Abstract
Topological indices have been applied to build QSAR models for a set of 20 an-timalarial cyclic peroxy cetals. In order to evaluate the reliability of the proposed linearmodels leave-n-out and Internal Test Sets (ITS) approaches have been considered. The pro-posed procedure resulted in a robust and consensued prediction equation and here it isshown why it is superior to the employed standard cross-validation algorithms involvingmultilinear regression models.
Highlights
The objective of the present work is to study true prediction possibilities in a congeneric group of antimalarials by using graph-theoretical indices as molecular descriptors
This statistical parameter is the co-logarithm of the probability of finding a linear model involving a certain number of descriptors and objects and having an equal or greater value of the correlation coefficient
It would be ideal to find a maximal value for clogPP, indicating how many descriptors must be taken in the model
Summary
The objective of the present work is to study true prediction possibilities in a congeneric group of antimalarials by using graph-theoretical indices as molecular descriptors.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have