{"id":"https://openalex.org/W2773938469","doi":"https://doi.org/10.1093/bioinformatics/btx779","title":"Identifying functionally informative evolutionary sequence profiles","display_name":"Identifying functionally informative evolutionary sequence profiles","publication_year":2017,"publication_date":"2017-11-30","ids":{"openalex":"https://openalex.org/W2773938469","doi":"https://doi.org/10.1093/bioinformatics/btx779","mag":"2773938469","pmid":"https://pubmed.ncbi.nlm.nih.gov/29211823","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/5905606"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btx779","doi":"https://doi.org/10.1093/bioinformatics/btx779","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx779","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/8/1278/25171215/btx779.pdf","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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/34/8/1278/25171215/btx779.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027391620","display_name":"Nelson Gil","orcid":"https://orcid.org/0000-0002-0771-2292","observed_orcids":["https://orcid.org/0000-0002-0771-2292"]},"institutions":[{"id":"https://openalex.org/I129975664","display_name":"Albert Einstein College of Medicine","ror":"https://ror.org/05cf8a891","country_code":"US","type":"education","lineage":["https://openalex.org/I129975664","https://openalex.org/I4210112371"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nelson Gil","raw_affiliation_strings":["Department of Systems & Computational Biology, Albert Einstein College of Medicine, Bronx, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems & Computational Biology, Albert Einstein College of Medicine, Bronx, NY, USA","institution_ids":["https://openalex.org/I129975664"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040379692","display_name":"Andr\u00e1s Fiser","orcid":"https://orcid.org/0000-0003-0085-5335","observed_orcids":["https://orcid.org/0000-0003-0085-5335"]},"institutions":[{"id":"https://openalex.org/I129975664","display_name":"Albert Einstein College of Medicine","ror":"https://ror.org/05cf8a891","country_code":"US","type":"education","lineage":["https://openalex.org/I129975664","https://openalex.org/I4210112371"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andras Fiser","raw_affiliation_strings":["Department of Systems & Computational Biology, Albert Einstein College of Medicine, Bronx, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems & Computational Biology, Albert Einstein College of Medicine, Bronx, NY, USA","institution_ids":["https://openalex.org/I129975664"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5040379692"],"corresponding_institution_ids":["https://openalex.org/I129975664"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":null,"fwci":0.5583,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.64032133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"34","issue":"8","first_page":"1278","last_page":"1286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9077000021934509,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9077000021934509,"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":0.047600001096725464,"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":0.028699999675154686,"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/multiple-sequence-alignment","display_name":"multiple sequence alignment","score":0.8550000190734863},{"id":"https://openalex.org/keywords/mutual-information","display_name":"mutual information","score":0.9279999732971191},{"id":"https://openalex.org/keywords/protein-sequence-conservation","display_name":"protein sequence conservation","score":0.4909999966621399},{"id":"https://openalex.org/keywords/functional-site-prediction","display_name":"functional site prediction","score":0.8220000267028809},{"id":"https://openalex.org/keywords/protein-ligand-interactions","display_name":"protein-ligand interactions","score":0.8679999709129333},{"id":"https://openalex.org/keywords/protein-protein-interaction","display_name":"protein-protein interaction","score":0.9869999885559082},{"id":"https://openalex.org/keywords/sequence-diversity","display_name":"sequence diversity","score":0.5450000166893005},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"protein structure prediction","score":0.6489999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6733089089393616},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6489470601081848},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6065992712974548},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5897179841995239},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5457767844200134},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5455739498138428},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5392223000526428},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4952196180820465},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4828210771083832},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.48130002617836},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4740276634693146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28327715396881104},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2671087980270386},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.21911370754241943},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.14330780506134033},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12529024481773376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12317988276481628},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D005075","descriptor_name":"Biological Evolution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btx779","doi":"https://doi.org/10.1093/bioinformatics/btx779","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx779","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/8/1278/25171215/btx779.pdf","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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"pmh:oai:europepmc.org:5444726","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5905606","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:5905606","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5905606","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"Bioinformatics","raw_type":"Text"},{"id":"pmid:29211823","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29211823","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":"Bioinformatics (Oxford, England)","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btx779","doi":"https://doi.org/10.1093/bioinformatics/btx779","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx779","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/8/1278/25171215/btx779.pdf","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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2307236718","display_name":"The molecular basis of receptor-ligand recognition on the immunological synapse","funder_award_id":"F31GM116570","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G2933434049","display_name":"Molecular basis of recognition in the Immunological Synapse","funder_award_id":"R35GM136357","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G310438342","display_name":null,"funder_award_id":"F31GM116570","funder_id":"https://openalex.org/F4320311255","funder_display_name":"Israel National Road Safety Authority"},{"id":"https://openalex.org/G4358409836","display_name":"Molecular basis of receptor-ligand recognition in the Immunological Synapse","funder_award_id":"R01GM118709","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G4737709065","display_name":null,"funder_award_id":"ACI-1053575","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6778350887","display_name":"XSEDE: eXtreme Science and Engineering Discovery Environment","funder_award_id":"1053575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G87033130","display_name":"Medical Scientist Training Program","funder_award_id":"T32GM007288","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320311255","display_name":"Israel National Road Safety Authority","ror":"https://ror.org/03zqvfs52"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2773938469.pdf","grobid_xml":"https://content.openalex.org/works/W2773938469.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1030883578","https://openalex.org/W1570448133","https://openalex.org/W1825227346","https://openalex.org/W1870852322","https://openalex.org/W1967292572","https://openalex.org/W1967293793","https://openalex.org/W1976666280","https://openalex.org/W1995924392","https://openalex.org/W2000892449","https://openalex.org/W2007933226","https://openalex.org/W2008545402","https://openalex.org/W2013425283","https://openalex.org/W2018661561","https://openalex.org/W2023346730","https://openalex.org/W2027893274","https://openalex.org/W2035503835","https://openalex.org/W2040216242","https://openalex.org/W2048154580","https://openalex.org/W2048310584","https://openalex.org/W2061042699","https://openalex.org/W2076514152","https://openalex.org/W2080942850","https://openalex.org/W2081598613","https://openalex.org/W2089649677","https://openalex.org/W2092006899","https://openalex.org/W2092079765","https://openalex.org/W2095439994","https://openalex.org/W2099111195","https://openalex.org/W2107029482","https://openalex.org/W2107103206","https://openalex.org/W2107517961","https://openalex.org/W2107648570","https://openalex.org/W2109766743","https://openalex.org/W2110919845","https://openalex.org/W2111551123","https://openalex.org/W2113358325","https://openalex.org/W2114340287","https://openalex.org/W2120549641","https://openalex.org/W2120836664","https://openalex.org/W2131474431","https://openalex.org/W2133350649","https://openalex.org/W2136570298","https://openalex.org/W2136799255","https://openalex.org/W2137722843","https://openalex.org/W2139520668","https://openalex.org/W2141411672","https://openalex.org/W2143210482","https://openalex.org/W2144860551","https://openalex.org/W2146891463","https://openalex.org/W2151457629","https://openalex.org/W2151550848","https://openalex.org/W2158714788","https://openalex.org/W2165181282","https://openalex.org/W2166701319","https://openalex.org/W2166718648","https://openalex.org/W2171641243","https://openalex.org/W2258865027","https://openalex.org/W2337819340","https://openalex.org/W2478708596","https://openalex.org/W2524386004","https://openalex.org/W6678192332"],"related_works":["https://openalex.org/W2810846340","https://openalex.org/W4412728552","https://openalex.org/W2398424372","https://openalex.org/W2127296617","https://openalex.org/W1990200500","https://openalex.org/W7099495243","https://openalex.org/W2028697242","https://openalex.org/W2127102885","https://openalex.org/W2163585514","https://openalex.org/W2104587248"],"abstract_inverted_index":{"Motivation:":[0],"Multiple":[1],"sequence":[2,74],"alignments":[3],"(MSAs)":[4],"can":[5],"provide":[6],"essential":[7],"input":[8],"to":[9,26,58,115],"many":[10],"bioinformatics":[11],"applications,":[12],"including":[13,154],"protein":[14,110],"structure":[15],"prediction":[16,122],"and":[17,37,107,140,143,148],"functional":[18,119],"annotation.":[19],"However,":[20],"the":[21,84,98,104],"optimal":[22,62],"selection":[23],"of":[24,47,68,79,103,125,131],"sequences":[25],"obtain":[27],"biologically":[28],"informative":[29],"MSAs":[30,95,117],"for":[31,93,118],"such":[32],"purposes":[33],"is":[34,82,159],"poorly":[35],"explored,":[36],"has":[38],"traditionally":[39],"been":[40],"performed":[41],"manually.":[42],"Results:":[43],"We":[44],"present":[45],"Selection":[46],"Alignment":[48],"by":[49,123],"Maximal":[50],"Mutual":[51],"Information":[52],"(SAMMI),":[53],"an":[54,61],"automated,":[55],"sequence-based":[56],"approach":[57,81],"objectively":[59],"select":[60,116],"MSA":[63,88],"from":[64,71,135],"a":[65,72,129],"large":[66],"set":[67,101,130],"alternatives":[69],"sampled":[70],"general":[73],"database":[75],"search.":[76],"The":[77],"hypothesis":[78],"this":[80],"that":[83,96],"mutual":[85],"information":[86],"among":[87],"columns":[89],"will":[90],"be":[91],"maximal":[92],"those":[94],"contain":[97],"most":[99,105],"diverse":[100],"possible":[102],"structurally":[106],"functionally":[108],"homogeneous":[109],"sequences.":[111],"SAMMI":[112,158],"was":[113],"tested":[114],"site":[120],"residue":[121],"analysis":[124],"conservation":[126],"patterns":[127],"on":[128],"435":[132],"proteins":[133],"obtained":[134],"protein-ligand":[136],"(peptides,":[137],"nucleic":[138],"acids":[139],"small":[141],"substrates)":[142],"protein-protein":[144],"interaction":[145],"databases.":[146],"Availability":[147],"implementation:":[149],"A":[150],"freely":[151],"accessible":[152],"program,":[153],"source":[155],"code,":[156],"implementing":[157],"available":[160,170],"at":[161,171],"https://github.com/nelsongil92/SAMMI.git.":[162],"Contact:":[163],"andras.fiser@einstein.yu.edu.":[164],"Supplementary":[165,167],"information:":[166],"data":[168],"are":[169],"Bioinformatics":[172],"online.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2017-12-22T00:00:00"}