Abstract: OBJECTIVE To develop a predictable 3D-QSAR model for designing novel p53-MDM2 binding inhibitors. METHODS A series of isoquinolone derivatives inhibitors of p53-MDM2 binding were subjected to three-dimensional quantitative structureeactivity relationship (3D-QSAR) studies using the comparative molecular field analysis (CoMFA) and comparative molecular similarity indices analysis (CoMSIA) approaches. RESULTS The CoMFA model included steric and electrostatic fields for the training set with the cross validated q² value of 0.545 and the non-cross-validated r² value of 0.984. The cross-validated q² value of CoMSIA model was 0.528 and the non-cross-vaildated r² value was 0.972. CONCLUSION Based on the inoformation obtained from the model, this model is predictable and therefor more derivatives will be designed for further studies.