The characterization of proteins is necessary as proteins perform certain functions by interacting with other proteins (protein-protein interaction) or with small molecules (protein-ligand interaction). Active sites are the pocket regions in proteins where protein-ligand interaction takes place and to know the geometrical characteristics of these binding sites helps us in drug design discovery and many other biological processes. In this thesis, we have computed geometrical features that come from differential geometry on the main protease MPro surface to identify cavities and attractive sites that could be the best match in binding with other protein molecules. These geometrical descriptors from differential geometry have already experimented on 3D face surfaces for face recognition methodologies with considerable results.