{"id":"https://openalex.org/W2025540189","doi":"https://doi.org/10.1021/ci034138n","title":"Mining Biological Data Using Self-Organizing Map","display_name":"Mining Biological Data Using Self-Organizing Map","publication_year":2003,"publication_date":"2003-11-01","ids":{"openalex":"https://openalex.org/W2025540189","doi":"https://doi.org/10.1021/ci034138n","mag":"2025540189","pmid":"https://pubmed.ncbi.nlm.nih.gov/14632420"},"language":"en","primary_location":{"id":"doi:10.1021/ci034138n","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci034138n","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Computer Sciences","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/A5101837304","display_name":"Zheng Rong Yang","orcid":"https://orcid.org/0000-0002-6733-7893"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zheng Rong Yang","raw_affiliation_strings":["Department of Computer Science, Exeter University, Exeter EX4 4PT, U.K., Gordon Life Science Institute, San Diego, California 92130, and Tianjin Institute of Bioinformatics and Drug Discovery (TIBDD), Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Exeter University, Exeter EX4 4PT, U.K., Gordon Life Science Institute, San Diego, California 92130, and Tianjin Institute of Bioinformatics and Drug Discovery (TIBDD), Tianjin, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113500576","display_name":"Kuo\u2010Chen Chou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuo-Chen Chou","raw_affiliation_strings":["Department of Computer Science, Exeter University, Exeter EX4 4PT, U.K., Gordon Life Science Institute, San Diego, California 92130, and Tianjin Institute of Bioinformatics and Drug Discovery (TIBDD), Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Exeter University, Exeter EX4 4PT, U.K., Gordon Life Science Institute, San Diego, California 92130, and Tianjin Institute of Bioinformatics and Drug Discovery (TIBDD), Tianjin, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101837304"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6872,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.66847264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"43","issue":"6","first_page":"1748","last_page":"1753"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9993000030517578,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9993000030517578,"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":0.9987000226974487,"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/T12867","display_name":"Advanced Biosensing Techniques and Applications","score":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.589420735836029},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5877614617347717},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.4886329770088196},{"id":"https://openalex.org/keywords/self-organizing-map","display_name":"Self-organizing map","score":0.4721270501613617},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4627724885940552},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.4467499852180481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42648324370384216},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4229907989501953},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.40288597345352173},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.37097370624542236},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3575758635997772},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.23511287569999695},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1884126365184784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.589420735836029},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5877614617347717},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.4886329770088196},{"id":"https://openalex.org/C111168008","wikidata":"https://www.wikidata.org/wiki/Q1136838","display_name":"Self-organizing map","level":3,"score":0.4721270501613617},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4627724885940552},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.4467499852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42648324370384216},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4229907989501953},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.40288597345352173},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.37097370624542236},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3575758635997772},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.23511287569999695},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1884126365184784},{"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/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":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009154","descriptor_name":"Mutation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009842","descriptor_name":"Oligopeptides","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009842","descriptor_name":"Oligopeptides","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009842","descriptor_name":"Oligopeptides","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009842","descriptor_name":"Oligopeptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009842","descriptor_name":"Oligopeptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009842","descriptor_name":"Oligopeptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016333","descriptor_name":"HIV