{"id":"https://openalex.org/W1977243766","doi":"https://doi.org/10.1021/ci010376b","title":"Chemical Library Subset Selection Algorithms:\u2009 A Unified Derivation Using Spatial Statistics","display_name":"Chemical Library Subset Selection Algorithms:\u2009 A Unified Derivation Using Spatial Statistics","publication_year":2002,"publication_date":"2002-03-01","ids":{"openalex":"https://openalex.org/W1977243766","doi":"https://doi.org/10.1021/ci010376b","mag":"1977243766","pmid":"https://pubmed.ncbi.nlm.nih.gov/11911712"},"language":"en","primary_location":{"id":"doi:10.1021/ci010376b","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci010376b","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/A5020048224","display_name":"Fred A. Hamprecht","orcid":"https://orcid.org/0000-0003-4148-5043"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I4210090782","display_name":"Max-Planck-Institut f\u00fcr Kohlenforschung","ror":"https://ror.org/00a7vgh58","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210090782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Fred A. Hamprecht","raw_affiliation_strings":["Interdisciplinary Center for Scientific Computing (IWR), University of Heidelberg, Im Neuenheimer Feld 368, 69120 Heidelberg, Germany, Max-Planck-Institut f\u00fcr Kohlenforschung, 45470 M\u00fclheim an der Ruhr, Germany, and Laboratory of Physical Chemistry, Swiss Federal Institute of Technology, 8092 Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Center for Scientific Computing (IWR), University of Heidelberg, Im Neuenheimer Feld 368, 69120 Heidelberg, Germany, Max-Planck-Institut f\u00fcr Kohlenforschung, 45470 M\u00fclheim an der Ruhr, Germany, and Laboratory of Physical Chemistry, Swiss Federal Institute of Technology, 8092 Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I4210090782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073581192","display_name":"Walter Thiel","orcid":"https://orcid.org/0000-0001-6780-0350"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I4210090782","display_name":"Max-Planck-Institut f\u00fcr Kohlenforschung","ror":"https://ror.org/00a7vgh58","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210090782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Walter Thiel","raw_affiliation_strings":["Interdisciplinary Center for Scientific Computing (IWR), University of Heidelberg, Im Neuenheimer Feld 368, 69120 Heidelberg, Germany, Max-Planck-Institut f\u00fcr Kohlenforschung, 45470 M\u00fclheim an der Ruhr, Germany, and Laboratory of Physical Chemistry, Swiss Federal Institute of Technology, 8092 Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Center for Scientific Computing (IWR), University of Heidelberg, Im Neuenheimer Feld 368, 69120 Heidelberg, Germany, Max-Planck-Institut f\u00fcr Kohlenforschung, 45470 M\u00fclheim an der Ruhr, Germany, and Laboratory of Physical Chemistry, Swiss Federal Institute of Technology, 8092 Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I4210090782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063856246","display_name":"Wilfred F. van Gunsteren","orcid":"https://orcid.org/0000-0002-9583-7019"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I4210090782","display_name":"Max-Planck-Institut f\u00fcr Kohlenforschung","ror":"https://ror.org/00a7vgh58","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210090782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wilfred F. van Gunsteren","raw_affiliation_strings":["Interdisciplinary Center for Scientific Computing (IWR), University of Heidelberg, Im Neuenheimer Feld 368, 69120 Heidelberg, Germany, Max-Planck-Institut f\u00fcr Kohlenforschung, 45470 M\u00fclheim an der Ruhr, Germany, and Laboratory of Physical Chemistry, Swiss Federal Institute of Technology, 8092 Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Center for Scientific Computing (IWR), University of Heidelberg, Im Neuenheimer Feld 368, 69120 Heidelberg, Germany, Max-Planck-Institut f\u00fcr Kohlenforschung, 45470 M\u00fclheim an der Ruhr, Germany, and Laboratory of Physical Chemistry, Swiss Federal Institute of Technology, 8092 Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I223822909","https://openalex.org/I4210090782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020048224"],"corresponding_institution_ids":["https://openalex.org/I223822909","https://openalex.org/I4210090782"],"apc_list":null,"apc_paid":null,"fwci":2.5478,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89264612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"2","first_page":"414","last_page":"428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11798","display_name":"Optimal Experimental Design Methods","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11798","display_name":"Optimal Experimental Design Methods","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9952999949455261,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9487000107765198,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.7004135251045227},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6729748845100403},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5549415946006775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5470935702323914},{"id":"https://openalex.org/keywords/minimum-mean-square-error","display_name":"Minimum mean square error","score":0.5173829793930054},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5100935101509094},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.48787689208984375},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4462050795555115},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4369892179965973},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.43084901571273804},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43074846267700195},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4171678423881531},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.35839298367500305},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.35682564973831177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.188848614692688}],"concepts":[{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.7004135251045227},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6729748845100403},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5549415946006775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5470935702323914},{"id":"https://openalex.org/C90652560","wikidata":"https://www.wikidata.org/wiki/Q11091747","display_name":"Minimum mean square