{"id":"https://openalex.org/W4387969474","doi":"https://doi.org/10.7554/elife.91415.3","title":"Sensitive remote homology search by local alignment of small positional embeddings from protein language models","display_name":"Sensitive remote homology search by local alignment of small positional embeddings from protein language models","publication_year":2023,"publication_date":"2023-10-27","ids":{"openalex":"https://openalex.org/W4387969474","doi":"https://doi.org/10.7554/elife.91415.3","pmid":"https://pubmed.ncbi.nlm.nih.gov/38488154","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/10942778"},"language":"en","primary_location":{"id":"doi:10.7554/elife.91415.3","doi":"https://doi.org/10.7554/elife.91415.3","is_oa":true,"landing_page_url":"https://doi.org/10.7554/elife.91415.3","pdf_url":null,"source":{"id":"https://openalex.org/S1336409049","display_name":"eLife","issn_l":"2050-084X","issn":["2050-084X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311710","host_organization_name":"eLife Sciences Publications Ltd","host_organization_lineage":["https://openalex.org/P4310311710"],"host_organization_lineage_names":["eLife Sciences Publications Ltd"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"eLife","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.7554/elife.91415.3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020339193","display_name":"Sean R. Johnson","orcid":"https://orcid.org/0000-0001-8261-9015","observed_orcids":["https://orcid.org/0000-0001-8261-9015"]},"institutions":[{"id":"https://openalex.org/I115020962","display_name":"New England Biolabs (United States)","ror":"https://ror.org/04ywg3445","country_code":"US","type":"company","lineage":["https://openalex.org/I115020962"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sean R. Johnson","raw_affiliation_strings":["New England Biolabs Inc., 240 County Road, Ipswich, MA 01938, United States"],"raw_orcid":"https://orcid.org/0000-0001-8261-9015","affiliations":[{"raw_affiliation_string":"New England Biolabs Inc., 240 County Road, Ipswich, MA 01938, United States","institution_ids":["https://openalex.org/I115020962"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113127192","display_name":"Meghana Peshwa","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I115020962","display_name":"New England Biolabs (United States)","ror":"https://ror.org/04ywg3445","country_code":"US","type":"company","lineage":["https://openalex.org/I115020962"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meghana Peshwa","raw_affiliation_strings":["New England Biolabs Inc., 240 County Road, Ipswich, MA 01938, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New England Biolabs Inc., 240 County Road, Ipswich, MA 01938, United States","institution_ids":["https://openalex.org/I115020962"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037417025","display_name":"Zhiyi Sun","orcid":"https://orcid.org/0000-0002-6106-5356","observed_orcids":["https://orcid.org/0000-0002-6106-5356"]},"institutions":[{"id":"https://openalex.org/I115020962","display_name":"New England Biolabs (United States)","ror":"https://ror.org/04ywg3445","country_code":"US","type":"company","lineage":["https://openalex.org/I115020962"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhiyi Sun","raw_affiliation_strings":["New England Biolabs Inc., 240 County Road, Ipswich, MA 01938, United States"],"raw_orcid":"https://orcid.org/0000-0002-6106-5356","affiliations":[{"raw_affiliation_string":"New England Biolabs Inc., 240 County Road, Ipswich, MA 01938, United States","institution_ids":["https://openalex.org/I115020962"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020339193","https://openalex.org/A5037417025"],"corresponding_institution_ids":["https://openalex.org/I115020962"],"apc_list":{"value":3000,"currency":"USD","value_usd":2500},"apc_paid":{"value":3000,"currency":"USD","value_usd":2500},"fwci":1.5447,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.83172167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"12","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.7329000234603882,"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":0.7329000234603882,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.13619999587535858,"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":0.08829999715089798,"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/remote-homology-detection","display_name":"remote homology detection","score":0.8999999761581421},{"id":"https://openalex.org/keywords/positional-encoding","display_name":"positional encoding","score":0.9350000023841858},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.9190000295639038},{"id":"https://openalex.org/keywords/esm-2","display_name":"ESM-2","score":0.871999979019165},{"id":"https://openalex.org/keywords/local-sequence-alignment","display_name":"local alignment","score":0.5569999814033508},{"id":"https://openalex.org/keywords/amino-acid-composition","display_name":"amino acid composition","score":0.7110000252723694},{"id":"https://openalex.org/keywords/foldseek","display_name":"Foldseek","score":0.6290000081062317},{"id":"https://openalex.org/keywords/protein-sequence-comparison","display_name":"protein