{"id":"https://openalex.org/W2120344408","doi":"https://doi.org/10.1093/bioinformatics/bti090","title":"Relation between weight matrix and substitution matrix: motif search by similarity","display_name":"Relation between weight matrix and substitution matrix: motif search by similarity","publication_year":2004,"publication_date":"2004-10-28","ids":{"openalex":"https://openalex.org/W2120344408","doi":"https://doi.org/10.1093/bioinformatics/bti090","mag":"2120344408","pmid":"https://pubmed.ncbi.nlm.nih.gov/15514002"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti090","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti090","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/7/938/48966414/bioinformatics_21_7_938.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,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/21/7/938/48966414/bioinformatics_21_7_938.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021041719","display_name":"Wei\u2010Mou Zheng","orcid":"https://orcid.org/0000-0001-6546-2917"},"institutions":[{"id":"https://openalex.org/I4210125404","display_name":"Institute of Theoretical Physics","ror":"https://ror.org/02xtbq882","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210125404"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei-Mou Zheng","raw_affiliation_strings":["Institute of Theoretical Physics, Academia Sinica Beijing 100080, China","*Institute of Theoretical Physics, Academia Sinica, Beijing 100080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Theoretical Physics, Academia Sinica Beijing 100080, China","institution_ids":["https://openalex.org/I4210125404"]},{"raw_affiliation_string":"*Institute of Theoretical Physics, Academia Sinica, Beijing 100080, China","institution_ids":["https://openalex.org/I4210125404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5021041719"],"corresponding_institution_ids":["https://openalex.org/I4210125404"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":null,"fwci":0.2283,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.53157829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"21","issue":"7","first_page":"938","last_page":"943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.2687000036239624,"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":0.2687000036239624,"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/T10885","display_name":"Gene expression and cancer classification","score":0.12290000170469284,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.04650000110268593,"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/mathematics","display_name":"Mathematics","score":0.5181571245193481},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5102083683013916},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.48346075415611267},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4627310037612915},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4575336277484894},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4558878540992737},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.4437094032764435},{"id":"https://openalex.org/keywords/substitution","display_name":"Substitution (logic)","score":0.4215378761291504},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.41127943992614746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3975027799606323},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.27878227829933167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22975149750709534},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.07914113998413086}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5181571245193481},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5102083683013916},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.48346075415611267},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4627310037612915},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4575336277484894},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4558878540992737},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.4437094032764435},{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.4215378761291504},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.41127943992614746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3975027799606323},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27878227829933167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22975149750709534},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.07914113998413086},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","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":"D008969","descriptor_name":"Molecular Sequence Data","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":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","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":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","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":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","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":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":3,"locations":[{"id":"doi:10.1093/bioinformatics/bti090","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti090","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/7/938/48966414/bioinformatics_21_7_938.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,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:15514002","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15514002","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":"Bioinformatics (Oxford, England)","raw_type":"Comparative Study"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.610.7477","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.610.7477","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/early/2004/10/28/bioinformatics.bti090.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bti090","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti090","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/7/938/48966414/bioinformatics_21_7_938.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,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2120344408.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W21816278","https://openalex.org/W642011965","https://openalex.org/W1998300401","https://openalex.org/W2032231928","https://openalex.org/W2056002855","https://openalex.org/W2096139934","https://openalex.org/W2097555181","https://openalex.org/W2110455321","https://openalex.org/W2138309709","https://openalex.org/W2143210482","https://openalex.org/W2162111678","https://openalex.org/W3150945973","https://openalex.org/W4388278741"],"related_works":["https://openalex.org/W1978042415","https://openalex.org/W3102632868","https://openalex.org/W2891776881","https://openalex.org/W1998707102","https://openalex.org/W2032649343","https://openalex.org/W1558704946","https://openalex.org/W2400403148","https://openalex.org/W2027565429","https://openalex.org/W4313308036","https://openalex.org/W3095407089"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,66,206],"discovery":[2],"of":[3,54,96,141,172,186],"patterns":[4],"shared":[5],"by":[6,58,74,79,190,217],"several":[7],"sequences":[8,143],"that":[9],"differ":[10],"greatly":[11],"is":[12,101,110],"a":[13,21,63,91,94,108,148,160,170,180,197],"basic":[14],"task":[15],"in":[16,62,106],"sequence":[17,99,123,177],"analysis,":[18],"and":[19,44,133],"still":[20],"challenge.":[22],"Several":[23],"methods":[24,69],"have":[25],"been":[26],"developed":[27],"for":[28,34,152,175,213],"detecting":[29],"patterns.":[30],"Methods":[31],"commonly":[32],"used":[33,194],"motif":[35,92,109],"search":[36],"include":[37],"the":[38,52,55,59,102,122,126,130,165,210,214],"Gibbs":[39,60],"sampler,":[40],"Expectation-Maximization":[41],"(EM)":[42],"algorithm":[43,207],"some":[45],"intuitive":[46],"greedy":[47,80,219],"approaches.":[48],"One":[49],"cannot":[50],"guarantee":[51],"optimality":[53],"result":[56],"produced":[57],"sampler":[61],"single":[64],"run.":[65],"deterministic":[67],"EM":[68],"tend":[70],"to":[71,120,163,195],"get":[72],"trapped":[73],"local":[75,97],"optima.":[76],"Solutions":[77],"found":[78],"approaches":[81],"are":[82,118,157],"rarely":[83],"sufficiently":[84],"good.":[85],"RESULTS:":[86],"A":[87],"simple":[88],"model":[89],"describing":[90],"or":[93,201],"portion":[95],"multiple":[98,176],"alignment":[100],"weight":[103,127,134,199],"matrix":[104,132,200],"model,":[105],"which":[107,168],"characterized":[111],"with":[112,125,144,159],"position-specific":[113],"probabilities.":[114],"Two":[115],"substitution":[116,131,204],"matrices":[117],"proposed":[119],"relate":[121],"similarity":[124,181,191],"matrix.":[128,205],"Combining":[129],"matrix,":[135],"we":[136],"examine":[137],"three":[138],"typical":[139],"sets":[140,216],"protein":[142],"increasing":[145],"complexity.":[146],"At":[147],"low":[149],"score":[150,166],"threshold":[151],"pair":[153],"similarity,":[154],"sliding":[155],"windows":[156],"compared":[158],"seed":[161],"window":[162],"find":[164],"sum,":[167],"provides":[169],"measure":[171],"statistical":[173],"significance":[174],"comparison.":[178],"Such":[179],"analysis":[182],"reveals":[183],"many":[184],"aspects":[185],"motifs.":[187],"Blocks":[188],"determined":[189],"can":[192],"be":[193],"deduce":[196],"primary":[198],"an":[202],"improved":[203],"successfully":[208],"obtains":[209],"optimal":[211],"solution":[212],"test":[215],"just":[218],"iteration.":[220]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}