{"id":"https://openalex.org/W2118353525","doi":"https://doi.org/10.1186/1748-7188-5-9","title":"A tree-based method for the rapid screening of chemical fingerprints","display_name":"A tree-based method for the rapid screening of chemical fingerprints","publication_year":2010,"publication_date":"2010-01-04","ids":{"openalex":"https://openalex.org/W2118353525","doi":"https://doi.org/10.1186/1748-7188-5-9","mag":"2118353525","pmid":"https://pubmed.ncbi.nlm.nih.gov/20047665"},"language":"en","primary_location":{"id":"doi:10.1186/1748-7188-5-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1748-7188-5-9","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-5-9","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-5-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087083975","display_name":"Thomas G. Kristensen","orcid":null},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Thomas G Kristensen","raw_affiliation_strings":["Bioinformatics Research Center, Aarhus University, CF M\u00f8llers All\u00e9 8, DK-8000 Arhus C, Denmark. tgk@birc.au.dk","Bioinformatics Research Center (BiRC), Aarhus University, \u00c5rhus C, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Research Center, Aarhus University, CF M\u00f8llers All\u00e9 8, DK-8000 Arhus C, Denmark. tgk@birc.au.dk","institution_ids":["https://openalex.org/I204337017"]},{"raw_affiliation_string":"Bioinformatics Research Center (BiRC), Aarhus University, \u00c5rhus C, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067885668","display_name":"Jesper Buus Nielsen","orcid":"https://orcid.org/0000-0002-7074-0683"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Nielsen","raw_affiliation_strings":["Bioinformatics Research Center (BiRC), Aarhus University, CF M\u00f8llers All\u00e9 8, DK-8000, \u00c5rhus C, Denmark","Bioinformatics Research Center (BiRC), Aarhus University, \u00c5rhus C, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Research Center (BiRC), Aarhus University, CF M\u00f8llers All\u00e9 8, DK-8000, \u00c5rhus C, Denmark","institution_ids":["https://openalex.org/I204337017"]},{"raw_affiliation_string":"Bioinformatics Research Center (BiRC), Aarhus University, \u00c5rhus C, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103578511","display_name":"Christian NS Pedersen","orcid":null},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Christian NS Pedersen","raw_affiliation_strings":["Bioinformatics Research Center (BiRC), Aarhus University, CF M\u00f8llers All\u00e9 8, DK-8000, \u00c5rhus C, Denmark","Bioinformatics Research Center (BiRC), Aarhus University, \u00c5rhus C, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Research Center (BiRC), Aarhus University, CF M\u00f8llers All\u00e9 8, DK-8000, \u00c5rhus C, Denmark","institution_ids":["https://openalex.org/I204337017"]},{"raw_affiliation_string":"Bioinformatics Research Center (BiRC), Aarhus University, \u00c5rhus C, Denmark","institution_ids":["https://openalex.org/I204337017"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087083975"],"corresponding_institution_ids":["https://openalex.org/I204337017"],"apc_list":{"value":1490,"currency":"GBP","value_usd":1827},"apc_paid":{"value":1490,"currency":"GBP","value_usd":1827},"fwci":5.1484,"has_fulltext":true,"cited_by_count":49,"citation_normalized_percentile":{"value":0.95758383,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"5","issue":"1","first_page":"9","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.8223999738693237,"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":0.8223999738693237,"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":0.04399999976158142,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.01489999983459711,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7796313762664795},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.7421320080757141},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.733506441116333},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6295738220214844},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6282321214675903},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5807916522026062},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5627829432487488},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5453954339027405},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4846223294734955},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4263778030872345},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33819815516471863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20139554142951965},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13756197690963745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7796313762664795},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.7421320080757141},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.733506441116333},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6295738220214844},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6282321214675903},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5807916522026062},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5627829432487488},