{"id":"https://openalex.org/W3202136137","doi":"https://doi.org/10.1093/bioinformatics/btab659","title":"Accelerating Big Data Analysis through LASSO-Random Forest Algorithm in QSAR Studies","display_name":"Accelerating Big Data Analysis through LASSO-Random Forest Algorithm in QSAR Studies","publication_year":2021,"publication_date":"2021-09-30","ids":{"openalex":"https://openalex.org/W3202136137","doi":"https://doi.org/10.1093/bioinformatics/btab659","mag":"3202136137","pmid":"https://pubmed.ncbi.nlm.nih.gov/34979024"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab659","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab659","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","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/A5078121236","display_name":"Fahimeh Motamedi","orcid":null},"institutions":[{"id":"https://openalex.org/I114982161","display_name":"Isfahan University of Medical Sciences","ror":"https://ror.org/04waqzz56","country_code":"IR","type":"education","lineage":["https://openalex.org/I114982161"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Fahimeh Motamedi","raw_affiliation_strings":["Department of Bioinformatics and Systems Biology, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences , Isfahan 8174673461, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioinformatics and Systems Biology, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences , Isfahan 8174673461, Iran","institution_ids":["https://openalex.org/I114982161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037673215","display_name":"Horacio P\u00e9rez\u2010S\u00e1nchez","orcid":"https://orcid.org/0000-0003-4468-7898"},"institutions":[{"id":"https://openalex.org/I68763199","display_name":"Universidad Cat\u00f3lica de Murcia","ror":"https://ror.org/05b1rsv17","country_code":"ES","type":"education","lineage":["https://openalex.org/I68763199"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Horacio P\u00e9rez-S\u00e1nchez","raw_affiliation_strings":["Structural Bioinformatics and High Performance Computing Reseach Group (BIO-HPC), Computer Engineering Department, UCAM Universidad Cat\u00f3lica de Murcia , Murcia E30107, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Structural Bioinformatics and High Performance Computing Reseach Group (BIO-HPC), Computer Engineering Department, UCAM Universidad Cat\u00f3lica de Murcia , Murcia E30107, Spain","institution_ids":["https://openalex.org/I68763199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042724473","display_name":"Alireza Mehridehnavi","orcid":"https://orcid.org/0000-0002-7964-0478"},"institutions":[{"id":"https://openalex.org/I114982161","display_name":"Isfahan University of Medical Sciences","ror":"https://ror.org/04waqzz56","country_code":"IR","type":"education","lineage":["https://openalex.org/I114982161"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Alireza Mehridehnavi","raw_affiliation_strings":["Department of Bioinformatics and Systems Biology, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences , Isfahan 8174673461, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioinformatics and Systems Biology, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences , Isfahan 8174673461, Iran","institution_ids":["https://openalex.org/I114982161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060103268","display_name":"Afshin Fassihi","orcid":"https://orcid.org/0000-0002-8042-5986"},"institutions":[{"id":"https://openalex.org/I114982161","display_name":"Isfahan University of Medical Sciences","ror":"https://ror.org/04waqzz56","country_code":"IR","type":"education","lineage":["https://openalex.org/I114982161"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Afshin Fassihi","raw_affiliation_strings":["Department of Medicinal Chemistry, School of Pharmacology and Pharmaceutical Sciences, Isfahan University of Medical Sciences , Isfahan 8174673461, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicinal Chemistry, School of Pharmacology and Pharmaceutical Sciences, Isfahan University of Medical Sciences , Isfahan 8174673461, Iran","institution_ids":["https://openalex.org/I114982161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101531041","display_name":"Fahimeh Ghasemi","orcid":"https://orcid.org/0000-0001-9333-4699"},"institutions":[{"id":"https://openalex.org/I114982161","display_name":"Isfahan University of Medical Sciences","ror":"https://ror.org/04waqzz56","country_code":"IR","type":"education","lineage":["https://openalex.org/I114982161"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Fahimeh Ghasemi","raw_affiliation_strings":["Biosensor Research Centre, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences , Isfahan 8174673461, Iran","Department of Bioinformatics and Systems Biology, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences , Isfahan 8174673461, Iran"],"raw_orcid":"https://orcid.org/0000-0001-9333-4699","affiliations":[{"raw_affiliation_string":"Biosensor Research Centre, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences , Isfahan 8174673461, Iran","institution_ids":["https://openalex.org/I114982161"]},{"raw_affiliation_string":"Department of Bioinformatics and Systems Biology, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences , Isfahan 8174673461, Iran","institution_ids":["https://openalex.org/I114982161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101531041"],"corresponding_institution_ids":["https://openalex.org/I114982161"],"apc_list":{"value":3478,"currency":"USD","value_usd":3478},"apc_paid":null,"fwci":6.9616,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.97495528,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":"38","issue":"2","first_page":"469","last_page":"475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9623000025749207,"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":0.9623000025749207,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.02239999920129776,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.0017000000225380063,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.8719570636749268},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7461773157119751},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.7376864552497864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6865410208702087},{"id":"https://openalex.org/keywords/lasso","display_name":"Lasso (programming language)","score":0.6771190166473389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5877102017402649},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5738682746887207},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5445430874824524},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5144370198249817},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.44278404116630554},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4170231521129608},{"id":"https://openalex.org/keywords/applicability-domain","display_name":"Applicability domain","score":0.4157855808734894},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3964829742908478},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39436906576156616}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.8719570636749268},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7461773157119751},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.7376864552497864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6865410208702087},{"id":"https://openalex.org/C37616216","wikidata":"https://www.wikidata.org/wiki/Q3218363","display_name":"Lasso (programming language)","level":2,"score":0.6771190166473389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5877102017402649},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5738682746887207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5445430874824524},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5144370198249817},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.44278404116630554},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4170231521129608},{"id":"https://openalex.org/C107908354","wikidata":"https://www.wikidata.org/wiki/Q4781456","display_name":"Applicability domain","level":3,"score":0.4157855808734894},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3964829742908478},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39436906576156616},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000078332","descriptor_name":"Data Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000078332","descriptor_name":"Data Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000078332","descriptor_name":"Data Analysis","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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btab659","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab659","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34979024","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34979024","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":"Bioinformatics (Oxford, England)","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.7200000286102295,"display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G4097890777","display_name":null,"funder_award_id":"198111","funder_id":"https://openalex.org/F4320322245","funder_display_name":"Isfahan University of Medical Sciences"},{"id":"https://openalex.org/G7094668729","display_name":null,"funder_award_id":"298219","funder_id":"https://openalex.org/F4320322245","funder_display_name":"Isfahan