{"id":"https://openalex.org/W2062145093","doi":"https://doi.org/10.1021/ci700350n","title":"How To Winnow Actives from Inactives:\u2009 Introducing Molecular Orthogonal Sparse Bigrams (MOSBs) and Multiclass Winnow","display_name":"How To Winnow Actives from Inactives:\u2009 Introducing Molecular Orthogonal Sparse Bigrams (MOSBs) and Multiclass Winnow","publication_year":2008,"publication_date":"2008-01-26","ids":{"openalex":"https://openalex.org/W2062145093","doi":"https://doi.org/10.1021/ci700350n","mag":"2062145093","pmid":"https://pubmed.ncbi.nlm.nih.gov/18220378"},"language":"en","primary_location":{"id":"doi:10.1021/ci700350n","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci700350n","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/A5059360993","display_name":"Florian Nigsch","orcid":"https://orcid.org/0000-0002-2919-8749"},"institutions":[{"id":"https://openalex.org/I1342131907","display_name":"Unilever (United Kingdom)","ror":"https://ror.org/05n8ah907","country_code":"GB","type":"company","lineage":["https://openalex.org/I1342131907"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Florian Nigsch","raw_affiliation_strings":["Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, United Kingdom","Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, United Kingdom,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, United Kingdom","institution_ids":["https://openalex.org/I1342131907","https://openalex.org/I241749"]},{"raw_affiliation_string":"Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, United Kingdom,","institution_ids":["https://openalex.org/I1342131907","https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046050351","display_name":"John B. O. Mitchell","orcid":"https://orcid.org/0000-0002-0379-6097"},"institutions":[{"id":"https://openalex.org/I1342131907","display_name":"Unilever (United Kingdom)","ror":"https://ror.org/05n8ah907","country_code":"GB","type":"company","lineage":["https://openalex.org/I1342131907"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John B. O. Mitchell","raw_affiliation_strings":["Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, United Kingdom","Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, United Kingdom,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, United Kingdom","institution_ids":["https://openalex.org/I1342131907","https://openalex.org/I241749"]},{"raw_affiliation_string":"Unilever Centre for Molecular Science Informatics, Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, United Kingdom,","institution_ids":["https://openalex.org/I1342131907","https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3268,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93964512,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"48","issue":"2","first_page":"306","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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":1.0,"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":0.9745000004768372,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9671000242233276,"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/bigram","display_name":"Bigram","score":0.8774330019950867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7583585977554321},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.6144927144050598},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5678694248199463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5455013513565063},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5406605005264282},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5364153385162354},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4002126455307007},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3644103705883026},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3583011031150818},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09455734491348267}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.8774330019950867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583585977554321},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.6144927144050598},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5678694248199463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5455013513565063},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5406605005264282},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5364153385162354},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4002126455307007},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3644103705883026},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3583011031150818},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09455734491348267},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1021/ci700350n","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci700350n","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:18220378","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18220378","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":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1972860770","https://openalex.org/W1973420497","https://openalex.org/W1978163942","https://openalex.org/W1980069772","https://openalex.org/W1992908416","https://openalex.org/W2020756525","https://openalex.org/W2034484539","https://openalex.org/W2052943632","https://openalex.org/W2068337719","https://openalex.org/W2092581985","https://openalex.org/W2093896943","https://openalex.org/W2112912103","https://openalex.org/W2135835957","https://openalex.org/W2135860083","https://openalex.org/W2208175234","https://openalex.org/W2620858438","https://openalex.org/W2999905431"],"related_works":["https://openalex.org/W3173084154","https://openalex.org/W2334448532","https://openalex.org/W2982021180","https://openalex.org/W2131563376","https://openalex.org/W2251497876","https://openalex.org/W2241081188","https://openalex.org/W159278796","https://openalex.org/W2128567707","https://openalex.org/W4327499987","https://openalex.org/W2011383762"],"abstract_inverted_index":{"In":[0],"the":[1,6,28,42,46,55,63,96,102,126,144,148,157,167,230,249],"present":[2],"paper":[3],"we":[4,61,113,134,165,247],"combine":[5],"Winnow":[7,23,64],"algorithm":[8,65],"and":[9,94,120,185,226,236],"an":[10],"advanced":[11],"scheme":[12],"for":[13,19,45],"feature":[14,231],"generation":[15],"into":[16,251],"a":[17,69,76,83,136,222,252],"tool":[18],"multiclass":[20],"classification.":[21],"The":[22],"algorithm,":[24],"specifically":[25],"designed":[26],"in":[27,66,87,153,175,196,203,210],"late":[29],"1980s":[30],"to":[31,101,125,146,182,200,219,238],"work":[32],"well":[33],"with":[34,68,162,242,267],"high-dimensional":[35],"data,":[36],"by":[37],"design":[38],"ignores":[39],"most":[40],"of":[41,48,57,78,98,104,128,130,139,159,171,212,254],"irrelevant":[43],"features":[44,60,74],"scoring":[47],"each":[49],"single":[50],"training/test":[51],"case.":[52],"To":[53,155],"augment":[54],"pool":[56,253],"available":[58],"molecular":[59,108],"use":[62,97,166],"conjunction":[67],"process":[70],"that":[71,99,187,261],"creates":[72],"additional":[73],"from":[75],"set":[77,152,170],"given":[79],"ones.":[80],"We":[81,178],"adapt":[82],"technique":[84],"formerly":[85],"employed":[86],"text":[88],"classification":[89,129,197],"termed":[90],"\"orthogonal":[91],"sparse":[92,117],"bigrams\"":[93,118],"extend":[95],"method":[100,161,181,189,263],"domain":[103],"cheminformatics.":[105],"Using":[106],"circular":[107],"fingerprints":[109],"as":[110],"initial":[111],"features,":[112],"create":[114],"\"molecular":[115],"orthogonal":[116],"(MOSBs)":[119],"report":[121],"their":[122],"successful":[123],"application":[124],"task":[127],"bioactive":[131],"molecules.":[132,257],"Additionally,":[133],"introduce":[135],"memory-efficient":[137],"way":[138],"bagging":[140],"individual":[141],"classifiers,":[142],"avoiding":[143],"need":[145],"hold":[147],"complete":[149],"training":[150],"data":[151,169,244],"memory.":[154],"compare":[156,179],"performance":[158],"our":[160,180,188],"published":[163],"results,":[164],"Hert":[168],"8293":[172],"active":[173],"molecules":[174],"11":[176],"classes.":[177],"Random":[183],"Forest":[184],"find":[186],"not":[190],"only":[191],"is":[192,217,259],"comparable":[193],"or":[194],"better":[195],"accuracy":[198],"(up":[199],"50%":[201],"higher":[202,209],"MCC":[204],"[Matthews":[205],"correlation":[206],"coefficient],":[207],"98%":[208],"fraction":[211],"correct":[213],"predictions)":[214],"but":[215],"also":[216],"quicker":[218],"train":[220],"(by":[221],"factor":[223],"between":[224],"2":[225],"18,":[227],"depending":[228],"on":[229],"generation),":[232],"more":[233,240],"memory":[234],"efficient,":[235],"able":[237],"cope":[239],"easily":[241],"large":[243],"sets":[245],"when":[246],"seeded":[248],"actives":[250],"94290":[255],"inactive":[256],"It":[258],"shown":[260],"this":[262],"can":[264],"be":[265],"used":[266],"different":[268],"fingerprints.":[269]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}