Combinatorial Preferences Affect Molecular Similarity/Diversity Calculations Using Binary Fingerprints and Tanimoto Coefficients. Godden, J., Xue, L., & Bajorath, J. Journal of Chemical Information and Computer Sciences, 40(1):163--166, AMER CHEMICAL SOC, 1155 16TH ST, NW, WASHINGTON, DC 20036 USA, 2000. abstract bibtex A combinatorial method was developed to calculate complete distributions of the Tanimoto coefficient (Tc) for binary fingerprint (FP) representations of specified length, regardless of the chemical parameters they reflect. Theoretical Tc distributions were calculated for FPs consisting of up to 67 bit positions which revealed significant statistical preferences of certain Tc values. Calculation of Tc distributions in a large compound database using different FPs mirrored the effects identified by our general analysis. On the basis of these findings, an average Tc is biased by statistically preferred values.
@article{Godden:2000zy,
Abstract = {A combinatorial method was developed to calculate complete distributions of the Tanimoto coefficient (Tc) for binary fingerprint (FP) representations of specified length, regardless of the chemical parameters they reflect. Theoretical Tc distributions were calculated for FPs consisting of up to 67 bit positions which revealed significant statistical preferences of certain Tc values. Calculation of Tc distributions in a large compound database using different FPs mirrored the effects identified by our general analysis. On the basis of these findings, an average Tc is biased by statistically preferred values.},
Address = {1155 16TH ST, NW, WASHINGTON, DC 20036 USA},
Author = {Godden, J.W. and Xue, L. and Bajorath, J.},
Date = {JAN-FEB 2000},
Date-Added = {2009-04-27 17:22:21 -0400},
Date-Modified = {2009-04-27 17:23:45 -0400},
Isi = {000085016800019},
Isi-Recid = {113522230},
Isi-Ref-Recids = {99053860 106344604 94340817 111945582 105356633 96941656 96052168 110305858 100644581 96932908 106074355 113522232 84874237 107858246 111945581},
Journal = {Journal of Chemical Information and Computer Sciences},
Keywords = {diversity; fingerprint; similarity},
Number = {1},
Pages = {163--166},
Publisher = {AMER CHEMICAL SOC},
Timescited = {38},
Title = {Combinatorial Preferences Affect Molecular Similarity/Diversity Calculations Using Binary Fingerprints and Tanimoto Coefficients},
Volume = {40},
Year = {2000},
Bdsk-File-1 = {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},
Bdsk-Url-1 = {http://dx.doi.org/10.1021/ci990316u}}
Downloads: 0
{"_id":"AjiNQsprLZ7CeqfwG","bibbaseid":"godden-xue-bajorath-combinatorialpreferencesaffectmolecularsimilaritydiversitycalculationsusingbinaryfingerprintsandtanimotocoefficients-2000","downloads":0,"creationDate":"2016-02-18T13:03:30.408Z","title":"Combinatorial Preferences Affect Molecular Similarity/Diversity Calculations Using Binary Fingerprints and Tanimoto Coefficients","author_short":["Godden, J.","Xue, L.","Bajorath, J."],"year":2000,"bibtype":"article","biburl":"https://dl.dropboxusercontent.com/u/26998770/main.bib","bibdata":{"bibtype":"article","type":"article","abstract":"A combinatorial method was developed to calculate complete distributions of the Tanimoto coefficient (Tc) for binary fingerprint (FP) representations of specified length, regardless of the chemical parameters they reflect. Theoretical Tc distributions were calculated for FPs consisting of up to 67 bit positions which revealed significant statistical preferences of certain Tc values. Calculation of Tc distributions in a large compound database using different FPs mirrored the effects identified by our general analysis. On the basis of these findings, an average Tc is biased by statistically preferred values.","address":"1155 16TH ST, NW, WASHINGTON, DC 20036 USA","author":[{"propositions":[],"lastnames":["Godden"],"firstnames":["J.W."],"suffixes":[]},{"propositions":[],"lastnames":["Xue"],"firstnames":["L."],"suffixes":[]},{"propositions":[],"lastnames":["Bajorath"],"firstnames":["J."],"suffixes":[]}],"date":"JAN-FEB 2000","date-added":"2009-04-27 17:22:21 -0400","date-modified":"2009-04-27 17:23:45 -0400","isi":"000085016800019","isi-recid":"113522230","isi-ref-recids":"99053860 106344604 94340817 111945582 105356633 96941656 96052168 110305858 100644581 96932908 106074355 113522232 84874237 107858246 111945581","journal":"Journal of Chemical Information and Computer Sciences","keywords":"diversity; fingerprint; similarity","number":"1","pages":"163--166","publisher":"AMER CHEMICAL SOC","timescited":"38","title":"Combinatorial Preferences Affect Molecular Similarity/Diversity Calculations Using Binary Fingerprints and Tanimoto Coefficients","volume":"40","year":"2000","bdsk-file-1":"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","bdsk-url-1":"http://dx.doi.org/10.1021/ci990316u","bibtex":"@article{Godden:2000zy,\n\tAbstract = {A combinatorial method was developed to calculate complete distributions of the Tanimoto coefficient (Tc) for binary fingerprint (FP) representations of specified length, regardless of the chemical parameters they reflect. Theoretical Tc distributions were calculated for FPs consisting of up to 67 bit positions which revealed significant statistical preferences of certain Tc values. Calculation of Tc distributions in a large compound database using different FPs mirrored the effects identified by our general analysis. On the basis of these findings, an average Tc is biased by statistically preferred values.},\n\tAddress = {1155 16TH ST, NW, WASHINGTON, DC 20036 USA},\n\tAuthor = {Godden, J.W. and Xue, L. and Bajorath, J.},\n\tDate = {JAN-FEB 2000},\n\tDate-Added = {2009-04-27 17:22:21 -0400},\n\tDate-Modified = {2009-04-27 17:23:45 -0400},\n\tIsi = {000085016800019},\n\tIsi-Recid = {113522230},\n\tIsi-Ref-Recids = {99053860 106344604 94340817 111945582 105356633 96941656 96052168 110305858 100644581 96932908 106074355 113522232 84874237 107858246 111945581},\n\tJournal = {Journal of Chemical Information and Computer Sciences},\n\tKeywords = {diversity; fingerprint; similarity},\n\tNumber = {1},\n\tPages = {163--166},\n\tPublisher = {AMER CHEMICAL SOC},\n\tTimescited = {38},\n\tTitle = {Combinatorial Preferences Affect Molecular Similarity/Diversity Calculations Using Binary Fingerprints and Tanimoto Coefficients},\n\tVolume = {40},\n\tYear = {2000},\n\tBdsk-File-1 = {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},\n\tBdsk-Url-1 = {http://dx.doi.org/10.1021/ci990316u}}\n\n","author_short":["Godden, J.","Xue, L.","Bajorath, J."],"key":"Godden:2000zy","id":"Godden:2000zy","bibbaseid":"godden-xue-bajorath-combinatorialpreferencesaffectmolecularsimilaritydiversitycalculationsusingbinaryfingerprintsandtanimotocoefficients-2000","role":"author","urls":{},"keyword":["diversity; fingerprint; similarity"],"downloads":0},"search_terms":["combinatorial","preferences","affect","molecular","similarity","diversity","calculations","using","binary","fingerprints","tanimoto","coefficients","godden","xue","bajorath"],"keywords":["diversity; fingerprint; similarity"],"authorIDs":[],"dataSources":["c5japf9eAQRaeMS4h"]}