{"id":"https://openalex.org/W7127653797","doi":"https://doi.org/10.1093/bioinformatics/btag058","title":"Multi-scale structural similarity embedding search across entire proteomes","display_name":"Multi-scale structural similarity embedding search across entire proteomes","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7127653797","doi":"https://doi.org/10.1093/bioinformatics/btag058","pmid":"https://pubmed.ncbi.nlm.nih.gov/41632625"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag058","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag058","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btag058","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007270631","display_name":"Joan Segura","orcid":"https://orcid.org/0000-0001-5593-735X"},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joan Segura","raw_affiliation_strings":["Research Collaboratory for Structural Bioinformatics Protein Data Bank, San Diego Supercomputer Center, University of California San Diego , San Diego, CA 92093,"],"raw_orcid":"https://orcid.org/0000-0001-5593-735X","affiliations":[{"raw_affiliation_string":"Research Collaboratory for Structural Bioinformatics Protein Data Bank, San Diego Supercomputer Center, University of California San Diego , San Diego, CA 92093,","institution_ids":["https://openalex.org/I181653535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125042933","display_name":"Ruben Sanchez-Garcia","orcid":null},"institutions":[{"id":"https://openalex.org/I125068653","display_name":"IE University","ror":"https://ror.org/02jjdwm75","country_code":"ES","type":"education","lineage":["https://openalex.org/I125068653"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ruben Sanchez-Garcia","raw_affiliation_strings":["School of Science and Technology, IE University , 28046 Madrid,"],"raw_orcid":"https://orcid.org/0000-0001-6156-3542","affiliations":[{"raw_affiliation_string":"School of Science and Technology, IE University , 28046 Madrid,","institution_ids":["https://openalex.org/I125068653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017772944","display_name":"Sebastian Bittrich","orcid":"https://orcid.org/0000-0003-3576-0387"},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastian Bittrich","raw_affiliation_strings":["Research Collaboratory for Structural Bioinformatics Protein Data Bank, San Diego Supercomputer Center, University of California San Diego , San Diego, CA 92093,"],"raw_orcid":"https://orcid.org/0000-0003-3576-0387","affiliations":[{"raw_affiliation_string":"Research Collaboratory for Structural Bioinformatics Protein Data Bank, San Diego Supercomputer Center, University of California San Diego , San Diego, CA 92093,","institution_ids":["https://openalex.org/I181653535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061045572","display_name":"Yana Rose","orcid":"https://orcid.org/0000-0003-1018-5718"},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yana Rose","raw_affiliation_strings":["Research Collaboratory for Structural Bioinformatics Protein Data Bank, San Diego Supercomputer Center, University of California San Diego , San Diego, CA 92093,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Collaboratory for Structural Bioinformatics Protein Data Bank, San Diego Supercomputer Center, University of California San Diego , San Diego, CA 92093,","institution_ids":["https://openalex.org/I181653535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068648875","display_name":"S.K. Burley","orcid":"https://orcid.org/0000-0002-2487-9713"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]},{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"Stephen K Burley","raw_affiliation_strings":["Department of Chemistry and Chemical Biology, Rutgers, The State University of New Jersey , Piscataway, NJ 08854,","Research Collaboratory for Structural Bioinformatics Protein Data Bank and the Institute for Quantitative Biomedicine, Rutgers, The State University of New Jersey , Piscataway, NJ 08854,","Research Collaboratory for Structural Bioinformatics Protein Data Bank, San Diego Supercomputer Center, University of California San Diego , San Diego, CA 92093,","Rutgers Artificial Intelligence and Data Science (RAD) Collaboratory, Rutgers, The State University of New Jersey , Piscataway, NJ 08854,","Rutgers Cancer Institute , Rutgers, , New Brunswick, NJ 08901,","The State University of New Jersey , Rutgers, , New Brunswick, NJ 08901,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Chemical Biology, Rutgers, The State University of New Jersey , Piscataway, NJ 08854,","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Research Collaboratory for Structural Bioinformatics Protein Data Bank and the Institute for Quantitative Biomedicine, Rutgers, The State University of New Jersey , Piscataway, NJ 08854,","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Research