{"id":"https://openalex.org/W2114687365","doi":"https://doi.org/10.1093/bioinformatics/btq067","title":"Accelerated similarity searching and clustering of large compound sets by geometric embedding and locality sensitive hashing","display_name":"Accelerated similarity searching and clustering of large compound sets by geometric embedding and locality sensitive hashing","publication_year":2010,"publication_date":"2010-02-23","ids":{"openalex":"https://openalex.org/W2114687365","doi":"https://doi.org/10.1093/bioinformatics/btq067","mag":"2114687365","pmid":"https://pubmed.ncbi.nlm.nih.gov/20179075"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btq067","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btq067","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/26/7/953/16898265/btq067.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/26/7/953/16898265/btq067.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012783881","display_name":"Yiqun Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yiqun Cao","raw_affiliation_strings":["1 Department of Computer Science & Engineering and 2 Department of Botany & Plant Sciences, University of California, Riverside, CA 92521, USA","Department of Computer Science and Engineering and Department of Botany and Plant Sciences, University of California, Riverside, CA 92521, USA"],"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science & Engineering and 2 Department of Botany & Plant Sciences, University of California, Riverside, CA 92521, USA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"Department of Computer Science and Engineering and Department of Botany and Plant Sciences, University of California, Riverside, CA 92521, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101911266","display_name":"Tao Jiang","orcid":"https://orcid.org/0000-0003-3833-4498"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Jiang","raw_affiliation_strings":["1 Department of Computer Science & Engineering and 2 Department of Botany & Plant Sciences, University of California, Riverside, CA 92521, USA"],"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science & Engineering and 2 Department of Botany & Plant Sciences, University of California, Riverside, CA 92521, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039923525","display_name":"Thomas Girke","orcid":"https://orcid.org/0000-0003-0710-3777"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Girke","raw_affiliation_strings":["1 Department of Computer Science & Engineering and 2 Department of Botany & Plant Sciences, University of California, Riverside, CA 92521, USA"],"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science & Engineering and 2 Department of Botany & Plant Sciences, University of California, Riverside, CA 92521, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012783881"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":4.1015,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94015166,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"26","issue":"7","first_page":"953","last_page":"959"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9980999827384949,"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":0.9980999827384949,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9797999858856201,"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9578999876976013,"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/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.853800892829895},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8134833574295044},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.6912826895713806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6735702753067017},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6010836958885193},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5635576248168945},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5481191873550415},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5171725153923035},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.46438443660736084},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3258301019668579},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.27172625064849854},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.27091819047927856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.268917977809906},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2544492483139038}],"concepts":[{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.853800892829895},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8134833574295044},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.6912826895713806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6735702753067017},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6010836958885193},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5635576248168945},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5481191873550415},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5171725153923035},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.46438443660736084},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3258301019668579},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.27172625064849854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27091819047927856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.268917977809906},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2544492483139038},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","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},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","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":5,"locations":[{"id":"doi:10.1093/bioinformatics/btq067","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btq067","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/26/7/953/16898265/btq067.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:20179075","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20179075","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:ark:/13030/qt3bb0p0n9","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:escholarship.org/ark:/13030/qt3bb0p0n9","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/3bb0p0n9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics (Oxford, England), vol 26, iss 7","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2844998","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2844998","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btq067","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btq067","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/26/7/953/16898265/btq067.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1083704393","display_name":"III-CXT: Collaborative Research: A High-Throughput Approach to the Assignment of Orthologous Genes Based on Genome Rearrangement","funder_award_id":"0711129","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2233320577","display_name":"IGERT in Chemical Genomics:  Forging Complementation at the Interface of Chemistry, Engineering, Computational Sciences and Cell Biology","funder_award_id":"0504249","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6595151660","display_name":"Integrating the \"Unknown-eome\" with Abiotic Stress Response Networks in Arabidopsis","funder_award_id":"0420033","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7633504260","display_name":"2010 Collaborative Research: Integrating the Unknown-eome with Abiotic Stress Response Networks in Arabidopsis","funder_award_id":"0420152","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8164471825","display_name":null,"funder_award_id":"IGERT","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332550","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2114687365.pdf","grobid_xml":"https://content.openalex.org/works/W2114687365.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1489843519","https://openalex.org/W1502916507","https://openalex.org/W1541459201","https://openalex.org/W1553258895","https://openalex.org/W1640748652","https://openalex.org/W1970995121","https://openalex.org/W1983775902","https://openalex.org/W1993216012","https://openalex.org/W1996528078","https://openalex.org/W2001141328","https://openalex.org/W2005126631","https://openalex.org/W2007304801","https://openalex.org/W2008999889","https://openalex.org/W2018408116","https://openalex.org/W2019538911","https://openalex.org/W2033146918","https://openalex.org/W2034225957","https://openalex.org/W2036387645","https://openalex.org/W2048384644","https://openalex.org/W2050083547","https://openalex.org/W2053186076","https://openalex.org/W2057280422","https://openalex.org/W2058799364","https://openalex.org/W2058903936","https://openalex.org/W2077341638","https://openalex.org/W2087595965","https://openalex.org/W2096729078","https://openalex.org/W2124222502","https://openalex.org/W2125253492","https://openalex.org/W2128966273","https://openalex.org/W2130037055","https://openalex.org/W2134738108","https://openalex.org/W2136109916","https://openalex.org/W2145546477","https://openalex.org/W2145725688","https://openalex.org/W2162006472","https://openalex.org/W2165558283","https://openalex.org/W2167081989","https://openalex.org/W2167187529","https://openalex.org/W2170037597","https://openalex.org/W2176516200","https://openalex.org/W2176720124","https://openalex.org/W2554073607","https://openalex.org/W3147295069","https://openalex.org/W4231655980","https://openalex.org/W4246354968","https://openalex.org/W6629956336","https://openalex.org/W6632397832","https://openalex.org/W6633057035","https://openalex.org/W6665290868","https://openalex.org/W6679025786","https://openalex.org/W6679473677","https://openalex.org/W6685012337","https://openalex.org/W6884729671"],"related_works":["https://openalex.org/W2000601968","https://openalex.org/W3094967175","https://openalex.org/W2144265691","https://openalex.org/W1949910768","https://openalex.org/W2045263322","https://openalex.org/W2166822184","https://openalex.org/W2393322642","https://openalex.org/W3096071782","https://openalex.org/W50423144","https://openalex.org/W1480566255"],"abstract_inverted_index":{"Software":[0],"implementations":[1],"and":[2,26],"online":[3,17],"services":[4,18],"have":[5],"been":[6],"developed":[7],"based":[8],"on":[9],"the":[10,22,31],"methods":[11],"introduced":[12],"in":[13],"this":[14],"study.":[15],"The":[16],"provide":[19],"access":[20],"to":[21],"generated":[23],"clustering":[24],"results":[25],"ultra-fast":[27],"similarity":[28],"searching":[29],"of":[30],"PubChem":[32],"Compound":[33],"database":[34],"with":[35],"subsecond":[36],"response":[37],"time.":[38]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
