{"id":"https://openalex.org/W2200017991","doi":"https://doi.org/10.1021/ci010132r","title":"Reoptimization of MDL Keys for Use in Drug Discovery","display_name":"Reoptimization of MDL Keys for Use in Drug Discovery","publication_year":2002,"publication_date":"2002-09-14","ids":{"openalex":"https://openalex.org/W2200017991","doi":"https://doi.org/10.1021/ci010132r","mag":"2200017991","pmid":"https://pubmed.ncbi.nlm.nih.gov/12444722"},"language":"en","primary_location":{"id":"doi:10.1021/ci010132r","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci010132r","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"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 Computer Sciences","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/A5111760044","display_name":"Joseph L. Durant","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140678","display_name":"Information Systems Laboratories (United States)","ror":"https://ror.org/049k0qb06","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140678"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joseph L. Durant","raw_affiliation_strings":["MDL Information Systems, 14600 Catalina Street, San Leandro, California 94577"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MDL Information Systems, 14600 Catalina Street, San Leandro, California 94577","institution_ids":["https://openalex.org/I4210140678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011319169","display_name":"Burton A. Leland","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140678","display_name":"Information Systems Laboratories (United States)","ror":"https://ror.org/049k0qb06","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140678"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Burton A. Leland","raw_affiliation_strings":["MDL Information Systems, 14600 Catalina Street, San Leandro, California 94577"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MDL Information Systems, 14600 Catalina Street, San Leandro, California 94577","institution_ids":["https://openalex.org/I4210140678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062279956","display_name":"Douglas R. Henry","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140678","display_name":"Information Systems Laboratories (United States)","ror":"https://ror.org/049k0qb06","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140678"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas R. Henry","raw_affiliation_strings":["MDL Information Systems, 14600 Catalina Street, San Leandro, California 94577"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MDL Information Systems, 14600 Catalina Street, San Leandro, California 94577","institution_ids":["https://openalex.org/I4210140678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109935277","display_name":"James G. Nourse","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140678","display_name":"Information Systems Laboratories (United States)","ror":"https://ror.org/049k0qb06","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140678"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James G. Nourse","raw_affiliation_strings":["MDL Information Systems, 14600 Catalina Street, San Leandro, California 94577"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MDL Information Systems, 14600 Catalina Street, San Leandro, California 94577","institution_ids":["https://openalex.org/I4210140678"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5111760044"],"corresponding_institution_ids":["https://openalex.org/I4210140678"],"apc_list":null,"apc_paid":null,"fwci":8.4001,"has_fulltext":false,"cited_by_count":1896,"citation_normalized_percentile":{"value":0.98394387,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"42","issue":"6","first_page":"1273","last_page":"1280"},"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/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9864000082015991,"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/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.9746999740600586,"subfield":{"id":"https://openalex.org/subfields/2736","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7349124550819397},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.6655574440956116},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6108452677726746},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.5524948835372925},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5322957038879395},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5129625201225281},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.506550669670105},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.48571309447288513},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4802742004394531},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4514939486980438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41984355449676514},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.41330254077911377},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3930710256099701}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7349124550819397},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.6655574440956116},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6108452677726746},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.5524948835372925},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5322957038879395},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5129625201225281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.506550669670105},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48571309447288513},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4802742004394531},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4514939486980438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41984355449676514},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.41330254077911377},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3930710256099701},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"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":"D004353","descriptor_name":"Drug Evaluation, Preclinical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004353","descriptor_name":"Drug Evaluation, Preclinical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004353","descriptor_name":"Drug Evaluation, Preclinical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D005823","descriptor_name":"Genetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005823","descriptor_name":"Genetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005823","descriptor_name":"Genetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1021/ci010132r","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci010132r","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"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 Computer Sciences","raw_type":"journal-article"},{"id":"pmid:12444722","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12444722","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 computer sciences","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.89.4402","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.89.4402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.akosgmbh.de/pdf/Reoptimization_960_key.