CoMFA predictive ability

One of the most attractive features of the CoMFA and CoMFA-like methods is that, because of the nature of molecular field descriptors, these approaches yield models that are relatively easy to interpret in chemical terms. Famous CoMFA contour plots, which are obtained as a result of any successful CoMFA study, tell chemists in rather plain terms how the change in the compounds size or charge distribution as a result of chemical modification correlate with the binding constant or activity. These observations may immediately suggest to a chemist possible ways to modify molecules to increase their potencies. However as demonstrated in the next section, these predictions should be taken with caution only after sufficient work has been done to prove the statistical significance and predictive ability of the models. 

Bohac, M., Loeprecht, B., Damborsky, J. and Schiiiirmann, G. (2002) Impact of orthogonal signal correction (OSC) on the predictive ability of CoMFA models for the dilate toxicity of nitrobenzenes. Quant. Struct. -Act. Relat., 21, 3-11. 

The last step in a CoMFA study is a partial least squares (PLS) analysis (chapter 5.3) to determine the minimal set of grid points which is necessary to explain the biological activities of the compounds. Most often good to excellent results are obtained. However, the predictive value of the model must be checked by cross-validation if necessary, the model is refined and the analysis is repeated until a model of high predictive ability is obtained. 

Thus, the 3D-QSAR models obtained by CMF are comparable by the predictive ability with models built by means of such popular state-of-the-art approaches as CoMFA and CoMSIA. Moreover, in some cases, e.g. for data sets ACE, AChE, BZR and DHFR, the CMF approach is clearly advantageous. 

The results of the 4D-QSAR case study are interesting and provide large amounts of data about the system of interest, and, unlike static 3D-QSAR methods (CoMFA and SOMFA), 4D-QSAR is able to provide the exact locations of statistically important interaction pharmacophore elements. The ability of this method to overcome the question of What conformation to use and predict the bioactive conformation is impressive and a major reason to use the software. Yet it is the ability to construct manifold models and examine several models for the same alignment that is the true benefit of this method. Add to the list the ability to determine the best alignment scheme (based on statistical and experimental results) and this method will provide more information than one could imagine. This abundance of information is key when troubleshooting results that are not in agreement with current beliefs. 

---