{"id":"https://openalex.org/W4297003082","doi":"https://doi.org/10.1186/s12859-022-04930-5","title":"Organizing the bacterial annotation space with amino acid sequence embeddings","display_name":"Organizing the bacterial annotation space with amino acid sequence embeddings","publication_year":2022,"publication_date":"2022-09-23","ids":{"openalex":"https://openalex.org/W4297003082","doi":"https://doi.org/10.1186/s12859-022-04930-5","pmid":"https://pubmed.ncbi.nlm.nih.gov/36151519"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-022-04930-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-04930-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-04930-5","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","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-04930-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026459851","display_name":"Susanna R. Grigson","orcid":"https://orcid.org/0000-0003-4738-3451"},"institutions":[{"id":"https://openalex.org/I169541294","display_name":"Flinders University","ror":"https://ror.org/01kpzv902","country_code":"AU","type":"education","lineage":["https://openalex.org/I169541294"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Susanna R. Grigson","raw_affiliation_strings":["Flinders Accelerator for Microbiome Exploration, College of Science and Engineering, Flinders University, Adelaide, South Australia, 5042, Australia. susie.grigson@flinders.edu.au","Flinders Accelerator for Microbiome Exploration, College of Science and Engineering, Flinders University, Adelaide, South Australia, 5042, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4738-3451","affiliations":[{"raw_affiliation_string":"Flinders Accelerator for Microbiome Exploration, College of Science and Engineering, Flinders University, Adelaide, South Australia, 5042, Australia. susie.grigson@flinders.edu.au","institution_ids":["https://openalex.org/I169541294"]},{"raw_affiliation_string":"Flinders Accelerator for Microbiome Exploration, College of Science and Engineering, Flinders University, Adelaide, South Australia, 5042, Australia","institution_ids":["https://openalex.org/I169541294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032770661","display_name":"Jody C. McKerral","orcid":null},"institutions":[{"id":"https://openalex.org/I169541294","display_name":"Flinders University","ror":"https://ror.org/01kpzv902","country_code":"AU","type":"education","lineage":["https://openalex.org/I169541294"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jody C. McKerral","raw_affiliation_strings":["Flinders Accelerator for Microbiome Exploration, College of Science and Engineering, Flinders University, Adelaide, South Australia, 5042, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1830-6695","affiliations":[{"raw_affiliation_string":"Flinders Accelerator for Microbiome Exploration, College of Science and Engineering, Flinders University, Adelaide, South Australia, 5042, Australia","institution_ids":["https://openalex.org/I169541294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051905584","display_name":"James G. Mitchell","orcid":"https://orcid.org/0000-0002-8445-0935"},"institutions":[{"id":"https://openalex.org/I169541294","display_name":"Flinders University","ror":"https://ror.org/01kpzv902","country_code":"AU","type":"education","lineage":["https://openalex.org/I169541294"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"James G. Mitchell","raw_affiliation_strings":["Flinders Accelerator for Microbiome Exploration, College of Science and Engineering, Flinders University, Adelaide, South Australia, 5042, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8445-0935","affiliations":[{"raw_affiliation_string":"Flinders Accelerator for Microbiome Exploration, College of Science and Engineering, Flinders University, Adelaide, South Australia, 5042, Australia","institution_ids":["https://openalex.org/I169541294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036802114","display_name":"Robert A. Edwards","orcid":"https://orcid.org/0000-0001-8383-8949"},"institutions":[{"id":"https://openalex.org/I169541294","display_name":"Flinders University","ror":"https://ror.org/01kpzv902","country_code":"AU","type":"education","lineage":["https://openalex.org/I169541294"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Robert A. Edwards","raw_affiliation_strings":["Flinders Accelerator for Microbiome Exploration, College of Science and Engineering, Flinders University, Adelaide, South Australia, 5042, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8383-8949","affiliations":[{"raw_affiliation_string":"Flinders Accelerator for Microbiome Exploration, College of Science and Engineering, Flinders University, Adelaide, South Australia, 