{"id":"https://openalex.org/W2070962918","doi":"https://doi.org/10.1021/ci900035z","title":"Mining Statistically Significant Molecular Substructures for Efficient Molecular Classification","display_name":"Mining Statistically Significant Molecular Substructures for Efficient Molecular Classification","publication_year":2009,"publication_date":"2009-10-28","ids":{"openalex":"https://openalex.org/W2070962918","doi":"https://doi.org/10.1021/ci900035z","mag":"2070962918","pmid":"https://pubmed.ncbi.nlm.nih.gov/19928835"},"language":"en","primary_location":{"id":"doi:10.1021/ci900035z","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci900035z","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"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 Modeling","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/A5054697900","display_name":"Sayan Ranu","orcid":"https://orcid.org/0000-0003-4147-9372"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sayan Ranu","raw_affiliation_strings":["Department of Computer Science, University of California, Santa Barbara, California","Department of Computer Science University of California Santa Barbara California USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Santa Barbara, California","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"Department of Computer Science University of California Santa Barbara California USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036639779","display_name":"Ambuj K. Singh","orcid":"https://orcid.org/0000-0002-1997-7140"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ambuj K. Singh","raw_affiliation_strings":["Department of Computer Science, University of California, Santa Barbara, California","[Department of Computer Science, University of California, Santa Barbara, California]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Santa Barbara, California","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"[Department of Computer Science, University of California, Santa Barbara, California]","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5036639779","https://openalex.org/A5054697900"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":2.4302,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.88530296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"49","issue":"11","first_page":"2537","last_page":"2550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9775999784469604,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9595999717712402,"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":0.7061451077461243},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6773781776428223},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5948618054389954},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5907611846923828},{"id":"https://openalex.org/keywords/molecular-descriptor","display_name":"Molecular descriptor","score":0.48384585976600647},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.476900577545166},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.4656001031398773},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.46265560388565063},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36754733324050903},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36501404643058777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3576054275035858},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.19709590077400208},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.13654181361198425},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.09575155377388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7061451077461243},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6773781776428223},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5948618054389954},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5907611846923828},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.48384585976600647},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.476900577545166},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.4656001031398773},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.46265560388565063},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36754733324050903},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36501404643058777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3576054275035858},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.19709590077400208},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13654181361198425},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.09575155377388},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci900035z","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci900035z","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"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 Modeling","raw_type":"journal-article"},{"id":"pmid:19928835","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19928835","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 modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1487233798","https://openalex.org/W1544481768","https://openalex.org/W1595350250","https://openalex.org/W1963917497","https://openalex.org/W1970651561","https://openalex.org/W1970969454","https://openalex.org/W1972043917","https://openalex.org/W1977609268","https://openalex.org/W1978811796","https://openalex.org/W1981069378","https://openalex.org/W1993416723","https://openalex.org/W1994126845","https://openalex.org/W2002987877","https://openalex.org/W2040930785","https://openalex.org/W2042110087","https://openalex.org/W2063389953","https://openalex.org/W2065903747","https://openalex.org/W2084664715","https://openalex.org/W2085946956","https://openalex.org/W2091860620","https://openalex.org/W2094125466","https://openalex.org/W2095556681","https://openalex.org/W2096729078","https://openalex.org/W2101156500","https://openalex.org/W2113820449","https://openalex.org/W2121216262","https://openalex.org/W2136507529","https://openalex.org/W2136593687","https://openalex.org/W2137262074","https://openalex.org/W2148603752","https://openalex.org/W2153635508","https://openalex.org/W2161723275","https://openalex.org/W2162481448","https://openalex.org/W2168137269","https://openalex.org/W2203775767","https://openalex.org/W2320034101","https://openalex.org/W2554073607","https://openalex.org/W2949243165","https://openalex.org/W2950098937","https://openalex.org/W4213245422","https://openalex.org/W4234821032","https://openalex.org/W4244195804"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2011430815","https://openalex.org/W4321606653"],"abstract_inverted_index":{"The":[0,105],"increased":[1],"availability":[2],"of":[3,6,32,43,68,76,107,171,176],"large":[4],"repositories":[5],"chemical":[7,33,111],"compounds":[8,34],"has":[9,145],"created":[10],"new":[11],"challenges":[12],"in":[13,27,64,147,169],"designing":[14],"efficient":[15],"molecular":[16,62,102],"querying":[17],"and":[18,37,92,115,150,163],"mining":[19,77],"systems.":[20],"Molecular":[21],"classification":[22,172],"is":[23,113,179],"an":[24,95],"important":[25],"problem":[26],"drug":[28],"development":[29],"where":[30],"libraries":[31],"are":[35,49,119,134,155],"screened":[36],"molecules":[38,123],"with":[39,89],"the":[40,73,131,160,177],"highest":[41],"probability":[42],"success":[44],"against":[45],"a":[46,54,65,80,110],"given":[47,66],"target":[48],"selected.":[50],"We":[51],"have":[52],"developed":[53],"technique":[55],"called":[56],"GraphSig":[57,70,86,108],"to":[58,100,121,158],"mine":[59],"significantly":[60],"over-represented":[61,132],"substructures":[63],"class":[67],"molecules.":[69],"successfully":[71],"overcomes":[72],"scalability":[74],"bottleneck":[75],"patterns":[78,126,133],"at":[79,185],"low":[81],"frequency.":[82],"Patterns":[83],"mined":[84,127],"by":[85,125,141],"display":[87],"correlation":[88],"biological":[90],"activities":[91],"serve":[93],"as":[94,109],"excellent":[96],"platform":[97],"on":[98],"which":[99],"build":[101],"analysis":[103],"tools.":[104],"potential":[106,146],"descriptor":[112],"explored,":[114],"support":[116],"vector":[117],"machines":[118],"used":[120],"classify":[122],"described":[124],"using":[128],"GraphSig.":[129],"Furthermore,":[130],"more":[135],"informative":[136],"than":[137],"features":[138],"generated":[139],"exhaustively":[140],"traditional":[142],"fingerprints;":[143],"this":[144],"providing":[148],"scaffolds":[149],"lead":[151],"generation.":[152],"Extensive":[153],"experiments":[154],"carried":[156],"out":[157],"evaluate":[159],"proposed":[161],"techniques,":[162],"empirical":[164],"results":[165],"show":[166],"promising":[167],"performance":[168],"terms":[170],"quality.":[173],"An":[174],"implementation":[175],"algorithm":[178],"available":[180],"free":[181],"for":[182],"academic":[183],"use":[184],"http://www.uweb.ucsb.edu/":[186],"approximately":[187],"sayan/software/GraphSig.tar.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"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":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2025-10-10T00:00:00"}