Three-Dimensional Quantitative Similarity−Activity Relationships (3D QSiAR) from SEAL Similarity Matrices

Abstract

The program SEAL is suited to describe the electrostatic, steric, hydrophobic, and hydrogen bond donor and acceptor similarity of different molecules in a quantitative manner. Similarity scores AF can be calculated for pairs of molecules, using either a certain molecular property or a sum of weighted properties. Alternatively, their mutual similarity can be derived from distances d or covariances c between SEAL-based property fields that are calculated in a regular grid. For a set of N chemically related molecules, such values form an N x N similarity matrix which can be correlated with biological activities, using either regression analysis and an appropriate variable selection procedure or partial least-squares (PLS) analysis. For the Cramer steroid data set, the test set predictivities (r2pred = 0.53-0.84) of different PLS models, based on a weighted sum of molecular properties, are superior to published results of CoMFA and CoMSIA studies (r2pred = 0.31-0.40), regardless of whether a common alignment or individual, pairwise alignments of all molecules are used in the calculation of the similarity matrices. Training and test set selections have a significant influence on the external predictivities of the models. Although the SEAL similarity score between two molecules is a single number, its value is based on the 3D properties of both molecules. The term 3D quantitative similarity-activity analyses (3D QSiAR) is proposed for approaches which correlate 3D structure-derived similarity matrices with biological activities.

Identification of structural requirements of estrogen receptor modulators using pharmacoinformatics techniques for application to estrogen therapy

“…The Q 2 and se were calculated based on predicted activity of training compounds. High Q 2 (>0.5) and low se (<0.5) explained better predictive ability of the model (Kubinyi et al 1998) …”

Virtual Screening of Molecular Databases Using a Support Vector Machine.

“…Previous QSAR studies have shown a similar lack of correspondence between the predicted performance of a model, as indicated by the value of a cross-validation statistic obtained from the training set, and the performance of the model when applied to test set data. [34][35][36] A third factor affecting the performance of the SVM-based enrichment method is the choice of descriptors. The automated selection of descriptors contrasts with a number of other chemistry papers in which the descriptors for the SVM appear to have been selected by hand.…”

Exploration of the structural requirements of HIV-protease inhibitors using pharmacophore, virtual screening and molecular docking approaches for lead identification

“…The LOO crossvalidated correlation coefficient (Q 2 ) and error of estimation (se) were calculated based on predicted activity of training compounds as explained above. High Q 2 (>0.5) and low se (<0.5) explained better predictive ability [49].…”