SAR and QSAR study on the bioactivities of human epidermal growth factor receptor-2 (HER2) inhibitors

Abstract

In this paper, structure-activity relationship (SAR, classification) and quantitative structure-activity relationship (QSAR) models have been established to predict the bioactivity of human epidermal growth factor receptor-2 (HER2) inhibitors. For the SAR study, we established six SAR (or classification) models to distinguish highly and weakly active HER2 inhibitors. The dataset contained 868 HER2 inhibitors, which was split into a training set including 580 inhibitors and a test set including 288 inhibitors by a Kohonen's self-organizing map (SOM), or a random method. The SAR models were performed using support vector machine (SVM), random forest (RF) and multilayer perceptron (MLP) methods. Among the six models, SVM models obtained superior results compared with other models. The prediction accuracy of the best model (model 1A) was 90.27% and the Matthews correlation coefficient (MCC) was 0.80 on the test set. For the QSAR study, we chose 286 HER2 inhibitors to establish six quantitative prediction models using MLR, SVM and MLP methods. The correlation coefficient (r) of the best model (model 4B) was 0.92 on the test set. The descriptors analysis showed that HAccN, lone pair electronegativity and π electronegativity were closely related to the bioactivity of HER2 inhibitors.

Structural and molecular insights from dual inhibitors of EGFR and VEGFR2 as a strategy to improve the efficacy of cancer therapy

“…This protein family also consists of three other members: HER2/ErbB2, HER3/ErbB3, and HER4/ErbB4. Upon binding endogenous ligands, the extracellular domain of EGFR, HER3, and HER4 undergoes a conformational change from closed to open conformation and allows dimerization to form both homodimers and heterodimers (Qu et al., 2017). Meanwhile, HER2 is unique, always in an open conformation even in the absence of endogenous ligands, and ready to dimerize.…”

A SAR and QSAR study on cyclin dependent kinase 4 inhibitors using machine learning methods

“…Computer-aided drug design (CADD) as a convenient and lowcost approach 21 is used to discover CDK4 inhibitor lead compounds. As a method of CADD, a classication model [22][23][24][25][26] is used for structure-activity relationship research and virtual screening of inhibitors, and a QSAR model [27][28][29][30][31][32][33][34][35][36][37][38][39] is used to predict the inhibitory activity of a compound. Wu et al 22 built classication models and QSAR models to study the structure-activity relationship of tyrosinase inhibitors.…”