{"id":"https://openalex.org/W1967293793","doi":"https://doi.org/10.1093/bioinformatics/btm270","title":"Predicting functionally important residues from sequence conservation","display_name":"Predicting functionally important residues from sequence conservation","publication_year":2007,"publication_date":"2007-05-22","ids":{"openalex":"https://openalex.org/W1967293793","doi":"https://doi.org/10.1093/bioinformatics/btm270","mag":"1967293793","pmid":"https://pubmed.ncbi.nlm.nih.gov/17519246"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btm270","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm270","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017645655","display_name":"John A. Capra","orcid":"https://orcid.org/0000-0001-9743-1795"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John A. Capra","raw_affiliation_strings":["Department of Computer Science and Lewis-Sigler Institute for Integrative Genomics, Princeton University, Princeton, NJ 08540, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Lewis-Sigler Institute for Integrative Genomics, Princeton University, Princeton, NJ 08540, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085615320","display_name":"Mona Singh","orcid":"https://orcid.org/0000-0001-8271-6026"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mona Singh","raw_affiliation_strings":["Department of Computer Science and Lewis-Sigler Institute for Integrative Genomics, Princeton University, Princeton, NJ 08540, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Lewis-Sigler Institute for Integrative Genomics, Princeton University, Princeton, NJ 08540, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":9.2869,"has_fulltext":false,"cited_by_count":741,"citation_normalized_percentile":{"value":0.98719308,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"23","issue":"15","first_page":"1875","last_page":"1882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.882099986076355,"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":0.882099986076355,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.0357000008225441,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.02329999953508377,"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/heuristic","display_name":"Heuristic","score":0.5574935674667358},{"id":"https://openalex.org/keywords/conserved-sequence","display_name":"Conserved sequence","score":0.5303500294685364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5013344287872314},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4835936427116394},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.481581449508667},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4472157955169678},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35309353470802307},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.34220758080482483},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33342015743255615},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.24903306365013123},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.24731025099754333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1872273087501526},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1053655743598938},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08561825752258301}],"concepts":[{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5574935674667358},{"id":"https://openalex.org/C199216141","wikidata":"https://www.wikidata.org/wiki/Q4995178","display_name":"Conserved sequence","level":4,"score":0.5303500294685364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5013344287872314},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4835936427116394},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.481581449508667},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4472157955169678},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35309353470802307},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.34220758080482483},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33342015743255615},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.24903306365013123},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.24731025099754333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1872273087501526},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1053655743598938},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08561825752258301},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":"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":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","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":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btm270","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm270","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:17519246","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17519246","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