{"id":"https://openalex.org/W2131479294","doi":"https://doi.org/10.1093/bioinformatics/btm479","title":"Improved BLAST searches using longer words for protein seeding","display_name":"Improved BLAST searches using longer words for protein seeding","publication_year":2007,"publication_date":"2007-10-06","ids":{"openalex":"https://openalex.org/W2131479294","doi":"https://doi.org/10.1093/bioinformatics/btm479","mag":"2131479294","pmid":"https://pubmed.ncbi.nlm.nih.gov/17921491"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btm479","doi":"https://doi.org/10.1093/bioinformatics/btm479","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm479","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/21/2949/49822796/bioinformatics_23_21_2949.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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/23/21/2949/49822796/bioinformatics_23_21_2949.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072196261","display_name":"Sergey A. Shiryev","orcid":"https://orcid.org/0009-0007-2799-0111","observed_orcids":["https://orcid.org/0009-0007-2799-0111"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey A. Shiryev","raw_affiliation_strings":["Department of Health and Human Services, National Center for Biotechnology Information, National Institutes of Health","Department of Health and Human Services, National Center for Biotechnology Information, National Institutes of Health, Bethesda, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Health and Human Services, National Center for Biotechnology Information, National Institutes of Health","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]},{"raw_affiliation_string":"Department of Health and Human Services, National Center for Biotechnology Information, National Institutes of Health, Bethesda, MD, USA","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021448822","display_name":"Jason S. Papadopoulos","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason S. Papadopoulos","raw_affiliation_strings":["Department of Health and Human Services, National Center for Biotechnology Information, National Institutes of Health"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Health and Human Services, National Center for Biotechnology Information, National Institutes of Health","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000317216","display_name":"Alejandro A. Sch\u00e4ffer","orcid":"https://orcid.org/0000-0002-2147-8033","observed_orcids":["https://orcid.org/0000-0002-2147-8033"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alejandro A. Sch\u00e4ffer","raw_affiliation_strings":["Department of Health and Human Services, National Center for Biotechnology Information, National Institutes of Health"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Health and Human Services, National Center for Biotechnology Information, National Institutes of Health","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032663560","display_name":"Richa Agarwala","orcid":"https://orcid.org/0000-0002-5518-9723","observed_orcids":["https://orcid.org/0000-0002-5518-9723"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Richa Agarwala","raw_affiliation_strings":["Department of Health and Human Services, National Center for Biotechnology Information, National Institutes of Health"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Health and Human Services, National Center for Biotechnology Information, National Institutes of Health","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032663560"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":{"value":3989,"currency":"USD","value_usd":3989},"fwci":0.3275,"has_fulltext":true,"cited_by_count":112,"citation_normalized_percentile":{"value":0.5368896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"23","issue":"21","first_page":"2949","last_page":"2951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.5785999894142151,"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":0.5785999894142151,"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/T11269","display_name":"Algorithms and Data Compression","score":0.4009000062942505,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.010400000028312206,"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/blast","display_name":"BLAST","score":0.984000027179718},{"id":"https://openalex.org/keywords/word-length","display_name":"word length","score":0.7429999709129333},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"sequence alignment","score":0.38199999928474426},{"id":"https://openalex.org/keywords/execution-time-reduction","display_name":"execution time reduction","score":0.49300000071525574},{"id":"https://openalex.org/keywords/retrieval-accuracy","display_name":"retrieval accuracy","score":0.7910000085830688},{"id":"https://openalex.org/keywords/score-thresholds","display_name":"score thresholds","score":0.8149999976158142},{"id":"https://openalex.org/keywords/protein-sequence-search","display_name":"protein sequence search","score":0.37400001287460327}],"concepts":[{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.804696261882782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485977411270142},{"id":"https://openalex.org/C169485995","wikidata":"https://www.wikidata.org/wiki/Q42283","display_name":"File Transfer Protocol","level":3,"score":0.5422208905220032},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5173396468162537},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.502739429473877},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.502143383026123},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.41512736678123474},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35545629262924194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3358456790447235},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3255467414855957},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2284412980079651},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12822294235229492},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10801872611045837},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09862753748893738},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.07793182134628296},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btm479","doi":"https://doi.org/10.1093/bioinformatics/btm479","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm479","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/21/2949/49822796/bioinformatics_23_21_2949.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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"pmid:17921491","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17921491","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,"listed_in":[],"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":"Journal Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.106.299","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.106.299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/cgi/reprint/btm479v1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.502.3366","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.502.3366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/23/21/2949.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btm479","doi":"https://doi.org/10.1093/bioinformatics/btm479","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm479","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/21/2949/49822796/bioinformatics_23_21_2949.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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2131479294.pdf","grobid_xml":"https://content.openalex.org/works/W2131479294.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1973578915","https://openalex.org/W1988670311","https://openalex.org/W2006290495","https://openalex.org/W2046892081","https://openalex.org/W2055043387","https://openalex.org/W2057783089","https://openalex.org/W2084787613","https://openalex.org/W2116744776","https://openalex.org/W2133312664","https://openalex.org/W2133657429","https://openalex.org/W2143210482","https://openalex.org/W2158714788"],"related_works":["https://openalex.org/W7098288047","https://openalex.org/W2142678478","https://openalex.org/W7099393142","https://openalex.org/W2147553376","https://openalex.org/W2183241353","https://openalex.org/W1764926552","https://openalex.org/W2158714788","https://openalex.org/W1026917223","https://openalex.org/W68404534","https://openalex.org/W2022057459"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,105],"blastp":[2],"and":[3,18,66,116],"tblastn":[4],"modules":[5],"of":[6,38,53,126],"BLAST":[7,26],"are":[8],"widely":[9],"used":[10,24,74,131],"methods":[11],"for":[12,75,120],"searching":[13],"protein":[14,17],"queries":[15],"against":[16],"nucleotide":[19],"databases,":[20],"respectively.":[21],"One":[22],"heuristic":[23],"in":[25,112],"is":[27,111,137],"to":[28,43,50,97,107,132],"consider":[29],"only":[30],"database":[31],"sequences":[32],"that":[33],"contain":[34],"a":[35],"high-scoring":[36],"match":[37],"length":[39,54],"at":[40],"most":[41],"5":[42],"the":[44,48,71,81,113,134],"query.":[45],"We":[46,58],"implemented":[47],"capability":[49],"use":[51,108],"words":[52,110],"6":[55],"or":[56],"7.":[57],"demonstrate":[59],"an":[60],"improved":[61],"trade-off":[62],"between":[63],"running":[64,82],"time":[65,83],"retrieval":[67],"accuracy,":[68],"controlled":[69],"by":[70,87],"score":[72],"threshold":[73],"short":[76],"word":[77],"matches.":[78],"For":[79],"example,":[80],"can":[84],"be":[85],"reduced":[86],"20-30%":[88],"while":[89],"achieving":[90],"ROC":[91],"(receiver":[92],"operator":[93],"characteristic)":[94],"scores":[95],"similar":[96],"those":[98],"obtained":[99],"with":[100,123],"current":[101],"default":[102],"parameters.":[103],"AVAILABILITY:":[104],"option":[106],"long":[109],"NCBI":[114],"C":[115],"C++":[117],"toolkit":[118],"code":[119],"BLAST,":[121],"starting":[122],"version":[124],"2.2.16":[125],"blastall.":[127],"A":[128],"Linux":[129],"executable":[130],"produce":[133],"results":[135],"herein":[136],"available":[138],"at:":[139],"ftp://ftp.ncbi.nlm.nih.gov/pub/agarwala/protein_longwords":[140]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2016-06-24T00:00:00"}
