{"id":"https://openalex.org/W2106304690","doi":"https://doi.org/10.1093/bioinformatics/btg1072","title":"Finding subtle motifs by branching from sample strings","display_name":"Finding subtle motifs by branching from sample strings","publication_year":2003,"publication_date":"2003-09-27","ids":{"openalex":"https://openalex.org/W2106304690","doi":"https://doi.org/10.1093/bioinformatics/btg1072","mag":"2106304690","pmid":"https://pubmed.ncbi.nlm.nih.gov/14534184"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btg1072","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg1072","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066797582","display_name":"Alkes L. Price","orcid":"https://orcid.org/0000-0002-2971-7975"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alkes Price","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California at San Diego, La Jolla, CA 92093-0114, USA. aprice@cs.ucsd.edu","Department of Computer Science and Engineering, University of California at San Diego, La Jolla, CA 92093-0114, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California at San Diego, La Jolla, CA 92093-0114, USA. aprice@cs.ucsd.edu","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California at San Diego, La Jolla, CA 92093-0114, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011815986","display_name":"Sriram Ramabhadran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sriram Ramabhadran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027480961","display_name":"Pavel A. Pevzner","orcid":"https://orcid.org/0000-0002-0418-165X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pavel A. Pevzner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":4.1244,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.94839332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"19","issue":"suppl_2","first_page":"ii149","last_page":"ii155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.25609999895095825,"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/T10885","display_name":"Gene expression and cancer classification","score":0.25609999895095825,"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":0.21930000185966492,"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/T10604","display_name":"RNA Research and Splicing","score":0.08009999990463257,"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/substring","display_name":"Substring","score":0.7427427172660828},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6010890007019043},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.5869705080986023},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.4409847557544708},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.43793898820877075},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4355952739715576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40534138679504395},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35626620054244995},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3065096139907837},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10198700428009033},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.08133378624916077}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.7427427172660828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6010890007019043},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.5869705080986023},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.4409847557544708},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43793898820877075},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4355952739715576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40534138679504395},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35626620054244995},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3065096139907837},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10198700428009033},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.08133378624916077},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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":"D000595","descriptor_name":"Amino Acid Sequence","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":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base 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":"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":"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":"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":"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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","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":"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}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btg1072","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg1072","pdf_url":null,"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:14534184","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/14534184","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":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.3.650","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ucsd.edu/~nramabha/eccb2003.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.44999998807907104,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1214546200","https://openalex.org/W1519517812","https://openalex.org/W1580213736","https://openalex.org/W1592870802","https://openalex.org/W1594947347","https://openalex.org/W1973754133","https://openalex.org/W1975924111","https://openalex.org/W1998300401","https://openalex.org/W2003967338","https://openalex.org/W2028904582","https://openalex.org/W2034206030","https://openalex.org/W2054984882","https://openalex.org/W2070310544","https://openalex.org/W2074526138","https://openalex.org/W2099316694","https://openalex.org/W2117168988","https://openalex.org/W2126873530","https://openalex.org/W2128091972","https://openalex.org/W2148014281","https://openalex.org/W3087694578"],"related_works":["https://openalex.org/W1583922594","https://openalex.org/W1542422837","https://openalex.org/W1974038726","https://openalex.org/W2998448420","https://openalex.org/W1598224733","https://openalex.org/W4280502676","https://openalex.org/W2000769876","https://openalex.org/W2112822946","https://openalex.org/W204227468","https://openalex.org/W2157233202"],"abstract_inverted_index":{"UNLABELLED:":[0],"Many":[1],"motif":[2,97,125],"finding":[3,126],"algorithms":[4,118],"apply":[5],"local":[6],"search":[7],"techniques":[8],"to":[9,27,54,85,123],"a":[10,92],"set":[11],"of":[12,37,60,66],"seeds.":[13],"For":[14],"example,":[15],"GibbsDNA":[16],"(Lawrence":[17],"et":[18],"al.":[19],"1993,":[20],"Science,":[21],"262,":[22],"208-214)":[23],"applies":[24,50],"Gibbs":[25],"sampling":[26],"random":[28,75],"seeds,":[29],"and":[30,33,77,104,111,116],"MEME":[31],"(Bailey":[32],"Elkan,":[34],"1994,":[35],"Proceedings":[36],"the":[38,51,61,64,86],"Second":[39],"International":[40],"Conference":[41],"on":[42],"Intelligent":[43],"Systems":[44],"for":[45],"Molecular":[46],"Biology":[47],"(ISMB-94),":[48],"28-36)":[49],"EM":[52],"algorithm":[53],"selected":[55,78],"sample":[56,79,102],"strings,":[57,103],"i.e.":[58],"substrings":[59],"sample.":[62],"In":[63],"case":[65],"subtle":[67],"motifs,":[68],"recent":[69],"benchmarking":[70],"efforts":[71],"show":[72],"that":[73],"both":[74,109],"seeds":[76],"strings":[80],"may":[81],"never":[82],"get":[83],"close":[84],"globally":[87],"optimal":[88],"motif.":[89],"We":[90],"propose":[91],"new":[93],"approach":[94],"which":[95],"searches":[96],"space":[98],"by":[99],"branching":[100],"from":[101],"implement":[105],"this":[106],"idea":[107],"in":[108],"pattern-based":[110],"profile-based":[112],"settings.":[113],"Our":[114],"PatternBranching":[115],"ProfileBranching":[117],"achieve":[119],"favorable":[120],"results":[121],"relative":[122],"other":[124],"algorithms.":[127],"AVAILABILITY:":[128],"http://www-cse.ucsd.edu/groups/bioinformatics/software.html":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
