{"id":"https://openalex.org/W4406967915","doi":"https://doi.org/10.1021/acs.jcim.4c01980","title":"Dedenser: A Python Package for Clustering and Downsampling Chemical Libraries","display_name":"Dedenser: A Python Package for Clustering and Downsampling Chemical Libraries","publication_year":2025,"publication_date":"2025-01-30","ids":{"openalex":"https://openalex.org/W4406967915","doi":"https://doi.org/10.1021/acs.jcim.4c01980","pmid":"https://pubmed.ncbi.nlm.nih.gov/39883037"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.4c01980","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c01980","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/A5043874124","display_name":"Armen G. Beck","orcid":"https://orcid.org/0009-0006-2193-0807"},"institutions":[{"id":"https://openalex.org/I1285764155","display_name":"Merck & Co., Inc., Rahway, NJ, USA (United States)","ror":"https://ror.org/02891sr49","country_code":"US","type":"company","lineage":["https://openalex.org/I1285764155"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Armen G. Beck","raw_affiliation_strings":["Analytical Research & Development","MRL, Merck & Co., Inc","Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, New Jersey 07065, United States"],"affiliations":[{"raw_affiliation_string":"Analytical Research & Development","institution_ids":[]},{"raw_affiliation_string":"MRL, Merck & Co., Inc","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005464954","display_name":"Jonathan Fine","orcid":"https://orcid.org/0000-0002-3685-8581"},"institutions":[{"id":"https://openalex.org/I1285764155","display_name":"Merck & Co., Inc., Rahway, NJ, USA (United States)","ror":"https://ror.org/02891sr49","country_code":"US","type":"company","lineage":["https://openalex.org/I1285764155"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Fine","raw_affiliation_strings":["Analytical Research & Development","MRL, Merck & Co., Inc","Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, New Jersey 07065, United States"],"affiliations":[{"raw_affiliation_string":"Analytical Research & Development","institution_ids":[]},{"raw_affiliation_string":"MRL, Merck & Co., Inc","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028770904","display_name":"Yu\u2010hong Lam","orcid":"https://orcid.org/0000-0002-4946-1487"},"institutions":[{"id":"https://openalex.org/I1285764155","display_name":"Merck & Co., Inc., Rahway, NJ, USA (United States)","ror":"https://ror.org/02891sr49","country_code":"US","type":"company","lineage":["https://openalex.org/I1285764155"]},{"id":"https://openalex.org/I4210136724","display_name":"Institute of Computational Modeling","ror":"https://ror.org/047f8bv22","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210136724"]}],"countries":["RU","US"],"is_corresponding":false,"raw_author_name":"Yu-hong Lam","raw_affiliation_strings":["Merck & Co., Inc","Modeling and Informatics, MRL","Modeling and Informatics, MRL, Merck & Co., Inc., Rahway, New Jersey 07065, United States"],"affiliations":[{"raw_affiliation_string":"Merck & Co., Inc","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Modeling and Informatics, MRL","institution_ids":["https://openalex.org/I4210136724"]},{"raw_affiliation_string":"Modeling and Informatics, MRL, Merck & Co., Inc., Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027788085","display_name":"Edward C. Sherer","orcid":"https://orcid.org/0000-0001-8178-9186"},"institutions":[{"id":"https://openalex.org/I1285764155","display_name":"Merck & Co., Inc., Rahway, NJ, USA (United States)","ror":"https://ror.org/02891sr49","country_code":"US","type":"company","lineage":["https://openalex.org/I1285764155"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward C. Sherer","raw_affiliation_strings":["Analytical Research & Development","MRL, Merck & Co., Inc","Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, New Jersey 07065, United States"],"affiliations":[{"raw_affiliation_string":"Analytical Research & Development","institution_ids":[]},{"raw_affiliation_string":"MRL, Merck & Co., Inc","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008916264","display_name":"Erik L. Regalado","orcid":"https://orcid.org/0000-0002-7352-6391"},"institutions":[{"id":"https://openalex.org/I1285764155","display_name":"Merck & Co., Inc., Rahway, NJ, USA (United States)","ror":"https://ror.org/02891sr49","country_code":"US","type":"company","lineage":["https://openalex.org/I1285764155"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik L. Regalado","raw_affiliation_strings":["Analytical Research & Development","MRL, Merck & Co., Inc","Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, New Jersey 07065, United States"],"affiliations":[{"raw_affiliation_string":"Analytical Research & Development","institution_ids":[]},{"raw_affiliation_string":"MRL, Merck & Co., Inc","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023819333","display_name":"Pankaj Aggarwal","orcid":"https://orcid.org/0009-0005-0344-5886"},"institutions":[{"id":"https://openalex.org/I1285764155","display_name":"Merck & Co., Inc., Rahway, NJ, USA (United States)","ror":"https://ror.org/02891sr49","country_code":"US","type":"company","lineage":["https://openalex.org/I1285764155"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pankaj Aggarwal","raw_affiliation_strings":["Analytical Research & Development","MRL, Merck & Co., Inc","Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, New Jersey 07065, United States"],"affiliations":[{"raw_affiliation_string":"Analytical Research & Development","institution_ids":[]},{"raw_affiliation_string":"MRL, Merck & Co., Inc","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5023819333","https://openalex.org/A5043874124"],"corresponding_institution_ids":["https://openalex.org/I1285764155"],"apc_list":null,"apc_paid":null,"fwci":2.7791,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88967999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"65","issue":"3","first_page":"1053","last_page":"1060"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9794999957084656,"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":0.9794999957084656,"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/T12327","display_name":"Various Chemistry Research Topics","score":0.9642000198364258,"subfield":{"id":"https://openalex.org/subfields/1606","display_name":"Physical and Theoretical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9599000215530396,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7803430557250977},{"id":"https://openalex.org/keywords/r-package","display_name":"R package","score":0.6873646378517151},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5604596138000488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.548815906047821},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.4846966564655304},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34315812587738037},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24558913707733154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23757490515708923}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7803430557250977},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.6873646378517151},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5604596138000488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.548815906047821},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.4846966564655304},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34315812587738037},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24558913707733154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23757490515708923},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","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":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","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":false},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.4c01980","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c01980","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:39883037","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39883037","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W167712241","https://openalex.org/W1980417767","https://openalex.org/W1983393839","https://openalex.org/W1986170186","https://openalex.org/W1986473362","https://openalex.org/W1992156271","https://openalex.org/W1995089537","https://openalex.org/W2027482274","https://openalex.org/W2032726880","https://openalex.org/W2034845925","https://openalex.org/W2049615701","https://openalex.org/W2061843861","https://openalex.org/W2063199883","https://openalex.org/W2071791280","https://openalex.org/W2072598797","https://openalex.org/W2078293348","https://openalex.org/W2079615548","https://openalex.org/W2130716625","https://openalex.org/W2140972311","https://openalex.org/W2161782568","https://openalex.org/W2163915395","https://openalex.org/W2197388599","https://openalex.org/W2529996553","https://openalex.org/W2551556495","https://openalex.org/W2584122919","https://openalex.org/W2592262780","https://openalex.org/W2617121149","https://openalex.org/W2619824656","https://openalex.org/W2746802101","https://openalex.org/W2769484073","https://openalex.org/W2773987374","https://openalex.org/W2786672974","https://openalex.org/W2791162249","https://openalex.org/W2791355014","https://openalex.org/W2801991413","https://openalex.org/W2809927589","https://openalex.org/W2920702708","https://openalex.org/W2963899413","https://openalex.org/W2979874034","https://openalex.org/W2980583144","https://openalex.org/W3003257820","https://openalex.org/W3006781192","https://openalex.org/W3030402150","https://openalex.org/W3033134881","https://openalex.org/W3035965352","https://openalex.org/W3099878876","https://openalex.org/W3100751385","https://openalex.org/W3115142961","https://openalex.org/W3119872582","https://openalex.org/W3123775255","https://openalex.org/W3143638934","https://openalex.org/W3144750446","https://openalex.org/W3181426828","https://openalex.org/W3209805961","https://openalex.org/W3217568487","https://openalex.org/W4200583473","https://openalex.org/W4211010347","https://openalex.org/W4213080228","https://openalex.org/W4220799686","https://openalex.org/W4224003537","https://openalex.org/W4281720176","https://openalex.org/W4283012064","https://openalex.org/W4295988913","https://openalex.org/W4386845728","https://openalex.org/W4387241462","https://openalex.org/W4387426283","https://openalex.org/W4388464545","https://openalex.org/W4391033617","https://openalex.org/W4391993349","https://openalex.org/W4393178210","https://openalex.org/W4394611864","https://openalex.org/W6911422139","https://openalex.org/W6912621387"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W1983892167","https://openalex.org/W4401016539","https://openalex.org/W4400651710","https://openalex.org/W4406202791","https://openalex.org/W4405093211","https://openalex.org/W4403672447"],"abstract_inverted_index":{"The":[0],"screening":[1,22,38,58],"of":[2,23,30,47,59,67,77,83,94,103,130,182,220,225,232],"chemical":[3,68,78,95,106,117,141,162,183],"libraries":[4,79],"is":[5,33,54,120,247],"an":[6],"essential":[7],"starting":[8],"point":[9,107,142,184],"in":[10,116,139,161],"the":[11,44,57,92,101,111,180,211],"drug":[12,24,48],"discovery":[13],"process.":[14],"While":[15],"some":[16],"researchers":[17],"desire":[18],"a":[19,27,51,89,121],"more":[20],"thorough":[21],"targets":[25],"against":[26],"narrower":[28],"scope":[29],"molecules,":[31,60,84],"it":[32],"not":[34],"uncommon":[35],"for":[36,91,179,188,198,245],"diverse":[37],"sets":[39,227],"to":[40,134,152,217],"be":[41],"favored":[42],"during":[43],"early":[45],"stages":[46],"discovery.":[49],"However,":[50],"cost":[52],"burden":[53],"associated":[55],"with":[56,61,132,175],"potential":[62],"drawbacks":[63],"if":[64],"particular":[65],"areas":[66],"space":[69],"are":[70,173,223],"needlessly":[71],"overrepresented.":[72],"To":[73],"facilitate":[74],"triaged":[75],"sampling":[76,151],"and":[80,144,169,192,196,228,250],"other":[81],"collections":[82,219],"we":[85],"have":[86],"developed":[87],"Dedenser,":[88,176],"tool":[90,168],"downsampling":[93],"clusters.":[96,242],"Dedenser":[97,119,208,246],"functions":[98],"by":[99,147,213],"reducing":[100],"membership":[102],"clusters":[104,137,153,235],"within":[105,234],"clouds":[108,143],"while":[109],"maintaining":[110],"initial":[112],"topology":[113],"or":[114,159],"distribution":[115],"space.":[118,163],"Python":[122],"package":[123],"that":[124,207,222],"utilizes":[125],"Hierarchical":[126],"Density-Based":[127],"Spatial":[128],"Clustering":[129],"Applications":[131],"Noise":[133],"first":[135],"identify":[136],"present":[138],"3D":[140,199],"then":[145],"downsamples":[146],"applying":[148],"Poisson":[149],"disk":[150],"based":[154],"on":[155],"either":[156],"their":[157],"volume":[158],"density":[160],"A":[164],"command":[165],"line":[166],"interface":[167,172],"graphic":[170],"user":[171],"available":[174,251],"which":[177],"allow":[178],"generation":[181],"clouds,":[185],"using":[186],"Mordred":[187],"QSAR":[189],"descriptor":[190],"calculations":[191],"uniform":[193],"manifold":[194],"approximation":[195],"projection":[197],"embedding,":[200],"as":[201,203],"well":[202],"visualization.":[204],"We":[205],"hope":[206],"will":[209],"serve":[210],"community":[212],"enabling":[214],"quick":[215],"access":[216],"reduced":[218],"molecules":[221,233,240],"representative":[224,239],"larger":[226],"selecting":[229],"even":[230],"distributions":[231],"rather":[236],"than":[237],"single":[238],"from":[241],"All":[243],"code":[244],"open":[248],"source":[249],"at":[252],"https://github.com/MSDLLCpapers/dedenser.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}