gene3D with Functional Fingerprints to Characterise Proteins","funder_award_id":"BB/K020013/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"}],"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/F4320332167","display_name":"Directorate for Biological Sciences","ror":"https://ror.org/001xhss06"},{"id":"https://openalex.org/F4320334629","display_name":"Biotechnology and Biological Sciences Research Council","ror":"https://ror.org/00cwqg982"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3161612534.pdf","grobid_xml":"https://content.openalex.org/works/W3161612534.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1501531009","https://openalex.org/W1892752174","https://openalex.org/W1989840001","https://openalex.org/W2018661561","https://openalex.org/W2050748701","https://openalex.org/W2063971957","https://openalex.org/W2100383158","https://openalex.org/W2101234009","https://openalex.org/W2101335101","https://openalex.org/W2104601544","https://openalex.org/W2106053110","https://openalex.org/W2108067237","https://openalex.org/W2126751256","https://openalex.org/W2128312954","https://openalex.org/W2137736270","https://openalex.org/W2139919097","https://openalex.org/W2791796577","https://openalex.org/W2793397305","https://openalex.org/W2896457183","https://openalex.org/W2899664253","https://openalex.org/W2943495267","https://openalex.org/W2951433247","https://openalex.org/W2951765074","https://openalex.org/W2959593662","https://openalex.org/W2962739339","https://openalex.org/W2964308564","https://openalex.org/W2971227267","https://openalex.org/W2972411752","https://openalex.org/W2980789587","https://openalex.org/W2985502476","https://openalex.org/W2989608901","https://openalex.org/W2995514860","https://openalex.org/W3010387158","https://openalex.org/W3013303091","https://openalex.org/W3024553150","https://openalex.org/W3037620288","https://openalex.org/W3037888463","https://openalex.org/W3049692992","https://openalex.org/W3096305909","https://openalex.org/W3096655658","https://openalex.org/W3106745904","https://openalex.org/W3118936575","https://openalex.org/W3136918052","https://openalex.org/W3146944767","https://openalex.org/W3157437194","https://openalex.org/W3158236124","https://openalex.org/W4230533398","https://openalex.org/W4239849280","https://openalex.org/W4287724045","https://openalex.org/W6675354045","https://openalex.org/W6675751002","https://openalex.org/W6679434410","https://openalex.org/W6755207826","https://openalex.org/W6762363781","https://openalex.org/W6774110404","https://openalex.org/W6780110802","https://openalex.org/W6780145172","https://openalex.org/W6785711794","https://openalex.org/W6794409167"],"related_works":["https://openalex.org/W3006513224","https://openalex.org/W2046456988","https://openalex.org/W2357409937","https://openalex.org/W2074430941","https://openalex.org/W2113096305","https://openalex.org/W2580722822","https://openalex.org/W1486338765","https://openalex.org/W2023876576","https://openalex.org/W2772305933","https://openalex.org/W4387454008"],"abstract_inverted_index":{"MOTIVATION:":[0],"Classifying":[1],"proteins":[2,32,40,48,121,226],"into":[3,44,84],"functional":[4,23,73,206],"families":[5,24,167],"can":[6,14,197],"improve":[7],"our":[8],"understanding":[9],"of":[10,47,52,57,64,68,147,193,212,225],"protein":[11],"function":[12],"and":[13,63,113,136,141,234],"allow":[15,208],"transferring":[16,101],"annotations":[17,62],"within":[18,41],"one":[19],"family.":[20],"For":[21],"this,":[22],"need":[25],"to":[26,80,118,123,138,153,161,218],"be":[27],"'pure',":[28],"i.e.,":[29],"contain":[30,60],"only":[31],"with":[33,204],"identical":[34],"function.":[35,50,194],"Functional":[36],"Families":[37],"(FunFams)":[38],"cluster":[39,82,139],"CATH":[42,129],"superfamilies":[43],"such":[45],"groups":[46],"sharing":[49],"11%":[51],"all":[53],"FunFams":[54,83,140,162],"(22":[55],"830":[56],"203":[58],"639)":[59],"EC":[61,174],"those,":[65],"7%":[66],"(1526":[67],"22":[69],"830)":[70],"have":[71,114],"inconsistent":[72],"annotations.":[74,182,213],"RESULTS:":[75],"We":[76,214],"propose":[77],"an":[78,186],"approach":[79,157,217],"further":[81,116],"functionally":[85],"more":[86,209],"consistent":[87],"sub-families":[88],"by":[89,227],"encoding":[90],"their":[91,228],"sequences":[92],"through":[93],"embeddings.":[94],"These":[95],"embeddings":[96,135,235],"originate":[97],"from":[98,104],"language":[99],"models":[100],"knowledge":[102],"gained":[103],"predicting":[105],"missing":[106],"amino":[107],"acids":[108],"in":[109],"a":[110,127],"sequence":[111,170],"(ProtBERT)":[112],"been":[115],"optimized":[117],"distinguish":[119],"between":[120,134],"belonging":[122],"the":[124,145,201],"same":[125],"or":[126],"different":[128],"superfamily":[130],"(PB-Tucker).":[131],"Using":[132],"distances":[133],"DBSCAN":[137],"identify":[142],"outliers,":[143],"doubled":[144],"number":[146],"pure":[148],"clusters":[149,203],"per":[150],"FunFam":[151],"compared":[152],"random":[154],"clustering.":[155],"Our":[156,195],"was":[158],"not":[159],"limited":[160],"but":[163],"also":[164,189],"succeeded":[165],"on":[166],"created":[168],"using":[169],"similarity":[171],"alone.":[172],"Complementing":[173],"annotations,":[175],"we":[176,184],"observed":[177],"similar":[178],"results":[179,196],"for":[180,190,221],"binding":[181],"Thus,":[183],"expect":[185,215],"increased":[187],"purity":[188],"other":[191,223],"aspects":[192],"help":[198],"generating":[199],"FunFams;":[200],"resulting":[202],"improved":[205],"consistency":[207],"reliable":[210],"inference":[211],"this":[216],"succeed":[219],"equally":[220],"any":[222],"grouping":[224],"phenotypes.":[229],"AVAILABILITY":[230],"AND":[231],"IMPLEMENTATION:":[232],"Code":[233],"are":[236,245],"available":[237,246],"via":[238],"GitHub:":[239],"https://github.com/Rostlab/FunFamsClustering.":[240],"SUPPLEMENTARY":[241],"INFORMATION:":[242],"Supplementary":[243],"data":[244],"at":[247],"Bioinformatics":[248],"online.":[249]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":7}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}