{"id":"https://openalex.org/W2105687791","doi":"https://doi.org/10.1021/ci8000887","title":"Toward an Improved Clustering of Large Data Sets Using Maximum Common Substructures and Topological Fingerprints","display_name":"Toward an Improved Clustering of Large Data Sets Using Maximum Common Substructures and Topological Fingerprints","publication_year":2008,"publication_date":"2008-10-29","ids":{"openalex":"https://openalex.org/W2105687791","doi":"https://doi.org/10.1021/ci8000887","mag":"2105687791","pmid":"https://pubmed.ncbi.nlm.nih.gov/18956832"},"language":"en","primary_location":{"id":"doi:10.1021/ci8000887","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci8000887","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/A5053150473","display_name":"Alexander B\u00f6cker","orcid":null},"institutions":[{"id":"https://openalex.org/I1330995197","display_name":"Boehringer Ingelheim (Germany)","ror":"https://ror.org/00q32j219","country_code":"DE","type":"company","lineage":["https://openalex.org/I1330995197"]},{"id":"https://openalex.org/I4210138665","display_name":"Boehringer Ingelheim (Canada)","ror":"https://ror.org/031sxg258","country_code":"CA","type":"company","lineage":["https://openalex.org/I1330995197","https://openalex.org/I4210138665"]}],"countries":["CA","DE"],"is_corresponding":true,"raw_author_name":"Alexander B\u00f6cker","raw_affiliation_strings":["Boehringer Ingelheim (Canada) Ltd. Research & Development, 2100 Cunard Street, Laval, Quebec, Canada H7S 2G5","Boechringer Ingelheim (Canada) Ltd. Research & Development, 2100 Cunard Street, Laval, Quebec, Canada H7S 2G5. Alexander.bocker@boehringer-ingelheim.com"],"affiliations":[{"raw_affiliation_string":"Boehringer Ingelheim (Canada) Ltd. Research & Development, 2100 Cunard Street, Laval, Quebec, Canada H7S 2G5","institution_ids":["https://openalex.org/I4210138665"]},{"raw_affiliation_string":"Boechringer Ingelheim (Canada) Ltd. Research & Development, 2100 Cunard Street, Laval, Quebec, Canada H7S 2G5. Alexander.bocker@boehringer-ingelheim.com","institution_ids":["https://openalex.org/I1330995197"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5053150473"],"corresponding_institution_ids":["https://openalex.org/I1330995197","https://openalex.org/I4210138665"],"apc_list":null,"apc_paid":null,"fwci":4.8063,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.95024195,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"48","issue":"11","first_page":"2097","last_page":"2107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998000264167786,"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":0.9998000264167786,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9889000058174133,"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/T11882","display_name":"Plant biochemistry and biosynthesis","score":0.9588000178337097,"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/chemotype","display_name":"Chemotype","score":0.9506493806838989},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5853085517883301},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5456401705741882},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4882369339466095},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4870896339416504},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4168722331523895},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3423624038696289},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.33093833923339844},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.22299444675445557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20010364055633545},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18661591410636902}],"concepts":[{"id":"https://openalex.org/C153784791","wikidata":"https://www.wikidata.org/wiki/Q2212766","display_name":"Chemotype","level":3,"score":0.9506493806838989},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5853085517883301},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5456401705741882},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4882369339466095},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4870896339416504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4168722331523895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3423624038696289},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.33093833923339844},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.22299444675445557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20010364055633545},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18661591410636902},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C2777278459","wikidata":"https://www.wikidata.org/wiki/Q170885","display_name":"Essential oil","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":"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":"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":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D018894","descriptor_name":"Reverse Transcriptase Inhibitors","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D018894","descriptor_name":"Reverse Transcriptase Inhibitors","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D018894","descriptor_name":"Reverse Transcriptase Inhibitors","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D018894","descriptor_name":"Reverse Transcriptase Inhibitors","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D018894","descriptor_name":"Reverse Transcriptase Inhibitors","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D018894","descriptor_name":"Reverse Transcriptase Inhibitors","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D019380","descriptor_name":"Anti-HIV Agents","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D019380","descriptor_name":"Anti-HIV