{"id":"https://openalex.org/W2043122083","doi":"https://doi.org/10.1021/ci050403o","title":"Scalable Partitioning and Exploration of Chemical Spaces Using Geometric Hashing","display_name":"Scalable Partitioning and Exploration of Chemical Spaces Using Geometric Hashing","publication_year":2005,"publication_date":"2005-11-08","ids":{"openalex":"https://openalex.org/W2043122083","doi":"https://doi.org/10.1021/ci050403o","mag":"2043122083","pmid":"https://pubmed.ncbi.nlm.nih.gov/16426067"},"language":"en","primary_location":{"id":"doi:10.1021/ci050403o","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci050403o","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/A5113845539","display_name":"Debojyoti Dutta","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debojyoti Dutta","raw_affiliation_strings":["Department of Computational Biology, University of Southern California, Los Angeles, California 90089, and Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Biology, University of Southern California, Los Angeles, California 90089, and Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069062997","display_name":"Rajarshi Guha","orcid":"https://orcid.org/0000-0001-7403-8819"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajarshi Guha","raw_affiliation_strings":["Department of Computational Biology, University of Southern California, Los Angeles, California 90089, and Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Biology, University of Southern California, Los Angeles, California 90089, and Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109171233","display_name":"Peter C. Jurs","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter C. Jurs","raw_affiliation_strings":["Department of Computational Biology, University of Southern California, Los Angeles, California 90089, and Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Biology, University of Southern California, Los Angeles, California 90089, and Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100443173","display_name":"Ting Chen","orcid":"https://orcid.org/0000-0001-8414-6346"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting Chen","raw_affiliation_strings":["Department of Computational Biology, University of Southern California, Los Angeles, California 90089, and Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Biology, University of Southern California, Los Angeles, California 90089, and Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.328,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88534689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"46","issue":"1","first_page":"321","last_page":"333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9987999796867371,"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":0.9987999796867371,"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9955000281333923,"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"}},{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9865999817848206,"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/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.8257138133049011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7761227488517761},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6199924349784851},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.6161047220230103},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6001031994819641},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5637539625167847},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.49542033672332764},{"id":"https://openalex.org/keywords/best-bin-first","display_name":"Best bin first","score":0.4686027765274048},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.42505815625190735},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3330078125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21811917424201965},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.2062930166721344},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.17151769995689392},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17093461751937866}],"concepts":[{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.8257138133049011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7761227488517761},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6199924349784851},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.6161047220230103},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6001031994819641},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5637539625167847},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.49542033672332764},{"id":"https://openalex.org/C161986146","wikidata":"https://www.wikidata.org/wiki/Q4896845","display_name":"Best bin first","level":3,"score":0.4686027765274048},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.42505815625190735},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3330078125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21811917424201965},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.2062930166721344},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.17151769995689392},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17093461751937866},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1021/ci050403o","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci050403o","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:16426067","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16426067","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},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.215.1096","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.215.1096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cmb.usc.edu/people/tingchen/MyPublication/JCIM-VirtualScreening-2005.