{"id":"https://openalex.org/W2111498093","doi":"https://doi.org/10.1186/1758-2946-5-s1-p50","title":"Using graph-based consensus clustering for combining K-means clustering of heterogeneous chemical structures","display_name":"Using graph-based consensus clustering for combining K-means clustering of heterogeneous chemical structures","publication_year":2013,"publication_date":"2013-03-01","ids":{"openalex":"https://openalex.org/W2111498093","doi":"https://doi.org/10.1186/1758-2946-5-s1-p50","mag":"2111498093"},"language":"en","primary_location":{"id":"doi:10.1186/1758-2946-5-s1-p50","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-s1-p50","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-5-S1-P50","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-5-S1-P50","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018312503","display_name":"Faisal Saeed","orcid":"https://orcid.org/0000-0002-2822-1708"},"institutions":[{"id":"https://openalex.org/I4576418","display_name":"University of Technology Malaysia","ror":"https://ror.org/026w31v75","country_code":"MY","type":"education","lineage":["https://openalex.org/I4576418"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Faisal Saeed","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, Universiti Teknologi Malaysia, Johor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, Universiti Teknologi Malaysia, Johor, Malaysia","institution_ids":["https://openalex.org/I4576418"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012641332","display_name":"Naomie Salim","orcid":"https://orcid.org/0000-0001-8509-3055"},"institutions":[{"id":"https://openalex.org/I4576418","display_name":"University of Technology Malaysia","ror":"https://ror.org/026w31v75","country_code":"MY","type":"education","lineage":["https://openalex.org/I4576418"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Naomie Salim","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, Universiti Teknologi Malaysia, Johor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, Universiti Teknologi Malaysia, Johor, Malaysia","institution_ids":["https://openalex.org/I4576418"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011865103","display_name":"Ammar Abdo","orcid":"https://orcid.org/0000-0003-4569-2744"},"institutions":[{"id":"https://openalex.org/I4576418","display_name":"University of Technology Malaysia","ror":"https://ror.org/026w31v75","country_code":"MY","type":"education","lineage":["https://openalex.org/I4576418"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ammar Abdo","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, Universiti Teknologi Malaysia, Johor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, Universiti Teknologi Malaysia, Johor, Malaysia","institution_ids":["https://openalex.org/I4576418"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008179027","display_name":"Hentabli Hamza","orcid":"https://orcid.org/0000-0002-9530-2815"},"institutions":[{"id":"https://openalex.org/I4576418","display_name":"University of Technology Malaysia","ror":"https://ror.org/026w31v75","country_code":"MY","type":"education","lineage":["https://openalex.org/I4576418"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Hentabli Hamza","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, Universiti Teknologi Malaysia, Johor, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, Universiti Teknologi Malaysia, Johor, Malaysia","institution_ids":["https://openalex.org/I4576418"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5018312503"],"corresponding_institution_ids":["https://openalex.org/I4576418"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":0.0,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.13082846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":"S1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9926000237464905,"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":0.9836999773979187,"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/cluster-analysis","display_name":"Cluster