{"id":"https://openalex.org/W6602908","doi":"https://doi.org/10.1021/ci0600859","title":"A Fast Clustering Algorithm for Analyzing Highly Similar Compounds of Very Large Libraries","display_name":"A Fast Clustering Algorithm for Analyzing Highly Similar Compounds of Very Large Libraries","publication_year":2006,"publication_date":"2006-08-08","ids":{"openalex":"https://openalex.org/W6602908","doi":"https://doi.org/10.1021/ci0600859","mag":"6602908","pmid":"https://pubmed.ncbi.nlm.nih.gov/16995722"},"language":"en","primary_location":{"id":"doi:10.1021/ci0600859","doi":"https://doi.org/10.1021/ci0600859","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci0600859","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,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"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"},"volume":null,"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/A5027145422","display_name":"Weizhong Li","orcid":"https://orcid.org/0000-0003-1804-9403","observed_orcids":["https://orcid.org/0000-0003-1804-9403"]},"institutions":[{"id":"https://openalex.org/I188891513","display_name":"Sanford Burnham Prebys Medical Discovery Institute","ror":"https://ror.org/03m1g2s55","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I188891513"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weizhong Li","raw_affiliation_strings":["Burnham Institute for Medical Research, 10901 N. Torrey Pines Rd., La Jolla, California 92037","Burnham Institute for Medical Research, 10901 N. Torrey Pines Rd., La Jolla, California 92037, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Burnham Institute for Medical Research, 10901 N. Torrey Pines Rd., La Jolla, California 92037","institution_ids":["https://openalex.org/I188891513"]},{"raw_affiliation_string":"Burnham Institute for Medical Research, 10901 N. Torrey Pines Rd., La Jolla, California 92037, USA","institution_ids":["https://openalex.org/I188891513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5027145422"],"corresponding_institution_ids":["https://openalex.org/I188891513"],"apc_list":{"value":4500,"currency":"USD","value_usd":4500},"apc_paid":null,"fwci":1.0492,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.75398851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"46","issue":"5","first_page":"1919","last_page":"1923"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9951000213623047,"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":0.9951000213623047,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/compound-clustering","display_name":"compound clustering","score":0.8619999885559082},{"id":"https://openalex.org/keywords/molecular-similarity","display_name":"molecular similarity","score":0.531000018119812},{"id":"https://openalex.org/keywords/incremental-clustering","display_name":"incremental clustering","score":0.8690000176429749}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8686732649803162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7219656705856323},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6419475078582764},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6194301247596741},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4992034435272217},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47247669100761414},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4222898781299591},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.41108939051628113},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32479608058929443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20492711663246155},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.18149036169052124},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci0600859","doi":"https://doi.org/10.1021/ci0600859","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci0600859","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,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"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:16995722","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16995722","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,"listed_in":[],"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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1965534201","https://openalex.org/W1973826313","https://openalex.org/W1981953390","https://openalex.org/W1984994707","https://openalex.org/W1990726059","https://openalex.org/W1992579349","https://openalex.org/W2000376564","https://openalex.org/W2021827987","https://openalex.org/W2027926002","https://openalex.org/W2032726880","https://openalex.org/W2036387645","https://openalex.org/W2042035902","https://openalex.org/W2049615701","https://openalex.org/W2050615111","https://openalex.org/W2056838301","https://openalex.org/W2057445960","https://openalex.org/W2069530087","https://openalex.org/W2070598941","https://openalex.org/W2072286363","https://openalex.org/W2077018271","https://openalex.org/W2137995988","https://openalex.org/W2141822110","https://openalex.org/W2177658341","https://openalex.org/W2178594120","https://openalex.org/W2213138713","https://openalex.org/W2952213121","https://openalex.org/W4236513156","https://openalex.org/W4240703037"],"related_works":["https://openalex.org/W1995747683","https://openalex.org/W2114687365","https://openalex.org/W2056838301","https://openalex.org/W2951497098","https://openalex.org/W2100005623","https://openalex.org/W2010528862","https://openalex.org/W2071541305","https://openalex.org/W2049615701","https://openalex.org/W2108763231","https://openalex.org/W1974147654"],"abstract_inverted_index":{"As":[0],"a":[1,37,77,97,109],"result":[2],"of":[3,7,15,27,60,91,104],"the":[4,13,88],"recent":[5],"developments":[6],"high-throughput":[8],"screening":[9,17],"in":[10,106],"drug":[11],"discovery,":[12],"number":[14],"available":[16,53,121],"compounds":[18,31,42,105],"has":[19],"been":[20],"growing":[21],"rapidly.":[22],"Chemical":[23],"vendors":[24],"provide":[25],"millions":[26,103],"compounds;":[28,61],"however,":[29],"these":[30],"are":[32,63,66],"highly":[33],"redundant.":[34],"Clustering":[35],"analysis,":[36],"technique":[38],"that":[39],"groups":[40],"similar":[41],"into":[43],"families,":[44],"can":[45,95],"be":[46],"used":[47],"to":[48],"analyze":[49],"such":[50],"redundancy.":[51],"Many":[52],"clustering":[54,79,85],"methods":[55],"focus":[56],"on":[57,82,108],"accurate":[58],"classification":[59],"they":[62],"slow":[64],"and":[65,87],"not":[67],"suitable":[68],"for":[69],"very":[70,98],"large":[71,99],"compound":[72],"libraries.":[73],"Here":[74],"is":[75,120],"described":[76],"fast":[78],"method":[80,94],"based":[81],"an":[83],"incremental":[84],"algorithm":[86],"2D":[89],"fingerprints":[90],"compounds.":[92],"This":[93],"cluster":[96],"data":[100],"set":[101],"with":[102,115],"hours":[107],"single":[110],"computer.":[111],"A":[112],"program":[113],"implemented":[114],"this":[116],"method,":[117],"called":[118],"cd-hit-fp,":[119],"from":[122],"http://chemspace.org.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}