{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T03:34:51Z","timestamp":1791516891907,"version":"4.3.4"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,3,1]],"date-time":"2013-03-01T00:00:00Z","timestamp":1362096000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Comput Aided Mol Des"],"published-print":{"date-parts":[[2013,3]]},"DOI":"10.1007\/s10822-013-9639-5","type":"journal-article","created":{"date-parts":[[2013,3,15]],"date-time":"2013-03-15T16:12:03Z","timestamp":1363363923000},"page":"203-219","source":"Crossref","is-referenced-by-count":36,"title":["QSAR with experimental and predictive distributions: an information theoretic approach for assessing model quality"],"prefix":"10.1007","volume":"27","author":[{"given":"David J.","family":"Wood","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lars","family":"Carlsson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Eklund","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ulf","family":"Norinder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonna","family":"St\u00e5lring","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2013,3,16]]},"reference":[{"key":"9639_CR1","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1007\/s10822-007-9162-7","volume":"22","author":"AM Doweyko","year":"2008","unstructured":"Doweyko AM (2008) QSAR: dead or alive? J Comput Aided Mol Des 22:81\u201389","journal-title":"J Comput Aided Mol Des"},{"key":"9639_CR2","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1002\/qsar.200390007","volume":"1","author":"A Tropsha","year":"2003","unstructured":"Tropsha A, Gramatica P, Gombar V (2003) The importance of being earnest: validation is the absolute essential for successful application and interpretation of QSPR models. QSAR Comb Sci 1:69\u201377","journal-title":"QSAR Comb Sci"},{"issue":"11","key":"9639_CR3","doi-asserted-by":"crossref","first-page":"1435","DOI":"10.1517\/17425255.2012.711317","volume":"8","author":"MP Gleeson","year":"2012","unstructured":"Gleeson MP, Montanari D (2012) Strategies for the generation, validation and application of in silico ADMET models in lead generation and optimization. Expert Opin Drug Meta Toxicol 8(11):1435\u20131446","journal-title":"Expert Opin Drug Meta Toxicol"},{"key":"9639_CR4","unstructured":"Organisation for Economic Co-operation and Development (2007) Guidance document on the validation of (Quantitative) structure-activity relationships [(Q)SAR] models. Report Number ENV\/JM\/MONO"},{"key":"9639_CR5","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1016\/j.datak.2008.08.001","volume":"3","author":"Z Bosni\u0107","year":"2008","unstructured":"Bosni\u0107 Z, Kononenko I (2008) Comparison of approaches for estimating reliability of individual regression predictions. Data Knowl Eng 3:504\u2013516","journal-title":"Data Knowl Eng"},{"key":"9639_CR6","doi-asserted-by":"crossref","first-page":"1912","DOI":"10.1021\/ci049782w","volume":"6","author":"RP Sheridan","year":"2004","unstructured":"Sheridan RP, Feuston BP, Maiorov VN, Kearsley SK (2004) Similarity to molecules in the training set is a good discriminator for prediction accuracy in QSAR. J Chem Inf Comput Sci 6:1912\u20131928","journal-title":"J Chem Inf Comput Sci"},{"key":"9639_CR7","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1016\/j.jmgm.2008.01.002","volume":"8","author":"S Weaver","year":"2008","unstructured":"Weaver S, Gleeson MP (2008) The importance of the domain of applicability in QSAR modeling. J Mol Graph Model 8:1315\u20131326","journal-title":"J Mol Graph Model"},{"key":"9639_CR8","doi-asserted-by":"crossref","first-page":"2094","DOI":"10.1021\/ci100253r","volume":"12","author":"I Sushko","year":"2010","unstructured":"Sushko I, Novotarskyi S, Korner R, Pandey AK, Cherkasov A, Li J, Gramatica P, Hansen K, Schroeter T, Muller K, Xi L, Liu H, Yao X, Oberg T, Hormozdiari F, Dao P, Sahinalp C, Todeschini R, Polishchuk P, Artemenko A, Kuz\u00e2min V, Martin TM, Young DM, Fourches D, Muratov E, Tropsha A, Baskin I, Horvath D, Marcou G, Muller C, Varnek A, Prokopenko VV, Tetko IV (2010) Applicability domains for classification problems: benchmarking of distance to models for Ames mutagenicity set. J Chem Inf Model 12:2094\u20132111","journal-title":"J Chem Inf Model"},{"key":"9639_CR9","doi-asserted-by":"crossref","first-page":"1733","DOI":"10.1021\/ci800151m","volume":"48","author":"IV