{"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":{"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":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/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"},"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":0.509,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":7,"citation_normalized_percentile":{"value":0.554574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":82,"max":83},"biblio":{"volume":"34","issue":"8","first_page":"1278","last_page":"1286"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998,"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":0.9998,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9991,"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":0.9989,"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":0.6065993},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.48130003}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6733089},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.64894706},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6065993},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.589718},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5457768},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.54557395},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5392223},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.49521962},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48282108},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.48130003},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.47402766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28327715},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2671088},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.21911371},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1433078},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12529024},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12317988},{"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":"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},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005075","descriptor_name":"Biological Evolution","qualifier_ui":"","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":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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}],"locations_count":4,"locations":[{"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":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/pmc5905606","pdf_url":"https://europepmc.org/articles/pmc5905606?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/PMC5905606","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/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,"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/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":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":[{"score":0.65,"id":"https://metadata.un.org/sdg/15","display_name":"Life on land"}],"grants":[{"funder":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation","award_id":"ACI-1053575"},{"funder":"https://openalex.org/F4320311255","funder_display_name":"Israel National Road Safety Authority","award_id":"F31GM116570"},{"funder":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health","award_id":"R01 GM118709"}],"datasets":[],"versions":[],"referenced_works_count":60,"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"],"related_works":["https://openalex.org/W4289175812","https://openalex.org/W3186624150","https://openalex.org/W2804480386","https://openalex.org/W2140187548","https://openalex.org/W2121560377","https://openalex.org/W2103210188","https://openalex.org/W2070753511","https://openalex.org/W2053803793","https://openalex.org/W2008335091","https://openalex.org/W1936662467"],"abstract_inverted_index":{"Multiple":[0],"sequence":[1,71],"alignments":[2],"(MSAs)":[3],"can":[4],"provide":[5],"essential":[6],"input":[7],"to":[8,25,55,112],"many":[9],"bioinformatics":[10],"applications,":[11],"including":[12,151],"protein":[13,107],"structure":[14],"prediction":[15,119],"and":[16,36,104,137,140,145],"functional":[17,116],"annotation.":[18],"However,":[19],"the":[20,81,95,101],"optimal":[21,59],"selection":[22],"of":[23,44,65,76,100,122,128],"sequences":[24],"obtain":[26],"biologically":[27],"informative":[28],"MSAs":[29,92,114],"for":[30,90,115],"such":[31],"purposes":[32],"is":[33,79,156],"poorly":[34],"explored,":[35],"has":[37],"traditionally":[38],"been":[39],"performed":[40],"manually.We":[41],"present":[42],"Selection":[43],"Alignment":[45],"by":[46,120],"Maximal":[47],"Mutual":[48],"Information":[49],"(SAMMI),":[50],"an":[51,58],"automated,":[52],"sequence-based":[53],"approach":[54,78],"objectively":[56],"select":[57,113],"MSA":[60,85],"from":[61,68,132],"a":[62,69,126],"large":[63],"set":[64,98,127],"alternatives":[66],"sampled":[67],"general":[70],"database":[72],"search.":[73],"The":[74],"hypothesis":[75],"this":[77],"that":[80,93],"mutual":[82],"information":[83],"among":[84],"columns":[86],"will":[87],"be":[88],"maximal":[89],"those":[91],"contain":[94],"most":[96,102],"diverse":[97],"possible":[99],"structurally":[103],"functionally":[105],"homogeneous":[106],"sequences.":[108],"SAMMI":[109,155],"was":[110],"tested":[111],"site":[117],"residue":[118],"analysis":[121],"conservation":[123],"patterns":[124],"on":[125],"435":[129],"proteins":[130],"obtained":[131],"protein-ligand":[133],"(peptides,":[134],"nucleic":[135],"acids":[136],"small":[138],"substrates)":[139],"protein-protein":[141],"interaction":[142],"databases.":[143],"Availability":[144],"implementation:":[146],"A":[147],"freely":[148],"accessible":[149],"program,":[150],"source":[152],"code,":[153],"implementing":[154],"available":[157,162],"at":[158,163],"https://github.com/nelsongil92/SAMMI.git.andras.fiser@einstein.yu.edu.Supplementary":[159],"data":[160],"are":[161],"Bioinformatics":[164],"online.":[165]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2773938469","counts_by_year":[{"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":"2024-12-09T03:01:05.329254","created_date":"2017-12-22"}