Collaboratory for Structural Bioinformatics Protein Data Bank, San Diego Supercomputer Center, University of California San Diego , San Diego, CA 92093,","institution_ids":["https://openalex.org/I181653535"]},{"raw_affiliation_string":"Rutgers Artificial Intelligence and Data Science (RAD) Collaboratory, Rutgers, The State University of New Jersey , Piscataway, NJ 08854,","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Rutgers Cancer Institute , Rutgers, , New Brunswick, NJ 08901,","institution_ids":["https://openalex.org/I102322142","https://openalex.org/I4210096112"]},{"raw_affiliation_string":"The State University of New Jersey , Rutgers, , New Brunswick, NJ 08901,","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125084204","display_name":"Jose M Duarte","orcid":null},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose M Duarte","raw_affiliation_strings":["Research Collaboratory for Structural Bioinformatics Protein Data Bank, San Diego Supercomputer Center, University of California San Diego , San Diego, CA 92093,"],"raw_orcid":"https://orcid.org/0000-0002-9544-5621","affiliations":[{"raw_affiliation_string":"Research Collaboratory for Structural Bioinformatics Protein Data Bank, San Diego Supercomputer Center, University of California San Diego , San Diego, CA 92093,","institution_ids":["https://openalex.org/I181653535"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007270631"],"corresponding_institution_ids":["https://openalex.org/I181653535"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":5.4404,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91689607,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"42","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.46219998598098755,"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":0.46219998598098755,"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":0.4124000072479248,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.028999999165534973,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.7961000204086304},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7419000267982483},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6388999819755554},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5975000262260437},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5947999954223633},{"id":"https://openalex.org/keywords/protein-methods","display_name":"Protein methods","score":0.421099990606308},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4066999852657318},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.38920000195503235}],"concepts":[{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.7961000204086304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454000115394592},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7419000267982483},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6388999819755554},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5975000262260437},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5947999954223633},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43959999084472656},{"id":"https://openalex.org/C111364199","wikidata":"https://www.wikidata.org/wiki/Q2915896","display_name":"Protein methods","level":4,"score":0.421099990606308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41499999165534973},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.38920000195503235},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.35659998655319214},{"id":"https://openalex.org/C139489369","wikidata":"https://www.wikidata.org/wiki/Q770846","display_name":"Structural similarity","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32409998774528503},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.30730000138282776},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.2685000002384186}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":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":"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":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btag058","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag058","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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:41632625","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41632625","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:pubmedcentral.nih.gov:12955762","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12955762/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12955762/pdf/btag058.pdf","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"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag058","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag058","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":[{"id":"https://metadata.un.org/sdg/2","score":0.7377699613571167,"display_name":"Zero