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5453954339027405},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4846223294734955},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4263778030872345},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33819815516471863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20139554142951965},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13756197690963745},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/1748-7188-5-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1748-7188-5-9","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-5-9","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},{"id":"pmid:20047665","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20047665","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":"Algorithms for molecular biology : AMB","raw_type":null},{"id":"pmh:oai:doaj.org/article:34f041d8bbaa45fa9a9128ee29a3a4a5","is_oa":false,"landing_page_url":"https://doaj.org/article/34f041d8bbaa45fa9a9128ee29a3a4a5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms for Molecular Biology, Vol 5, Iss 1, p 9 (2010)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2830925","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2830925","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms Mol Biol","raw_type":"Text"},{"id":"pmh:oai:pure.atira.dk:publications/5c9c4630-d782-11df-a891-000ea68e967b","is_oa":false,"landing_page_url":"https://pure.au.dk/portal/en/publications/5c9c4630-d782-11df-a891-000ea68e967b","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kristensen, T G, Nielsen, J & Pedersen, C N S 2010, 'A tree-based method for the rapid screening of chemical fingerprints', Algorithms for Molecular Biology, vol. 5, no. 9. https://doi.org/10.1186/1748-7188-5-9","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1186/1748-7188-5-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1748-7188-5-9","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-5-9","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2118353525.pdf","grobid_xml":"https://content.openalex.org/works/W2118353525.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1531524766","https://openalex.org/W2008999889","https://openalex.org/W2058033857","https://openalex.org/W2092581985","https://openalex.org/W2096729078","https://openalex.org/W2097706568","https://openalex.org/W2148797284","https://openalex.org/W2176516200","https://openalex.org/W2176720124","https://openalex.org/W2203775767"],"related_works":["https://openalex.org/W2339806289","https://openalex.org/W3008853525","https://openalex.org/W2109424811","https://openalex.org/W2368132270","https://openalex.org/W2173185020","https://openalex.org/W2986003362","https://openalex.org/W4292477917","https://openalex.org/W4246757943","https://openalex.org/W109501413","https://openalex.org/W2375480909"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,81,103,129],"fingerprint":[2,75],"of":[3,32,93,125,189],"a":[4,7,50,59,67,77,153,166],"molecule":[5],"is":[6,83,106],"bitstring":[8],"based":[9,84,107],"on":[10,85,108,122,152],"its":[11],"structure,":[12],"constructed":[13],"such":[14],"that":[15,161],"structurally":[16],"similar":[17,21,48,142],"molecules":[18,45],"will":[19,192],"have":[20,145],"fingerprints.":[22,190],"Molecular":[23],"fingerprints":[24,47,65,111],"can":[25],"be":[26],"used":[27],"in":[28,66],"an":[29],"initial":[30],"phase":[31],"drug":[33,38],"development":[34],"for":[35,44,90,186],"identifying":[36],"novel":[37,87,175],"candidates":[39],"by":[40],"screening":[41,92],"large":[42,94,154,208],"databases":[43,188],"with":[46,69],"to":[49,72,119,140,195,205],"query":[51,74],"fingerprint.":[52],"RESULTS:":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"present":[58],"method":[60,82,148,163],"which":[61],"efficiently":[62],"finds":[63],"all":[64],"database":[68],"Tanimoto":[70],"coefficient":[71],"the":[73,96,100,110,123,126,174,183],"above":[76],"user":[78],"defined":[79],"threshold.":[80],"two":[86],"data":[88,156],"structures":[89],"rapid":[91],"databases:":[95],"kD":[97,104,176],"grid":[98,105,177],"and":[99,116,135,149,178,203],"Multibit":[101,130,179],"tree.":[102],"splitting":[109],"into":[112],"k":[113],"shorter":[114],"bitstrings":[115],"utilising":[117],"these":[118],"compute":[120,141],"bounds":[121],"similarity":[124,136],"complete":[127],"bitstrings.":[128],"tree":[131,180],"uses":[132],"hierarchical":[133],"clustering":[134],"within":[137],"each":[138],"cluster":[139],"bounds.":[143],"We":[144],"implemented":[146],"our":[147,162],"tested":[150],"it":[151],"real-world":[155],"set.":[157],"Our":[158],"experiments":[159],"show":[160],"yields":[164],"approximately":[165],"three-fold":[167],"speed-up":[168],"over":[169],"previous":[170],"methods.":[171],"CONCLUSIONS:":[172],"Using":[173],"significantly":[181],"reduce":[182],"time":[184],"needed":[185],"searching":[187],"This":[191],"allow":[193],"researchers":[194],"(1)":[196],"perform":[197],"more":[198],"searches":[199],"than":[200],"previously":[201],"possible":[202],"(2)":[204],"easily":[206],"search":[207],"databases.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}