{"id":"https://openalex.org/W4315621825","doi":"https://doi.org/10.1093/bib/bbac599","title":"Alignment-free estimation of sequence conservation for identifying functional sites using protein sequence embeddings","display_name":"Alignment-free estimation of sequence conservation for identifying functional sites using protein sequence embeddings","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4315621825","doi":"https://doi.org/10.1093/bib/bbac599","pmid":"https://pubmed.ncbi.nlm.nih.gov/36631405"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbac599","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbac599","pdf_url":"https://academic.oup.com/bib/article-pdf/24/1/bbac599/48782835/bbac599.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bib/article-pdf/24/1/bbac599/48782835/bbac599.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066141945","display_name":"Wayland Yeung","orcid":"https://orcid.org/0000-0002-2523-4984"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wayland Yeung","raw_affiliation_strings":["University of Georgia Institute of Bioinformatics, , 30602, Georgia , USA"],"affiliations":[{"raw_affiliation_string":"University of Georgia Institute of Bioinformatics, , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050749778","display_name":"Zhongliang Zhou","orcid":"https://orcid.org/0000-0003-4471-6759"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongliang Zhou","raw_affiliation_strings":["University of Georgia School of Computing, , 30602, Georgia , USA"],"affiliations":[{"raw_affiliation_string":"University of Georgia School of Computing, , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359839","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0003-1205-8632"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sheng Li","raw_affiliation_strings":["University of Virginia School of Data Science, , 22903, Virginia , USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia School of Data Science, , 22903, Virginia , USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033384464","display_name":"Natarajan Kannan","orcid":"https://orcid.org/0000-0002-2833-8375"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Natarajan Kannan","raw_affiliation_strings":["University of Georgia Department of Biochemistry and Molecular Biology, , 30602, Georgia , USA","University of Georgia Institute of Bioinformatics, , 30602, Georgia , USA"],"affiliations":[{"raw_affiliation_string":"University of Georgia Department of Biochemistry and Molecular Biology, , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]},{"raw_affiliation_string":"University of Georgia Institute of Bioinformatics, , 30602, Georgia , USA","institution_ids":["https://openalex.org/I165733156"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033384464","https://openalex.org/A5100359839"],"corresponding_institution_ids":["https://openalex.org/I165733156","https://openalex.org/I51556381"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":{"value":4011,"currency":"USD","value_usd":4011},"fwci":4.2633,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.9457742,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"24","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9998000264167786,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9998000264167786,"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":0.9994999766349792,"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":0.9991999864578247,"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/sequence","display_name":"Sequence (biology)","score":0.7921842932701111},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5604265332221985},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5480067133903503},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.5460479259490967},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4894386827945709},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4575369358062744},{"id":"https://openalex.org/keywords/sequence-analysis","display_name":"Sequence analysis","score":0.4236738681793213},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.41305840015411377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3648275136947632},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3313857316970825},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.27178290486335754},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.26349538564682007},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.20877382159233093},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09762537479400635},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.07051444053649902}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7921842932701111},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5604265332221985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5480067133903503},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.5460479259490967},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4894386827945709},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4575369358062744},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.4236738681793213},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.41305840015411377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3648275136947632},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3313857316970825},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.27178290486335754},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.26349538564682007},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.20877382159233093},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09762537479400635},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07051444053649902},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[{"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"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":"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":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","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}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbac599","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbac599","pdf_url":"https://academic.oup.com/bib/article-pdf/24/1/bbac599/48782835/bbac599.