{"id":"https://openalex.org/W4392235646","doi":"https://doi.org/10.1186/s12859-024-05699-5","title":"Protein embedding based alignment","display_name":"Protein embedding based alignment","publication_year":2024,"publication_date":"2024-02-28","ids":{"openalex":"https://openalex.org/W4392235646","doi":"https://doi.org/10.1186/s12859-024-05699-5","pmid":"https://pubmed.ncbi.nlm.nih.gov/38413857"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-024-05699-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05699-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05699-5","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/s12859-024-05699-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092040763","display_name":"Benjamin Giovanni Iovino","orcid":"https://orcid.org/0009-0007-6512-4214"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Giovanni Iovino","raw_affiliation_strings":["Luddy School of Informatics, Computing and Engineering, Indiana University, 700 N. Woodlawn Avenue, Bloomington, IN, 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luddy School of Informatics, Computing and Engineering, Indiana University, 700 N. Woodlawn Avenue, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082620694","display_name":"Yuzhen Ye","orcid":"https://orcid.org/0000-0003-3707-3185"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuzhen Ye","raw_affiliation_strings":["Luddy School of Informatics, Computing and Engineering, Indiana University, 700 N. Woodlawn Avenue, Bloomington, IN, 47408, USA. yye@iu.edu","Luddy School of Informatics, Computing and Engineering, Indiana University, 700 N. Woodlawn Avenue, Bloomington, IN, 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luddy School of Informatics, Computing and Engineering, Indiana University, 700 N. Woodlawn Avenue, Bloomington, IN, 47408, USA. yye@iu.edu","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Luddy School of Informatics, Computing and Engineering, Indiana University, 700 N. Woodlawn Avenue, Bloomington, IN, 47408, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082620694"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":5.0244,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.96135442,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"25","issue":"1","first_page":"85","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.5497000217437744,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.5497000217437744,"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":0.24799999594688416,"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":0.02979999966919422,"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":0.7262665629386902},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.6910860538482666},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.6710052490234375},{"id":"https://openalex.org/keywords/structural-alignment","display_name":"Structural alignment","score":0.6578441262245178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6270131468772888},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.621710479259491},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5701499581336975},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5134145021438599},{"id":"https://openalex.org/keywords/distance-matrix","display_name":"Distance matrix","score":0.4909255802631378},{"id":"https://openalex.org/keywords/smith\u2013waterman-algorithm","display_name":"Smith\u2013Waterman algorithm","score":0.4568236172199249},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.45299574732780457},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43408361077308655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4185936152935028},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4137086868286133},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3409144878387451},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3371255397796631},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.21375054121017456},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.20117676258087158},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10794681310653687},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1052527129650116},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1025647521018982},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09243038296699524}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7262665629386902},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.6910860538482666},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.6710052490234375},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.6578441262245178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6270131468772888},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.621710479259491},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5701499581336975},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5134145021438599},{"id":"https://openalex.org/C111208986","wikidata":"https://www.wikidata.org/wiki/Q901698","display_name":"Distance