{"id":"https://openalex.org/W2043046527","doi":"https://doi.org/10.1186/1471-2105-10-396","title":"Optimizing substitution matrix choice and gap parameters for sequence alignment","display_name":"Optimizing substitution matrix choice and gap parameters for sequence alignment","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2043046527","doi":"https://doi.org/10.1186/1471-2105-10-396","mag":"2043046527","pmid":"https://pubmed.ncbi.nlm.nih.gov/19954534"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-10-396","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-396","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-396","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-396","any_repository_has_fulltext":true},"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/I4210097329","display_name":"Tiburon Associates (United States)","ror":"https://ror.org/00wns3e34","country_code":"US","type":"company","lineage":["https://openalex.org/I4210097329"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Robert C Edgar","raw_affiliation_strings":["bob@drive5.com","Tiburon, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"bob@drive5.com","institution_ids":[]},{"raw_affiliation_string":"Tiburon, USA","institution_ids":["https://openalex.org/I4210097329"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5077667471"],"corresponding_institution_ids":["https://openalex.org/I4210097329"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":1.2595,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.78145971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"10","issue":"1","first_page":"396","last_page":"396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.6040999889373779,"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":0.6040999889373779,"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":0.17550000548362732,"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":0.05000000074505806,"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/substitution","display_name":"Substitution (logic)","score":0.6856204271316528},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5910597443580627},{"id":"https://openalex.org/keywords/structural-alignment","display_name":"Structural alignment","score":0.5694023370742798},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.5689122080802917},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.522084653377533},{"id":"https://openalex.org/keywords/rounding","display_name":"Rounding","score":0.5027773380279541},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.48750802874565125},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.4780067503452301},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.47422122955322266},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4617246985435486},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45486611127853394},{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.4175020158290863},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3290240168571472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25488096475601196},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13794124126434326},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08865547180175781}],"concepts":[{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.6856204271316528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5910597443580627},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.5694023370742798},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.5689122080802917},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.522084653377533},{"id":"https://openalex.org/C136625980","wikidata":"https://www.wikidata.org/wiki/Q663208","display_name":"Rounding","level":2,"score":0.5027773380279541},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.48750802874565125},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.4780067503452301},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.47422122955322266},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4617246985435486},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45486611127853394},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.4175020158290863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3290240168571472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25488096475601196},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13794124126434326},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08865547180175781},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","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":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-10-396","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-396","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-396","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:19954534","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19954534","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:c89f34b17d1144109360f9a1fa80fd18","is_oa":false,"landing_page_url":"https://doaj.org/article/c89f34b17d1144109360f9a1fa80fd18","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 10, Iss 1, p 396 (2009)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2791778","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2791778","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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-10-396","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-396","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-396","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2043046527.pdf","grobid_xml":"https://content.openalex.org/works/W2043046527.