{"id":"https://openalex.org/W2045342295","doi":"https://doi.org/10.1089/106652703321825955","title":"Discovering Simple Regions in Biological Sequences Associated with Scoring Schemes","display_name":"Discovering Simple Regions in Biological Sequences Associated with Scoring Schemes","publication_year":2003,"publication_date":"2003-04-01","ids":{"openalex":"https://openalex.org/W2045342295","doi":"https://doi.org/10.1089/106652703321825955","mag":"2045342295","pmid":"https://pubmed.ncbi.nlm.nih.gov/12804090"},"language":"en","primary_location":{"id":"doi:10.1089/106652703321825955","doi":"https://doi.org/10.1089/106652703321825955","is_oa":false,"landing_page_url":"https://doi.org/10.1089/106652703321825955","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,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1"],"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"},"volume":null,"type":"article","is_traditional":true,"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/A5111858543","display_name":"Honghui Wan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1310183320","display_name":"National Center for Genome Resources","ror":"https://ror.org/01p4cne93","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1310183320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Honghui Wan","raw_affiliation_strings":["National Center for Genome Resources, Santa Fe, NM 87505","National Center for Genome Resources Santa Fe NM 87505 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Genome Resources, Santa Fe, NM 87505","institution_ids":["https://openalex.org/I1310183320"]},{"raw_affiliation_string":"National Center for Genome Resources Santa Fe NM 87505 USA","institution_ids":["https://openalex.org/I1310183320"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062917780","display_name":"Lugang Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lugang Li","raw_affiliation_strings":["Department of Protective Medicine, Nanjing Army Medical College, Second Army Medical University, Nanjing, Jiangsu 210099, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Protective Medicine, Nanjing Army Medical College, Second Army Medical University, Nanjing, Jiangsu 210099, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046762591","display_name":"Scott Federhen","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":"Scott Federhen","raw_affiliation_strings":["Computational Biology Branch, National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Branch, National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110276911","display_name":"John C. Wootton","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":"John C. Wootton","raw_affiliation_strings":["Computational Biology Branch, National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda,          MD 20894"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Branch, National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda,          MD 20894","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2257,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.75774033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"10","issue":"2","first_page":"171","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.4514000117778778,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.4514000117778778,"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":0.35670000314712524,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.09160000085830688,"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/scoring-system","display_name":"scoring system","score":0.5429999828338623},{"id":"https://openalex.org/keywords/sequence-masking","display_name":"sequence masking","score":0.6190000176429749},{"id":"https://openalex.org/keywords/database-searching","display_name":"database searching","score":0.4519999921321869},{"id":"https://openalex.org/keywords/swiss-prot","display_name":"Swiss-Prot","score":0.7940000295639038}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6490402817726135},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6299458146095276},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5184499621391296},{"id":"https://openalex.org/C2778217198","wikidata":"https://www.wikidata.org/wiki/Q556977","display_name":"Cutoff","level":2,"score":0.5165923833847046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4833599925041199},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.44506219029426575},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.43720319867134094},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4315016269683838},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.42847275733947754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4149414598941803},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.24676302075386047},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16136839985847473},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13479015231132507},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D009206","descriptor_name":"Myocardium","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011509","descriptor_name":"Proteoglycans","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011509","descriptor_name":"Proteoglycans","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012714","descriptor_name":"Serine-tRNA Ligase","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012714","descriptor_name":"Serine-tRNA Ligase","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","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":false},{"descriptor_ui":"D016326","descriptor_name":"Extracellular