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36631405","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36631405","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":"Briefings in bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9851297","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9851297","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9851297/pdf/bbac599.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Brief Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bib/bbac599","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbac599","pdf_url":"https://academic.oup.com/bib/article-pdf/24/1/bbac599/48782835/bbac599.pdf","source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G1432373144","display_name":null,"funder_award_id":"W911NF-21-1-","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G3497591915","display_name":null,"funder_award_id":"(NIH)","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6742976396","display_name":null,"funder_award_id":"R35 GM139656","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8771980258","display_name":null,"funder_award_id":"W911NF-21-1-0028","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8998121839","display_name":null,"funder_award_id":"911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4315621825.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1892433039","https://openalex.org/W1967293793","https://openalex.org/W1974966731","https://openalex.org/W2015323647","https://openalex.org/W2036696353","https://openalex.org/W2122825543","https://openalex.org/W2143210482","https://openalex.org/W2146950091","https://openalex.org/W2158266834","https://openalex.org/W2163352757","https://openalex.org/W2761430568","https://openalex.org/W2791299132","https://openalex.org/W2972411752","https://openalex.org/W2986717577","https://openalex.org/W2991012415","https://openalex.org/W3095583226","https://openalex.org/W3112376646","https://openalex.org/W3144701084","https://openalex.org/W3146944767","https://openalex.org/W3166142427","https://openalex.org/W3170504813","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3211795435","https://openalex.org/W4225868104","https://openalex.org/W4283205649","https://openalex.org/W6748650044","https://openalex.org/W6797574328"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W2162923930","https://openalex.org/W1482324242","https://openalex.org/W2133116680","https://openalex.org/W2091678889","https://openalex.org/W1525517788","https://openalex.org/W2804480386","https://openalex.org/W3186624150","https://openalex.org/W65850283"],"abstract_inverted_index":{"Protein":[0],"language":[1,54,62],"modeling":[2],"is":[3,155],"a":[4,39,108,156],"fast-emerging":[5],"deep":[6],"learning":[7],"method":[8,40,81,119,159],"in":[9,107,144,148,165,173],"bioinformatics":[10],"with":[11],"diverse":[12],"applications":[13],"such":[14],"as":[15,131],"structure":[16],"prediction":[17,30],"and":[18,170],"protein":[19,53,61,84,149,168,182],"design.":[20],"However,":[21],"application":[22],"toward":[23],"estimating":[24,171],"sequence":[25,46,49,128,169,183],"conservation":[26,47,77,153,172],"for":[27,41,76,104,160],"functional":[28,124,163],"site":[29],"has":[31],"not":[32,92],"been":[33],"systematically":[34],"explored.":[35],"Here,":[36],"we":[37,86,135],"present":[38],"the":[42,69,95,112,138],"alignment-free":[43,175],"estimation":[44],"of":[45,97,140,184],"using":[48],"embeddings":[50],"generated":[51],"from":[52],"models.":[55],"Comprehensive":[56],"benchmarks":[57],"across":[58],"publicly":[59],"available":[60],"models":[63,67],"reveal":[64],"that":[65,88],"ESM2":[66],"provide":[68],"best":[70],"performance":[71],"to":[72,82,94,114],"computational":[73],"cost":[74],"ratio":[75],"estimation.":[78],"Applying":[79],"our":[80,187],"full-length":[83,167],"sequences,":[85],"demonstrate":[87,136],"embedding-based":[89,152],"methods":[90],"are":[91],"sensitive":[93],"order":[96],"conserved":[98,123,141],"elements-conservation":[99],"scores":[100],"can":[101,120],"be":[102],"calculated":[103],"multidomain":[105],"proteins":[106],"single":[109],"run,":[110],"without":[111],"need":[113],"separate":[115],"individual":[116],"domains.":[117],"Our":[118],"also":[121],"identify":[122],"sites":[125,164],"within":[126],"fast-evolving":[127],"regions":[129],"(such":[130],"domain":[132],"inserts),":[133],"which":[134],"through":[137],"identification":[139],"phosphorylation":[142],"motifs":[143],"variable":[145],"insert":[146],"segments":[147],"kinases.":[150],"Overall,":[151],"analysis":[154],"broadly":[157],"applicable":[158],"identifying":[161],"potential":[162],"any":[166],"an":[174],"manner.":[176],"To":[177],"run":[178],"this":[179],"on":[180],"your":[181],"interest,":[185],"try":[186],"scripts":[188],"at":[189],"https://github.com/esbgkannan/kibby.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
