%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Function to determine neucleotide density.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

function [density] = ntuple(sequence, Window, nbin, bin)
  %"ntuple" finds density of n-tuple neucleotide
  %'sequence' is genetic sequence, 'window' is counting window, bin = n-tuple
  
  seq=sequence;
  
  for i=1:length(seq)-(nbin-1)
     atg(1,i)=isequal(seq(i:i+nbin-1),bin);
  end
  
  window=Window;
  w=1/window*ones(1,window);
  sum=zeros(1,length(atg));
  
  for i=1:length(w)
     sum=sum+w(i)*[zeros(1,i-1) atg(1:(length(atg)-(i-1)))];
  end
  
  len = length(atg);
  sa=sum;
  sa(1:window-1) = sa(1:window-1) * window./(1:window-1);
  density=sa;
end

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Function to determine all single neucleotide density.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

function [totdensity] = onemerdensity(Sequence, Window, nbin)

%"ntuple" finds density of n-tuple neucleotide
%'sequence' is genetic sequence, 'window' is counting window, nbin = No of letters in bin

labelcount = 0;
n=4^nbin;
labels = cell(1,n);
  for first = 1:4
     codon = int2nt([first]);
    labelcount = labelcount + 1;
    labels{labelcount} = codon;
  end

  for k=1:n
    char=labels{1,k};
   nmer=ntuple(Sequence, Window, nbin, char);
   totdensity(k,:)=nmer;
  end
end

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Function for Principal Component Analysis.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

function [coeff,score,eigenvaluescovariance,tsquared,variancepercentage] = pc(i)

% "i" denotes the Sequence Name which exist in a path.
%  The individual sequence name is given as "1", "2" .. etc.

  Window=51;nbin=1;
  string=int2str(i);
  ch=char(39);
  [Header Sequence]=eval(['fastaread(',ch,'C:\Users\~PATH\',string,ch,');']);
  onedensity=onemerdensity(Sequence, Window, nbin);
  [coeff,score,eigenvaluescovariance,tsquared,variancepercentage] = pca(onedensity);   % Principal Component 
end


%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Use of PCA function for Cluster determination.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Window is the width of the sliding window.
% nbin is the length of the bin.

  labelcount = 0;nbin=1;         % Bin Construction
  n=4^nbin;
  labels = cell(1,n);
  for first = 1:4
      bin = int2nt([first]);
      labelcount = labelcount + 1;
      labels{labelcount} = bin;
  end

  categories=labels';

  name=cell(1,10);
  name{1}='Callithrix';name{2}='Equus';
  name{3}='Gallus';name{4}='Homo';name{5}='Macaca';name{6}='Mus';
  name{7}='Pan';name{8}='Papio';name{9}='Rattus';name{10}='Sus';
  specis=cell(1,40);
  count = 0;

 for j=1:10
     for i=1:4
       count = count + 1;
       specis{count} =name{j};
     end
 end

 for i=1:10
  c=int2str(i);
  eval(['z',c,'=pc(',c,');'])
 end
 zscore=[z1;z2;z3;z4;z5;z6;z7;z8;z9;z10];


% PC for 'A'
a=[z1(1,:);z2(1,:);z3(1,:);z4(1,:);z5(1,:);z6(1,:);z7(1,:);z8(1,:);z9(1,:);z10(1,:)];
figure
gscatter(a(:,1),a(:,2),name')
xlabel('PC1');
ylabel('PC2');
title('Principal Component Scatter Plot with Colored Clusters');

% PC for 'C'
c=[z1(2,:);z2(2,:);z3(2,:);z4(2,:);z5(2,:);z6(2,:);z7(2,:);z8(2,:);z9(2,:);z10(2,:)];
figure
gscatter(c(:,1),c(:,2),name')
xlabel('PC1');
ylabel('PC2');
title('Principal Component Scatter Plot with Colored Clusters');

% PC Value for 'G'
g=[z1(3,:);z2(3,:);z3(3,:);z4(3,:);z5(3,:);z6(3,:);z7(3,:);z8(3,:);z9(3,:);z10(3,:)];
figure
gscatter(g(:,1),g(:,2),name')
xlabel('PC1');
ylabel('PC2');
title('Principal Component Scatter Plot with Colored Clusters');

% PC for 'T'
t=[z1(4,:);z2(4,:);z3(4,:);z4(4,:);z5(4,:);z6(4,:);z7(4,:);z8(4,:);z9(4,:);z10(4,:)];
figure
gscatter(t(:,1),t(:,2),name')
xlabel('PC1');
ylabel('PC2');
title('Principal Component Scatter Plot with Colored Clusters');


%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Function to determine 2-gram neucleotide density.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

function [totdensity] = nmerdensity(Sequence, Window, nbin)

%"ntuple" finds density of n-tuple neucleotide
%'sequence' is genetic sequence, 'window' is counting window, nbin = No of letters in bin

  labelcount = 0;
  n=4^nbin;
  labels = cell(1,n);

  for first = 1:4
      for second = 1:4
         codon = int2nt([first second]);
         labelcount = labelcount + 1;
        labels{labelcount} = codon;
      end
  end

  for k=1:n
  char=labels{1,k};
  nmer=ntuple(Sequence, Window, nbin, char);
  totdensity(k,:)=nmer;
  end
end