Agents","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D019380","descriptor_name":"Anti-HIV Agents","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D019380","descriptor_name":"Anti-HIV Agents","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D019380","descriptor_name":"Anti-HIV Agents","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D019380","descriptor_name":"Anti-HIV Agents","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D029424","descriptor_name":"Pulmonary Disease, Chronic Obstructive","qualifier_ui":"Q000188","qualifier_name":"drug therapy","is_major_topic":false},{"descriptor_ui":"D029424","descriptor_name":"Pulmonary Disease, Chronic Obstructive","qualifier_ui":"Q000188","qualifier_name":"drug therapy","is_major_topic":false},{"descriptor_ui":"D029424","descriptor_name":"Pulmonary Disease, Chronic Obstructive","qualifier_ui":"Q000188","qualifier_name":"drug therapy","is_major_topic":false},{"descriptor_ui":"D048088","descriptor_name":"Informatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D048088","descriptor_name":"Informatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D048088","descriptor_name":"Informatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054303","descriptor_name":"HIV Reverse Transcriptase","qualifier_ui":"Q000037","qualifier_name":"antagonists & inhibitors","is_major_topic":false},{"descriptor_ui":"D054303","descriptor_name":"HIV Reverse Transcriptase","qualifier_ui":"Q000037","qualifier_name":"antagonists & inhibitors","is_major_topic":false},{"descriptor_ui":"D054303","descriptor_name":"HIV Reverse Transcriptase","qualifier_ui":"Q000037","qualifier_name":"antagonists & inhibitors","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci8000887","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci8000887","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:18956832","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18956832","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321026","display_name":"Ministry of Earth Sciences","ror":"https://ror.org/013cf5k59"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W65738273","https://openalex.org/W1972266664","https://openalex.org/W1973826313","https://openalex.org/W1975137637","https://openalex.org/W2003708609","https://openalex.org/W2005685204","https://openalex.org/W2015381630","https://openalex.org/W2016381774","https://openalex.org/W2045802827","https://openalex.org/W2049615701","https://openalex.org/W2059556517","https://openalex.org/W2082194907","https://openalex.org/W2089923519","https://openalex.org/W2096729078","https://openalex.org/W2100005623","https://openalex.org/W2110032189","https://openalex.org/W2156077095","https://openalex.org/W2177658341","https://openalex.org/W2197388599","https://openalex.org/W2204197091","https://openalex.org/W2792455800","https://openalex.org/W2951440056","https://openalex.org/W3022351671","https://openalex.org/W6630096803"],"related_works":["https://openalex.org/W2738670501","https://openalex.org/W1999419815","https://openalex.org/W2887903305","https://openalex.org/W2018628688","https://openalex.org/W3109833960","https://openalex.org/W2084985154","https://openalex.org/W2037775237","https://openalex.org/W3130298030","https://openalex.org/W1990374482","https://openalex.org/W3200375535"],"abstract_inverted_index":{"A":[0,171],"new":[1],"clustering":[2],"algorithm":[3,24,118,186],"was":[4,174],"developed":[5],"that":[6,82],"is":[7],"able":[8],"to":[9,20,56,78,86,119,128],"group":[10],"large":[11],"data":[12,27],"sets":[13],"with":[14,197],"more":[15],"than":[16],"100,000":[17],"molecules":[18],"according":[19],"their":[21],"chemotypes.":[22,80],"The":[23,185],"preclusters":[25],"a":[26,30,46,53,58,111,121],"set":[28],"using":[29],"fingerprint":[31],"version":[32],"of":[33,61,96,114,144,154,166,181,191],"the":[34,42,94,99,106,115,139,145,159,164,177,189],"hierarchical":[35,116,123],"k-means":[36,117],"algorithm.":[37],"Chemotypes":[38],"are":[39,76,89,108,126,149],"extracted":[40],"from":[41,102],"terminal":[43],"clusters":[44],"via":[45],"maximum":[47],"common":[48],"substructure":[49],"approach.":[50],"Molecules":[51],"forming":[52],"chemotype":[54,88,104,178],"have":[55],"share":[57],"predefined":[59],"number":[60],"rings,":[62],"atoms,":[63],"and":[64,74,105,162,193],"non-carbon":[65],"heavy":[66],"atoms.":[67],"In":[68],"an":[69,129],"iterative":[70],"procedure,":[71],"similar":[72],"chemotypes":[73,153],"singletons":[75,107],"fused":[77],"larger":[79],"Singletons":[81],"cannot":[83],"be":[84],"assigned":[85],"any":[87],"then":[90],"grouped":[91],"based":[92],"on":[93,176],"proportion":[95],"overlap":[97],"between":[98],"molecules.":[100,146],"Representatives":[101],"each":[103,182],"used":[109],"in":[110,158],"second":[112],"round":[113],"provide":[120],"final":[122],"grouping.":[124],"Results":[125],"reported":[127],"interactive":[130],"graphical":[131],"user":[132],"interface":[133],"which":[134],"allows":[135],"initial":[136],"insights":[137],"about":[138],"structure":[140],"activity":[141],"relationship":[142],"(SAR)":[143],"Example":[147],"applications":[148],"shown":[150],"for":[151,163],"two":[152],"reverse":[155],"transcriptase":[156],"inhibitors":[157],"MDDR":[160],"database":[161],"evaluation":[165],"descriptor-based":[167],"similarity":[168],"searching":[169],"routines.":[170],"special":[172],"focus":[173],"laid":[175],"hopping":[179],"potential":[180],"individual":[183],"routine.":[184],"will":[187],"allow":[188],"analysis":[190],"high-throughput":[192],"virtual":[194],"screening":[195],"results":[196],"improved":[198],"quality.":[199]},"counts_by_year":[{"year":2024,"cited_by_count":10},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}