{"id":"https://openalex.org/W2610909925","doi":"https://doi.org/10.1089/10665270050081531","title":"Winnowing Sequences from a Database Search","display_name":"Winnowing Sequences from a Database Search","publication_year":2000,"publication_date":"2000-02-01","ids":{"openalex":"https://openalex.org/W2610909925","doi":"https://doi.org/10.1089/10665270050081531","mag":"2610909925","pmid":"https://pubmed.ncbi.nlm.nih.gov/10890403"},"language":"en","primary_location":{"id":"doi:10.1089/10665270050081531","is_oa":false,"landing_page_url":"https://doi.org/10.1089/10665270050081531","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"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"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/A5023910624","display_name":"Piotr Berman","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Piotr Berman","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459168","display_name":"Zheng Zhang","orcid":"https://orcid.org/0000-0003-1470-6998"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012792532","display_name":"Yuri I. Wolf","orcid":"https://orcid.org/0000-0002-0247-8708"},"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":"Yuri I. Wolf","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035240489","display_name":"Eugene V. Koonin","orcid":"https://orcid.org/0000-0003-3943-8299"},"institutions":[{"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"]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene V. Koonin","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071092709","display_name":"Webb Miller","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Webb Miller","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5023910624"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.5126,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.78796825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"7","issue":"1-2","first_page":"293","last_page":"302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.982699990272522,"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/sequence","display_name":"Sequence (biology)","score":0.6799072027206421},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.612295389175415},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5591988563537598},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5167843103408813},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47866353392601013},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4659961462020874},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.4421382546424866},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4345250427722931},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4077826738357544},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.36166325211524963},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3473619818687439},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33720460534095764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1553952395915985}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6799072027206421},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.612295389175415},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5591988563537598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5167843103408813},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47866353392601013},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4659961462020874},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.4421382546424866},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4345250427722931},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4077826738357544},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.36166325211524963},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3473619818687439},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33720460534095764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1553952395915985},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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":"D001699","descriptor_name":"Biometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001699","descriptor_name":"Biometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001699","descriptor_name":"Biometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005970","descriptor_name":"Glutamate Synthase","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005970","descriptor_name":"Glutamate Synthase","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005970","descriptor_name":"Glutamate Synthase","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D017017","descriptor_name":"Methanococcus","qualifier_ui":"Q000201","qualifier_name":"enzymology","is_major_topic":false},{"descriptor_ui":"D017017","descriptor_name":"Methanococcus","qualifier_ui":"Q000201","qualifier_name":"enzymology","is_major_topic":false},{"descriptor_ui":"D017017","descriptor_name":"Methanococcus","qualifier_ui":"Q000201","qualifier_name":"enzymology","is_major_topic":false},{"descriptor_ui":"D017017","descriptor_name":"Methanococcus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017017","descriptor_name":"Methanococcus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017017","descriptor_name":"Methanococcus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1089/10665270050081531","is_oa":false,"landing_page_url":"https://doi.org/10.1089/10665270050081531","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"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"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:10890403","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/10890403","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2018804864","https://openalex.org/W2049864887","https://openalex.org/W2055043387","https://openalex.org/W2070991879","https://openalex.org/W2091082218","https://openalex.org/W2138524348","https://openalex.org/W2144164911","https://openalex.org/W2148616821","https://openalex.org/W2152506638","https://openalex.org/W2158714788","https://openalex.org/W2611102567","https://openalex.org/W4244897565"],"related_works":["https://openalex.org/W1495042958","https://openalex.org/W2494338568","https://openalex.org/W2122678784","https://openalex.org/W2282510344","https://openalex.org/W139987158","https://openalex.org/W2183994405","https://openalex.org/W4311992195","https://openalex.org/W2037896692","https://openalex.org/W2136066520","https://openalex.org/W2354598492"],"abstract_inverted_index":{"In":[0,28],"database":[1,73,176],"searches":[2],"for":[3,44,174],"sequence":[4,10,68],"similarity,":[5],"matches":[6,20],"to":[7,21,30,38,71,102,111,137],"a":[8,49,72,127,159],"distinct":[9],"region":[11,23],"(e.g.,":[12],"protein":[13],"domain)":[14],"are":[15,36,197],"frequently":[16,169],"obscured":[17],"by":[18,105,118],"numerous":[19],"another":[22],"of":[24,51,63,80,130,154,194],"the":[25,61,66,76,81,139,152,182],"same":[26],"sequence.":[27],"order":[29],"cope":[31],"with":[32,48,54,188],"this":[33,45,195],"problem,":[34],"algorithms":[35],"developed":[37,136],"discard":[39],"redundant":[40],"matches.":[41],"One":[42],"model":[43],"problem":[46,108,140],"begins":[47],"list":[50],"intervals,":[52,123],"each":[53,58,113],"an":[55],"associated":[56],"score;":[57],"interval":[59,84,89,114],"gives":[60],"range":[62],"positions":[64],"in":[65,88,141,181],"query":[67],"that":[69,79,115,163],"align":[70],"sequence,":[74],"and":[75,91,146,156,167,192],"score":[77,93],"is":[78,86,94,100,109,116,126,135,151,158,168],"alignment.":[82],"If":[83],"I":[85,99],"contained":[87],"J,":[90],"I's":[92],"less":[95],"than":[96],"J's,":[97],"then":[98,110],"said":[101],"be":[103],"dominated":[104,117],"J.":[106],"The":[107],"identify":[112],"at":[119],"least":[120],"K":[121,125],"other":[122],"where":[124,149],"given":[128],"level":[129],"\"tolerable":[131],"redundancy.\"":[132],"An":[133],"algorithm":[134],"solve":[138],"O(N":[142],"log":[143],"N)":[144],"time":[145],"O(N*)":[147],"space,":[148],"N":[150,166],"number":[153],"intervals":[155],"N*":[157],"precisely":[160],"defined":[161],"value":[162],"never":[164],"exceeds":[165],"much":[170],"smaller.":[171],"This":[172],"criterion":[173],"discarding":[175],"hits":[177],"has":[178],"been":[179],"implemented":[180],"Blast":[183],"program,":[184],"as":[185],"illustrated":[186],"herein":[187],"examples.":[189],"Several":[190],"variations":[191],"extensions":[193],"approach":[196],"also":[198],"described.":[199]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
