{"id":"https://openalex.org/W2794662645","doi":"https://doi.org/10.25781/kaust-uy8y6","title":"Novel Data Mining Methods for Virtual Screening of Biological Active Chemical Compounds","display_name":"Novel Data Mining Methods for Virtual Screening of Biological Active Chemical Compounds","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2794662645","doi":"https://doi.org/10.25781/kaust-uy8y6","mag":"2794662645"},"language":"en","primary_location":{"id":"pmh:oai:repository.kaust.edu.sa:10754/621873","is_oa":true,"landing_page_url":"http://hdl.handle.net/10754/621873","pdf_url":"http://hdl.handle.net/10754/621873","source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10754/621873","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074769323","display_name":"Othman Soufan","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Soufan, Othman","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5074769323"],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9424999952316284,"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":0.9424999952316284,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/virtual-screening","display_name":"Virtual screening","score":0.6200003623962402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4445103704929352},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.40127256512641907},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3976069390773773},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.391928106546402},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.3237662613391876},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.25799596309661865},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.2222362756729126},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.20533233880996704}],"concepts":[{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.6200003623962402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4445103704929352},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.40127256512641907},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3976069390773773},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.391928106546402},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3237662613391876},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.25799596309661865},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2222362756729126},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.20533233880996704}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:repository.kaust.edu.sa:10754/621873","is_oa":true,"landing_page_url":"http://hdl.handle.net/10754/621873","pdf_url":"http://hdl.handle.net/10754/621873","source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},{"id":"mag:2794662645","is_oa":false,"landing_page_url":"https://repository.kaust.edu.sa/handle/10754/621873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null},{"id":"doi:10.25781/kaust-uy8y6","is_oa":true,"landing_page_url":"https://doi.org/10.25781/kaust-uy8y6","pdf_url":null,"source":{"id":"https://openalex.org/S7407051967","display_name":"KAUST Research Repository","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"pmh:oai:repository.kaust.edu.sa:10754/621873","is_oa":true,"landing_page_url":"http://hdl.handle.net/10754/621873","pdf_url":"http://hdl.handle.net/10754/621873","source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2794662645.pdf","grobid_xml":"https://content.openalex.org/works/W2794662645.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1485182514","https://openalex.org/W1982769922","https://openalex.org/W2073963385","https://openalex.org/W2761625430","https://openalex.org/W2130594592","https://openalex.org/W1747041133","https://openalex.org/W2912035568","https://openalex.org/W1996975182","https://openalex.org/W2162424885","https://openalex.org/W2156732033","https://openalex.org/W198046168","https://openalex.org/W2766231741","https://openalex.org/W2020195882","https://openalex.org/W2612690748","https://openalex.org/W2903559008","https://openalex.org/W2781735430","https://openalex.org/W2751625431","https://openalex.org/W2770640132","https://openalex.org/W3127375172","https://openalex.org/W2964842136"],"abstract_inverted_index":{"Drug":[0],"discovery":[1],"is":[2,29,75,263],"a":[3,17,21,36,52,59,66,142,162,176,237,250,254],"process":[4,28],"that":[5,103,245],"takes":[6],"many":[7],"years":[8],"and":[9,90,134],"hundreds":[10],"of":[11,13,25,38,71,131,137,170,212,215,229,249],"millions":[12,228],"dollars":[14],"to":[15,34,116,140,181,256,265],"reveal":[16],"confident":[18],"conclusion":[19],"about":[20],"specific":[22,191],"treatment.":[23,46],"Part":[24],"this":[26,56,96,168],"sophisticated":[27],"based":[30,208],"on":[31,209],"preliminary":[32],"investigations":[33],"suggest":[35,174],"set":[37],"chemical":[39,143],"compounds":[40],"as":[41,62,253],"candidate":[42,185],"drugs":[43],"for":[44,111,145,156,204,236],"the":[45,82,100,129,260],"Computational":[47],"resources":[48,74],"have":[49],"been":[50],"playing":[51],"significant":[53,267],"role":[54],"in":[55,77,88],"part":[57],"through":[58,226],"step":[60,255],"known":[61],"virtual":[63,112,120,157,206,224],"screening.":[64,113],"From":[65],"data":[67,73,89,106,123,154],"mining":[68,107],"perspective,":[69],"availability":[70],"rich":[72],"key":[76],"training":[78],"prediction":[79],"models.":[80],"Yet,":[81],"difficulties":[83],"imposed":[84],"by":[85,127,161],"big":[86],"expansion":[87],"its":[91],"dimensionality":[92],"are":[93,109,159,196,201],"inevitable.":[94],"In":[95,114],"thesis,":[97],"I":[98,125,173,218],"address":[99],"main":[101],"challenges":[102],"come":[104],"when":[105],"techniques":[108],"used":[110,155],"order":[115],"achieve":[117,266],"an":[118,146],"efficient":[119],"screening":[121,148,151,158,207,225],"using":[122,175],"mining,":[124],"start":[126],"addressing":[128],"problem":[130,169],"feature":[132],"selection":[133],"provide":[135],"analysis":[136],"best":[138],"ways":[139],"describe":[141],"compound":[144],"enhanced":[147],"performance.":[149],"High-throughput":[150],"(HTS)":[152],"assays":[153],"characterized":[160],"great":[163],"class":[164,171],"imbalance.":[165],"To":[166],"handle":[167],"imbalance,":[172],"novel":[177,241],"algorithm":[178],"called":[179,243],"DRAMOTE":[180],"narrow":[182],"down":[183],"promising":[184],"chemicals":[186],"aimed":[187],"at":[188],"interaction":[189,230],"with":[190],"molecular":[192],"targets":[193],"before":[194],"they":[195],"experimentally":[197],"evaluated.":[198],"Existing":[199],"works":[200],"mostly":[202],"proposed":[203],"small-scale":[205],"making":[210],"use":[211],"few":[213],"thousands":[214],"interactions.":[216],"Thus,":[217],"propose":[219],"enabling":[220],"large-scale":[221],"(or":[222],"big)":[223],"learning":[227,248],"while":[231],"exploiting":[232],"any":[233],"relevant":[234],"dependency":[235,258],"better":[238],"accuracy.":[239],"A":[240],"solution":[242],"DRABAL":[244],"incorporates":[246],"structure":[247],"Bayesian":[251],"Network":[252],"model":[257],"between":[259],"HTS":[261],"assays,":[262],"showed":[264],"improvements":[268],"over":[269],"existing":[270],"state-of-the-art":[271],"approaches.":[272]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}