analysis","score":0.821831226348877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6738237142562866},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.645564079284668},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.5742003321647644},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4668023884296417},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4451950192451477},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.3224589228630066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30027610063552856},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.15914872288703918},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.10818120837211609}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.821831226348877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6738237142562866},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.645564079284668},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.5742003321647644},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4668023884296417},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4451950192451477},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.3224589228630066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30027610063552856},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.15914872288703918},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.10818120837211609},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/1758-2946-5-s1-p50","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-s1-p50","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-5-S1-P50","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:2605471","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3606194","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1758-2946-5-s1-p50","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-s1-p50","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-5-S1-P50","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2111498093.pdf","grobid_xml":"https://content.openalex.org/works/W2111498093.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1974041968","https://openalex.org/W1991493796","https://openalex.org/W1992418208","https://openalex.org/W2030087063","https://openalex.org/W2103420095","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2588528840","https://openalex.org/W2199594781","https://openalex.org/W2767663474","https://openalex.org/W2945382830","https://openalex.org/W4224807364","https://openalex.org/W2744974730","https://openalex.org/W2596632494","https://openalex.org/W2535986621","https://openalex.org/W3192757256","https://openalex.org/W4388110928"],"abstract_inverted_index":{"Consensus":[0],"clustering":[1,20,30,53,77,137,305,309,400,412,426,436,457,468,493,504,523,542,556,578,611,620,674,687,709,717,723,733,740],"methods":[2,173,413,710],"are":[3,147,155,259,277,381,543,561,579,649],"motivated":[4],"by":[5,31,149,190,197,319,533,591,741],"the":[6,25,33,58,70,75,104,106,112,136,169,172,208,214,219,225,233,241,249,265,275,284,288,297,307,355,364,384,389,395,446,454,464,489,525,536,582,593,622,677,721,736,743,750],"success":[7],"of":[8,27,39,100,171,210,221,235,243,251,267,322,329,334,378,388,397,410,422,425,427,435,437,445,456,458,466,477,491,521,529,540,547,554,566,571,602,605,627,645,647,663,679,685,700,738],"combining":[9],"multiple":[10,320],"classifiers":[11],"in":[12,66,213,224,237,245,253,337,485,573,698],"many":[13,121],"areas.":[14],"In":[15,473],"this":[16,43,338],"paper,":[17],"graph-based":[18,672,731],"consensus":[19,365,411,478,492,503,522,528,541,555,577,585,610,619,673,686,708,732],"is":[21,54,216,293,340,369,513,633,656,688],"used":[22,90,119,145],"to":[23,60,174,295,346,362,450,487,581,595,630,666,720,748],"improve":[24,676,735],"quality":[26,183,289,737],"chemical":[28,80,680,759],"compound":[29],"enhancing":[32],"robustness,":[34],"novelty,":[35],"consistency":[36],"and":[37,69,158,263,281,375,403,461,507,597,639,694,715,718],"stability":[38],"individual":[40,304,567,606,637,739],"clusterings.":[41,568],"For":[42,103,135,642],"purpose,":[44],"Hyper-Graph":[45],"Partitioning":[46],"Algorithm":[47],"(HGPA)":[48],"[1],":[49],"was":[50,109,188],"applied.":[51],"The":[52,79,126,270,332,406,498,519,552,569,599,615,683,725],"evaluated":[55,166],"based":[56,167],"on":[57,168,658],"ability":[59],"separate":[61,175],"actives":[62,176,236,252,276],"from":[63,111,177,283,545],"inactives":[64,244],"molecules":[65,179,212,223,646],"each":[67,325,372,415,481],"cluster":[68,201,205,215,330],"results":[71,164,298,447,499,559,616],"were":[72,165,358,483],"compared":[73,301,608],"with":[74,302,326,350,494,609,624,661,752],"Ward's":[76,303,462],"method.":[78,641],"dataset":[81,107,116,127,226,399,530],"MDL":[82,93],"Drug":[83,94],"Data":[84,95],"Report":[85,96],"(MDDR)":[86,97],"database":[87,98],"has":[88,117,316,417],"been":[89,118,317,418],"for":[91,120,206,311,371,414,420,470,480,576,612,755],"experiments.