{"id":"https://openalex.org/W4309609816","doi":"https://doi.org/10.3389/fbinf.2022.1033775","title":"Nearest neighbor search on embeddings rapidly identifies distant protein relations","display_name":"Nearest neighbor search on embeddings rapidly identifies distant protein relations","publication_year":2022,"publication_date":"2022-11-17","ids":{"openalex":"https://openalex.org/W4309609816","doi":"https://doi.org/10.3389/fbinf.2022.1033775","pmid":"https://pubmed.ncbi.nlm.nih.gov/36466147"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2022.1033775","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2022.1033775","pdf_url":null,"source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in 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/10.3389/fbinf.2022.1033775","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Konstantin Sch\u00fctze","raw_affiliation_strings":["TUM (Technical University of Munich) Department of Informatics, Bioinformatics & Computational Biology-i12, Munich, Germany","TUM (Technical University of Munich) Department of Informatics, Bioinformatics & Computational Biology\u2014i12, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TUM (Technical University of Munich) Department of Informatics, Bioinformatics & Computational Biology-i12, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"TUM (Technical University of Munich) Department of Informatics, Bioinformatics & Computational Biology\u2014i12, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"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":["TUM (Technical University of Munich) Department of Informatics, Bioinformatics & Computational Biology-i12, Munich, Germany","TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Garching, Germany","TUM (Technical University of Munich) Department of Informatics, Bioinformatics & Computational Biology\u2014i12, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TUM (Technical University of Munich) Department of Informatics, Bioinformatics & Computational Biology-i12, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Garching, Germany","institution_ids":[]},{"raw_affiliation_string":"TUM (Technical University of Munich) Department of Informatics, Bioinformatics & Computational Biology\u2014i12, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019985343","display_name":"Martin Steinegger","orcid":"https://orcid.org/0000-0001-8781-9753"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Martin Steinegger","raw_affiliation_strings":["Artificial Intelligence Institute, Seoul National University, Seoul, South Korea","School of Biological Sciences, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Institute, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"School of Biological Sciences, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"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":false,"raw_author_name":"Burkhard Rost","raw_affiliation_strings":["Institute for Advanced Study (TUM-IAS), Germany & TUM School of Life Sciences Weihenstephan (WZW), Freising, Germany","TUM (Technical University of Munich) Department of Informatics, Bioinformatics & Computational Biology-i12, Munich, Germany","TUM (Technical University of Munich) Department of Informatics, Bioinformatics & Computational Biology\u2014i12, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Advanced Study (TUM-IAS), Germany & TUM School of Life Sciences Weihenstephan (WZW), Freising, Germany","institution_ids":["https://openalex.org/I309496635","https://openalex.org/I4210137766"]},{"raw_affiliation_string":"TUM (Technical University of Munich) Department of Informatics, Bioinformatics & Computational Biology-i12, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"TUM (Technical University of Munich) Department of Informatics, Bioinformatics & Computational Biology\u2014i12, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062361890"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1893,"currency":"EUR","value_usd":2041},"fwci":3.1836,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.93340072,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"2","issue":null,"first_page":"1033775","last_page":"1033775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10015","display_name":"Genomics and Phylogenetic Studies","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"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9977999925613403,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.7297496795654297},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.57363361120224},{"id":"https://openalex.org/keywords/homology","display_name":"Homology (biology)","score":0.5522305965423584},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5472745895385742},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.531525194644928},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5251200795173645},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.471794068813324},{"id":"https://openalex.org/keywords/sequence-homology","display_name":"Sequence homology","score":0.4599681496620178},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45701223611831665},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4537437856197357},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3720516860485077},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3466797471046448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33234745264053345},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.29769444465637207},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2557833194732666},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.19298291206359863},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08109486103057861}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7297496795654297},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.57363361120224},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.5522305965423584},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5472745895385742},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.531525194644928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5251200795173645},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.471794068813324},{"id":"https://openalex.org/C2779315201","wikidata":"https://www.wikidata.org/wiki/Q414601","display_name":"Sequence homology","level":4,"score":0.4599681496620178},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45701223611831665},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4537437856197357},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3720516860485077},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3466797471046448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33234745264053345},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.29769444465637207},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2557833194732666},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.19298291206359863},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08109486103057861},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3389/fbinf.2022.1033775","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2022.1033775","pdf_url":null,"source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36466147","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36466147","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":"Frontiers in bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:ffad0397dd8d402ea06aee96cf68be6f","is_oa":true,"landing_page_url":"https://doaj.org/article/ffad0397dd8d402ea06aee96cf68be6f","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":"Frontiers in Bioinformatics, Vol 2 (2022)","raw_type":"article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1693362","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1693362","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1694927","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1694927","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9714024","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9714024","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":"Front Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fbinf.2022.1033775","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2022.1033775","pdf_url":null,"source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1549957888","display_name":null,"funder_award_id":"2021R1C1C102065","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G2088101978","display_name":null,"funder_award_id":"2019R1A6A1A10073437","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3360897862","display_name":null,"funder_award_id":"2019R1A6A1A10073437","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"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/G7525901750","display_name":null,"funder_award_id":"RO 1320/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8959955562","display_name":null,"funder_award_id":"2020M3A9G7103933","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"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/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":95,"referenced_works":["https://openalex.org/W1486358519","https://openalex.org/W1977538576","https://openalex.org/W2020498246","https://openalex.org/W2051210555","https://openalex.org/W2069458148","https://openalex.org/W2087064593","https://openalex.org/W2094519647","https://openalex.org/W2095318832","https://openalex.org/W2099075703","https://openalex.org/W2099919278","https://openalex.org/W2101220662","https://openalex.org/W2102122585","https://openalex.org/W2102461176","https://openalex.org/W2106258670","https://openalex.org/W2108067237","https://openalex.org/W2114496049","https://openalex.org/W2115595474","https://openalex.org/W2124509324","https://openalex.org/W2129448726","https://openalex.org/W2135531426","https://openalex.org/W2135621733","https://openalex.org/W2137146016","https://openalex.org/W2141885858","https://openalex.org/W2147739124","https://openalex.org/W2157750263","https://openalex.org/W2157975034","https://openalex.org/W2158714788","https://openalex.org/W2171572695","https://openalex.org/W2201551179","https://openalex.org/W2620998958","https://openalex.org/W2767095293","https://openalex.org/W2779238054","https://openalex.org/W2883560622","https://openalex.org/W2898402099","https://openalex.org/W2899664253","https://openalex.org/W2901613577","https://openalex.org/W2909727437","https://openalex.org/W2949342052","https://openalex.org/W2950954328","https://openalex.org/W2951433247","https://openalex.org/W2953008890","https://openalex.org/W2962739339","https://openalex.org/W2963213349","https://openalex.org/W2963469388","https://openalex.org/W2971227267","https://openalex.org/W2980789587","https://openalex.org/W2995514860","https://openalex.org/W2998702515","https://openalex.org/W3083095175","https://openalex.org/W3083386021","https://openalex.org/W3094824894","https://openalex.org/W3118936575","https://openalex.org/W3143063265","https://openalex.org/W3144701084","https://openalex.org/W3146944767","https://openalex.org/W3157437194","https://openalex.org/W3161612534","https://openalex.org/W3167923341","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3183475563","https://openalex.org/W4205620281","https://openalex.org/W4206395022","https://openalex.org/W4210702584","https://openalex.org/W4213112325","https://openalex.org/W4220978941","https://openalex.org/W4225438928","https://openalex.org/W4225868104","https://openalex.org/W4242765109","https://openalex.org/W4252166161","https://openalex.org/W4281291878","https://openalex.org/W4281552152","https://openalex.org/W4281790889","https://openalex.org/W4282984452","https://openalex.org/W4287724045","https://openalex.org/W4288087322","https://openalex.org/W4288089799","https://openalex.org/W4300750523","https://openalex.org/W4316926589","https://openalex.org/W4376133226","https://openalex.org/W4385245566","https://openalex.org/W4386496033","https://openalex.org/W6674881462","https://openalex.org/W6677235195","https://openalex.org/W6699972550","https://openalex.org/W6734897383","https://openalex.org/W6739901393","https://openalex.org/W6748415309","https://openalex.org/W6756634121","https://openalex.org/W6758485811","https://openalex.org/W6763868836","https://openalex.org/W6769627184","https://openalex.org/W6770813465","https://openalex.org/W6780145172","https://openalex.org/W6799956455"],"related_works":["https://openalex.org/W2148008870","https://openalex.org/W2381195555","https://openalex.org/W4246757943","https://openalex.org/W2368606575","https://openalex.org/W2132753198","https://openalex.org/W2369874856","https://openalex.org/W2182477562","https://openalex.org/W2792185758","https://openalex.org/W2787484455","https://openalex.org/W2119808169"],"abstract_inverted_index":{"Since":[0],"1992,":[1],"all":[2,138],"state-of-the-art":[3],"methods":[4,140],"for":[5,53,69,81,143],"fast":[6],"and":[7,13,26,96,136],"sensitive":[8],"identification":[9],"of":[10,71,125],"evolutionary,":[11],"structural,":[12],"functional":[14],"relations":[15,59],"between":[16,60],"proteins":[17,82,95],"(also":[18],"referred":[19],"to":[20,49,57,93,101,117,131],"as":[21,40],"\"homology":[22],"detection\")":[23],"use":[24,50],"sequences":[25,65],"sequence-profiles":[27],"(PSSMs).":[28],"Protein":[29],"Language":[30],"Models":[31],"(pLMs)":[32],"generalize":[33],"sequences,":[34],"possibly":[35],"capturing":[36],"the":[37,88,123,132],"same":[38],"constraints":[39],"PSSMs,":[41],"e.g.,":[42],"through":[43],"embeddings.":[44],"Here,":[45],"we":[46,86],"explored":[47],"how":[48,100],"such":[51],"embeddings":[52],"nearest":[54,126],"neighbor":[55,127],"searches":[56],"identify":[58],"protein":[61,133],"pairs":[62],"with":[63,83],"diverged":[64],"(remote":[66],"homology":[67],"detection":[68],"levels":[70],"<20%":[72],"pairwise":[73],"sequence":[74],"identity,":[75],"PIDE).":[76],"While":[77],"this":[78,92],"approach":[79],"excelled":[80],"single":[84],"domains,":[85],"demonstrated":[87],"current":[89],"challenges":[90],"applying":[91],"multi-domain":[94],"presented":[97],"some":[98],"ideas":[99],"overcome":[102],"existing":[103],"limitations,":[104],"in":[105],"principle.":[106],"We":[107],"observed":[108],"that":[109],"sufficiently":[110],"challenging":[111],"data":[112],"set":[113],"separations":[114],"were":[115],"crucial":[116],"provide":[118],"deeply":[119],"relevant":[120],"insights":[121],"into":[122],"behavior":[124],"search":[128],"when":[129],"applied":[130],"embedding":[134],"space,":[135],"made":[137],"our":[139],"readily":[141],"available":[142],"others.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}