{"id":"https://openalex.org/W2103938833","doi":"https://doi.org/10.1186/1758-2946-5-s1-o5","title":"Statistical modeling of value distributions of similarity coefficients in virtual screening and its application to predicting fingerprint search performance","display_name":"Statistical modeling of value distributions of similarity coefficients in virtual screening and its application to predicting fingerprint search performance","publication_year":2013,"publication_date":"2013-03-01","ids":{"openalex":"https://openalex.org/W2103938833","doi":"https://doi.org/10.1186/1758-2946-5-s1-o5","mag":"2103938833"},"language":"en","primary_location":{"id":"doi:10.1186/1758-2946-5-s1-o5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-s1-o5","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-5-S1-O5","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/10.1186/1758-2946-5-S1-O5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016304883","display_name":"Martin Vogt","orcid":"https://orcid.org/0000-0002-3931-9516"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Martin Vogt","raw_affiliation_strings":["Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Bonn, 53113, Germany","Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Bonn, 53113, Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039926688","display_name":"J\u00fcrgen Bajorath","orcid":"https://orcid.org/0000-0002-0557-5714"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Bajorath","raw_affiliation_strings":["Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Bonn, 53113, Germany","Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Bonn, 53113, Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016304883"],"corresponding_institution_ids":["https://openalex.org/I135140700"],"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":0.14128668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"5","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":0.9977999925613403,"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":0.9977999925613403,"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/T11423","display_name":"Pesticide Residue Analysis and Safety","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13192","display_name":"Forensic Fingerprint Detection Methods","score":0.9632999897003174,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.8267002105712891},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.7763521671295166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6215202808380127},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5445845127105713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5306103825569153},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.48467209935188293},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.47168806195259094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45736604928970337},{"id":"https://openalex.org/keywords/bernoullis-principle","display_name":"Bernoulli's principle","score":0.43886905908584595},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43463683128356934},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07211571931838989}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.8267002105712891},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.7763521671295166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6215202808380127},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5445845127105713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5306103825569153},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.48467209935188293},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.47168806195259094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45736604928970337},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.43886905908584595},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43463683128356934},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07211571931838989},{"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/1758-2946-5-s1-o5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-s1-o5","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-5-S1-O5","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:europepmc.org:2605442","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3606147","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1758-2946-5-s1-o5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-5-s1-o5","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/1758-2946-5-S1-O5","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":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2103938833.pdf"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W1999794103"],"related_works":["https://openalex.org/W1619264321","https://openalex.org/W2899588557","https://openalex.org/W4254565718","https://openalex.org/W3094386089","https://openalex.org/W2180382450","https://openalex.org/W4298392611","https://openalex.org/W4233030079","https://openalex.org/W2129020938","https://openalex.org/W2188500270","https://openalex.org/W2303858293"],"abstract_inverted_index":{"Similarity":[0],"searching":[1],"using":[2],"fingerprints":[3,209],"is":[4,15,28,84,94,112],"a":[5,103,166,169,216,220],"popular":[6],"ligand-based":[7],"virtual":[8,62],"screening":[9],"approach.":[10],"The":[11,156],"Tanimoto":[12,142],"coefficient":[13],"(Tc)":[14],"the":[16,33,36,49,70,78,87,92,107,120,163,180,188,206],"most":[17],"widely":[18],"used":[19,85],"measure":[20],"for":[21,61,90],"quantifying":[22],"fingerprint":[23,82,93,124,196],"similarity.":[24],"In":[25,48,96],"general,":[26],"it":[27,159,199],"very":[29,67],"difficult":[30],"to":[31,98,152,161,179,203,210],"assess":[32,205],"significance":[34],"of":[35,38,72,81,123,141,145,165,185,191,194,208,222],"similarity":[37,59,73,100,116,143,192],"two":[39],"molecules":[40,186,214,225],"solely":[41],"based":[42,118,173],"on":[43,77,119,174],"their":[44],"calculated":[45],"Tc":[46,51,176],"values.":[47],"literature,":[50],"cut-off":[52],"values":[53,144,193],"are":[54,132,148],"frequently":[55],"intuitively":[56],"chosen":[57],"as":[58,134],"criteria":[60],"screening.":[63],"This":[64,182],"can":[65,200],"be":[66,201],"problematic":[68],"because":[69],"distribution":[71,122],"scores":[74,117],"largely":[75],"depends":[76],"specific":[79],"type":[80],"that":[83,114],"and":[86,138],"reference":[88,154,224],"compound":[89,128,167],"which":[91],"calculated.":[95],"order":[97],"rationalize":[99],"value":[101,177],"considerations,":[102],"statistical":[104,121],"approach":[105],"named":[106],"conditional":[108,139],"correlated":[109],"Bernoulli":[110,136],"model":[111,157],"presented":[113],"models":[115],"features":[125,131],"in":[126,168,215],"large":[127],"databases.":[129],"Fingerprint":[130],"modeled":[133],"dependent":[135],"variables":[137],"distributions":[140],"database":[146,170,217],"compounds":[147],"determined":[149],"with":[150],"respect":[151],"given":[153,219],"compounds.":[155],"makes":[158],"possible":[160],"estimate":[162],"position":[164],"ranking":[171],"only":[172],"its":[175],"relative":[178],"reference.":[181],"rank":[183],"estimation":[184],"enables":[187],"quantitative":[189],"comparison":[190],"different":[195],"types.":[197],"Moreover,":[198],"utilized":[202],"rapidly":[204],"potential":[207],"identify":[211],"new":[212],"active":[213],"search":[218],"set":[221],"known":[223],"[1].":[226]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}