\r\n\r\nThe":[92],"consists":[99],"102516":[101],"molecules.":[102,286],"experiments,":[105,138],"DS1":[108,648],"chosen":[110],"MDDR":[113,398,430,440,459],"database.":[114],"This":[115,367],"virtual":[122],"screening":[123],"experiments":[124,726],"[2-4].":[125],"DS1contains":[128],"10":[129],"heterogeneous":[130],"activity":[131,386],"classes":[132,387],"(8568":[133],"molecules).":[134],"two":[139],"2D":[140],"fingerprint":[141,373,482,660],"descriptors":[142],"will":[143,299],"be":[144,232,300,451],"which":[146,187,207,531,560,632],"developed":[148],"Scitegic's":[150],"Pipeline":[151],"Pilot":[152],"[5].":[153],"These":[154],"120-bit":[156],"ALOGP":[157,402,432,659,702],"1024-bit":[159],"extended":[160],"connectivity":[161],"fingerprints":[162],"(ECFP_4).\r\n\r\nThe":[163],"effectiveness":[170,396,455,490,678],"non-actives":[178],"using":[180,360,401,517,701,705,742],"QPI-":[181],"(for":[182],"partition":[184,290,621],"index)":[185],"measure,":[186],"devised":[189],"Varin":[191],"et":[192],"al.":[193],"[6].":[194],"As":[195],"defined":[196,294],"[7],":[198],"an":[199],"active":[200,211,222,238,246,261],"as":[202,227,651],"a":[203,228],"non-singleton":[204],"percentage":[209,220,626],"greater":[217],"than":[218,563,636],"whole.":[229],"Let":[230],"p":[231],"number":[234,242,250,266,333,662],"clusters,":[239,247],"q":[240],"r":[248],"inactive":[254,285],"clusters":[255,257,590,604,664],"(i.e.,":[256],"that":[258,501,618,671,730],"not":[260],"clusters)":[262],"s":[264],"singleton":[268,603,628],"actives.":[269],"high":[271,428,438],"value":[272,409],"occurs":[273],"when":[274,510,653],"clustered":[278,650],"tightly":[279],"together":[280],"separated":[282],"Then":[287],"index,":[291],"QPI,":[292],"be:\r\n\r\n\r\n\r\nQPI=pp+q+r+s\r\n\r\n(1)\r\n\r\n\r\n\r\nThen,":[296],"method,":[306,463],"standard":[308],"method":[310,469,655,697],"chemoinformatics":[312,471],"applications.\r\n\r\nThe":[313],"generation":[314],"process":[315,368],"done":[318,370],"run":[321,514],"K-means":[323,511,746],"algorithms,":[324],"random":[327],"initialization":[328],"centroids.":[331],"partitions":[335,357],"generated":[336,356],"step":[339],"ranged":[341],"between":[342,453],"n":[343,347,549],"=":[344,348,550],"5":[345],"50,":[349],"5-times":[351],"step.":[352],"Then,":[353],"all":[354],"combined":[359],"HGPA":[361,502],"obtain":[363],"partition.":[366],"(ALOGP":[374],"ECFP_4).\r\n\r\nThe":[376],"mean":[377],"QPI":[379,538,572],"values":[380,539,570],"averaged":[382],"over":[383],"ten":[385,475],"datasets.":[390,760],"Tables":[391],"\u200bTables1,1,":[392],"\u200b,22":[393],"show":[394,500,617],"ECFP_4":[404,442,534,706],"fingerprints.":[405,614],"best":[407,465,537],"PQI":[408],"column":[416],"bold-faced":[419],"ease":[421],"reference.\r\n\r\n\r\n\r\nTable":[423],"1\r\n\r\nEffectivenss":[424],"diverse":[429,439,758],"dataset:":[431,441],"Fingerprint.\r\n\r\n\r\n\r\n\r\n\r\nTable":[433],"2\r\n\r\nEffectivenss":[434],"Fingerprint.\r\n\r\n\r\n\r\nVisual":[443],"inspection":[444],"enables":[448],"comparisons":[449],"made":[452],"datasets":[460,575,623],"choice":[467],"applications.":[472],"addition,":[474],"times":[476,516],"clustering,":[479,586],"observed":[484],"order":[486],"study":[488],"different":[495],"ensemble":[496,751],"sizes.":[497],"gives":[505,557],"robust":[506,558],"novel":[508],"result":[509],"algorithm":[512],"20-50":[515],"ALOGP.":[518],"performance":[520,553,565,684],"outperforms":[524],"Wards'":[526,640,696],"method.\r\n\r\nFor":[527],"represented":[532],"fingerprint,":[535,707],"obtained":[544],"ensembles":[546],"size":[548,753],"20-50.":[551],"better":[562,635],"overall":[564],"both":[574,613,756],"close":[580,719],"Wards":[583,654,722],"method.\r\n\r\nThe":[584],"HGPA,":[587],"provide":[588,711],"stable":[589],"decreasing":[592],"sensitivity":[594],"noise":[596],"outliers.":[598],"average":[600,625],"percentages":[601],"clusterings":[607,638],"equal":[629,665],"zero,":[631],"much":[634],"example,":[643],"16.72%":[644],"singletons":[652],"applied":[657],"1000":[667],"clusters.\r\n\r\nFinally":[668],"we":[669],"conclude":[670],"can":[675,734],"compounds":[681],"clustering.":[682],"more":[689,712],"robust,":[690,713],"novel,":[691],"stable,":[692,714],"consistent,":[693],"out-perform":[695],"case":[699],"fingerprint.":[703],"By":[704],"consistent":[716],"results.":[724],"reported":[727],"here":[728],"suggest":[729],"efficient":[744],"algorithm,":[745,747],"generate":[749],"(20-50)":[754],"structurally":[757]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}