5042, Australia","institution_ids":["https://openalex.org/I169541294"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026459851"],"corresponding_institution_ids":["https://openalex.org/I169541294"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.2599,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52471068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"23","issue":"1","first_page":"385","last_page":"385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.6104000210762024,"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":0.6104000210762024,"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":0.17739999294281006,"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":0.12449999898672104,"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/annotation","display_name":"Annotation","score":0.6127585172653198},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6084638833999634},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.5831804275512695},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5536094307899475},{"id":"https://openalex.org/keywords/sequence-space","display_name":"Sequence space","score":0.551574170589447},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5355261564254761},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.504604697227478},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5015912055969238},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4972288906574249},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4494454860687256},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.440473735332489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4304898679256439},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4158465266227722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31996721029281616},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3097546696662903},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.23385584354400635},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.16509705781936646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09268122911453247}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6127585172653198},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6084638833999634},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.5831804275512695},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5536094307899475},{"id":"https://openalex.org/C30711495","wikidata":"https://www.wikidata.org/wiki/Q289411","display_name":"Sequence space","level":3,"score":0.551574170589447},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5355261564254761},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.504604697227478},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5015912055969238},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4972288906574249},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4494454860687256},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.440473735332489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4304898679256439},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4158465266227722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31996721029281616},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3097546696662903},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.23385584354400635},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.16509705781936646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09268122911453247},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C132954091","wikidata":"https://www.wikidata.org/wiki/Q194397","display_name":"Banach space","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-022-04930-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-04930-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-04930-5","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:36151519","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36151519","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:546912aedeca49ba9bd81294cf29caa2","is_oa":true,"landing_page_url":"https://doaj.org/article/546912aedeca49ba9bd81294cf29caa2","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 23, Iss 1, Pp 1-14 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9502642","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9502642","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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-022-04930-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-04930-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-04930-5","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":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3349938402","display_name":null,"funder_award_id":"RC2DK116713","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G510100752","display_name":null,"funder_award_id":"RC2DK116713","funder_id":"https://openalex.org/F4320337357","funder_display_name":"National Institute of Diabetes and Digestive and Kidney Diseases"},{"id":"https://openalex.org/G5211754784","display_name":"Quantitative Metagenomics","funder_award_id":"DP220102915","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G7238246478","display_name":null,"funder_award_id":"RC2 DK116713","funder_id":"https://openalex.org/F4320337357","funder_display_name":"National Institute of Diabetes and Digestive and Kidney Diseases"}],"funders":[{"id":"https://openalex.org/F4320320977","display_name":"Flinders University","ror":"https://ror.org/01kpzv902"},{"id":"https://openalex.org/F4320323570","display_name":"Australian Mathematical Sciences Institute","ror":"https://ror.org/00yn60108"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"},{"id":"https://openalex.org/F4320337357","display_name":"National Institute of Diabetes and Digestive and Kidney Diseases","ror":"https://ror.org/00adh9b73"},{"id":"https://openalex.org/F4320337380","display_name":"Division of Mathematical Sciences","ror":"https://ror.org/051fftw81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297003082.pdf","grobid_xml":"https://content.openalex.org/works/W4297003082.