{"id":"https://openalex.org/W4316363330","doi":"https://doi.org/10.1093/bib/bbac619","title":"Tree visualizations of protein sequence embedding space enable improved functional clustering of diverse protein superfamilies","display_name":"Tree visualizations of protein sequence embedding space enable improved functional clustering of diverse protein superfamilies","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4316363330","doi":"https://doi.org/10.1093/bib/bbac619","pmid":"https://pubmed.ncbi.nlm.nih.gov/36642409"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbac619","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbac619","pdf_url":"https://academic.oup.com/bib/article-pdf/24/1/bbac619/48782812/bbac619.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in 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/bib/article-pdf/24/1/bbac619/48782812/bbac619.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066141945","display_name":"Wayland Yeung","orcid":"https://orcid.org/0000-0002-2523-4984"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wayland Yeung","raw_affiliation_strings":["Institute of Bioinformatics, University of Georgia , 30602, Georgia , USA"],"affiliations":[{"raw_affiliation_string":"Institute of Bioinformatics, University of Georgia , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050749778","display_name":"Zhongliang Zhou","orcid":"https://orcid.org/0000-0003-4471-6759"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongliang Zhou","raw_affiliation_strings":["School of Computing, University of Georgia , 30602, Georgia , USA"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Georgia , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019876344","display_name":"Liju Mathew","orcid":null},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liju Mathew","raw_affiliation_strings":["Department of Microbiology, University of Georgia , 30602, Georgia , USA"],"affiliations":[{"raw_affiliation_string":"Department of Microbiology, University of Georgia , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078827216","display_name":"Nathan Gravel","orcid":"https://orcid.org/0000-0002-8482-4255"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Gravel","raw_affiliation_strings":["Institute of Bioinformatics, University of Georgia , 30602, Georgia , USA"],"affiliations":[{"raw_affiliation_string":"Institute of Bioinformatics, University of Georgia , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084948037","display_name":"Rahil Taujale","orcid":"https://orcid.org/0000-0003-1292-1619"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahil Taujale","raw_affiliation_strings":["Institute of Bioinformatics, University of Georgia , 30602, Georgia , USA"],"affiliations":[{"raw_affiliation_string":"Institute of Bioinformatics, University of Georgia , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035554946","display_name":"Brady O\u2019Boyle","orcid":"https://orcid.org/0000-0002-5191-3577"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brady O\u2019Boyle","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, University of Georgia , 30602, Georgia , USA"],"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, University of Georgia , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020459889","display_name":"Mariah Salcedo","orcid":"https://orcid.org/0009-0008-0490-2446"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mariah Salcedo","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, University of Georgia , 30602, Georgia , USA"],"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, University of Georgia , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089553328","display_name":"Aarya Venkat","orcid":"https://orcid.org/0000-0002-8793-4097"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aarya Venkat","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, University of Georgia , 30602, Georgia , USA"],"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, University of Georgia , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055436683","display_name":"William N. Lanzilotta","orcid":"https://orcid.org/0000-0002-4852-321X"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Lanzilotta","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, University of Georgia , 30602, Georgia , USA"],"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, University of Georgia , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359839","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0003-1205-8632"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sheng Li","raw_affiliation_strings":["School of Data Science, University of Virginia , 22903, Virginia , USA"],"affiliations":[{"raw_affiliation_string":"School of Data Science, University of Virginia , 22903, Virginia , USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033384464","display_name":"Natarajan Kannan","orcid":"https://orcid.org/0000-0002-2833-8375"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Natarajan Kannan","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, University of Georgia , 30602, Georgia , USA","Institute of Bioinformatics, University of Georgia , 30602, Georgia , USA"],"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, University of Georgia , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]},{"raw_affiliation_string":"Institute of Bioinformatics, University of Georgia , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5033384464","https://openalex.org/A5100359839"],"corresponding_institution_ids":["https://openalex.org/I165733156","https://openalex.org/I51556381"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":{"value":4011,"currency":"USD","value_usd":4011},"fwci":3.7134,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.93368291,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"24","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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":0.9994000196456909,"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/T10887","display_name":"Bioinformatics and Genomic Networks","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6928380727767944},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.582318902015686},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5819259285926819},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.549128532409668},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4963873028755188},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.48460444808006287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47911953926086426},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.47789180278778076},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.46907562017440796},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45520830154418945},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4540071189403534},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44882330298423767},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.42518889904022217},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4248409569263458},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.41295525431632996},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.22201529145240784},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2057788074016571},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.17645862698554993},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16141238808631897},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15788286924362183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6928380727767944},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.582318902015686},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5819259285926819},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.549128532409668},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4963873028755188},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.48460444808006287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