Tetko","year":"2008","unstructured":"Tetko IV, Sushko I, Pandey AK, Zhu H, Tropsha A, Papa E, Oberg T, Todeschini R, Fourches D, Varnek A (2008) Critical assessment of QSAR models of environmental toxicity against tetrahymena pyriformis: focusing on applicability domain and overfitting by variable selection. J Chem Inf Model 48:1733\u20131746","journal-title":"J Chem Inf Model"},{"key":"9639_CR10","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/1758-2946-1-11","volume":"1","author":"RD Clark","year":"2009","unstructured":"Clark RD (2009) DPRESS: localizing estimates of predictive uncertainty. J Cheminf 1:11","journal-title":"J Cheminf"},{"key":"9639_CR11","doi-asserted-by":"crossref","first-page":"2660","DOI":"10.1021\/ci900313u","volume":"12","author":"R Kuhne","year":"2009","unstructured":"Kuhne R, Ebert R, Schuurmann G (2009) Chemical domain of QSAR models from atom-centered fragments. J Chem Inf Model 12:2660\u20132669","journal-title":"J Chem Inf Model"},{"key":"9639_CR12","doi-asserted-by":"crossref","first-page":"814","DOI":"10.1021\/ci300004n","volume":"3","author":"R Sheridan","year":"2012","unstructured":"Sheridan R (2012) Three useful dimensions for domain applicability in QSAR models using random forest. J Chem Inf Model 3:814\u2013823","journal-title":"J Chem Inf Model"},{"key":"9639_CR13","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1002\/qsar.200630020","volume":"2","author":"TW Schultz","year":"2007","unstructured":"Schultz TW, Hewitt M, Netzeva TI, Cronin MTD (2007) Assessing applicability domains of toxicological QSARs: definition, confidence in predicted values, and the role of mechanisms of action. QSAR Comb Sci 2:238\u2013254","journal-title":"QSAR Comb Sci"},{"key":"9639_CR14","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.1021\/ci0504014","volume":"3","author":"P Bruneau","year":"2006","unstructured":"Bruneau P, McElroy NR (2006) logD7.4 modeling using bayesian regularized neural networks. Assessment and correction of the errors of prediction. J Chem Inf Model 3:1379\u20131387","journal-title":"J Chem Inf Model"},{"key":"9639_CR15","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1002\/minf.201000177","volume":"6\u20137","author":"U Sahlin","year":"2011","unstructured":"Sahlin U, Filipsson M, \u00d6berg T (2011) A risk assessment perspective of current practice in characterizing uncertainties in QSAR regression predictions. Mol Inform 6\u20137:551\u2013564","journal-title":"Mol Inform"},{"key":"9639_CR16","doi-asserted-by":"crossref","first-page":"1847","DOI":"10.1021\/ci7000633","volume":"5","author":"O Obrezanova","year":"2007","unstructured":"Obrezanova O, Cs\u00e1nyi G, Gola JMR, Segall MD (2007) Gaussian processes: a method for automatic QSAR modeling of ADME properties. J Chem Inf Model 5:1847\u20131857","journal-title":"J Chem Inf Model"},{"key":"9639_CR17","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3206.001.0001","volume-title":"Gaussian processes for machine learning (adaptive computation and machine learning)","author":"C Rasmussen","year":"2005","unstructured":"Rasmussen C, Williams C (2005) Gaussian processes for machine learning (adaptive computation and machine learning). The MIT Press, Cambridge"},{"key":"9639_CR18","doi-asserted-by":"crossref","first-page":"830","DOI":"10.1021\/ci000459c","volume":"3","author":"FR Burden","year":"2001","unstructured":"Burden FR (2001) Quantitative structure\u2212activity relationship studies using Gaussian processes. J Chem Inf Comput Sci 3:830\u2013835","journal-title":"J Chem Inf Comput Sci"},{"key":"9639_CR19","first-page":"1","volume-title":"Model selection and multimodel inference: a practical information-theoretic approach","author":"K Burnham","year":"2002","unstructured":"Burnham K, Anderson D (2002) Model selection and multimodel inference: a practical information-theoretic approach. Springer, Berlin, pp 1\u2013488"},{"key":"9639_CR20","unstructured":"Nicholls A (2008) Information and measurement. Presentation in the computers in chemistry division of the American chemical society national meeting"},{"key":"9639_CR21","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/TAC.1974.1100705","volume":"6","author":"H Akaike","year":"1974","unstructured":"Akaike H (1974) A new look at the statistical model identification. IEEE Trans Autom Control 6:716\u2013723","journal-title":"IEEE Trans Autom