2D-QSAR and 3D-QSAR Analyses for EGFR Inhibitors

Abstract

Epidermal growth factor receptor (EGFR) is an important target for cancer therapy. In this study, EGFR inhibitors were investigated to build a two-dimensional quantitative structure-activity relationship (2D-QSAR) model and a three-dimensional quantitative structure-activity relationship (3D-QSAR) model. In the 2D-QSAR model, the support vector machine (SVM) classifier combined with the feature selection method was applied to predict whether a compound was an EGFR inhibitor. As a result, the prediction accuracy of the 2D-QSAR model was 98.99% by using tenfold cross-validation test and 97.67% by using independent set test. Then, in the 3D-QSAR model, the model with q2 = 0.565 (cross-validated correlation coefficient) and r2 = 0.888 (non-cross-validated correlation coefficient) was built to predict the activity of EGFR inhibitors. The mean absolute error (MAE) of the training set and test set was 0.308 log units and 0.526 log units, respectively. In addition, molecular docking was also employed to investigate the interaction between EGFR inhibitors and EGFR.

2D-SAR, Topomer CoMFA and molecular docking studies on avian influenza neuraminidase inhibitors

“…The CfsSubsetEval (CFS) method combined with Best-first (BF) search was employed to search the optimal feature subset in this study. CFS [33,34] is a heuristic feature-selection algorithm for evaluating the worth of a subset of attributes by considering the individual predictive ability of each feature along with the degree of redundancy between them. Therefore, feature-class and feature-feature correlations of training set were first calculated by CFS and the merit was calculated according to function (1):Sn=itruecitalicfc¯i+ii−1cfftrue¯where S n is the heuristic “merit” of a feature subset S , truecitalicfc¯ is the mean feature-class correlation, and truecitalicff¯ is the average feature-feature inter-correlation.…”

Ligand-based pharmacophore modeling and molecular dynamic simulation approaches to identify putative MMP-9 inhibitors

“…38 Besides, to determine the presence of systematic error prediction, absolute value means of the number of negative prediction errors (nNE), negative prediction errors (MNE), the average absolute prediction errors (AAE), the absolute value of average prediction errors (AE), the mean of positive prediction errors (MPE), number of positive prediction errors (nPE) were employed using Xternal validation plus 1.1 tool. 39,40 The results obtained using the current method are considered satisfactory if any one or more of the above-mentioned prediction errors obeys the rules demarcated using the MAE-based criterion method (ESI, Table S4 †).…”

Advances in Research of Adult Gliomas

“…QSAR models have been previously utilised in the design and virtual testing of new EGFR inhibitors, which could provide future treatments for EGFR-amplified glioma. The study conducted by Zhao et al employed 2D-QSAR to first ascertain whether or not a series of potential drugs would be classed as EGFR inhibitors [ 146 ]. The 2D-QSAR model was first ‘trained’ using a combined set of inhibitors and non-inhibitors and when tested against an independent data set, was found to predict EGFR inhibitors with 97.67% accuracy.…”