Quality of Fit and Predictive Ability of a continuous QSAR Model

According to A. Tropsha et al. (QSAR Comb. Sci. 22 (2003) 69-77 & Mol. Inf.  2010, 29, 476-488) the following statistical criteria must be satisfied by a predictive model:

1.    R^2 >0.6
2.    Rcvext^2 >0.5  
3.    (R^2 - R0^2)/R^2  < 0.1  
4.    (R^2 - R'0^2)/R^2  < 0.1   
5.    abs(R0^2 - R'0^2) < 0.3
6.    0.85 ≤ k ≤ 1.15
7.    0.85 ≤ k' ≤ 1.15

R^2 Correlation coefficient between the predicted and observed activities
Rcvext^2 External cross validation
R0^2 Coefficient of determination: predicted versus observed activities
R'0^2 Coefficient of determination: observed versus predicted activities
k = slope: predicted versus observed activities regression lines through the origin
k’= slope: observed versus predicted activities regression lines through the origin 

If this node is useful to you, please cite the following papers:

Melagraki*, G., Afantitis*, A. “Enalos KNIME nodes: Exploring corrosion inhibition of steel in acidic medium” (2013) Chemometrics and Intelligent Laboratory Systems, 123, pp. 9-14. (link)

Georgia Melagraki*, Antreas Afantitis*, Enalos InSilicoNano Platform: An online decision support tool for the design and virtual screening of nanoparticles  RSC Advances 2014, 4, 50713-50725 2014 (link)

Melagraki Georgia*; Afantitis Antreas* A Risk Assessment Tool for the Virtual Screening of Metal Oxide Nanoparticles through Enalos InSilicoNano Platform Current Topics in Medicinal Chemistry, Volume 15, Number 18, September 2015, pp. 1827-1836(10) 2015 (link)

E. Vrontaki, G. Melagraki*, T. Mavromoustakos, A. Afantitis*. Searching for Anthranilic Αcid-Βased Thumb Pocket 2 HCV NS5B Polymerase Inhibitors through a Combination of Molecular Docking, 3D-QSAR and Virtual Screening Journal of Enzyme Inhibition and Medicinal Chemistry DOI:10.3109/14756366.2014.1003925 (link)

KNIME Node Options:

Input Ports
0    Values for the dependent variable, predicted by the model (ypred)
1    Values for the dependent variable for the test set (yexp)
2    Values for the dependent variable for the training set (ytr)

Output Ports
0  Quality of Fit and Predictive Ability Statistics of a continuous QSAR Model