sequence comparison","score":0.4320000112056732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6296311616897583},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.5359770655632019},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.5054643154144287},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.46418824791908264},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45735564827919006},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4534301161766052},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4501122236251831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4385567009449005},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.436116099357605},{"id":"https://openalex.org/C200307862","wikidata":"https://www.wikidata.org/wiki/Q7797175","display_name":"Threading (protein sequence)","level":3,"score":0.42479225993156433},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.420878529548645},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.41753077507019043},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.34859687089920044},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.27859726548194885},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.2752882242202759},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25483590364456177},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.25393128395080566},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.22633764147758484},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13782376050949097},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":false}],"locations_count":8,"locations":[{"id":"doi:10.7554/elife.91415.3","doi":"https://doi.org/10.7554/elife.91415.3","is_oa":true,"landing_page_url":"https://doi.org/10.7554/elife.91415.3","pdf_url":null,"source":{"id":"https://openalex.org/S1336409049","display_name":"eLife","issn_l":"2050-084X","issn":["2050-084X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311710","host_organization_name":"eLife Sciences Publications Ltd","host_organization_lineage":["https://openalex.org/P4310311710"],"host_organization_lineage_names":["eLife Sciences Publications Ltd"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"eLife","raw_type":"journal-article"},{"id":"doi:10.7554/elife.91415","doi":"https://doi.org/10.7554/elife.91415","is_oa":true,"landing_page_url":"https://doi.org/10.7554/elife.91415","pdf_url":"https://github.com/elifesciences/enhanced-preprints-data/raw/master/data/91415/v1/91415-v1.pdf","source":{"id":"https://openalex.org/S1336409049","display_name":"eLife","issn_l":"2050-084X","issn":["2050-084X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311710","host_organization_name":"eLife Sciences Publications Ltd","host_organization_lineage":["https://openalex.org/P4310311710"],"host_organization_lineage_names":["eLife Sciences Publications Ltd"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"eLife","raw_type":"journal-article"},{"id":"doi:10.7554/elife.91415.2","doi":"https://doi.org/10.7554/elife.91415.2","is_oa":true,"landing_page_url":"https://doi.org/10.7554/elife.91415.2","pdf_url":null,"source":{"id":"https://openalex.org/S1336409049","display_name":"eLife","issn_l":"2050-084X","issn":["2050-084X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311710","host_organization_name":"eLife Sciences Publications Ltd","host_organization_lineage":["https://openalex.org/P4310311710"],"host_organization_lineage_names":["eLife Sciences Publications Ltd"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"eLife","raw_type":"posted-content"},{"id":"doi:10.7554/elife.91415.1","doi":"https://doi.org/10.7554/elife.91415.1","is_oa":true,"landing_page_url":"https://doi.org/10.7554/elife.91415.1","pdf_url":null,"source":{"id":"https://openalex.org/S1336409049","display_name":"eLife","issn_l":"2050-084X","issn":["2050-084X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311710","host_organization_name":"eLife Sciences Publications Ltd","host_organization_lineage":["https://openalex.org/P4310311710"],"host_organization_lineage_names":["eLife Sciences Publications Ltd"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"eLife","raw_type":"posted-content"},{"id":"doi:10.1101/2023.07.26.550718","doi":"https://doi.org/10.1101/2023.07.26.550718","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2023.07.26.550718","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2023/07/29/2023.07.26.550718.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:10942778","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10942778","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10942778/pdf/elife-91415.