The index of ideality of correlation: QSAR studies of hepatitis C virus NS3/4A protease inhibitors using SMILES descriptors

Ecotoxicological prediction of organic chemicals toward Pseudokirchneriella subcapitata by Monte Carlo approach

“…The models constructed based on the hybrid descriptors are statistically better than the models constructed by individually SMILES or graph descriptors. 19–21…”

“…The models constructed based on the hybrid descriptors are statistically better than the models constructed by individually SMILES or graph descriptors. [19][20][21] The index of ideality of correlation (IIC) has been implemented by the theoretical chemist to validate and improve the predictive potential constructed QSAR/QSTR models. 14,[22][23][24][25] The IIC is a parameter for assessing the predictive capability of QSPR/QSAR models that takes into account not only the coef-cient of correlation, but also the organization of the group of dots images relative to the diagonal, in "observed-calculated" endpoint coordinates.…”

Monte Carlo optimization method based QSAR modeling of postmortem redistribution of structurally diverse drugs

“…The presented eqn (4)-( 6) emphasize that the preferable values of the T and N epoch for split 1 are 15 and 8, respectively; the preferable values of the T and N epoch for split 2 are 4 and 25, respectively; and the preferable values of T and N epoch for split 3 are 2 and 7, respectively. One of the chief aims of this research was to determine the molecular fragments, defined as the optimal SMILES notation descriptors that have a positive and negative influence on the studied activity, according to published methodology; 27,28,[43][44][45] the full list of the calculated molecular descriptors, based both on the molecular graph and the SMILES notation, is presented in Table S2 (ESI †). Table 3 presents an example of calculating a molecule's summarized correlation weight (DCW) and the studied activity (C : P ratio).…”

A simple and reliable QSPR model for prediction of chromatography retention indices of volatile organic compounds in peppers

“…active training, passive training, calibration and validation. [23][24][25][26][27][28][29][30][31] The objective of this study is to construct a predictive QSPR model using the Monte Carlo technique of the CORAL soware for the retention index property of 273 VOCs recognized in peppers. Ten random splits are made and each split is divided into four subsets.…”