Minimalist and Consensus Overlay-Based QSAR Models

Minimalist and Consensus Overlay-Based QSAR Models 

Upon inclusion of ComPharm field descriptors in the initial pool of molecular indices, four of these are selected by the GA-driven QSAR building procedure to enter the minimalist six-variable overlay-based QSAR model. These ComPharm key points are 

At identical variable number, the overlay-based model outperforms its overlay-independent equivalent training RMS = 0.712 (pICso units), training = 0.712, validation RMS = 0.698, training = 0.724. ComPharm field descriptors therefore appear to have a better predictive power than pairwise pharmacophore feature counts alone. 

Yet more powerful than the minimalist approach, the optimal consensus Cox2 model displays an excellent training RMS of 0.56 pICso units, for example, R = 0.825, and behaves even better with respect to the external validation set (RMS = 0.53 pICso units, Q2 = 0.841). 

According to the minimalist model in Table 5.2, a potent Cox2 ligand is a molecule that 

---

Minimalist and Consensus Overlay-Based QSAR Models 129... 

---