Protease","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016333","descriptor_name":"HIV Protease","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016333","descriptor_name":"HIV Protease","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/ci034138n","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci034138n","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Computer Sciences","raw_type":"journal-article"},{"id":"pmid:14632420","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/14632420","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 chemical information and computer sciences","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.107.8629","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.107.8629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://gordonlifescience.org/members/kcchou/paper/JCICS_dada_mining.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W77031173","https://openalex.org/W195150910","https://openalex.org/W1514209943","https://openalex.org/W1966262721","https://openalex.org/W1966952510","https://openalex.org/W1967501922","https://openalex.org/W1968873679","https://openalex.org/W1974224443","https://openalex.org/W1977282539","https://openalex.org/W1978129111","https://openalex.org/W1979233714","https://openalex.org/W1980935152","https://openalex.org/W1981555301","https://openalex.org/W1987713050","https://openalex.org/W1990376815","https://openalex.org/W1991848143","https://openalex.org/W1995396220","https://openalex.org/W2006327082","https://openalex.org/W2008767404","https://openalex.org/W2008895011","https://openalex.org/W2008928574","https://openalex.org/W2013704461","https://openalex.org/W2014875362","https://openalex.org/W2015692100","https://openalex.org/W2015866424","https://openalex.org/W2018096960","https://openalex.org/W2018896510","https://openalex.org/W2019257250","https://openalex.org/W2023779075","https://openalex.org/W2024180247","https://openalex.org/W2026882865","https://openalex.org/W2037088203","https://openalex.org/W2045722009","https://openalex.org/W2054342685","https://openalex.org/W2055522016","https://openalex.org/W2060740730","https://openalex.org/W2070411414","https://openalex.org/W2076074498","https://openalex.org/W2076747662","https://openalex.org/W2080786231","https://openalex.org/W2081422975","https://openalex.org/W2083139287","https://openalex.org/W2085318243","https://openalex.org/W2086003834","https://openalex.org/W2087876594","https://openalex.org/W2094103647","https://openalex.org/W2095300338","https://openalex.org/W2096863518","https://openalex.org/W2098556826","https://openalex.org/W2102794349","https://openalex.org/W2103453943","https://openalex.org/W2119423166","https://openalex.org/W2120026469","https://openalex.org/W2120068166","https://openalex.org/W2122642866","https://openalex.org/W2122945697","https://openalex.org/W2124045874","https://openalex.org/W2125310307","https://openalex.org/W2131480593","https://openalex.org/W2135187880","https://openalex.org/W2135951244","https://openalex.org/W2143244636","https://openalex.org/W2145084154","https://openalex.org/W2149528591","https://openalex.org/W2150926065","https://openalex.org/W2151116772","https://openalex.org/W2156909104","https://openalex.org/W2158338599","https://openalex.org/W2158461363","https://openalex.org/W2165011536","https://openalex.org/W2165298438","https://openalex.org/W2165732545","https://openalex.org/W2466216302","https://openalex.org/W2600349519","https://openalex.org/W4210519020"],"related_works":["https://openalex.org/W2034551444","https://openalex.org/W3170299350","https://openalex.org/W2023416609","https://openalex.org/W2368410102","https://openalex.org/W2368037387","https://openalex.org/W190186656","https://openalex.org/W2377079823","https://openalex.org/W2902352756","https://openalex.org/W1844640764","https://openalex.org/W2605676258"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,11,17],"novel":[4],"method":[5,76],"of":[6,19,61],"mining":[7],"biological":[8],"data":[9],"using":[10,22],"self-organizing":[12],"map":[13],"(SOM).":[14],"After":[15],"partitioning":[16],"set":[18],"protein":[20],"sequences":[21],"SOM,":[23],"conventional":[24],"homology":[25],"alignment":[26],"is":[27],"applied":[28],"to":[29,32,58],"each":[30],"cluster":[31],"determine":[33],"the":[34,41,56,59,71,85],"conserved":[35],"local":[36,44],"motif":[37],"(biological":[38],"pattern)":[39],"for":[40,51],"cluster.":[42],"These":[43],"motifs":[45],"are":[46,77],"then":[47],"regarded":[48],"as":[49],"rules":[50,72],"prediction":[52,60],"and":[53],"classification.":[54],"In":[55],"application":[57],"HIV":[62],"protease":[63],"cleavage":[64],"sites":[65],"in":[66],"proteins,":[67],"we":[68],"found":[69],"that":[70],"derived":[73,83],"from":[74,84],"this":[75],"much":[78],"more":[79],"robust":[80],"than":[81],"those":[82],"decision":[86],"tree":[87],"method.":[88]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2025-10-10T00:00:00"}