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W290667870","https://openalex.org/W1513989461","https://openalex.org/W1519266993","https://openalex.org/W1531116739","https://openalex.org/W1590240800","https://openalex.org/W1996897910","https://openalex.org/W2004575181","https://openalex.org/W2017519756","https://openalex.org/W2018885841","https://openalex.org/W2022368654","https://openalex.org/W2026881360","https://openalex.org/W2066593167","https://openalex.org/W2080901145","https://openalex.org/W2096234003","https://openalex.org/W2097818324","https://openalex.org/W2102017611","https://openalex.org/W2102502076","https://openalex.org/W2106882534","https://openalex.org/W2109607376","https://openalex.org/W2116377237","https://openalex.org/W2132926880","https://openalex.org/W2137015675","https://openalex.org/W2140872496","https://openalex.org/W2143210482","https://openalex.org/W2158460069","https://openalex.org/W2163860567","https://openalex.org/W2166718648","https://openalex.org/W2168474259","https://openalex.org/W2170945060","https://openalex.org/W2601913882","https://openalex.org/W4246105018"],"related_works":["https://openalex.org/W2029514038","https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W1482324242","https://openalex.org/W1985408726","https://openalex.org/W2088487249","https://openalex.org/W2187357871","https://openalex.org/W2141411672","https://openalex.org/W1981307089","https://openalex.org/W2468116983"],"abstract_inverted_index":{"BACKGROUND:":[0],"While":[1],"substitution":[2,29,65],"matrices":[3,30,66,132,232],"can":[4],"readily":[5],"be":[6,108,136,196,228,236],"computed":[7],"from":[8,89,99,251],"reference":[9],"alignments,":[10],"it":[11],"is":[12,23,38,52,74,105,152,164,174,200,233,248],"challenging":[13],"to":[14,56,76,81,87,91,107,124,135,166,202,235],"compute":[15],"optimal":[16,19],"or":[17,122],"approximately":[18],"gap":[20,61],"penalties.":[21],"It":[22],"also":[24],"not":[25],"well":[26],"understood":[27],"which":[28],"are":[31,133],"the":[32,39,57,109,125,141,145,188,204,252],"most":[33,110],"effective":[34],"when":[35],"alignment":[36,116],"accuracy":[37,205],"goal":[40],"rather":[41],"than":[42,160],"homolog":[43],"recognition.":[44],"Here":[45],"a":[46,77,178],"new":[47],"parameter":[48],"optimization":[49],"procedure,":[50],"POP,":[51],"described":[53],"and":[54,63,83,85,212,245],"applied":[55],"problems":[58],"of":[59,190,206,223],"optimizing":[60],"penalties":[62],"selecting":[64,177],"for":[67,238],"pair-wise":[68,96,115],"global":[69,114],"protein":[70],"alignments.":[71],"RESULTS:":[72],"POP":[73],"compared":[75],"recent":[78],"method":[79],"due":[80],"Kim":[82],"Kececioglu":[84],"found":[86,134,165,175,201],"achieve":[88],"0.2%":[90],"1.3%":[92],"higher":[93],"accuracies":[94,156],"on":[95,112,181,210,214],"benchmarks":[97],"extracted":[98],"BALIBASE.":[100],"The":[101,149,217],"VTML":[102],"matrix":[103,179,241],"series":[104,151],"shown":[106,234],"accurate":[111,221],"several":[113],"benchmarks,":[117],"with":[118,140],"VTML200":[119,199],"giving":[120,155],"best":[121,126],"close":[123],"performance":[127],"in":[128,144,170,193],"all":[129],"tests.":[130],"BLOSUM":[131],"slightly":[137],"inferior,":[138],"even":[139],"marginal":[142],"improvements":[143],"bug-fixed":[146],"RBLOSUM":[147],"series.":[148],"PAM":[150],"significantly":[153],"worse,":[154],"typically":[157],"2%":[158],"less":[159],"VTML.":[161],"Integer":[162],"rounding":[163],"cause":[167],"slight":[168],"degradations":[169],"accuracy.":[171],"No":[172],"evidence":[173],"that":[176,187,219],"based":[180],"sequence":[182],"divergence":[183],"improves":[184],"accuracy,":[185],"suggesting":[186],"use":[189],"this":[191],"heuristic":[192],"CLUSTALW":[194,207],"may":[195,227],"ineffective.":[197],"Using":[198],"improve":[203],"by":[208],"8%":[209],"BALIBASE":[211],"5%":[213],"PREFAB.":[215],"CONCLUSION:":[216],"hypothesis":[218],"more":[220],"alignments":[222],"distantly":[224],"related":[225],"sequences":[226],"achieved":[229],"using":[230],"low-identity":[231],"false":[237],"commonly":[239],"used":[240],"types.":[242],"Source":[243],"code":[244],"test":[246],"data":[247],"freely":[249],"available":[250],"author's":[253],"web":[254],"site":[255],"at":[256],"http://www.drive5.com/pop.":[257]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}