{"id":"https://openalex.org/W2146932302","doi":"https://doi.org/10.1186/1758-2946-4-s1-p26","title":"A large scale classification of molecular fingerprints for the chemical space representation and SAR analysis","display_name":"A large scale classification of molecular fingerprints for the chemical space representation and SAR analysis","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2146932302","doi":"https://doi.org/10.1186/1758-2946-4-s1-p26","mag":"2146932302"},"language":"en","primary_location":{"id":"doi:10.1186/1758-2946-4-s1-p26","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-4-s1-p26","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-4-S1-P26","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"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":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-4-S1-P26","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041252377","display_name":"Fabi\u00e1n L\u00f3pez-Vallejo","orcid":"https://orcid.org/0000-0002-5802-9530"},"institutions":[{"id":"https://openalex.org/I40399489","display_name":"Torrey Pines Institute For Molecular Studies","ror":"https://ror.org/01grq2104","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I40399489"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fabian L\u00f3pez-Vallejo","raw_affiliation_strings":["Torrey Pines Institute for Molecular Studies, Port St. Lucie, Florida, 34987, USA","Torrey Pines Institute for Molecular Studies, Port St Lucie, USA"],"affiliations":[{"raw_affiliation_string":"Torrey Pines Institute for Molecular Studies, Port St. Lucie, Florida, 34987, USA","institution_ids":["https://openalex.org/I40399489"]},{"raw_affiliation_string":"Torrey Pines Institute for Molecular Studies, Port St Lucie, USA","institution_ids":["https://openalex.org/I40399489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018093551","display_name":"Jacob Waddell","orcid":null},"institutions":[{"id":"https://openalex.org/I40399489","display_name":"Torrey Pines Institute For Molecular Studies","ror":"https://ror.org/01grq2104","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I40399489"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Waddell","raw_affiliation_strings":["Torrey Pines Institute for Molecular Studies, Port St. Lucie, Florida, 34987, USA","Torrey Pines Institute for Molecular Studies, Port St Lucie, USA"],"affiliations":[{"raw_affiliation_string":"Torrey Pines Institute for Molecular Studies, Port St. Lucie, Florida, 34987, USA","institution_ids":["https://openalex.org/I40399489"]},{"raw_affiliation_string":"Torrey Pines Institute for Molecular Studies, Port St Lucie, USA","institution_ids":["https://openalex.org/I40399489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048145359","display_name":"Austin B. Yongye","orcid":null},"institutions":[{"id":"https://openalex.org/I40399489","display_name":"Torrey Pines Institute For Molecular Studies","ror":"https://ror.org/01grq2104","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I40399489"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin B Yongye","raw_affiliation_strings":["Torrey Pines Institute for Molecular Studies, Port St. Lucie, Florida, 34987, USA","Torrey Pines Institute for Molecular Studies, Port St Lucie, USA"],"affiliations":[{"raw_affiliation_string":"Torrey Pines Institute for Molecular Studies, Port St. Lucie, Florida, 34987, USA","institution_ids":["https://openalex.org/I40399489"]},{"raw_affiliation_string":"Torrey Pines Institute for Molecular Studies, Port St Lucie, USA","institution_ids":["https://openalex.org/I40399489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047419813","display_name":"Richard A. Houghten","orcid":"https://orcid.org/0000-0003-0310-4879"},"institutions":[{"id":"https://openalex.org/I40399489","display_name":"Torrey Pines Institute For Molecular Studies","ror":"https://ror.org/01grq2104","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I40399489"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard A Houghten","raw_affiliation_strings":["Torrey Pines Institute for Molecular Studies, Port St. Lucie, Florida, 34987, USA","Torrey Pines Institute for Molecular Studies, Port St Lucie, USA"],"affiliations":[{"raw_affiliation_string":"Torrey Pines Institute for Molecular Studies, Port St. Lucie, Florida, 34987, USA","institution_ids":["https://openalex.org/I40399489"]},{"raw_affiliation_string":"Torrey Pines Institute for Molecular Studies, Port St Lucie, USA","institution_ids":["https://openalex.org/I40399489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086421148","display_name":"Jos\u00e9 L. Medina\u2010Franco","orcid":"https://orcid.org/0000-0003-4940-1107"},"institutions":[{"id":"https://openalex.org/I40399489","display_name":"Torrey Pines Institute For Molecular Studies","ror":"https://ror.org/01grq2104","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I40399489"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 L Medina-Franco","raw_affiliation_strings":["Torrey Pines Institute for Molecular Studies, Port St. Lucie, Florida, 34987, USA","Torrey Pines Institute for Molecular Studies, Port St Lucie, USA"],"affiliations":[{"raw_affiliation_string":"Torrey Pines Institute for Molecular Studies, Port St. Lucie, Florida, 34987, USA","institution_ids":["https://openalex.org/I40399489"]},{"raw_affiliation_string":"Torrey Pines Institute for Molecular Studies, Port St Lucie, USA","institution_ids":["https://openalex.org/I40399489"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041252377"],"corresponding_institution_ids":["https://openalex.org/I40399489"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.17117962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"4","issue":"S1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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":1.0,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.982699990272522,"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"}},{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9627000093460083,"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/similarity","display_name":"Similarity (geometry)","score":0.8166698217391968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.706840991973877},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.7065690159797668},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.686329185962677},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.604315459728241},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.5147135853767395},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.49497169256210327},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4920770525932312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46896305680274963},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45504230260849},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4546518623828888},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.41245341300964355},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3960508406162262},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32784736156463623},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.14032208919525146},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.12425628304481506},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10916092991828918},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08530557155609131}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.8166698217391968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.706840991973877},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.7065690159797668},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.686329185962677},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.604315459728241},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.5147135853767395},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49497169256210327},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4920770525932312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46896305680274963},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45504230260849},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4546518623828888},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.41245341300964355},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3960508406162262},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32784736156463623},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.14032208919525146},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.12425628304481506},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10916092991828918},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08530557155609131},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/1758-2946-4-s1-p26","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-4-s1-p26","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-4-S1-P26","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"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":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:84bfca326b104386bc68a51c3e2c8a7a","is_oa":true,"landing_page_url":"https://doaj.org/article/84bfca326b104386bc68a51c3e2c8a7a","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 4, Iss Suppl 1, p P26 (2012)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:3341238","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3341238","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1758-2946-4-s1-p26","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-4-s1-p26","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-4-S1-P26","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"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":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2146932302.pdf","grobid_xml":"https://content.openalex.org/works/W2146932302.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1903660083","https://openalex.org/W1973552820","https://openalex.org/W2059511140","https://openalex.org/W2100916935","https://openalex.org/W2140972311","https://openalex.org/W2330150548"],"related_works":["https://openalex.org/W2902857455","https://openalex.org/W2161782568","https://openalex.org/W4212982662","https://openalex.org/W4226062292","https://openalex.org/W4281772408","https://openalex.org/W2078293348","https://openalex.org/W4254684673","https://openalex.org/W2023175890","https://openalex.org/W2068608913","https://openalex.org/W3191713309"],"abstract_inverted_index":{"Fingerprint-based":[0],"structure":[1,54],"representation":[2],"has":[3,29,75],"a":[4,57,124],"broad":[5],"range":[6],"of":[7,41,64,88,100,111,123,127,138,197],"applications":[8],"including,":[9],"but":[10],"not":[11,94],"limited":[12],"to,":[13],"diversity":[14,141],"analysis,":[15],"compound":[16],"classification,":[17],"chemical":[18,112],"space":[19,113],"visualization":[20],"[1],":[21],"activity":[22,46,72,115],"landscape":[23,73],"modelling":[24,74],"and":[25,114,132,186],"similarity":[26,42,65,146,182,195],"searching.":[27],"It":[28],"been":[30,76],"shown":[31],"that":[32],"depending":[33],"on":[34],"the":[35,39,62,86,121,165,192],"particular":[36],"fingerprints":[37,89,185,199],"used,":[38],"outcome":[40],"searching":[43,66],"[2]":[44],"or":[45],"landscapes":[47,116],"[3]":[48],"can":[49,176],"be":[50,91,177],"very":[51],"different.":[52],"Combining":[53],"representations":[55,70,106,110,135],"is":[56,93],"common":[58],"practice":[59],"to":[60,78,90,103,107,145,159,180],"increase":[61],"performance":[63,139],"[4].":[67],"Also,":[68],"combining":[69],"for":[71],"proposed":[77],"generate":[79,108],"robust":[80],"descriptive":[81],"SAR":[82],"models":[83],"[5].":[84],"However,":[85],"selection":[87],"combined":[92],"an":[95],"easy":[96],"task.":[97],"As":[98],"part":[99],"our":[101],"efforts":[102],"select":[104],"fingerprint":[105,134],"consensus":[109],"[5,6]":[117],"herein":[118],"we":[119],"discuss":[120,191],"results":[122],"systematic":[125],"comparison":[126],"more":[128,150],"than":[129,151],"10":[130],"2D":[131],"3D":[133],"in":[136,140],"terms":[137],"analysis":[142],"(as":[143],"opposed":[144],"searching).":[147],"We":[148,189],"employed":[149],"20":[152],"data":[153],"sets":[154],"from":[155,202],"different":[156,203],"sources":[157],"relevant":[158],"drug":[160],"discovery.":[161],"In":[162],"this":[163],"work":[164],"widely":[166],"used":[167],"Tanimoto":[168],"coefficient":[169],"was":[170],"employed.":[171],"The":[172],"approach":[173],"presented":[174],"here":[175],"easily":[178],"extended":[179],"other":[181],"measures,":[183],"additional":[184],"molecular":[187],"databases.":[188],"also":[190],"typical":[193],"mean/median":[194],"values":[196],"selected":[198],"across":[200],"databases":[201],"sources.":[204]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2016-06-24T00:00:00"}