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W36613436","https://openalex.org/W1496416236","https://openalex.org/W1595350250","https://openalex.org/W1599439509","https://openalex.org/W1975293246","https://openalex.org/W1976853272","https://openalex.org/W1981214699","https://openalex.org/W1991848280","https://openalex.org/W1999688528","https://openalex.org/W2000942311","https://openalex.org/W2007953805","https://openalex.org/W2021083597","https://openalex.org/W2024431634","https://openalex.org/W2025410235","https://openalex.org/W2030317976","https://openalex.org/W2038692188","https://openalex.org/W2042338355","https://openalex.org/W2058444859","https://openalex.org/W2060350094","https://openalex.org/W2066345214","https://openalex.org/W2073579345","https://openalex.org/W2075711463","https://openalex.org/W2085126686","https://openalex.org/W2093265335","https://openalex.org/W2135732933","https://openalex.org/W2167395325","https://openalex.org/W2207540273","https://openalex.org/W2950067905","https://openalex.org/W2952213121","https://openalex.org/W2963372334","https://openalex.org/W3147295069","https://openalex.org/W4240181695","https://openalex.org/W4245602869","https://openalex.org/W4248107770"],"related_works":["https://openalex.org/W2489956408","https://openalex.org/W2095614499","https://openalex.org/W2037989911","https://openalex.org/W349256592","https://openalex.org/W2086694237","https://openalex.org/W4213307346","https://openalex.org/W2068210614","https://openalex.org/W2130372067","https://openalex.org/W32469337","https://openalex.org/W85229681"],"abstract_inverted_index":{"For":[0],"a":[1,51,77,88,141,159,306,318],"number":[2,142],"of":[3,37,55,100,107,112,121,125,143,197,201,204,209,214,224,230,243,247,267,291,297,309,336],"years":[4],"MDL":[5,38],"products":[6],"have":[7],"exposed":[8],"both":[9],"166":[10,64],"bit":[11,14,65,72],"and":[12,25,67,85,109,130,165,181,312],"960":[13,71],"keysets":[15,21,39,164,193,253,276,327],"based":[16],"on":[17,32,194,240,264],"2D":[18],"descriptors.":[19,145],"These":[20,146],"were":[22],"originally":[23],"constructed":[24,162],"optimized":[26,91,166],"for":[27,43,50,62,69,76,87,227],"substructure":[28],"searching.":[29],"We":[30,96,161,286],"report":[31],"improvements":[33],"in":[34,45,158,169,252,294],"the":[35,63,70,101,105,110,192,195,202,205,210,215,222,241,244,248,265,268,289,295,302,313,337],"performance":[36,49,168,226,303],"which":[40,254,277,331],"are":[41],"reoptimized":[42],"use":[44,290],"molecular":[46],"similarity.":[47],"Classification":[48],"test":[52],"data":[53],"set":[54,153],"957":[56],"compounds":[57],"was":[58,174,185,272,304],"increased":[59],"from":[60,191,258,283],"0.65":[61],"keyset":[66,73,81,92,225,228,310],"0.67":[68],"to":[74,152,236,274,316],"0.71":[75,86],"surprisal":[78,203,211,245,269],"S/N":[79,212,270],"pruned":[80],"containing":[82,93],"208":[83],"bits":[84,157,190,250],"genetic":[89,292],"algorithm":[90],"548":[94],"bits.":[95,234],"present":[97],"an":[98],"overview":[99],"underlying":[102],"technology":[103,118],"supporting":[104,140],"definition":[106,120],"descriptors":[108,114,122,147,338],"encoding":[111],"these":[113],"into":[115],"keysets.":[116,299],"This":[117],"allows":[119],"as":[123,137,139],"combinations":[124],"atom":[126],"properties,":[127,129],"bond":[128],"atomic":[131],"neighborhoods":[132],"at":[133],"various":[134,163,249],"topological":[135],"separations":[136],"well":[138],"custom":[144],"can":[148],"then":[149],"be":[150,329],"used":[151],"one":[154],"or":[155,207],"more":[156,231,301],"keyset.":[160,322],"their":[167],"clustering":[170],"bioactive":[171],"substances.":[172],"Performance":[173],"measured":[175],"using":[176],"methodology":[177],"developed":[178],"by":[179,188],"Briem":[180],"Lessel.":[182],"\"Directed":[183],"pruning\"":[184],"carried":[186],"out":[187],"eliminating":[189],"basis":[196,242,266],"random":[198,218,259,284],"selection,":[199],"values":[200,208,246],"bit,":[206],"ratio":[213,271],"bit.":[216],"The":[217],"pruning":[219,239,263],"experiment":[220],"highlighted":[221],"insensitivity":[223],"lengths":[229],"than":[232,280],"1000":[233],"Contrary":[235],"initial":[237],"expectations,":[238],"resulted":[251],"underperformed":[255],"those":[256,281],"resulting":[257,282],"pruning.":[260,285],"In":[261],"contrast,":[262],"found":[273],"yield":[275],"performed":[278],"better":[279],"also":[287],"explored":[288],"algorithms":[293],"selection":[296],"optimal":[298,321,326],"Once":[300],"only":[305],"weak":[307],"function":[308],"size,":[311],"optimizations":[314],"failed":[315],"identify":[317],"single":[319],"globally":[320],"Instead":[323],"multiple,":[324],"equally":[325],"could":[328],"produced":[330],"had":[332],"relatively":[333],"low":[334],"overlap":[335],"they":[339],"encoded.":[340]},"counts_by_year":[{"year":2026,"cited_by_count":106},{"year":2025,"cited_by_count":285},{"year":2024,"cited_by_count":277},{"year":2023,"cited_by_count":214},{"year":2022,"cited_by_count":191},{"year":2021,"cited_by_count":168},{"year":2020,"cited_by_count":108},{"year":2019,"cited_by_count":82},{"year":2018,"cited_by_count":49},{"year":2017,"cited_by_count":44},{"year":2016,"cited_by_count":44},{"year":2015,"cited_by_count":39},{"year":2014,"cited_by_count":34},{"year":2013,"cited_by_count":33},{"year":2012,"cited_by_count":37}],"updated_date":"2026-05-22T09:01:20.584952","created_date":"2025-10-10T00:00:00"}