47911953926086426},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.47789180278778076},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.46907562017440796},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45520830154418945},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4540071189403534},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44882330298423767},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.42518889904022217},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4248409569263458},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.41295525431632996},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.22201529145240784},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2057788074016571},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.17645862698554993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16141238808631897},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15788286924362183},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","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":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbac619","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbac619","pdf_url":"https://academic.oup.com/bib/article-pdf/24/1/bbac619/48782812/bbac619.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36642409","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36642409","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":"Briefings in bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9851311","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9851311","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9851311/pdf/bbac619.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bib/bbac619","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbac619","pdf_url":"https://academic.oup.com/bib/article-pdf/24/1/bbac619/48782812/bbac619.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1432373144","display_name":null,"funder_award_id":"W911NF-21-1-","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G3497591915","display_name":null,"funder_award_id":"(NIH)","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6742976396","display_name":null,"funder_award_id":"R35 GM139656","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7212741451","display_name":null,"funder_award_id":"R01 GM124203","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8771980258","display_name":null,"funder_award_id":"W911NF-21-1-0028","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8998121839","display_name":null,"funder_award_id":"911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4316363330.pdf"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W1505870408","https://openalex.org/W1987971958","https://openalex.org/W2030205108","https://openalex.org/W2049726148","https://openalex.org/W2067338576","https://openalex.org/W2071465766","https://openalex.org/W2074511635","https://openalex.org/W2080989975","https://openalex.org/W2084998761","https://openalex.org/W2097706568","https://openalex.org/W2111595905","https://openalex.org/W2114463320","https://openalex.org/W2129816388","https://openalex.org/W2150541721","https://openalex.org/W2166834087","https://openalex.org/W2187089797","https://openalex.org/W2229908198","https://openalex.org/W2277953252","https://openalex.org/W2396643508","https://openalex.org/W2399932691","https://openalex.org/W2530969703","https://openalex.org/W2566439298","https://openalex.org/W2581502864","https://openalex.org/W2607132510","https://openalex.org/W2793278779","https://openalex.org/W2883050635","https://openalex.org/W2889326414","https://openalex.org/W2891893703","https://openalex.org/W2951433247","https://openalex.org/W2951670304","https://openalex.org/W2951747536","https://openalex.org/W2971227267","https://openalex.org/W2997958114","https://openalex.org/W2999481648","https://openalex.org/W3000273212","https://openalex.org/W3006945870","https://openalex.org/W3087038497","https://openalex.org/W3095583226","https://openalex.org/W3111145940","https://openalex.org/W3112376646","https://openalex.org/W3121267967","https://openalex.org/W3128274084","https://openalex.org/W3146944767","https://openalex.org/W3166142427","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3196645780","https://openalex.org/W3201757323","https://openalex.org/W4225264859","https://openalex.org/W4225868104","https://openalex.org/W4238306205","https://openalex.org/W4239535905","https://openalex.org/W4281291878","https://openalex.org/W4281719345","https://openalex.org/W4285794641","https://openalex.org/W4287724045","https://openalex.org/W6674647444","https://openalex.org/W6689475862","https://openalex.org/W6754904495","https://openalex.org/W6763868836","https://openalex.org/W6780145172","https://openalex.org/W6789837562","https://openalex.org/W6839106506"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W2162923930","https://openalex.org/W1482324242","https://openalex.org/W2133116680","https://openalex.org/W2091678889","https://openalex.org/W2029514038","https://openalex.org/W2804480386","https://openalex.org/W3186624150","https://openalex.org/W65850283"],"abstract_inverted_index":{"Protein":[0],"language":[1,28,92],"models,":[2],"trained":[3,31],"on":[4,32,139],"millions":[5],"of":[6,14,61,83,96,136,156,162],"biologically":[7],"observed":[8],"sequences,":[9],"generate":[10],"feature-rich":[11],"numerical":[12],"representations":[13],"protein":[15,27,70,84,91,169],"sequences.":[16],"These":[17],"representations,":[18],"called":[19],"sequence":[20,34,37,53,71,87,182,211],"embeddings,":[21],"can":[22],"infer":[23],"structure-functional":[24],"properties,":[25],"despite":[26],"models":[29],"being":[30],"primary":[33],"alone.":[35],"While":[36],"embeddings":[38,146],"have":[39,55],"been":[40,56,200],"applied":[41],"toward":[42,51],"tasks":[43],"such":[44,128],"as":[45,129],"structure":[46,113,121],"and":[47,66,77,131,168,177],"function":[48],"prediction,":[49],"applications":[50,209],"alignment-free":[52],"classification":[54,82,161,191],"hindered":[57],"by":[58,144],"the":[59,81,154,160,193],"lack":[60],"studies":[62],"to":[63,202],"derive,":[64],"quantify":[65],"evaluate":[67],"relationships":[68],"between":[69],"embeddings.":[72],"Here,":[73],"we":[74],"develop":[75],"workflows":[76],"visualization":[78,98],"methods":[79,99,158],"for":[80,192,224],"families":[85],"using":[86,147,204],"embedding":[88,105],"derived":[89],"from":[90],"models.":[93],"A":[94],"benchmark":[95],"manifold":[97],"reveals":[100],"that":[101],"Neighbor":[102],"Joining":[103],"(NJ)":[104],"trees":[106,218],"are":[107,219],"highly":[108],"effective":[109],"in":[110,118,159,210],"capturing":[111,119],"global":[112],"while":[114],"achieving":[115],"similar":[116],"performance":[117],"local":[120],"compared":[122],"with":[123,176],"popular":[124],"dimensionality":[125],"reduction":[126],"techniques":[127],"t-SNE":[130],"UMAP.":[132],"The":[133],"statistical":[134],"significance":[135],"hierarchical":[137,190],"clusters":[138],"a":[140,148,188,220],"tree":[141],"is":[142],"evaluated":[143],"resampling":[145],"variational":[149],"autoencoder":[150],"(VAE).":[151],"We":[152,185],"demonstrate":[153],"application":[155],"our":[157,213],"two":[163],"well-studied":[164],"enzyme":[165,196],"superfamilies,":[166],"phosphatases":[167],"kinases.":[170],"Our":[171],"embedding-based":[172],"classifications":[173],"remain":[174],"consistent":[175],"extend":[178],"upon":[179],"previously":[180],"published":[181],"alignment-based":[183,206],"classifications.":[184],"also":[186],"propose":[187],"new":[189],"S-Adenosyl-L-Methionine":[194],"(SAM)":[195],"superfamily":[197],"which":[198],"has":[199],"difficult":[201],"classify":[203],"traditional":[205],"approaches.":[207],"Beyond":[208],"classification,":[212],"results":[214],"further":[215],"suggest":[216],"NJ":[217],"promising":[221],"general":[222],"method":[223],"visualizing":[225],"high-dimensional":[226],"data":[227],"sets.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}