Control"},{"key":"9639_CR22","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1214\/aos\/1176344136","volume":"2","author":"G Schwarz","year":"1978","unstructured":"Schwarz G (1978) Estimating the dimension of a model. Ann Stat 2:461\u2013464","journal-title":"Ann Stat"},{"issue":"1","key":"9639_CR23","first-page":"1","volume":"4","author":"S Cha","year":"2007","unstructured":"Cha S (2007) Comprehensive survey on distance\/similarity measures between probability density functions. Int J Math Models Methods Appl Sci 4(1):1\u201324","journal-title":"Int J Math Models Methods Appl Sci"},{"issue":"6","key":"9639_CR24","doi-asserted-by":"crossref","first-page":"p1347","DOI":"10.1021\/ci900087y","volume":"49","author":"B Nisius","year":"2009","unstructured":"Nisius B, Vogt M, Bajorath J (2009) Development of a fingerprint reduction approach for bayesian similarity searching based on Kullback-Leibler divergence analysis. J Chem Inf Model 49(6):p1347\u20131358","journal-title":"J Chem Inf Model"},{"key":"9639_CR25","doi-asserted-by":"crossref","first-page":"960","DOI":"10.1002\/minf.201100107","volume":"30","author":"DJ Wood","year":"2011","unstructured":"Wood DJ, Buttar D, Cumming JG, Davis AM, Norinder U, Rodgers SL (2011) Automated QSAR with a hierarchy of global and local models. J Mol Inf 30:960\u2013972","journal-title":"J Mol Inf"},{"key":"9639_CR26","unstructured":"R Development (2008) C. T. R: a language and environment for statistical computing"},{"key":"9639_CR27","first-page":"1","volume":"2","author":"B Mevik","year":"2007","unstructured":"Mevik B, Wehrens R (2007) The pls package: principal component and partial least squares regression in R. J Stat Soft 2:1\u201324","journal-title":"J Stat Soft"},{"key":"9639_CR28","first-page":"18","volume":"3","author":"A Liaw","year":"2002","unstructured":"Liaw A, Wiener M (2002) Classification and regression by randomForest. R news 3:18\u201322","journal-title":"R news"},{"key":"9639_CR29","doi-asserted-by":"crossref","unstructured":"Chang C, Lin C (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3). http:\/\/dl.acm.org\/citation.cfm?id=1961199","DOI":"10.1145\/1961189.1961199"},{"key":"9639_CR30","unstructured":"Meyer D (2004) Support vector machines: The Interface to LIBSVM in Package e1071"},{"key":"9639_CR31","unstructured":"ACD\/Labs (2010) ACD\/PhysChem Suite"},{"key":"9639_CR32","unstructured":"Raevsky OA, Grigorev VJ, Trepalin SV (1999) HYBOT (Hydrogen Bond Thermodynamics) Program package registration by Russian state patent agency N 990090"},{"key":"9639_CR33","unstructured":"Olsson VS Selma is an In-house AstraZeneca Program. For further information Contact T. Olsson VS, synthesis and structure administration (SaSA), Astrazeneca R&D M\u00f6lndal, Sweden"},{"key":"9639_CR34","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1002\/cem.1225","volume":"4","author":"P Filzmoser","year":"2009","unstructured":"Filzmoser P, Liebmann B, Varmuza K (2009) Repeated double cross validation. J Chemometrics 4:160\u2013171","journal-title":"J Chemometrics"},{"key":"9639_CR35","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1186\/1471-2105-9-360","volume":"9","author":"M Eklund","year":"2008","unstructured":"Eklund M, Spjuth O, Wikberg KES (2008) A framework for simultaneous model selection and assessment. BMC Bioinform 9:360","journal-title":"BMC Bioinform"},{"key":"9639_CR36","doi-asserted-by":"crossref","unstructured":"Venables WN, Ripley BD (2002) Modern applied statistics with S, Springer, Berlin","DOI":"10.1007\/978-0-387-21706-2"},{"key":"9639_CR37","unstructured":"Breiman L (1994) Bagging predictors"},{"key":"9639_CR38","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1177\/1087057110396372","volume":"3","author":"MC Wenlock","year":"2011","unstructured":"Wenlock MC, Potter T, Barton P, Austin RP (2011) A method for measuring the lipophilicity of compounds in mixtures of 10. J Biomol Screen 3:348\u2013355","journal-title":"J Biomol Screen"},{"key":"9639_CR39","doi-asserted-by":"crossref","first-page":"1141","DOI":"10.1023\/A:1025032511040","volume":"8","author":"S Neuhoff","year":"2003","unstructured":"Neuhoff S, Ungell A, Zamora I, Artursson P (2003) pH-dependent bidirectional transport of weakly basic drugs across Caco-2 monolayers: implications for drug-drug interactions. Pharm Res 8:1141","journal-title":"Pharm Res"},{"key":"9639_CR40","doi-asserted-by":"crossref","first-page":"6672","DOI":"10.1021\/jm0605233","volume":"23","author":"AG