{"id":"https://openalex.org/W2001965063","doi":"https://doi.org/10.1089/cmb.2008.0053","title":"Code Optimization of the Subroutine to Remove Near Identical Matches in the Sequence Database Homology Search Tool PSI-BLAST","display_name":"Code Optimization of the Subroutine to Remove Near Identical Matches in the Sequence Database Homology Search Tool PSI-BLAST","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2001965063","doi":"https://doi.org/10.1089/cmb.2008.0053","mag":"2001965063","pmid":"https://pubmed.ncbi.nlm.nih.gov/20583927"},"language":"en","primary_location":{"id":"doi:10.1089/cmb.2008.0053","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2008.0053","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","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/A5064436729","display_name":"Mats Aspn\u00e4s","orcid":null},"institutions":[{"id":"https://openalex.org/I130217899","display_name":"\u00c5bo Akademi University","ror":"https://ror.org/029pk6x14","country_code":"FI","type":"education","lineage":["https://openalex.org/I130217899"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mats Aspn\u00e4s","raw_affiliation_strings":["Department of Information Technologies, Abo Akademi University, Abo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technologies, Abo Akademi University, Abo, Finland","institution_ids":["https://openalex.org/I130217899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025476541","display_name":"Kimmo Mattila","orcid":"https://orcid.org/0000-0002-9522-9830"},"institutions":[{"id":"https://openalex.org/I4210150043","display_name":"CSC - IT Center for Science (Finland)","ror":"https://ror.org/04m8m1253","country_code":"FI","type":"company","lineage":["https://openalex.org/I4210150043"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kimmo Mattila","raw_affiliation_strings":["CSC (Finnish IT Center for Science), Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSC (Finnish IT Center for Science), Espoo, Finland","institution_ids":["https://openalex.org/I4210150043"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052766094","display_name":"Kristoffer Osowski","orcid":null},"institutions":[{"id":"https://openalex.org/I130217899","display_name":"\u00c5bo Akademi University","ror":"https://ror.org/029pk6x14","country_code":"FI","type":"education","lineage":["https://openalex.org/I130217899"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kristoffer Osowski","raw_affiliation_strings":["Department of Information Technologies, Abo Akademi University, Abo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technologies, Abo Akademi University, Abo, Finland","institution_ids":["https://openalex.org/I130217899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068418488","display_name":"Jan Westerholm","orcid":"https://orcid.org/0000-0001-9082-350X"},"institutions":[{"id":"https://openalex.org/I130217899","display_name":"\u00c5bo Akademi University","ror":"https://ror.org/029pk6x14","country_code":"FI","type":"education","lineage":["https://openalex.org/I130217899"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Jan Westerholm","raw_affiliation_strings":["Department of Information Technologies, Abo Akademi University, Abo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technologies, Abo Akademi University, Abo, Finland","institution_ids":["https://openalex.org/I130217899"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068418488"],"corresponding_institution_ids":["https://openalex.org/I130217899"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.07132521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"17","issue":"6","first_page":"819","last_page":"823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9980000257492065,"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":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/subroutine","display_name":"Subroutine","score":0.8074575662612915},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.7094258666038513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6698296070098877},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.5761356353759766},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5631341934204102},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4995076656341553},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43243247270584106},{"id":"https://openalex.org/keywords/homology","display_name":"Homology (biology)","score":0.4110727906227112},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2753770649433136},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23252418637275696},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18285349011421204},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.13824084401130676},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.13425582647323608}],"concepts":[{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.8074575662612915},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.7094258666038513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6698296070098877},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.5761356353759766},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5631341934204102},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4995076656341553},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43243247270584106},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.4110727906227112},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2753770649433136},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23252418637275696},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18285349011421204},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.13824084401130676},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13425582647323608},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","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":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1089/cmb.2008.0053","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2008.0053","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmid:20583927","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20583927","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":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":null},{"id":"pmh:oai:pure.atira.dk:publications/5b5d91e5-05db-4a01-9b71-3e43f6297043","is_oa":false,"landing_page_url":"https://research.abo.fi/en/publications/5b5d91e5-05db-4a01-9b71-3e43f6297043","pdf_url":null,"source":{"id":"https://openalex.org/S4406923060","display_name":"\u00c5bo Akademi University Research Portal","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":"Aspn\u00e4s, M, Mattila, K, Osowski, K & Westerholm, J 2010, 'Code Optimization of the Subroutine to Remove Near Identical Matches in the Sequence Database Homology Search Tool PSI-BLAST', Journal of Computational Biology, vol. 17, no. 6, pp. 819\u2013823. https://doi.org/10.1089/cmb.2008.0053","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321855","display_name":"Tekes","ror":"https://ror.org/02ag8cq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2025002290","https://openalex.org/W2158714788","https://openalex.org/W2906604232"],"related_works":["https://openalex.org/W2036521446","https://openalex.org/W2926533301","https://openalex.org/W2066737015","https://openalex.org/W2105364679","https://openalex.org/W1975001431","https://openalex.org/W2149758239","https://openalex.org/W127272819","https://openalex.org/W2062123785","https://openalex.org/W2103210188","https://openalex.org/W1969436613"],"abstract_inverted_index":{"A":[0],"central":[1],"task":[2],"in":[3,22,89],"protein":[4,20],"sequence":[5,12],"characterization":[6],"is":[7,28,122],"the":[8,34,44,61,82,101,105,117,124,137],"use":[9],"of":[10,33,81,108,119],"a":[11,29,39,53],"database":[13],"homology":[14],"search":[15],"tool":[16],"to":[17,55,79],"find":[18,71],"similar":[19,58,73,120],"sequences":[21,47,59],"other":[23],"individuals":[24],"or":[25],"species.":[26],"PSI-BLAST":[27,69,126],"widely":[30],"used":[31],"module":[32],"BLAST":[35],"package":[36],"that":[37,99],"calculates":[38],"position-specific":[40],"score":[41],"matrix":[42],"from":[43],"best":[45],"matching":[46],"and":[48,66,76,104],"performs":[49],"iterated":[50],"searches":[51],"using":[52],"method":[54],"avoid":[56],"many":[57,72],"for":[60,114],"score.":[62],"For":[63],"some":[64],"queries":[65,115],"parameter":[67],"settings,":[68],"may":[70,86,128],"high-scoring":[74],"matches,":[75],"therefore":[77],"up":[78],"80%":[80],"total":[83],"run":[84],"time":[85],"be":[87,129],"spent":[88],"this":[90,93,109],"procedure.":[91,110],"In":[92],"article,":[94],"we":[95],"present":[96],"code":[97],"optimizations":[98],"improve":[100],"cache":[102],"utilization":[103],"overall":[106],"performance":[107],"Measurements":[111],"show":[112],"that,":[113],"where":[116],"number":[118],"matches":[121],"high,":[123],"optimized":[125],"program":[127],"as":[130,132],"much":[131],"2.9":[133],"times":[134],"faster":[135],"than":[136],"original":[138],"program.":[139]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}
