{"id":"https://openalex.org/W2810846340","doi":"https://doi.org/10.1093/bioinformatics/bty523","title":"The choice of sequence homologs included in multiple sequence alignments has a dramatic impact on evolutionary conservation analysis","display_name":"The choice of sequence homologs included in multiple sequence alignments has a dramatic impact on evolutionary conservation analysis","publication_year":2018,"publication_date":"2018-06-26","ids":{"openalex":"https://openalex.org/W2810846340","doi":"https://doi.org/10.1093/bioinformatics/bty523","mag":"2810846340","pmid":"https://pubmed.ncbi.nlm.nih.gov/29947739"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bty523","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty523","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/1/12/27182992/bty523.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,"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":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/35/1/12/27182992/bty523.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027391620","display_name":"Nelson Gil","orcid":"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"},"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":"https://orcid.org/0000-0003-0085-5335","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":0.7444,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.69052591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"35","issue":"1","first_page":"12","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.7329000234603882,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.7329000234603882,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.08959999680519104,"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/T11162","display_name":"Enzyme Structure and Function","score":0.04320000112056732,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.7373194694519043},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5673079490661621},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5126087069511414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4989502429962158},{"id":"https://openalex.org/keywords/protein-superfamily","display_name":"Protein superfamily","score":0.47912999987602234},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4762451946735382},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.46435999870300293},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.4282763600349426},{"id":"https://openalex.org/keywords/conserved-sequence","display_name":"Conserved sequence","score":0.4142484664916992},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.39633190631866455},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.339471697807312},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32865023612976074},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3264467120170593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32543033361434937},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2614782452583313},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.250038206577301},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24907729029655457}],"concepts":[{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.7373194694519043},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5673079490661621},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5126087069511414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4989502429962158},{"id":"https://openalex.org/C178180057","wikidata":"https://www.wikidata.org/wiki/Q7251477","display_name":"Protein superfamily","level":3,"score":0.47912999987602234},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4762451946735382},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.46435999870300293},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.4282763600349426},{"id":"https://openalex.org/C199216141","wikidata":"https://www.wikidata.org/wiki/Q4995178","display_name":"Conserved sequence","level":4,"score":0.4142484664916992},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.39633190631866455},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.339471697807312},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32865023612976074},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3264467120170593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32543033361434937},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2614782452583313},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.250038206577301},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24907729029655457},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","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},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":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":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bty523","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty523","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/1/12/27182992/bty523.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,"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:29947739","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29947739","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":"Journal Article"},{"id":"pmh:oai:europepmc.org:5888548","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6298051","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bty523","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty523","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/1/12/27182992/bty523.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,"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":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G4081026042","display_name":null,"funder_award_id":"R01 AI141816","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"},{"id":"https://openalex.org/G4358409836","display_name":"Molecular basis of receptor-ligand recognition in the Immunological Synapse","funder_award_id":"5r01gm118709-05","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"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/G503200962","display_name":null,"funder_award_id":"T32GM-007288","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"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/G7085535245","display_name":null,"funder_award_id":"R01 GM118709","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G8425617111","display_name":null,"funder_award_id":"R35 GM136357","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G87033130","display_name":"Medical Scientist Training Program","funder_award_id":"5t32gm007288-50","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G930088245","display_name":null,"funder_award_id":"F31 GM116570","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/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"},{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2810846340.pdf","grobid_xml":"https://content.openalex.org/works/W2810846340.