{"id":"https://openalex.org/W2314089972","doi":"https://doi.org/10.1142/9789812702098_0022","title":"TRAINING SET DESIGN FOR PATTERN DISCOVERY WITH APPLICATIONS TO PROTEIN MOTIF DETECTION","display_name":"TRAINING SET DESIGN FOR PATTERN DISCOVERY WITH APPLICATIONS TO PROTEIN MOTIF DETECTION","publication_year":2005,"publication_date":"2005-05-01","ids":{"openalex":"https://openalex.org/W2314089972","doi":"https://doi.org/10.1142/9789812702098_0022","mag":"2314089972"},"language":"en","primary_location":{"id":"doi:10.1142/9789812702098_0022","is_oa":false,"landing_page_url":"https://doi.org/10.1142/9789812702098_0022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Bioinformatics and Its Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5061841145","display_name":"Yanli Sun","orcid":"https://orcid.org/0000-0003-3144-5558"},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"YANLI SUN","raw_affiliation_strings":["Bioinformatics Research Group (BioRG), School of Computer Science, Florida International University, Miami, FL 33199, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Research Group (BioRG), School of Computer Science, Florida International University, Miami, FL 33199, USA","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061822058","display_name":"ZHENGYUE DENG","orcid":null},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"ZHENGYUE DENG","raw_affiliation_strings":["Bioinformatics Research Group (BioRG), School of Computer Science, Florida International University, Miami, FL 33199, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Research Group (BioRG), School of Computer Science, Florida International University, Miami, FL 33199, USA","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068890173","display_name":"Giri Narasimhan","orcid":"https://orcid.org/0000-0003-0535-4871"},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"GIRI NARASIMHAN","raw_affiliation_strings":["Bioinformatics Research Group (BioRG), School of Computer Science, Florida International University, Miami, FL 33199, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Research Group (BioRG), School of Computer Science, Florida International University, Miami, FL 33199, USA","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037360822","display_name":"Kalai Mathee","orcid":"https://orcid.org/0000-0003-4569-5419"},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"KALAI MATHEE","raw_affiliation_strings":["Department of Biological Sciences, Florida International University, Miami, FL 33199, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Florida International University, Miami, FL 33199, USA","institution_ids":["https://openalex.org/I19700959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15156996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"240","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9955999851226807,"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":0.9955999851226807,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9883999824523926,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9842000007629395,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.7720060348510742},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6467918157577515},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3843318223953247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35629135370254517},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12384837865829468}],"concepts":[{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.7720060348510742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6467918157577515},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3843318223953247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35629135370254517},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12384837865829468},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/9789812702098_0022","is_oa":false,"landing_page_url":"https://doi.org/10.1142/9789812702098_0022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Bioinformatics and Its Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.7322","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.7322","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.fiu.edu/~giri/papers/ICBA04_Sun.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W1495524224"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3170299350","https://openalex.org/W2368410102","https://openalex.org/W2368037387","https://openalex.org/W190186656","https://openalex.org/W2377079823","https://openalex.org/W2902352756","https://openalex.org/W2605676258","https://openalex.org/W2599962286","https://openalex.org/W2319582300"],"abstract_inverted_index":{"Supervised":[0],"pattern":[1],"discovery":[2],"techniques":[3],"have":[4],"been":[5],"successfully":[6],"used":[7],"for":[8,72],"motif":[9,93],"detection.":[10],"However,":[11],"this":[12,45],"requires":[13],"the":[14,33,40,49,84,98,101],"use":[15],"of":[16,27,51,108],"an":[17],"efficient":[18],"training":[19,41,60,75,87,109],"set.":[20,110],"Even":[21],"in":[22,86],"cases":[23],"where":[24],"a":[25,69,105,117],"lot":[26],"examples":[28,35],"are":[29,62],"known,":[30],"using":[31],"all":[32],"available":[34],"can":[36],"introduce":[37],"bias":[38,85],"during":[39],"process.":[42],"In":[43],"practice,":[44],"is":[46,57],"done":[47],"with":[48],"help":[50],"domain":[52],"experts.":[53],"Whenever":[54],"such":[55],"expertise":[56],"not":[58],"available,":[59],"sets":[61,76],"usually":[63],"picked":[64],"at":[65],"random.":[66],"We":[67],"present":[68],"new":[70],"strategy":[71],"designing":[73],"good":[74],"that":[77,97],"uses":[78],"phylogenetic":[79],"trees":[80],"to":[81,91],"automatically":[82],"reduce":[83],"sets.":[88],"When":[89],"applied":[90],"helix-turn-helix":[92],"detection,":[94],"we":[95],"show":[96,116],"technique":[99],"improved":[100],"error":[102],"rates":[103,115],"over":[104],"random":[106],"choice":[107],"More":[111],"specifically,":[112],"false":[113],"positive":[114],"marked":[118],"improvement.":[119],"1.":[120]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
