aaindex.m

base implementaion of the protein (starting from the amino acid sequence) feature extractor used in

%the function DCKMEANS is available at
%http://www.dcorney.com/ClusteringMatlab.html

%the file aaindex1 is available at http://www.genome.jp/dbget/aaindex.html

clear all
warning off

i=0;t=0;
fid=fopen('aaindex1','r');
for tento=1:20000
    P=fscanf(fid,'%c',1);%leggo prima lettera
    %leggo il codice
    if isequal(P,'H')
        nome{t+1}=fgetl(fid);
    elseif isequal(P,'D')
        titolo{t+1}=fgetl(fid);
    elseif isequal(P,'I')
        fgetl(fid);%leggo la linea
        i=i+1;t=t+1;
        %ora leggo gli amino-acidi
        for j=1:20
            MM(i,j)=fscanf(fid,'%f',1);
        end
    else
        fgetl(fid);%leggo la linea
    end
end



%to read a given dataset
%SEQ is the amino-acid sequence of a given protein

alfabeto=['A' 'R' 'N' 'D' 'C' 'Q' 'E' 'G' 'H' 'I' 'L' 'K' 'M' 'F' 'P' 'S' 'T' 'W' 'Y' 'V'];
for op=1:size(MM,1)%for each physicochemical property

    %clustering 5-gruppi usando propriet