{"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","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/6298051"},"language":"en","primary_location":{"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":true,"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/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","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":true},"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"],"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"],"affiliations":[{"raw_affiliation_string":"Department of Systems & Computational Biology, Albert Einstein College of Medicine, Bronx, NY, USA","institution_ids":["https://openalex.org/I129975664"]}]}],"institution_assertions":[],"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":3618,"currency":"USD","value_usd":3618,"provenance":"doaj"},"apc_paid":null,"fwci":0.788,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":19,"citation_normalized_percentile":{"value":0.770185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":91},"biblio":{"volume":"35","issue":"1","first_page":"12","last_page":"19"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9978,"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":0.9978,"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":0.992,"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/T11162","display_name":"Enzyme Structure and Function","score":0.9879,"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/sequence","display_name":"Sequence (biology)","score":0.56730795},{"id":"https://openalex.org/keywords/protein-superfamily","display_name":"Protein superfamily","score":0.47913},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.42827636},{"id":"https://openalex.org/keywords/conserved-sequence","display_name":"Conserved sequence","score":0.41424847}],"concepts":[{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.73731947},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.56730795},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5126087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49895024},{"id":"https://openalex.org/C178180057","wikidata":"https://www.wikidata.org/wiki/Q7251477","display_name":"Protein superfamily","level":3,"score":0.47913},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4762452},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.46436},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.42827636},{"id":"https://openalex.org/C199216141","wikidata":"https://www.wikidata.org/wiki/Q4995178","display_name":"Conserved sequence","level":4,"score":0.41424847},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.3963319},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3394717},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32865024},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3264467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32543033},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.26147825},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.2500382},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24907729},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":"","qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"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":true,"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/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://europepmc.org/articles/pmc6298051","pdf_url":"https://europepmc.org/articles/pmc6298051?pdf=render","source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":true,"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":["European Bioinformatics Institute"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6298051","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,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"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":true,"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/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life on land","score":0.7}],"grants":[{"funder":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation","award_id":"ACI-1053575"},{"funder":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health","award_id":"R01 GM118709"}],"datasets":[],"versions":[],"referenced_works_count":54,"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"],"related_works":["https://openalex.org/W2498689255","https://openalex.org/W2275032899","https://openalex.org/W2181549235","https://openalex.org/W2078298125","https://openalex.org/W2061567716","https://openalex.org/W2036521446","https://openalex.org/W2026660542","https://openalex.org/W2015399150","https://openalex.org/W2009133913","https://openalex.org/W2003319012"],"abstract_inverted_index":{"The":[0,53],"analysis":[1],"of":[2,25,38,47,56,63,69,78,82],"sequence":[3,87],"conservation":[4],"patterns":[5],"has":[6],"been":[7],"widely":[8],"utilized":[9],"to":[10,43],"identify":[11,45],"functionally":[12],"important":[13],"(catalytic":[14],"and":[15],"ligand-binding)":[16],"protein":[17],"residues":[18,42],"for":[19],"over":[20],"a":[21,39],"half-century.":[22],"Despite":[23],"decades":[24],"development,":[26],"on":[27,73],"average":[28],"state-of-the-art":[29],"non-template-based":[30],"functional":[31,50],"residue":[32],"prediction":[33],"methods":[34],"must":[35],"predict":[36],"\u223c25%":[37],"protein's":[40,49],"total":[41],"correctly":[44],"half":[46],"the":[48,67,74,79],"site":[51],"residues.":[52],"overwhelming":[54],"proportion":[55],"false":[57],"positives":[58],"results":[59],"in":[60,85],"reported":[61],"'F-Scores'":[62],"\u223c0.3.":[64],"We":[65],"investigated":[66],"limits":[68],"current":[70],"approaches,":[71],"focusing":[72],"so-far":[75],"neglected":[76],"impact":[77],"specific":[80],"choice":[81],"homologs":[83],"included":[84],"multiple":[86],"alignments":[88],"(MSAs).":[89]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2810846340","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2025-01-06T21:38:15.325454","created_date":"2018-07-10"}