Read the pdb file and create a 20*5 matrix that has 20 amino acid as rows and 0,1,2,3,4 as columns. The 20 amino acid are:
ALA
ARG
ASN
ASP
CYS
GLN
GLU
GLY
HIS
ILE
LEU
LYS
MET
PHE
PRO
SER
THR
TRP
TYR
VAL
Each shell is 1.5 angstroms thick. So the first shell is 0 to 1.5 and the second shell is between 1.5 and 3, etc. In the pdb file only read "CA" atoms for each amino acid.