We have developed a method for predicting disease prone sites in differenct cancer types including breast cancer (BRCA), Acute Myeloid Leukemia (LAML), Endometrium cancer (EC), Stomach cancer (STAD) and Skin cancer (SKCM). In this method we use amino acid sequence based features such as physicochemical properties, conservation scores, predicted secondary structure and peptide motifs to discriminate the disease prone and neutral sites in these cancer types. This method helps to identify crucial sites in different cancer types.