{"id":"https://openalex.org/W2081870567","doi":"https://doi.org/10.1109/bigdata.2014.7004386","title":"Predicting a biological response of molecules from their chemical properties using diverse and optimized ensembles of stochastic gradient boosting machine","display_name":"Predicting a biological response of molecules from their chemical properties using diverse and optimized ensembles of stochastic gradient boosting machine","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2081870567","doi":"https://doi.org/10.1109/bigdata.2014.7004386","mag":"2081870567"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","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/A5080757957","display_name":"Tarek Abdunabi","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tarek Abdunabi","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, Canada","University of Waterloo, 200 University Avenue West, Waterloo, Ontario Canada, N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, 200 University Avenue West, Waterloo, Ontario Canada, N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031048152","display_name":"Otman Basir","orcid":"https://orcid.org/0000-0002-6454-0538"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Otman Basir","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, Canada","University of Waterloo, 200 University Avenue West, Waterloo, Ontario Canada, N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, 200 University Avenue West, Waterloo, Ontario Canada, N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.13340173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"10","last_page":"17"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9930999875068665,"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/boosting","display_name":"Boosting (machine learning)","score":0.7587454915046692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7178497910499573},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.6570030450820923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6564954519271851},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5672531127929688},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5448117852210999},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47965696454048157},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.43251487612724304},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.41245320439338684},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22310668230056763},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.13694390654563904},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0917978286743164}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7587454915046692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178497910499573},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.6570030450820923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6564954519271851},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5672531127929688},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5448117852210999},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47965696454048157},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.43251487612724304},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.41245320439338684},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22310668230056763},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.13694390654563904},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0917978286743164},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2014.7004386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W190437827","https://openalex.org/W429766147","https://openalex.org/W1500895378","https://openalex.org/W1513618424","https://openalex.org/W1549412372","https://openalex.org/W1555148682","https://openalex.org/W1558918611","https://openalex.org/W1678356000","https://openalex.org/W1808644423","https://openalex.org/W1909101599","https://openalex.org/W1986760892","https://openalex.org/W1988790447","https://openalex.org/W2000432226","https://openalex.org/W2006617902","https://openalex.org/W2024046085","https://openalex.org/W2062930223","https://openalex.org/W2070493638","https://openalex.org/W2088794999","https://openalex.org/W2145541966","https://openalex.org/W2152120395","https://openalex.org/W2158698691","https://openalex.org/W2582743722","https://openalex.org/W2911964244","https://openalex.org/W4247439124","https://openalex.org/W4248437541","https://openalex.org/W6607693206","https://openalex.org/W6633604892"],"related_works":["https://openalex.org/W2967733078","https://openalex.org/W3204430031","https://openalex.org/W3137904399","https://openalex.org/W4310492845","https://openalex.org/W2885778889","https://openalex.org/W2766514146","https://openalex.org/W2885516856","https://openalex.org/W4289703016","https://openalex.org/W4310224730","https://openalex.org/W3094138326"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,17,40,51,162],"a":[3,22,122,143,154],"new":[4],"drug":[5],"largely":[6],"depends":[7],"on":[8],"trial":[9],"and":[10,29,42,114,146],"error.":[11],"It":[12],"typically":[13],"involves":[14],"synthesizing":[15],"thousands":[16],"compounds":[18],"that":[19,67,102],"finally":[20],"becomes":[21],"drug.":[23],"This":[24],"process":[25],"is":[26],"extremely":[27],"expensive":[28],"slow.":[30],"Therefore,":[31],"the":[32,37,44,55,109,132,136,159],"ability":[33],"to":[34,54,72],"accurately":[35],"predict":[36],"biological":[38],"activity":[39],"molecules,":[41],"understand":[43],"rationale":[45],"behind":[46],"those":[47],"predictions":[48],"would":[49],"be":[50,118],"great":[52],"value":[53],"pharmaceutical":[56],"industry.":[57],"Gradient":[58],"Boosting":[59],"Machines":[60],"(GBMs)":[61],"are":[62],"powerful":[63],"ensemble":[64],"learning":[65],"techniques":[66],"have":[68],"been":[69],"successfully":[70],"applied":[71],"several":[73],"low-dimensional":[74],"applications.":[75],"Despite":[76],"their":[77],"high":[78,87],"accuracy,":[79],"GBMs":[80,116],"suffer":[81],"from":[82],"major":[83],"drawbacks":[84],"such":[85],"as":[86],"memory-consumption.":[88],"In":[89,128],"this":[90],"paper,":[91],"using":[92,104,138],"real,":[93],"high-dimensional":[94],"(i.e.":[95],"1776":[96],"predictors)":[97],"molecules":[98],"dataset,":[99],"we":[100,152],"demonstrate":[101],"by":[103,130,135],"different":[105],"feature":[106],"selection/reduction":[107],"techniques,":[108,141],"computations":[110],"costs":[111],"for":[112],"building":[113],"tuning":[115],"can":[117],"substantially":[119],"reduced":[120],"at":[121],"slight":[123],"drop":[124],"in":[125],"prediction":[126,156],"accuracy.":[127],"addition,":[129],"fusing":[131],"decisions":[133],"made":[134],"ensembles":[137],"two":[139],"fusion":[140],"namely":[142],"majority":[144],"vote":[145],"an":[147],"optimized":[148],"feedforward":[149],"neural":[150],"network,":[151],"obtain":[153],"better":[155],"accuracy":[157,161],"than":[158],"individual":[160],"all":[163],"ensembles.":[164]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}