W217834111","https://openalex.org/W1561011671","https://openalex.org/W1631356911","https://openalex.org/W1633894399","https://openalex.org/W1964640688","https://openalex.org/W1965582988","https://openalex.org/W1968733906","https://openalex.org/W1970999032","https://openalex.org/W1972691129","https://openalex.org/W1986154009","https://openalex.org/W1987749411","https://openalex.org/W2004360551","https://openalex.org/W2009570821","https://openalex.org/W2009664421","https://openalex.org/W2023385944","https://openalex.org/W2043543538","https://openalex.org/W2043886357","https://openalex.org/W2045110975","https://openalex.org/W2045197143","https://openalex.org/W2046407284","https://openalex.org/W2062663912","https://openalex.org/W2069663555","https://openalex.org/W2078866107","https://openalex.org/W2083468430","https://openalex.org/W2099075703","https://openalex.org/W2099111195","https://openalex.org/W2099254366","https://openalex.org/W2103210604","https://openalex.org/W2104760790","https://openalex.org/W2108237355","https://openalex.org/W2111909811","https://openalex.org/W2111973517","https://openalex.org/W2116099439","https://openalex.org/W2117164735","https://openalex.org/W2121166097","https://openalex.org/W2126755078","https://openalex.org/W2130479394","https://openalex.org/W2135498219","https://openalex.org/W2137991504","https://openalex.org/W2138289501","https://openalex.org/W2139919097","https://openalex.org/W2143210482","https://openalex.org/W2146950091","https://openalex.org/W2154333184","https://openalex.org/W2155367844","https://openalex.org/W2764347725","https://openalex.org/W4245668478","https://openalex.org/W4285719527","https://openalex.org/W6770759485"],"related_works":["https://openalex.org/W3102632868","https://openalex.org/W1998707102","https://openalex.org/W2087080325","https://openalex.org/W1558704946","https://openalex.org/W2319409406","https://openalex.org/W2032649343","https://openalex.org/W3103393851","https://openalex.org/W2895425519","https://openalex.org/W1979053898","https://openalex.org/W2135470984"],"abstract_inverted_index":{"MOTIVATION:":[0],"All":[1],"residues":[2,43,163,174],"in":[3,44,89,94,158,172,175],"a":[4,64],"protein":[5,45],"are":[6,11,188],"not":[7,140],"equally":[8],"important.":[9],"Some":[10],"essential":[12],"for":[13,38,53,183],"the":[14,20,33,69,101,116,134],"proper":[15],"structure":[16],"and":[17,162,181],"function":[18],"of":[19,32,72,118,145],"protein,":[21],"whereas":[22],"others":[23],"can":[24],"be":[25],"readily":[26],"replaced.":[27],"Conservation":[28],"analysis":[29,123],"is":[30,97,155,168],"one":[31],"most":[34],"widely":[35],"used":[36,103],"methods":[37,120,129],"predicting":[39],"these":[40],"functionally":[41,91,146],"important":[42,92,147],"sequences.":[46],"RESULTS:":[47],"We":[48,61,107],"introduce":[49],"an":[50],"information-theoretic":[51],"approach":[52,84],"estimating":[54],"sequence":[55],"conservation":[56,71,111,154,185],"based":[57],"on":[58],"Jensen-Shannon":[59],"divergence.":[60],"also":[62,124],"develop":[63],"general":[65],"heuristic":[66],"that":[67,81,109,126,130,152],"considers":[68],"estimated":[70],"sequentially":[73],"neighboring":[74],"sites.":[75,148],"In":[76],"large-scale":[77],"testing,":[78],"we":[79,150],"demonstrate":[80],"our":[82],"combined":[83],"outperforms":[85],"previous":[86],"conservation-based":[87],"measures":[88,186],"identifying":[90,159,173],"residues;":[93],"particular,":[95],"it":[96,167],"significantly":[98],"better":[99,143],"than":[100],"commonly":[102],"Shannon":[104],"entropy":[105],"measure.":[106],"find":[108,151],"considering":[110],"at":[112,190],"sequential":[113],"neighbors":[114],"improves":[115],"performance":[117],"all":[119,184],"tested.":[121],"Our":[122],"reveals":[125],"many":[127],"existing":[128],"attempt":[131],"to":[132,142],"incorporate":[133],"relationships":[135],"between":[136],"amino":[137],"acids":[138],"do":[139],"lead":[141],"identification":[144],"Finally,":[149],"while":[153],"highly":[156],"predictive":[157],"catalytic":[160],"sites":[161],"near":[164],"bound":[165],"ligands,":[166],"much":[169],"less":[170],"effective":[171],"protein-protein":[176],"interfaces.":[177],"AVAILABILITY:":[178],"Data":[179],"sets":[180],"code":[182],"evaluated":[187],"available":[189],"http://compbio.cs.princeton.edu/conservation/":[191]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":51},{"year":2024,"cited_by_count":41},{"year":2023,"cited_by_count":43},{"year":2022,"cited_by_count":54},{"year":2021,"cited_by_count":85},{"year":2020,"cited_by_count":70},{"year":2019,"cited_by_count":56},{"year":2018,"cited_by_count":42},{"year":2017,"cited_by_count":32},{"year":2016,"cited_by_count":44},{"year":2015,"cited_by_count":34},{"year":2014,"cited_by_count":27},{"year":2013,"cited_by_count":22},{"year":2012,"cited_by_count":28}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}