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1501531009","https://openalex.org/W1527927437","https://openalex.org/W1986708244","https://openalex.org/W1999866852","https://openalex.org/W2025075516","https://openalex.org/W2085487226","https://openalex.org/W2097892623","https://openalex.org/W2099946731","https://openalex.org/W2131342905","https://openalex.org/W2137111266","https://openalex.org/W2142428670","https://openalex.org/W2143210482","https://openalex.org/W2148853951","https://openalex.org/W2169059428","https://openalex.org/W2170747616","https://openalex.org/W2189955651","https://openalex.org/W2470052926","https://openalex.org/W2515248967","https://openalex.org/W2559133556","https://openalex.org/W2766648240","https://openalex.org/W2768835663","https://openalex.org/W2783910833","https://openalex.org/W2786142325","https://openalex.org/W2797101767","https://openalex.org/W2800388620","https://openalex.org/W2807495535","https://openalex.org/W2807818025","https://openalex.org/W2891675266","https://openalex.org/W2943495267","https://openalex.org/W2957309664","https://openalex.org/W2963603716","https://openalex.org/W2964758100","https://openalex.org/W2980789587","https://openalex.org/W2991091214","https://openalex.org/W2995514860","https://openalex.org/W3003257820","https://openalex.org/W3013601039","https://openalex.org/W3019706413","https://openalex.org/W3023746197","https://openalex.org/W3033814770","https://openalex.org/W3049692992","https://openalex.org/W3094518056","https://openalex.org/W3095340190","https://openalex.org/W3096218861","https://openalex.org/W3101509328","https://openalex.org/W3103145119","https://openalex.org/W3146944767","https://openalex.org/W3161612534","https://openalex.org/W3184997006","https://openalex.org/W4213112325","https://openalex.org/W4220991280","https://openalex.org/W4398748092","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W2053028024","https://openalex.org/W2977684889","https://openalex.org/W2901595550","https://openalex.org/W4214858168","https://openalex.org/W2743276551","https://openalex.org/W2011602722","https://openalex.org/W4211066835","https://openalex.org/W2024383575","https://openalex.org/W3135130381","https://openalex.org/W3197882307"],"abstract_inverted_index":{"BACKGROUND:":[0],"Due":[1],"to":[2,77,159,206],"the":[3,7,93,115,121],"ever-expanding":[4],"gap":[5],"between":[6],"number":[8],"of":[9,95,128],"proteins":[10,205],"being":[11],"discovered":[12],"and":[13,53,201],"their":[14],"functional":[15,136],"characterization,":[16],"protein":[17,29,39,79,84,106,185,196],"function":[18],"inference":[19],"remains":[20],"a":[21,101,109,175],"fundamental":[22],"challenge":[23],"in":[24,33,49,66],"computational":[25],"biology.":[26],"Currently,":[27],"known":[28],"annotations":[30],"are":[31,157],"organized":[32,44],"human-curated":[34],"ontologies,":[35],"however,":[36],"all":[37],"possible":[38],"functions":[40,200],"may":[41,173,191],"not":[42],"be":[43,174,192],"accurately.":[45],"Meanwhile,":[46],"recent":[47],"advancements":[48],"natural":[50],"language":[51],"processing":[52],"machine":[54],"learning":[55],"have":[56,73,160],"developed":[57],"models":[58],"which":[59],"embed":[60],"amino":[61,96,142,169],"acid":[62,97,143,170],"sequences":[63,80,130,144,153,197],"as":[64,100],"vectors":[65],"n-dimensional":[67],"space.":[68],"So":[69],"far,":[70],"these":[71,151],"embeddings":[72,99,172,190],"primarily":[74],"been":[75],"used":[76],"classify":[78],"using":[81],"manually":[82],"constructed":[83],"classification":[85],"schemes.":[86],"RESULTS:":[87],"In":[88,188],"this":[89,132],"work,":[90],"we":[91,112,148],"describe":[92],"use":[94],"sequence":[98,110,171,186],"systematic":[102],"framework":[103],"for":[104,178,183,194],"studying":[105],"ontologies.":[107],"Using":[108],"embedding,":[111],"show":[113,149],"that":[114,150,156,168],"bacterial":[116],"carbohydrate":[117],"metabolism":[118],"class":[119,133],"within":[120],"SEED":[122],"annotation":[123],"system":[124],"contains":[125],"48":[126],"clusters":[127,155],"embedded":[129],"despite":[131],"containing":[134],"29":[135],"labels.":[137],"Furthermore,":[138],"by":[139],"embedding":[140],"Bacillus":[141],"with":[145,198],"unknown":[146,152,199],"functions,":[147],"form":[154],"likely":[158],"similar":[161],"biological":[162],"roles.":[163],"CONCLUSIONS:":[164],"This":[165],"study":[166],"demonstrates":[167],"powerful":[176],"tool":[177],"developing":[179],"more":[180],"robust":[181],"ontologies":[182],"annotating":[184],"data.":[187],"addition,":[189],"beneficial":[193],"clustering":[195],"selecting":[202],"optimal":[203],"candidate":[204],"characterize":[207],"experimentally.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}