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1570448133","https://openalex.org/W1967293793","https://openalex.org/W1967408543","https://openalex.org/W1969156759","https://openalex.org/W1979016574","https://openalex.org/W1987328021","https://openalex.org/W1989876752","https://openalex.org/W1995924392","https://openalex.org/W2006458211","https://openalex.org/W2011441819","https://openalex.org/W2018661561","https://openalex.org/W2024631466","https://openalex.org/W2032426558","https://openalex.org/W2043904638","https://openalex.org/W2045197143","https://openalex.org/W2046407284","https://openalex.org/W2055043387","https://openalex.org/W2074231493","https://openalex.org/W2087064593","https://openalex.org/W2092189515","https://openalex.org/W2096525273","https://openalex.org/W2099111195","https://openalex.org/W2100009368","https://openalex.org/W2102524821","https://openalex.org/W2103210604","https://openalex.org/W2109553965","https://openalex.org/W2110919845","https://openalex.org/W2113944588","https://openalex.org/W2122137509","https://openalex.org/W2122854841","https://openalex.org/W2130674742","https://openalex.org/W2131474431","https://openalex.org/W2132109794","https://openalex.org/W2133350649","https://openalex.org/W2137046528","https://openalex.org/W2137780217","https://openalex.org/W2137991504","https://openalex.org/W2139919097","https://openalex.org/W2145268834","https://openalex.org/W2148171419","https://openalex.org/W2151550848","https://openalex.org/W2158714788","https://openalex.org/W2162566191","https://openalex.org/W2169434145","https://openalex.org/W2264362083","https://openalex.org/W2411891477","https://openalex.org/W2468251533","https://openalex.org/W2478708596","https://openalex.org/W2523926726","https://openalex.org/W2722005050","https://openalex.org/W2739999456","https://openalex.org/W2757108520","https://openalex.org/W2773938469","https://openalex.org/W4234797890","https://openalex.org/W6679790772","https://openalex.org/W6715211488","https://openalex.org/W6740553298"],"related_works":["https://openalex.org/W2181549235","https://openalex.org/W2003319012","https://openalex.org/W2009133913","https://openalex.org/W2015399150","https://openalex.org/W2061567716","https://openalex.org/W2275032899","https://openalex.org/W2036521446","https://openalex.org/W2498689255","https://openalex.org/W2078298125","https://openalex.org/W2026660542"],"abstract_inverted_index":{"Motivation:":[0],"The":[1,54,92],"analysis":[2,112,177],"of":[3,26,39,48,57,64,70,79,83,94,106,113,116,128,173,181,197,219,243],"sequence":[4,88],"conservation":[5,111,176,248],"patterns":[6],"has":[7],"been":[8],"widely":[9],"utilized":[10],"to":[11,44,229],"identify":[12,46],"functionally":[13],"important":[14],"(catalytic":[15],"and":[16,239],"ligand-binding)":[17],"protein":[18],"residues":[19,43],"for":[20,143,247],"over":[21],"a":[22,40,122,130,147,155],"half-century.":[23],"Despite":[24],"decades":[25],"development,":[27],"on":[28,74],"average":[29,126,179],"state-of-the-art":[30,136,184],"non-template-based":[31],"functional":[32,51,96],"residue":[33,97],"prediction":[34,98,145],"methods":[35],"must":[36],"predict":[37],"\u223c25%":[38],"protein's":[41,50],"total":[42],"correctly":[45],"half":[47],"the":[49,68,75,80,103,144,194,201,211,237,240],"site":[52,206],"residues.":[53],"overwhelming":[55],"proportion":[56],"false":[58],"positives":[59],"results":[60],"in":[61,86,146,162,213],"reported":[62,134],"'F-Scores'":[63],"\u223c0.3.":[65],"We":[66,186],"investigated":[67],"limits":[69,93],"current":[71],"approaches,":[72],"focusing":[73],"so-far":[76],"neglected":[77],"impact":[78],"specific":[81],"choice":[82],"homologs":[84,119,174],"included":[85],"multiple":[87],"alignments":[89],"(MSAs).":[90],"Results:":[91],"conservation-based":[95],"were":[99],"explored":[100],"by":[101,135,217,221],"surveying":[102],"binding":[104,205],"sites":[105],"1023":[107],"proteins.":[108],"A":[109],"straightforward":[110],"MSAs":[114,246],"composed":[115,245],"randomly":[117],"selected":[118],"sampled":[120],"from":[121],"PSI-BLAST":[123],"search":[124],"achieves":[125],"F-Scores":[127,180],"\u223c0.3,":[129],"performance":[131,199],"matching":[132],"that":[133,154,189],"methods,":[137],"which":[138],"often":[139],"consider":[140],"additional":[141],"features":[142],"machine":[148],"learning":[149],"setting.":[150],"Interestingly,":[151],"we":[152,209],"found":[153],"simple":[156],"combinatorial":[157],"MSA":[158,168],"sampling":[159],"algorithm":[160],"will":[161],"almost":[163],"every":[164],"case":[165],"produce":[166],"an":[167,170,226],"with":[169],"optimal":[171],"set":[172],"whose":[175],"reaches":[178],"\u223c0.6,":[182],"doubling":[183],"performance.":[185],"also":[187],"show":[188],"this":[190,214],"is":[191],"nearly":[192],"at":[193,256],"theoretical":[195],"limit":[196],"possible":[198],"given":[200],"agreement":[202],"between":[203],"different":[204],"definitions.":[207],"Additionally,":[208],"showcase":[210],"progress":[212],"direction":[215],"made":[216],"Selection":[218],"Alignment":[220],"Maximal":[222],"Mutual":[223],"Information":[224],"(SAMMI),":[225],"information-theory-based":[227],"approach":[228],"identifying":[230],"biologically":[231],"informative":[232],"MSAs.":[233],"This":[234],"work":[235],"highlights":[236],"importance":[238],"unused":[241],"potential":[242],"optimally":[244],"analysis.":[249],"Supplementary":[250,252],"information:":[251],"data":[253],"are":[254],"available":[255],"Bioinformatics":[257],"online.":[258]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}