{"id":"https://openalex.org/W2139176775","doi":"https://doi.org/10.1093/bioinformatics/btn187","title":"BLASTing small molecules\u2014statistics and extreme statistics of chemical similarity scores","display_name":"BLASTing small molecules\u2014statistics and extreme statistics of chemical similarity scores","publication_year":2008,"publication_date":"2008-06-27","ids":{"openalex":"https://openalex.org/W2139176775","doi":"https://doi.org/10.1093/bioinformatics/btn187","mag":"2139176775","pmid":"https://pubmed.ncbi.nlm.nih.gov/18586735"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btn187","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn187","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/13/i357/49050631/bioinformatics_24_13_i357.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":null,"license_id":null,"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":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/24/13/i357/49050631/bioinformatics_24_13_i357.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088813478","display_name":"Pierre Baldi","orcid":"https://orcid.org/0000-0001-8752-4664"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pierre Baldi","raw_affiliation_strings":["1 Department of Computer Science, 2Institute for Genomics and Bioinformatics and 3Department of Biological Chemistry, University of California, Irvine, CA 92697-3435, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science, 2Institute for Genomics and Bioinformatics and 3Department of Biological Chemistry, University of California, Irvine, CA 92697-3435, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003755911","display_name":"Ryan W. Benz","orcid":"https://orcid.org/0000-0002-8924-6116"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan W. Benz","raw_affiliation_strings":["1 Department of Computer Science, 2Institute for Genomics and Bioinformatics and 3Department of Biological Chemistry, University of California, Irvine, CA 92697-3435, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science, 2Institute for Genomics and Bioinformatics and 3Department of Biological Chemistry, University of California, Irvine, CA 92697-3435, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088813478"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.2416,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.8183044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"24","issue":"13","first_page":"i357","last_page":"i365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.8184999823570251,"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":0.8184999823570251,"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/T13192","display_name":"Forensic Fingerprint Detection Methods","score":0.051600001752376556,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11476","display_name":"Graph theory and applications","score":0.012299999594688416,"subfield":{"id":"https://openalex.org/subfields/2608","display_name":"Geometry and Topology"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7275811433792114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5800607204437256},{"id":"https://openalex.org/keywords/concreteness","display_name":"Concreteness","score":0.5673797726631165},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5174870491027832},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5116155743598938},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.49227872490882874},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.47672978043556213},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.43555426597595215},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4214227795600891},{"id":"https://openalex.org/keywords/rock-blasting","display_name":"Rock blasting","score":0.4110887050628662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36107099056243896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32497620582580566},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30273181200027466},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.2027285099029541},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13310953974723816},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10320338606834412}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7275811433792114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5800607204437256},{"id":"https://openalex.org/C2778436841","wikidata":"https://www.wikidata.org/wiki/Q5159081","display_name":"Concreteness","level":2,"score":0.5673797726631165},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5174870491027832},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5116155743598938},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.49227872490882874},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.47672978043556213},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.43555426597595215},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4214227795600891},{"id":"https://openalex.org/C50933969","wikidata":"https://www.wikidata.org/wiki/Q2891954","display_name":"Rock blasting","level":2,"score":0.4110887050628662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36107099056243896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32497620582580566},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30273181200027466},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2027285099029541},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13310953974723816},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10320338606834412},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C187320778","wikidata":"https://www.wikidata.org/wiki/Q1349130","display_name":"Geotechnical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002623","descriptor_name":"Chemistry Techniques, Analytical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002623","descriptor_name":"Chemistry Techniques, Analytical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002623","descriptor_name":"Chemistry Techniques, Analytical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000737","qualifier_name":"chemistry","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":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btn187","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn187","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/13/i357/49050631/bioinformatics_24_13_i357.