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1488799823","https://openalex.org/W1502916507","https://openalex.org/W1506281249","https://openalex.org/W1585772109","https://openalex.org/W1597224949","https://openalex.org/W1973195696","https://openalex.org/W1977340881","https://openalex.org/W1979105104","https://openalex.org/W1983775902","https://openalex.org/W1994461795","https://openalex.org/W2002634496","https://openalex.org/W2003932708","https://openalex.org/W2008517160","https://openalex.org/W2013470095","https://openalex.org/W2016164337","https://openalex.org/W2021203532","https://openalex.org/W2031498906","https://openalex.org/W2033495141","https://openalex.org/W2050273205","https://openalex.org/W2052367365","https://openalex.org/W2065918898","https://openalex.org/W2067480766","https://openalex.org/W2079391392","https://openalex.org/W2088157201","https://openalex.org/W2089697073","https://openalex.org/W2091056080","https://openalex.org/W2122111042","https://openalex.org/W2123297508","https://openalex.org/W2134473756","https://openalex.org/W2162006472","https://openalex.org/W2318794083","https://openalex.org/W2409065277","https://openalex.org/W2799244375","https://openalex.org/W2950235751","https://openalex.org/W3142152711","https://openalex.org/W4251903194","https://openalex.org/W4302359066"],"related_works":["https://openalex.org/W2381195555","https://openalex.org/W2182477562","https://openalex.org/W4246757943","https://openalex.org/W2148008870","https://openalex.org/W1595303882","https://openalex.org/W1558159560","https://openalex.org/W2166822184","https://openalex.org/W3096071782","https://openalex.org/W2902799860","https://openalex.org/W4289129280"],"abstract_inverted_index":{"Virtual":[0],"screening":[1],"(VS)":[2],"has":[3],"become":[4],"a":[5,24,67,80,88,109,221,248,260,265],"preferred":[6],"tool":[7],"to":[8,103,128,138,179,229,242,280],"augment":[9],"high-throughput":[10],"screening(1)":[11],"and":[12,46,58,164,208,273],"determine":[13],"new":[14],"leads":[15],"in":[16,70,108,131,141,157,247,257,264],"the":[17,132,142,162,186,192,204,224],"drug":[18],"discovery":[19],"process.":[20],"The":[21,117],"core":[22,118],"of":[23,38,43,87,166,174,188,200,232,268],"VS":[25],"informatics":[26],"pipeline":[27],"includes":[28],"several":[29],"data":[30,64,81,147,172],"mining":[31,82],"algorithms":[32],"that":[33,99,125,185],"work":[34],"on":[35,85,169],"huge":[36,62,105],"databases":[37],"chemical":[39,63,106,122,250,269],"compounds":[40,246],"containing":[41],"millions":[42],"molecular":[44],"structures":[45],"their":[47],"associated":[48],"data.":[49],"Thus,":[50],"scaling":[51],"traditional":[52,205],"applications":[53],"such":[54],"as":[55,220],"classification,":[56],"partitioning,":[57],"outlier":[59],"detection":[60],"for":[61,213],"sets":[65,173],"without":[66],"significant":[68],"loss":[69],"accuracy":[71,163],"is":[72,195,209,254,262,275],"very":[73,113,155],"important.":[74],"In":[75],"this":[76,146,252],"paper,":[77],"we":[78],"introduce":[79],"framework":[83,168,241],"built":[84],"top":[86],"recently":[89],"developed":[90],"fast":[91],"approximate":[92,152],"nearest-neighbor-finding":[93],"algorithm(2)":[94],"called":[95],"locality-sensitive":[96],"hashing":[97],"(LSH)":[98],"can":[100,150],"be":[101],"used":[102],"mine":[104],"spaces":[107],"scalable":[110],"fashion":[111],"using":[112,191,283],"modest":[114],"computational":[115],"resources.":[116],"LSH":[119,193,225],"algorithm":[120,194,226,253],"hashes":[121],"descriptors":[123],"so":[124],"points":[126],"close":[127,137],"each":[129,139],"other":[130,140],"descriptor":[133],"space":[134,270],"are":[135],"also":[136,238],"hashed":[143],"space.":[144],"Using":[145],"structure,":[148],"one":[149],"perform":[151],"nearest-neighbor":[153,233],"searches":[154],"quickly,":[156],"sublinear":[158],"time.":[159],"We":[160,237],"validate":[161],"performance":[165],"our":[167,240],"three":[170],"real":[171],"sizes":[175],"ranging":[176],"from":[177],"4337":[178],"249":[180],"071":[181],"molecules.":[182],"Results":[183],"indicate":[184],"identification":[187],"nearest":[189],"neighbors":[190],"at":[196],"least":[197],"2":[198],"orders":[199],"magnitude":[201],"faster":[202],"than":[203],"k-nearest-neighbor":[206],"method":[207],"over":[210],"94%":[211],"accurate":[212,277],"most":[214],"query":[215],"parameters.":[216],"Furthermore,":[217],"when":[218,278],"viewed":[219],"data-partitioning":[222],"procedure,":[223],"lends":[227],"itself":[228],"easy":[230],"parallelization":[231],"classification":[234],"or":[235,271],"regression.":[236],"apply":[239],"detect":[243],"outlying":[244],"(diverse)":[245],"given":[249],"space;":[251],"extremely":[255],"rapid":[256],"determining":[258],"whether":[259],"compound":[261],"located":[263],"sparse":[266],"region":[267],"not,":[272],"it":[274],"quite":[276],"compared":[279],"results":[281],"obtained":[282],"principal-component-analysis-based":[284],"heuristics.":[285]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}