matrix","level":2,"score":0.4909255802631378},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.4568236172199249},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.45299574732780457},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43408361077308655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4185936152935028},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4137086868286133},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3409144878387451},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3371255397796631},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.21375054121017456},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.20117676258087158},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10794681310653687},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1052527129650116},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1025647521018982},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09243038296699524},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001897","descriptor_name":"Boronic Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001897","descriptor_name":"Boronic Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001897","descriptor_name":"Boronic Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001897","descriptor_name":"Boronic Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-024-05699-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05699-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05699-5","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:38413857","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38413857","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:pubmedcentral.nih.gov:10900708","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10900708","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10900708/pdf/12859_2024_Article_5699.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":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:0924ae79c6104d58a44e5fb015f4ef49","is_oa":true,"landing_page_url":"https://doaj.org/article/0924ae79c6104d58a44e5fb015f4ef49","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 25, Iss 1, Pp 1-16 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-024-05699-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05699-5","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05699-5","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":[],"awards":[{"id":"https://openalex.org/G5460455972","display_name":null,"funder_award_id":"1R01AI143254","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"}],"funders":[{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392235646.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2055043387","https://openalex.org/W2074231493","https://openalex.org/W2097270746","https://openalex.org/W2097642323","https://openalex.org/W2101220662","https://openalex.org/W2102461176","https://openalex.org/W2127322768","https://openalex.org/W2136570298","https://openalex.org/W2143210482","https://openalex.org/W2564980658","https://openalex.org/W2622814825","https://openalex.org/W2949342052","https://openalex.org/W2953008890","https://openalex.org/W3032758350","https://openalex.org/W3095583226","https://openalex.org/W3144701084","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W4309609816","https://openalex.org/W4311661986","https://openalex.org/W4327550249","https://openalex.org/W4383313853"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2103737249","https://openalex.org/W2029514038","https://openalex.org/W2468116983","https://openalex.org/W2111937814","https://openalex.org/W2948014085","https://openalex.org/W2187357871","https://openalex.org/W1974956921","https://openalex.org/W2141411672","https://openalex.org/W2188796099"],"abstract_inverted_index":{"PURPOSE:":[0],"Despite":[1],"the":[2,38,54,75,86,95,168,212],"many":[3],"progresses":[4],"with":[5,12,69,135,175,189,196],"alignment":[6,27,169,233],"algorithms,":[7],"aligning":[8,217],"divergent":[9],"protein":[10,102,201,218,229,242,253],"sequences":[11,68,174,188],"less":[13],"than":[14,255],"20-35%":[15],"pairwise":[16,71,114,160],"identity":[17],"(so":[18],"called":[19],"\"twilight":[20],"zone\")":[21],"remains":[22],"a":[23,81,101],"difficult":[24],"problem.":[25],"Many":[26],"algorithms":[28],"have":[29],"been":[30],"using":[31],"substitution":[32,158],"matrices":[33,45],"since":[34],"their":[35,98,124],"creation":[36],"in":[37],"1970's":[39],"to":[40,50,65,74,144],"generate":[41],"alignments,":[42,161],"however,":[43],"these":[44],"do":[46],"not":[47],"work":[48],"well":[49,147,184],"score":[51,88],"alignments":[52,115,254],"within":[53],"twilight":[55],"zone.":[56],"We":[57,106,192],"developed":[58,228],"Protein":[59],"Embedding":[60],"based":[61,93],"Alignments,":[62],"or":[63],"PEbA,":[64],"better":[66],"align":[67],"low":[70],"identity.":[72],"Similar":[73],"traditional":[76],"Smith-Waterman":[77],"algorithm,":[78],"PEbA":[79,108,143,154,195,220],"uses":[80],"dynamic":[82],"programming":[83],"algorithm":[84],"but":[85],"matching":[87],"of":[89,97,123,165,167,173,178,187],"amino":[90],"acids":[91],"is":[92],"on":[94,109],"similarity":[96,179],"embeddings":[99,197,215],"from":[100,116,121],"language":[103,202,230,243],"model.":[104],"METHODS:":[105],"tested":[107],"over":[110],"twelve":[111],"thousand":[112],"benchmark":[113],"BAliBASE,":[117],"each":[118,134],"one":[119,122],"extracted":[120],"multiple":[125],"sequence":[126,137],"alignments.":[127],"Five":[128],"different":[129,136,151,163,176,200],"BAliBASE":[130],"references":[131],"were":[132],"used,":[133],"identities,":[138],"motifs,":[139],"and":[140,205,207,224],"lengths,":[141],"allowing":[142],"showcase":[145],"how":[146],"it":[148],"aligns":[149],"under":[150],"circumstances.":[152],"RESULTS:":[153],"greatly":[155],"outperformed":[156,222],"BLOSUM":[157],"matrix-based":[159],"achieving":[162],"levels":[164,177],"improvements":[166],"quality":[170],"for":[171,185,216,249],"pairs":[172,186],"(over":[180],"four":[181],"times":[182],"as":[183],"<10%":[190],"identity).":[191],"also":[193,221],"compared":[194],"generated":[198],"by":[199],"models":[203,244],"(ProtT5":[204],"ESM-2)":[206],"found":[208],"that":[209,239],"ProtT5-XL-U50":[210],"produced":[211],"most":[213],"useful":[214,246],"sequences.":[219],"DEDAL":[223],"vcMSA,":[225],"two":[226],"recently":[227],"model":[231],"embedding-based":[232],"methods.":[234,258],"CONCLUSION:":[235],"Our":[236],"results":[237],"suggested":[238],"general":[240],"purpose":[241],"provide":[245],"contextual":[247],"information":[248],"generating":[250],"more":[251],"accurate":[252],"typically":[256],"used":[257]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2025-10-10T00:00:00"}