Journal of Medicinal Chemistry · 2012 · 231 citations · 14 references
ComputingBioinformaticsExperimental DesignStatistical ModelingUncertainty QuantificationMeasurement ErrorMeasurement UncertaintyMolecular Property PredictionPropagation Of UncertaintyUncertainty AnalysisUncertainty EstimationAccuracyExperimental Uncertainty AnalysisFilteringModel UncertaintyParameter Uncertainty QuantificationPearson Correlation CoefficientPredictive PerformanceTranscription Errors
The maximum achievable accuracy of in silico models depends on the quality of the experimental data. Consequently, experimental uncertainty defines a natural upper limit to the predictive performance possible. Models that yield errors smaller than the experimental uncertainty are necessarily overtrained. A reliable estimate of the experimental uncertainty is therefore of high importance to all originators and users of in silico models. The data deposited in ChEMBL was analyzed for reproducibility, i.e., the experimental uncertainty of independent measurements. Careful filtering of the data was required because ChEMBL contains unit-transcription errors, undifferentiated stereoisomers, and repeated citations of single measurements (90% of all pairs). The experimental uncertainty is estimated to yield a mean error of 0.44 pK(i) units, a standard deviation of 0.54 pK(i) units, and a median error of 0.34 pK(i) units. The maximum possible squared Pearson correlation coefficient (R(2)) on large data sets is estimated to be 0.81.
14
ChEMBL: a large-scale bioactivity database for drug discovery
Anna Gaulton, Louisa J. Bellis, A. Patrícia Bento et al. · Nucleic Acids Research · 2011 · 4.5K citations · Full text
The PDBbind Database: Methodologies and Updates
Renxiao Wang, Xueliang Fang, Yipin Lu et al. · Journal of Medicinal Chemistry · 2005 · 946 citations
Binding MOAD (Mother Of All Databases)
Liegi Hu, Mark L. Benson, Richard D. Smith et al. · Proteins Structure Function and Bioinformatics · 2005 · 332 citations · Full text