{"id":"https://openalex.org/W2120691184","doi":"https://doi.org/10.1093/bioinformatics/btt517","title":"Adjusting scoring matrices to correct overextended alignments","display_name":"Adjusting scoring matrices to correct overextended alignments","publication_year":2013,"publication_date":"2013-08-31","ids":{"openalex":"https://openalex.org/W2120691184","doi":"https://doi.org/10.1093/bioinformatics/btt517","mag":"2120691184"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btt517","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btt517","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/29/23/3007/681616/btt517.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/29/23/3007/681616/btt517.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059198403","display_name":"Lauren J. Mills","orcid":"https://orcid.org/0000-0002-8914-2587"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lauren J. Mills","raw_affiliation_strings":["1 Department of Molecular, Cell and Developmental Biology and 2Department of Biochemistry and Molecular Genetics, University of Virginia, Charlottesville, VA 22908, USA"],"affiliations":[{"raw_affiliation_string":"1 Department of Molecular, Cell and Developmental Biology and 2Department of Biochemistry and Molecular Genetics, University of Virginia, Charlottesville, VA 22908, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073334733","display_name":"William R. Pearson","orcid":"https://orcid.org/0000-0002-0727-3680"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William R. Pearson","raw_affiliation_strings":["1 Department of Molecular, Cell and Developmental Biology and 2Department of Biochemistry and Molecular Genetics, University of Virginia, Charlottesville, VA 22908, USA"],"affiliations":[{"raw_affiliation_string":"1 Department of Molecular, Cell and Developmental Biology and 2Department of Biochemistry and Molecular Genetics, University of Virginia, Charlottesville, VA 22908, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059198403"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.1918,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.788199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"29","issue":"23","first_page":"3007","last_page":"3013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9986000061035156,"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":0.9986000061035156,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6993805170059204},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.6692978739738464},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6510084867477417},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6437429785728455},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5837644934654236},{"id":"https://openalex.org/keywords/protein-superfamily","display_name":"Protein superfamily","score":0.5545199513435364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5531359314918518},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.5329077839851379},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5133825540542603},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4893609881401062},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3735445737838745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29314911365509033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27924594283103943},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2754901051521301},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2361697554588318},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.18191629648208618},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1327279508113861},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09381693601608276},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08262774348258972},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.06097421050071716}],"concepts":[{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6993805170059204},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.6692978739738464},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6510084867477417},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6437429785728455},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5837644934654236},{"id":"https://openalex.org/C178180057","wikidata":"https://www.wikidata.org/wiki/Q7251477","display_name":"Protein superfamily","level":3,"score":0.5545199513435364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5531359314918518},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.5329077839851379},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5133825540542603},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4893609881401062},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3735445737838745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29314911365509033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27924594283103943},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2754901051521301},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2361697554588318},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.18191629648208618},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1327279508113861},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09381693601608276},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08262774348258972},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.06097421050071716},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btt517","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btt517","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/29/23/3007/681616/btt517.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:2821377","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3834790","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/btt517","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btt517","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/29/23/3007/681616/btt517.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2120691184.pdf","grobid_xml":"https://content.openalex.org/works/W2120691184.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W21816278","https://openalex.org/W53898165","https://openalex.org/W1502621331","https://openalex.org/W1973578915","https://openalex.org/W2004215917","https://openalex.org/W2097818324","https://openalex.org/W2110434201","https://openalex.org/W2113416388","https://openalex.org/W2139271731","https://openalex.org/W2141885858","https://openalex.org/W2142678478","https://openalex.org/W2143210482","https://openalex.org/W2157975034","https://openalex.org/W2158714788","https://openalex.org/W2160871286","https://openalex.org/W2169686324","https://openalex.org/W2600349519","https://openalex.org/W2601913882","https://openalex.org/W4320301318","https://openalex.org/W6602161028","https://openalex.org/W6676902139"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W2009133913","https://openalex.org/W2015399150","https://openalex.org/W2061567716","https://openalex.org/W2275032899","https://openalex.org/W2498689255","https://openalex.org/W2032757954","https://openalex.org/W2075451741","https://openalex.org/W2505756865"],"abstract_inverted_index":{"Abstract":[0],"Motivation:":[1],"Sequence":[2],"similarity":[3],"searches":[4],"performed":[5],"with":[6,144],"BLAST,":[7],"SSEARCH":[8,76],"and":[9,67,73,168],"FASTA":[10,170],"achieve":[11],"high":[12],"sensitivity":[13],"by":[14],"using":[15,55,161],"scoring":[16,28,101,121,147],"matrices":[17,29],"(e.g.":[18],"BLOSUM62)":[19],"that":[20,41,69,92,123],"target":[21],"low":[22],"identity":[23,106,114,136],"(&amp;lt;33%)":[24],"alignments.":[25],"Although":[26],"such":[27],"can":[30,36,111],"effectively":[31],"identify":[32],"distant":[33],"homologs,":[34],"they":[35,86],"also":[37],"produce":[38],"local":[39,50],"alignments":[40,82,159],"extend":[42],"beyond":[43],"the":[44,61,100,105,108,120,134,139,145,169],"homologous":[45,109],"regions.":[46],"Results:":[47],"We":[48],"measured":[49],"alignment":[51,63,77,116,127],"start/stop":[52],"boundary":[53],"accuracy":[54],"a":[56,125],"set":[57],"of":[58,71,75,107,151],"queries":[59],"where":[60],"correct":[62,112,126,158],"boundaries":[64,78],"were":[65,79],"known,":[66],"found":[68],"7%":[70],"BLASTP":[72],"8%":[74],"overextended.":[80],"Overextended":[81],"include":[83],"non-homologous":[84],"sequences;":[85],"occur":[87],"most":[88],"frequently":[89],"between":[90],"sequences":[91,167],"are":[93,172],"more":[94,157],"closely":[95],"related":[96],"(&amp;gt;33%":[97],"identity).":[98],"Adjusting":[99],"matrix":[102,122,148],"to":[103],"reflect":[104],"sequence":[110,135],"higher":[113],"overextended":[115,153],"boundaries.":[117],"In":[118],"addition,":[119],"produced":[124],"could":[128],"be":[129],"reliably":[130],"predicted":[131,146],"based":[132],"on":[133],"seen":[137],"in":[138,156],"original":[140],"BLOSUM62":[141,162],"alignment.":[142],"Realigning":[143],"corrected":[149],"37%":[150],"all":[152],"alignments,":[154],"resulting":[155],"than":[160],"alone.":[163],"Availability:":[164],"RefProtDom2":[165],"(RPD2)":[166],"software":[171],"available":[173],"from":[174],"http://faculty.virginia.edu/wrpearson/fasta.":[175],"Contact:":[176],"wrp@virginia.edu":[177]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2016-06-24T00:00:00"}
