{"id":"https://openalex.org/W2106241755","doi":"https://doi.org/10.1093/bioinformatics/bth090","title":"A comparison of scoring functions for protein sequence profile alignment","display_name":"A comparison of scoring functions for protein sequence profile alignment","publication_year":2004,"publication_date":"2004-02-12","ids":{"openalex":"https://openalex.org/W2106241755","doi":"https://doi.org/10.1093/bioinformatics/bth090","mag":"2106241755","pmid":"https://pubmed.ncbi.nlm.nih.gov/14962936"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth090","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth090","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077667471","display_name":"R. C. Edgar","orcid":"https://orcid.org/0000-0001-7355-2541"},"institutions":[{"id":"https://openalex.org/I4210117505","display_name":"Mill Valley Public Library","ror":"https://ror.org/01sh98j38","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210117505"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Robert C. Edgar","raw_affiliation_strings":["bob@drive5.com","195 Roque Moraes Drive, Mill Valley, CA 94941, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"bob@drive5.com","institution_ids":[]},{"raw_affiliation_string":"195 Roque Moraes Drive, Mill Valley, CA 94941, USA#TAB#","institution_ids":["https://openalex.org/I4210117505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107849607","display_name":"Kimmen Sj\u00f6lander","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kimmen Sj\u00f6lander","raw_affiliation_strings":["Department of Bioengineering, University of California Berkeley, CA 94720, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioengineering, University of California Berkeley, CA 94720, USA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077667471"],"corresponding_institution_ids":["https://openalex.org/I4210117505"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":4.9096,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":{"value":0.96093386,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"20","issue":"8","first_page":"1301","last_page":"1308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.7127000093460083,"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":0.7127000093460083,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.15530000627040863,"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":0.07169999927282333,"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/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.8339468836784363},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.734263002872467},{"id":"https://openalex.org/keywords/alignment-free-sequence-analysis","display_name":"Alignment-free sequence analysis","score":0.7311328053474426},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.6959371566772461},{"id":"https://openalex.org/keywords/structural-alignment","display_name":"Structural alignment","score":0.5802531242370605},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5585863590240479},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5446807742118835},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.4668581783771515},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.41047078371047974},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38244932889938354},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36266186833381653},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3276279866695404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3193647265434265},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2102738618850708},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20685511827468872},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.17671310901641846},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.16124361753463745}],"concepts":[{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.8339468836784363},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.734263002872467},{"id":"https://openalex.org/C180384323","wikidata":"https://www.wikidata.org/wiki/Q16335137","display_name":"Alignment-free sequence analysis","level":5,"score":0.7311328053474426},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.6959371566772461},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.5802531242370605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5585863590240479},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5446807742118835},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.4668581783771515},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.41047078371047974},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38244932889938354},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36266186833381653},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3276279866695404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3193647265434265},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2102738618850708},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20685511827468872},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.17671310901641846},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.16124361753463745},{"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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/bth090","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth090","pdf_url":null,"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:14962936","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/14962936","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":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"},{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W21816278","https://openalex.org/W1558365920","https://openalex.org/W1590648220","https://openalex.org/W1970999032","https://openalex.org/W1984675929","https://openalex.org/W2000758249","https://openalex.org/W2001365663","https://openalex.org/W2003853681","https://openalex.org/W2023790301","https://openalex.org/W2055043387","https://openalex.org/W2057447180","https://openalex.org/W2062233253","https://openalex.org/W2062693912","https://openalex.org/W2068448872","https://openalex.org/W2069249633","https://openalex.org/W2078467971","https://openalex.org/W2087064593","https://openalex.org/W2097555181","https://openalex.org/W2099075703","https://openalex.org/W2102122585","https://openalex.org/W2105118494","https://openalex.org/W2106882534","https://openalex.org/W2110534451","https://openalex.org/W2112162865","https://openalex.org/W2117249420","https://openalex.org/W2122665495","https://openalex.org/W2129913453","https://openalex.org/W2130479394","https://openalex.org/W2140244239","https://openalex.org/W2141411672","https://openalex.org/W2143210482","https://openalex.org/W2147667050","https://openalex.org/W2149758239","https://openalex.org/W2151631782","https://openalex.org/W2152326664","https://openalex.org/W2157975034","https://openalex.org/W2158714788","https://openalex.org/W2741430469"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W2029514038","https://openalex.org/W2141411672","https://openalex.org/W2133116680","https://openalex.org/W1482324242","https://openalex.org/W2468116983","https://openalex.org/W408054492","https://openalex.org/W2149758239","https://openalex.org/W2105364679"],"abstract_inverted_index":{"MOTIVATION:":[0],"In":[1,63],"recent":[2],"years,":[3],"several":[4],"methods":[5,26,31],"have":[6],"been":[7],"proposed":[8],"for":[9,96],"aligning":[10],"two":[11],"protein":[12],"sequence":[13,44],"profiles,":[14],"with":[15,85,134,191],"reported":[16],"improvements":[17],"in":[18,41,175],"alignment":[19,35,45,69,148,162],"accuracy":[20,70],"and":[21,29,105,113,126,136,141,163,206],"homolog":[22],"discrimination":[23],"versus":[24],"sequence-sequence":[25,135,167],"(e.g.":[27,32],"BLAST)":[28],"profile-sequence":[30,161],"PSI-BLAST).":[33],"Profile-profile":[34],"is":[36,52,173],"also":[37],"the":[38,55,68,101,123,132,176,182],"iterated":[39],"step":[40],"progressive":[42],"multiple":[43],"algorithms":[46],"such":[47],"as":[48],"CLUSTALW.":[49],"However,":[50],"little":[51],"known":[53],"about":[54],"relative":[56,177],"performance":[57,178],"of":[58,71,80,83,108,157,179,181],"different":[59,73],"profile-profile":[60,74,147],"scoring":[61,75,98,183],"functions.":[62],"this":[64],"work,":[65],"we":[66],"evaluate":[67],"23":[72],"functions":[76,99,184],"by":[77],"comparing":[78],"alignments":[79,109,116,196,205],"488":[81],"pairs":[82],"sequences":[84],"identity":[86],"<":[87],"or":[88],"=30%":[89],"against":[90],"structural":[91,128],"alignments.":[92,200],"We":[93,130,144],"optimize":[94],"parameters":[95],"all":[97],"on":[100],"same":[102],"training":[103],"set":[104,156],"use":[106],"profiles":[107,192],"from":[110,119,194,198],"both":[111],"PSI-BLAST":[112,199],"SAM-T99.":[114],"Structural":[115],"are":[117,189,210],"constructed":[118,193],"a":[120],"consensus":[121],"between":[122],"FSSP":[124],"database":[125],"CE":[127],"aligner.":[129],"compare":[131],"results":[133,188,209],"sequence-profile":[137],"methods,":[138],"including":[139],"BLAST":[140],"PSI-BLAST.":[142],"RESULTS:":[143],"find":[145],"that":[146],"gives":[149],"an":[150],"average":[151],"improvement":[152],"over":[153,160,166],"our":[154],"test":[155],"typically":[158],"2-3%":[159],"approximately":[164],"40%":[165],"alignment.":[168],"No":[169],"statistically":[170],"significant":[171],"difference":[172],"seen":[174],"most":[180],"tested.":[185],"Significantly":[186],"better":[187],"obtained":[190],"SAM-T99":[195],"than":[197],"AVAILABILITY:":[201],"Source":[202],"code,":[203],"reference":[204],"more":[207],"detailed":[208],"freely":[211],"available":[212],"at":[213],"http://phylogenomics.berkeley.edu/profilealignment/":[214]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}
