Human papillomavirus (HPV) is an important pathogen which is classified into two, high- and low-risk groups. The proteins of high-risk and low-risk HPV types have different functions. Therefore, there is a need to develop a computational method for predicting these two groups. In the present study, the physiochemical properties of all early (E1, E2, E4, E5, E6, and E7) and late (L1 and L2) proteins in high- and low-risk HPV types have been studied. The concept of receiver operating characteristic analysis and support vector machines methods has been used for comparison of high- and low-risk HPV types. The results demonstrate that amino acid composition, physiochemical, and secondary structure of E2 protein are significantly different between these two groups. The results demonstrate that in silico properties can create useful information to predict high-risk and low-risk HPV types.