### Abstract

The design and optimization of p53–MDM2 interaction inhibitors has attracted a great deal of interest in the development of new anticancer agents. Systematical 2D-QSAR studies on 98 isoindolinone-based p53–MDM2 interaction inhibitors were carried out using linear and the non-linear mathematical methods. At first, a forward stepwise-multiple linear regression model (FS-MLR) was proposed with reasonable statistical parameters (*R*_{train}^{2} = 0.881, *Q*_{loo}^{2} = 0.847, *R*_{test}^{2} = 0.854). Then, enhanced replacement method–multiple linear regression (ERM-MLR) and support vector machine regression (SVMR) were applied to set up more accurate models (ERM-MLR: *R*_{train}^{2} = 0.914, *Q*_{loo}^{2} = 0.894 and *R*_{test}^{2} = 0.903; SVMR: *R*_{train}^{2} = 0.924, *Q*_{loo}^{2} = 0.920 and *R*_{test}^{2} of 0.874). Furthermore, the reliability and application value of the ERM and SVMR model was also validated in virtual screening through receiver operating characteristic studies.