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:18586735","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18586735","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:oai:CiteSeerX.psu:10.1.1.698.6888","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.698.6888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.igb.uci.edu/%7Epfbaldi/download/download.inc.php?pid%3D199","raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:2718662","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2718662","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/btn187","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn187","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/13/i357/49050631/bioinformatics_24_13_i357.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7355214454","display_name":"Acquisition of Cluster and Server for Computational Biology at the University of California, Irvine","funder_award_id":"0321390","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/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2139176775.pdf","grobid_xml":"https://content.openalex.org/works/W2139176775.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1500657154","https://openalex.org/W1531524766","https://openalex.org/W1969278343","https://openalex.org/W1969462276","https://openalex.org/W1975447964","https://openalex.org/W2003136010","https://openalex.org/W2017254234","https://openalex.org/W2028079794","https://openalex.org/W2041946761","https://openalex.org/W2042492924","https://openalex.org/W2059975159","https://openalex.org/W2060097376","https://openalex.org/W2089589794","https://openalex.org/W2109246257","https://openalex.org/W2112912103","https://openalex.org/W2126829482","https://openalex.org/W2153037537","https://openalex.org/W2155741020","https://openalex.org/W2158714788","https://openalex.org/W2160114756","https://openalex.org/W2167187529","https://openalex.org/W2176516200","https://openalex.org/W2176720124","https://openalex.org/W2186952842","https://openalex.org/W2203210191","https://openalex.org/W2492427238","https://openalex.org/W2972424502","https://openalex.org/W4206409990","https://openalex.org/W4300546246","https://openalex.org/W4301259139","https://openalex.org/W6672971785","https://openalex.org/W6686585516"],"related_works":["https://openalex.org/W2954165040","https://openalex.org/W2181274975","https://openalex.org/W2361478537","https://openalex.org/W4383681101","https://openalex.org/W3017620082","https://openalex.org/W4390976331","https://openalex.org/W4255280684","https://openalex.org/W2403482502","https://openalex.org/W4285209254","https://openalex.org/W2734627439"],"abstract_inverted_index":{"MOTIVATION:":[0],"Small":[1],"organic":[2],"molecules,":[3,54],"from":[4,179],"nucleotides":[5],"and":[6,11,20,30,87,113,128,157,159,176,189,202],"amino":[7],"acids":[8],"to":[9,28,37,41,47,81,103,185,196],"metabolites":[10],"drugs,":[12],"play":[13],"a":[14,49,69,82,140],"fundamental":[15],"role":[16],"in":[17],"chemistry,":[18],"biology":[19],"medicine.":[21],"As":[22],"databases":[23],"of":[24,62,73,84,110,132,142,151,162],"small":[25,53],"molecules":[26],"continue":[27],"grow":[29],"become":[31],"more":[32],"open,":[33],"it":[34,192],"is":[35],"important":[36],"develop":[38,48,68],"the":[39,59,95,108,126,149,160,163,173,180,187],"tools":[40],"search":[42],"them":[43],"efficiently.":[44],"In":[45,106],"order":[46],"BLAST-like":[50],"tool":[51],"for":[52,124],"one":[55],"must":[56],"first":[57],"understand":[58],"statistical":[60],"behavior":[61],"molecular":[63,74,85],"similarity":[64,75,88,133],"scores.":[65,134],"RESULTS:":[66],"We":[67],"new":[70],"detailed":[71],"theory":[72,147,188],"scores":[76],"that":[77],"can":[78,193],"be":[79,194],"applied":[80,102,195],"variety":[83],"representations":[86],"measures.":[89],"For":[90],"concreteness,":[91],"we":[92,120],"focus":[93],"on":[94],"most":[96],"widely":[97],"used":[98],"measure--the":[99],"Tanimoto":[100],"measure":[101],"chemical":[104,198],"fingerprints.":[105],"both":[107,125,172],"case":[109],"empirical":[111],"fingerprints":[112,114],"generated":[115],"by":[116],"several":[117],"stochastic":[118],"models,":[119],"derive":[121],"accurate":[122],"approximations":[123],"distribution":[127,131],"extreme":[129],"value":[130],"These":[135],"approximation":[136],"are":[137,183,205],"derived":[138],"using":[139,171],"ratio":[141],"correlated":[143],"Gaussians":[144],"approach.":[145],"The":[146],"enables":[148],"calculation":[150],"significance":[152],"scores,":[153],"such":[154],"as":[155],"Z-scores":[156],"P-values,":[158],"estimation":[161],"top":[164],"hits":[165],"list":[166],"size.":[167],"Empirical":[168],"results":[169],"obtained":[170],"random":[174],"models":[175],"real":[177],"data":[178],"ChemDB":[181],"database":[182],"given":[184],"corroborate":[186],"show":[190],"how":[191],"mine":[197],"space.":[199],"AVAILABILITY:":[200],"Data":[201],"related":[203],"resources":[204],"available":[206],"through":[207],"http://cdb.ics.uci.edu.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