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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"eLife","raw_type":"Text"},{"id":"pmid:38488154","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38488154","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,"listed_in":[],"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":"eLife","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:9a1b502e09ad41f1a33d993877310446","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/9a1b502e09ad41f1a33d993877310446","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,"listed_in":[],"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":"eLife, Vol 12 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.7554/elife.91415.3","doi":"https://doi.org/10.7554/elife.91415.3","is_oa":true,"landing_page_url":"https://doi.org/10.7554/elife.91415.3","pdf_url":null,"source":{"id":"https://openalex.org/S1336409049","display_name":"eLife","issn_l":"2050-084X","issn":["2050-084X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","jufo-2","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311710","host_organization_name":"eLife Sciences Publications Ltd","host_organization_lineage":["https://openalex.org/P4310311710"],"host_organization_lineage_names":["eLife Sciences Publications Ltd"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"eLife","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307991","display_name":"New England Biolabs","ror":"https://ror.org/04ywg3445"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387969474.pdf","grobid_xml":"https://content.openalex.org/works/W4387969474.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W2069458148","https://openalex.org/W2101220662","https://openalex.org/W2108588173","https://openalex.org/W2110115297","https://openalex.org/W2130479394","https://openalex.org/W2138122982","https://openalex.org/W2142678478","https://openalex.org/W2143210482","https://openalex.org/W2158714788","https://openalex.org/W2160378127","https://openalex.org/W2902353954","https://openalex.org/W2949476196","https://openalex.org/W2950954328","https://openalex.org/W2963341956","https://openalex.org/W2970971581","https://openalex.org/W2972411752","https://openalex.org/W3095583226","https://openalex.org/W3143063265","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3211795435","https://openalex.org/W4213112325","https://openalex.org/W4281790889","https://openalex.org/W4282922306","https://openalex.org/W4288077714","https://openalex.org/W4308687190","https://openalex.org/W4309609816","https://openalex.org/W4310957810","https://openalex.org/W4321748128","https://openalex.org/W4322494707","https://openalex.org/W4327550249","https://openalex.org/W4375858802","https://openalex.org/W4386860638","https://openalex.org/W4388823609","https://openalex.org/W4390590489","https://openalex.org/W4392235646","https://openalex.org/W4404447386"],"related_works":["https://openalex.org/W2034115630","https://openalex.org/W6950356521","https://openalex.org/W4386860638","https://openalex.org/W4393342758","https://openalex.org/W4412454118","https://openalex.org/W4416808213","https://openalex.org/W4401463754","https://openalex.org/W2892992490","https://openalex.org/W4220838716","https://openalex.org/W4402274204"],"abstract_inverted_index":{"Accurately":[0],"detecting":[1],"distant":[2],"evolutionary":[3,74],"relationships":[4],"between":[5,24],"proteins":[6],"remains":[7],"an":[8],"ongoing":[9],"challenge":[10],"in":[11,128],"bioinformatics.":[12],"Search":[13],"methods":[14,111],"based":[15],"on":[16],"primary":[17,146],"sequence":[18,46,68,198],"struggle":[19],"to":[20,80,93,99,144,165],"accurately":[21],"detect":[22],"homology":[23],"sequences":[25,147],"with":[26],"less":[27],"than":[28,82],"20%":[29],"amino":[30,156,196],"acid":[31,157,197],"identity.":[32],"Profile-":[33],"and":[34,55,70,84,103,107,159,171],"structure-based":[35],"strategies":[36],"extend":[37],"sensitive":[38,67],"search":[39,108,131,173,202],"capabilities":[40],"into":[41,149],"this":[42,116],"twilight":[43],"zone":[44],"of":[45,96,110,136],"similarity":[47],"but":[48,87],"require":[49],"slow":[50],"pre-processing":[51],"steps.":[52],"Recently,":[53],"whole-protein":[54,97],"positional":[56,113,122,179],"embeddings":[57,98,123,162,180],"from":[58],"deep":[59],"neural":[60],"networks":[61],"have":[62],"shown":[63],"promise":[64],"for":[65,191],"providing":[66],"comparison":[69],"annotation":[71],"at":[72],"long":[73],"distances.":[75],"Embeddings":[76],"are":[77],"generally":[78],"faster":[79],"compute":[81],"profiles":[83,158],"predicted":[85],"structures":[86],"still":[88],"suffer":[89],"several":[90],"drawbacks":[91],"related":[92],"the":[94,104,140,150,166],"ability":[95],"discriminate":[100],"domain-level":[101],"homology,":[102],"database":[105],"size":[106],"speed":[109],"using":[112],"embeddings.":[114],"In":[115],"work,":[117],"we":[118,138],"show":[119],"that":[120,178],"low-dimensionality":[121],"can":[124,187],"be":[125],"used":[126],"directly":[127,148],"speed-optimized":[129],"local":[130],"algorithms.":[132,174],"As":[133],"a":[134,184],"proof":[135],"concept,":[137],"use":[139,160],"ESM2":[141],"3B":[142],"model":[143],"convert":[145],"3D":[151],"interaction":[152],"(3Di)":[153],"alphabet":[154],"or":[155],"these":[161],"as":[163,181,183],"input":[164],"highly":[167],"optimized":[168],"Foldseek,":[169],"HMMER3,":[170],"HH-suite":[172],"Our":[175],"results":[176],"suggest":[177],"small":[182],"single":[185],"byte":[186],"provide":[188],"sufficient":[189],"information":[190],"dramatically":[192],"improved":[193],"sensitivity":[194],"over":[195],"searches":[199],"without":[200],"sacrificing":[201],"speed.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2023-10-28T00:00:00"}