error","level":3,"score":0.5173829793930054},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5100935101509094},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.48787689208984375},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4462050795555115},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4369892179965973},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.43084901571273804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43074846267700195},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4171678423881531},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.35839298367500305},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.35682564973831177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.188848614692688},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1021/ci010376b","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci010376b","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:11911712","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/11911712","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:10.1.1.20.4135","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.4135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://klimt.iwr.uni-heidelberg.de/mip/./fhamprecht/repdiv-tr.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:20115","is_oa":false,"landing_page_url":"http://edoc.mpg.de/20115","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Chemical Information and Computer Sciences, v.42, 414-428 (2002)","raw_type":"Article"},{"id":"pmh:oai:pure.mpg.de:item_1470051","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-000F-9A07-5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Chemical Information and Computer Sciences","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W55912154","https://openalex.org/W118818158","https://openalex.org/W204885769","https://openalex.org/W621908693","https://openalex.org/W645888856","https://openalex.org/W1510052597","https://openalex.org/W1966715677","https://openalex.org/W1973175049","https://openalex.org/W1981214699","https://openalex.org/W1984444191","https://openalex.org/W1987284672","https://openalex.org/W1987656037","https://openalex.org/W2002009218","https://openalex.org/W2002422940","https://openalex.org/W2004524148","https://openalex.org/W2017422910","https://openalex.org/W2021083597","https://openalex.org/W2025887562","https://openalex.org/W2031498906","https://openalex.org/W2033495664","https://openalex.org/W2035347370","https://openalex.org/W2044613736","https://openalex.org/W2051079112","https://openalex.org/W2053934160","https://openalex.org/W2066345214","https://openalex.org/W2069626069","https://openalex.org/W2071678676","https://openalex.org/W2071840184","https://openalex.org/W2073876332","https://openalex.org/W2077341638","https://openalex.org/W2079321251","https://openalex.org/W2083027289","https://openalex.org/W2091589454","https://openalex.org/W2092262344","https://openalex.org/W2094284491","https://openalex.org/W2096729078","https://openalex.org/W2098043077","https://openalex.org/W2106446203","https://openalex.org/W2116858093","https://openalex.org/W2134383396","https://openalex.org/W2337490104","https://openalex.org/W2796739798","https://openalex.org/W2949435151","https://openalex.org/W2950235751","https://openalex.org/W2952541077","https://openalex.org/W3103871524","https://openalex.org/W4210300258","https://openalex.org/W4239151193","https://openalex.org/W4248596865","https://openalex.org/W4250984232","https://openalex.org/W4254115559","https://openalex.org/W4293259454","https://openalex.org/W4298876635"],"related_works":["https://openalex.org/W2102148524","https://openalex.org/W2314720829","https://openalex.org/W1583991000","https://openalex.org/W4385074335","https://openalex.org/W2075897667","https://openalex.org/W2907746047","https://openalex.org/W3125536267","https://openalex.org/W2073909383","https://openalex.org/W2274645452","https://openalex.org/W2350826920"],"abstract_inverted_index":{"If":[0],"similar":[1,4],"compounds":[2],"have":[3],"activity,":[5],"rational":[6],"subset":[7],"selection":[8,13,234],"becomes":[9],"superior":[10],"to":[11,23,92,146,183],"random":[12],"in":[14,76,143,148],"screening":[15],"for":[16,157,168,206],"pharmacological":[17],"lead":[18],"discovery":[19],"programs.":[20],"Traditional":[21],"approaches":[22],"this":[24],"experimental":[25],"design":[26],"problem":[27],"fall":[28],"into":[29],"two":[30],"classes:":[31],"(i)":[32],"a":[33,69,77,82,120,204],"linear":[34,89],"or":[35,111,192,237],"quadratic":[36],"response":[37,155],"function":[38],"is":[39,46,141,166],"assumed":[40],"(ii)":[41],"some":[42],"space":[43],"filling":[44],"criterion":[45],"optimized.":[47],"The":[48],"assumptions":[49,231],"underlying":[50,135,232],"the":[51,60,87,99,105,112,149,158,173,186,193,211,221,230,233],"first":[52],"approach":[53,62,118],"are":[54],"clear":[55,70],"but":[56,67],"not":[57],"always":[58],"defendable;":[59],"second":[61],"yields":[63],"more":[64],"intuitive":[65],"designs":[66,96],"lacks":[68],"theoretical":[71],"foundation.":[72],"We":[73,114,181],"model":[74],"activity":[75],"bioassay":[78],"as":[79,127,195],"realization":[80],"of":[81,152,210,223,235],"stochastic":[83],"process":[84],"and":[85,130,178,202,228],"use":[86,184],"best":[88],"unbiased":[90],"estimator":[91],"construct":[93],"spatial":[94],"sampling":[95],"that":[97,116],"optimize":[98],"integrated":[100,159,174,187,212],"mean":[101,107,160,175,188,213],"square":[102,108,161,176,189,214],"prediction":[103,109,190,215],"error,":[104,110],"maximum":[106],"entropy.":[113],"argue":[115],"our":[117],"constitutes":[119],"unifying":[121],"framework":[122],"encompassing":[123],"most":[124],"proposed":[125],"techniques":[126],"limiting":[128,150],"cases":[129],"sheds":[131],"light":[132],"on":[133],"their":[134],"assumptions.":[136],"In":[137],"particular,":[138],"vector":[139],"quantization":[140],"obtained,":[142],"dimensions":[144],"up":[145],"eight,":[147],"case":[151],"very":[153,169],"smooth":[154],"surfaces":[156,171],"error":[162,177,191],"criterion.":[163],"Closest":[164],"packing":[165],"obtained":[167],"rough":[170],"under":[172],"entropy":[179,194],"criteria.":[180],"suggest":[182],"either":[185],"optimization":[196],"criteria":[197],"rather":[198],"than":[199],"approximations":[200],"thereof":[201],"propose":[203],"scheme":[205],"direct":[207],"iterative":[208],"minimization":[209],"error.":[216],"Finally,":[217],"we":[218],"discuss":[219],"how":[220],"quality":[222],"chemical":[224],"descriptors":[225],"manifests":[226],"itself":[227],"clarify":[229],"diverse":[236],"representative":[238],"subsets.":[239]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}