hunger"}],"awards":[{"id":"https://openalex.org/G2300401122","display_name":null,"funder_award_id":"DBI-2321666","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2800486080","display_name":"PDB Management by The Research Collaboratory for Structural Bioinformatics","funder_award_id":"2321666","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2813074050","display_name":null,"funder_award_id":"R01GM157729","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G292810974","display_name":null,"funder_award_id":"DE-SC0019749","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4053639993","display_name":null,"funder_award_id":"R01GM157729","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5119270449","display_name":null,"funder_award_id":"R01GM157729","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"},{"id":"https://openalex.org/G6928499274","display_name":null,"funder_award_id":"DE-SC0019749","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8098711524","display_name":null,"funder_award_id":"R01GM157729","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320317220","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1995808589","https://openalex.org/W2040548339","https://openalex.org/W2102245393","https://openalex.org/W2128674962","https://openalex.org/W2134815007","https://openalex.org/W2144998676","https://openalex.org/W2950954328","https://openalex.org/W2954851300","https://openalex.org/W2963469388","https://openalex.org/W2964121744","https://openalex.org/W3040969795","https://openalex.org/W3177828909","https://openalex.org/W3186179742","https://openalex.org/W3212854871","https://openalex.org/W3215918380","https://openalex.org/W4293475204","https://openalex.org/W4293832947","https://openalex.org/W4309908854","https://openalex.org/W4324143928","https://openalex.org/W4327550249","https://openalex.org/W4375858802","https://openalex.org/W4386123432","https://openalex.org/W4386496033","https://openalex.org/W4388464011","https://openalex.org/W4389174567","https://openalex.org/W4389235501","https://openalex.org/W4393230039","https://openalex.org/W4396721167","https://openalex.org/W4403925091","https://openalex.org/W4404797546","https://openalex.org/W4406440058","https://openalex.org/W4407150866","https://openalex.org/W4407367564"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1],"rapid":[2],"expansion":[3],"of":[4,52,71,152],"three-dimensional":[5],"(3D)":[6],"biomolecular":[7],"structure":[8,18,29,62,77,141],"information,":[9],"driven":[10],"by":[11,148],"breakthroughs":[12],"in":[13],"artificial":[14],"intelligence/deep":[15],"learning":[16],"(AI/DL)-based":[17],"predictions,":[19],"has":[20],"created":[21],"an":[22],"urgent":[23],"need":[24],"for":[25,125],"scalable":[26,61],"and":[27,44,75,89,129],"efficient":[28,103,139],"similarity":[30,63,124],"search":[31,64],"methods.":[32,82],"Traditional":[33],"alignment-based":[34],"approaches,":[35],"such":[36],"as":[37],"structural":[38],"superposition":[39],"tools,":[40],"are":[41],"computationally":[42],"expensive":[43],"challenging":[45],"to":[46,67,95,108],"scale":[47],"with":[48],"the":[49,118,144,149],"vast":[50],"number":[51],"available":[53,161,175],"macromolecular":[54],"structures.":[55],"RESULTS:":[56],"Herein,":[57],"we":[58],"present":[59],"a":[60,90],"strategy":[65],"designed":[66],"navigate":[68],"extensive":[69],"repositories":[70],"experimentally":[72],"determined":[73],"structures":[74,98],"computed":[76],"models":[78,88],"predicted":[79],"using":[80],"AI/DL":[81],"Our":[83],"approach":[84],"leverages":[85],"protein":[86],"language":[87],"deep":[91],"neural":[92],"network":[93],"architecture":[94],"transform":[96],"3D":[97,123,153],"into":[99],"fixed-length":[100],"vectors,":[101],"enabling":[102],"large-scale":[104,140],"comparisons.":[105],"Although":[106],"trained":[107],"predict":[109],"TM-scores":[110],"between":[111],"single-domain":[112],"structures,":[113],"our":[114,136],"model":[115],"generalizes":[116],"beyond":[117],"domain":[119],"level,":[120],"accurately":[121],"identifying":[122],"full-length":[126],"polypeptide":[127],"chains":[128],"multimeric":[130],"assemblies.":[131],"By":[132],"integrating":[133],"vector":[134],"databases,":[135],"method":[137],"facilitates":[138],"retrieval,":[142],"addressing":[143],"growing":[145],"challenges":[146],"posed":[147],"expanding":[150],"volume":[151],"biostructure":[154],"information.":[155],"AVAILABILITY":[156],"AND":[157],"IMPLEMENTATION:":[158],"Source":[159,164],"code":[160,165],"at":[162],"https://github.com/bioinsilico/rcsb-embedding-search.":[163],"DOI:":[166,170],"https://doi.org/10.6084/m9.figshare.30546698.v1.":[167],"Benchmark":[168],"datasets":[169],"https://doi.org/10.6084/m9.figshare.30546650.v1.":[171],"Web":[172],"server":[173],"prototype":[174],"at:":[176],"http://embedding-search.rcsb.org/.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-08T08:33:18.762332","created_date":"2026-02-06T00:00:00"}