Leach","year":"2006","unstructured":"Leach AG, Jones HD, Cosgrove DA, Kenny PW, Ruston L, MacFaul P, Wood JM, Colclough N, Law B (2006) Matched molecular pairs as a guide in the optimization of pharmaceutical properties; a study of aqueous solubility, plasma protein binding and oral exposure. J Med Chem 23:6672\u20136682","journal-title":"J Med Chem"},{"key":"9639_CR41","unstructured":"Plummer M (2003) In In JAGS: a program for analysis of Bayesian graphical models using gibbs sampling, Vienna, Austria"},{"key":"9639_CR42","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1016\/j.jclinepi.2006.01.012","volume":"9","author":"PC Austin","year":"2006","unstructured":"Austin PC, Mamdani MM, Juurlink DN, Hux JE (2006) Testing multiple statistical hypotheses resulted in spurious associations: a study of astrological signs and health. J Clin Epidemiol 9:964\u2013969","journal-title":"J Clin Epidemiol"},{"issue":"1","key":"9639_CR43","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/S0169-7439(99)00027-1","volume":"49","author":"NKM Faber","year":"1999","unstructured":"Faber NKM (1999) Estimating the uncertainty in estimates of root mean squared error of prediction: application to determining the size of an adequate test set in multivariate calibration. Chemometr Intell Lab Syst 49(1):79\u201389","journal-title":"Chemometr Intell Lab Syst"},{"key":"9639_CR44","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1039\/c2md20010d","volume":"5","author":"AG Leach","year":"2012","unstructured":"Leach AG, Pilling EA, Rabow AA, Tomasi S, Asaad N, Buurma NJ, Ballard A, Narduolo S (2012) Enantiomeric pairs reveal that key medicinal chemistry parameters vary more than simple physical property-based models can explain. Med Chem Commun 5:528\u2013540","journal-title":"Med Chem Commun"},{"key":"9639_CR45","doi-asserted-by":"crossref","first-page":"1292","DOI":"10.2174\/138161212799436430","volume":"18","author":"MD Segall","year":"2012","unstructured":"Segall MD (2012) Multi-parameter optimization: identifying high quality compounds with a balance of properties. Curr Pharm Des 18:1292\u20131310","journal-title":"Curr Pharm Des"},{"key":"9639_CR46","doi-asserted-by":"crossref","first-page":"2144","DOI":"10.1002\/cbdv.200900148","volume":"6","author":"M Segall","year":"2009","unstructured":"Segall M, Champness E, Obrezanova O, Leeding C (2009) Beyond profiling: using ADMET models to guide decisions. Chem Biodivers 6:2144\u20132151","journal-title":"Chem Biodivers"},{"issue":"2","key":"9639_CR47","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1517\/17425255.2.2.325","volume":"2","author":"MD Segall","year":"2006","unstructured":"Segall MD, Beresford AP, Gola JMR, Hawksley D, Tarbit MH (2006) Focus on success: using a probabilistic approach to achieve an optimal balance of compound properties in drug discovery. Expert Opin Drug Metab Toxicol 2(2):325\u2013337","journal-title":"Expert Opin Drug Metab Toxicol"},{"key":"9639_CR48","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1021\/ci7004498","volume":"5","author":"S Muchmore","year":"2008","unstructured":"Muchmore S, Debe D, Metz J, Brown S, Martin Y, Hajduk P (2008) Application of belief theory to similarity data fusion for use in analog searching and lead hopping. J Chem Inf Model 5:941\u2013948","journal-title":"J Chem Inf Model"},{"key":"9639_CR49","first-page":"89","volume":"1","author":"M Vuk","year":"2006","unstructured":"Vuk M, Curk T (2006) ROC curve, lift chart and calibration plot. Metodolo\u0161ki Zvezki 1:89\u2013108","journal-title":"Metodolo\u0161ki Zvezki"}],"container-title":["Journal of Computer-Aided Molecular Design"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10822-013-9639-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10822-013-9639-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10822-013-9639-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,10]],"date-time":"2019-07-10T21:13:46Z","timestamp":1562793226000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10822-013-9639-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,3]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,3]]}},"alternative-id":["9639"],"URL":"https:\/\/doi.org\/10.1007\/s10822-013-9639-5","relation":{},"ISSN":["0920-654X","1573-4951"],"issn-type":[{"value":"0920-654X","type":"print"},{"value":"1573-4951","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,3]]}}}