Matrix Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016963","descriptor_name":"Thermus thermophilus","qualifier_ui":"Q000201","qualifier_name":"enzymology","is_major_topic":true},{"descriptor_ui":"D018995","descriptor_name":"Myosin Heavy Chains","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018995","descriptor_name":"Myosin Heavy Chains","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D024042","descriptor_name":"Collagen Type I","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D024042","descriptor_name":"Collagen Type I","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D037181","descriptor_name":"Lectins, C-Type","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D053674","descriptor_name":"Aggrecans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1089/106652703321825955","doi":"https://doi.org/10.1089/106652703321825955","is_oa":false,"landing_page_url":"https://doi.org/10.1089/106652703321825955","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,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1"],"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:12804090","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12804090","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":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":"Comparative Study"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7991851250","display_name":null,"funder_award_id":"R01-GM0002511","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W21816278","https://openalex.org/W1513332069","https://openalex.org/W1556105006","https://openalex.org/W1577761579","https://openalex.org/W1964501091","https://openalex.org/W1970437513","https://openalex.org/W1973578915","https://openalex.org/W1995875735","https://openalex.org/W2002180966","https://openalex.org/W2028508093","https://openalex.org/W2045069244","https://openalex.org/W2045100386","https://openalex.org/W2045162258","https://openalex.org/W2051916497","https://openalex.org/W2088730122","https://openalex.org/W2089357374","https://openalex.org/W2143210482","https://openalex.org/W2158714788","https://openalex.org/W2164260969"],"related_works":["https://openalex.org/W2051119339","https://openalex.org/W2051916497","https://openalex.org/W2154610073","https://openalex.org/W7095082029","https://openalex.org/W2123178347","https://openalex.org/W2104412724","https://openalex.org/W2101979000","https://openalex.org/W2094969206","https://openalex.org/W2066737015","https://openalex.org/W1513332069"],"abstract_inverted_index":{"Let":[0],"A":[1],"denote":[2],"an":[3,63],"alphabet":[4],"consisting":[5],"of":[6,9,15,21,34,42,48,74,87,139,144,158,189,198,216,234,267],"n":[7],"types":[8],"letters.":[10],"Given":[11],"a":[12,38,118,155],"sequence":[13,78,95,212],"S":[14],"length":[16,113,248],"L":[17],"with":[18,81,109,201],"v(i)":[19],"letters":[20],"type":[22],"i":[23],"on":[24,59],"A,":[25],"to":[26,93,101,133,175,185],"describe":[27],"the":[28,45,88,94,102,128,142,161,181,208,221,225,244,258,271],"compositional":[29],"properties":[30],"and":[31,70,76,114,117,224,240,257],"combinatorial":[32],"structure":[33],"S,":[35,43,49],"we":[36,218],"propose":[37],"new":[39],"complexity":[40,47,61],"function":[41],"called":[44],"reciprocal":[46],"as":[50],"C(S)":[51],"=":[52,250,255],"(i=1)":[53],"product":[54],"operator":[55],"(n)":[56],"(L/nv(i))(vi)":[57],"Based":[58],"this":[60],"measure,":[62],"efficient":[64],"algorithm":[65,89,103],"is":[66,90,141,174,274],"developed":[67],"for":[68,147,231,270],"classifying":[69],"analyzing":[71],"simple":[72,145,177],"segments":[73],"protein":[75,124,199],"nucleotide":[77],"databases":[79],"associated":[80,108],"scoring":[82,119],"schemes.":[83],"The":[84,97,136,171,262],"running":[85],"time":[86],"nearly":[91],"proportional":[92],"length.":[96],"program":[98,183],"DSR":[99,140,153,182,245,268],"corresponding":[100,184],"was":[104],"written":[105],"in":[106],"C++,":[107],"two":[110],"parameters":[111,223],"(window":[112],"cutoff":[115,163,252],"value)":[116],"matrix.":[120,261],"Some":[121],"examples":[122],"regarding":[123],"sequences":[125,146,200,237],"illustrate":[126],"how":[127],"method":[129],"can":[130],"be":[131],"used":[132],"find":[134],"regions.":[135],"first":[137],"application":[138,173],"masking":[143],"searching":[148],"databases.":[149],"Queries":[150],"masked":[151],"by":[152,180,243],"returned":[154],"manageable":[156],"set":[157],"hits":[159],"below":[160],"E-value":[162],"score,":[164],"which":[165],"contained":[166],"all":[167],"true":[168],"positive":[169],"homologues.":[170],"second":[172],"study":[176],"regions":[178,242],"detected":[179],"known":[186],"structural":[187],"features":[188],"proteins.":[190],"An":[191],"extensive":[192],"computational":[193],"analysis":[194],"has":[195],"been":[196],"made":[197],"known,":[202],"physicochemically":[203],"defined":[204],"nonglobular":[205,239],"segments.":[206],"For":[207],"SWISS-PROT":[209,272],"amino":[210,235],"acid":[211,236],"database":[213,273],"(Release":[214],"40.2":[215],"02-Nov-2001),":[217],"determine":[219],"that":[220],"best":[222,226],"BLOSUM":[227,259],"matrix":[228],"are,":[229],"respectively,":[230],"automatic":[232],"segmentation":[233,269],"into":[238],"globular":[241],"program:":[246],"Window":[247],"k":[249],"35,":[251],"value":[253],"b":[254],"0.46,":[256],"62.5":[260],"average":[263],"\"agreement":[264],"accuracy":[265],"(sensitivity)\"":[266],"97.3%.":[275]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}