University of Medical Sciences"},{"id":"https://openalex.org/G7778575999","display_name":null,"funder_award_id":"297174","funder_id":"https://openalex.org/F4320322245","funder_display_name":"Isfahan University of Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320322245","display_name":"Isfahan University of Medical Sciences","ror":"https://ror.org/04waqzz56"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1700449338","https://openalex.org/W1947025626","https://openalex.org/W2020078097","https://openalex.org/W2030122595","https://openalex.org/W2033757486","https://openalex.org/W2081320283","https://openalex.org/W2129108548","https://openalex.org/W2600746833","https://openalex.org/W2766178498","https://openalex.org/W2770182351","https://openalex.org/W2795068716","https://openalex.org/W2896072522","https://openalex.org/W2911535432","https://openalex.org/W2912882859","https://openalex.org/W2924122678","https://openalex.org/W2965320224","https://openalex.org/W2967649043","https://openalex.org/W3019944201","https://openalex.org/W3185309216","https://openalex.org/W4232714830","https://openalex.org/W6758409184"],"related_works":["https://openalex.org/W4361806667","https://openalex.org/W2746158299","https://openalex.org/W1969085205","https://openalex.org/W1977382278","https://openalex.org/W2090257471","https://openalex.org/W1970841929","https://openalex.org/W3005120176","https://openalex.org/W2309296013","https://openalex.org/W2985099987","https://openalex.org/W2055287694"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,227],"aim":[2,162],"of":[3,24,52,64,68,99,120,129,139,157,163,170,194,205,249],"quantitative":[4],"structure-activity":[5],"prediction":[6,63,165,200],"(QSAR)":[7],"studies":[8,56],"is":[9,96,115,136,149],"to":[10,34,47,83,124,189,238],"identify":[11,35],"novel":[12],"drug-like":[13],"molecules":[14],"that":[15,153,230],"can":[16],"be":[17],"suggested":[18,207],"as":[19,71,91],"lead":[20],"compounds":[21],"by":[22,39],"means":[23],"two":[25],"approaches,":[26],"which":[27],"are":[28,256],"discussed":[29],"in":[30,61,87,110],"this":[31],"article.":[32],"First,":[33],"appropriate":[36],"molecular":[37,108,158,192],"descriptors":[38,109,159],"focusing":[40],"on":[41],"one":[42],"feature-selection":[43],"algorithms;":[44],"and":[45,143,167,173,179,202,222,243],"second":[46],"predict":[48,190],"the":[49,62,105,111,121,127,130,137,161,191,199,206,212,250],"biological":[50],"activities":[51,193],"designed":[53],"compounds.":[54,197],"Recent":[55],"have":[57],"shown":[58],"increased":[59],"interest":[60],"a":[65,150,155,184],"huge":[66],"number":[67],"molecules,":[69],"known":[70],"Big":[72],"Data,":[73],"using":[74],"deep":[75,100,219,223],"learning":[76,101],"models.":[77,102],"However,":[78],"despite":[79],"all":[80],"these":[81],"efforts":[82],"solve":[84],"critical":[85],"challenges":[86],"QSAR":[88],"models,":[89],"such":[90],"over-fitting,":[92],"massive":[93],"processing":[94],"procedures,":[95],"major":[97],"shortcomings":[98],"Hence,":[103],"finding":[104],"most":[106],"effective":[107],"shortest":[112],"possible":[113],"time":[114,204,242],"an":[116],"ongoing":[117],"task.":[118],"One":[119],"successful":[122],"methods":[123],"speed":[125],"up":[126],"extraction":[128],"best":[131],"features":[132],"from":[133],"big":[134],"datasets":[135],"use":[138],"least":[140],"absolute":[141],"shrinkage":[142],"selection":[144],"operator":[145],"(LASSO).":[146],"This":[147],"algorithm":[148],"regression":[151],"model":[152,208,244],"selects":[154],"subset":[156],"with":[160,211],"enhancing":[164],"accuracy":[166,248],"interpretability":[168],"because":[169],"removing":[171],"inappropriate":[172],"irrelevant":[174],"features.":[175],"RESULTS:":[176],"To":[177],"implement":[178],"test":[180],"our":[181],"proposed":[182],"model,":[183],"random":[185,220],"forest":[186,221,236],"was":[187],"built":[188],"Kaggle":[195],"competition":[196],"Finally,":[198],"results":[201,228],"computation":[203],"were":[209],"compared":[210],"other":[213],"well-known":[214],"algorithms,":[215],"i.e.":[216],"Boruta-random":[217],"forest,":[218],"belief":[224],"network":[225],"model.":[226],"revealed":[229],"improving":[231],"output":[232],"correlation":[233],"through":[234],"LASSO-random":[235],"leads":[237],"appreciably":[239],"reduced":[240],"implementation":[241],"complexity,":[245],"while":[246],"maintaining":[247],"predictions.":[251],"SUPPLEMENTARY":[252],"INFORMATION:":[253],"Supplementary":[254],"data":[255],"available":[257],"at":[258],"Bioinformatics":[259],"online.":[260]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-09-03T10:48:47.769340","created_date":"2025-10-10T00:00:00"}
