% ConvertPDB:  Convert Protein Data Bank (PDB) File
% to a simpler format
%
% Output is a file with one amino acid per row.
% Each row contains four entries:
%   1) One-letter amino acid code
%   2) x-axis position
%   3) y-axis position
%   4) z-axis position
%   
% Scott F. Smith
% Department of Electrical and Computer Engineering
% Boise State University
% SFSmith@BoiseState.edu
%
% 17 February 2004

% Filename to read (PDB/fname.txt) and write(Simple/fname.txt)
fname = '1gcv';

% Open files
fidPDB = fopen(['PDB/' fname '.txt']);
fidOut = fopen(['Simple/' fname '.txt'],'w');

% Process until the end of the input file
StringCount = 1;
while StringCount > 0

  % Read line from PDB file
  [StringIn, StringCount] = fscanf(fidPDB,'%s',1);

  % If the line starts with "ATOM", use it
  if length(StringIn) > 3
    if StringIn(1:4) == 'ATOM'

      % Ignore atom number
      [StringIn, StringCount] = fscanf(fidPDB,'%s',1);

      % If this atom is an alpha carbon, use it
      [StringIn, StringCount] = fscanf(fidPDB,'%s',1);
      if length(StringIn) > 1
        if StringIn(1:2) == 'CA'

          % Get the type of amino acid and convert to single letter
          [StringIn, StringCount] = fscanf(fidPDB,'%s',1);
          AcidChar = StringIn(1);
          if StringIn(1:3) == 'PHE'
            AcidChar = 'F';
          end
          if StringIn(1:3) == 'ASP'
            AcidChar = 'D';
          end
          if StringIn(1:3) == 'GLU'
            AcidChar = 'E';
          end
          if StringIn(1:3) == 'LYS'
            AcidChar = 'K';
          end
          if StringIn(1:3) == 'ARG'
            AcidChar = 'R';
          end
          if StringIn(1:3) == 'TYR'
            AcidChar = 'Y';
          end
          if StringIn(1:3) == 'ASN'
            AcidChar = 'N';
          end
          if StringIn(1:3) == 'GLN'
            AcidChar = 'Q';
          end
          if StringIn(1:3) == 'TRP'
            AcidChar = 'W';
          end
          if StringIn(1:3) == 'ASX'
            AcidChar = 'B';
          end
          if StringIn(1:3) == 'GLX'
            AcidChar = 'Z';
          end

          % Ignore amino acid number
          [StringIn, StringCount] = fscanf(fidPDB,'%s',1);

          % Get next string and check if it has a "." in it
          [StringIn, StringCount] = fscanf(fidPDB,'%s',1);
          NumbDecPoints = length(find(StringIn == '.'));

          % Get the x-axis location of this alpha carbon atom
          if NumbDecPoints > 0
            Xloc = sscanf(StringIn,'%f',1);
          else
            [StringIn, StringCount] = fscanf(fidPDB,'%s',1);
            NumbDecPoints = length(find(StringIn == '.'));
            if NumbDecPoints > 0
              Xloc = sscanf(StringIn,'%f',1);
            else
              [Xloc, StringCount] = fscanf(fidPDB,'%f',1);
            end 
          end

          % Get the y-axis location of this alpha carbon atom
          [Yloc, StringCount] = fscanf(fidPDB,'%f',1);

          % Get the z-axis location of this alpha carbon atom
          [Zloc, StringCount] = fscanf(fidPDB,'%f',1);

          % Place values in output file
          fprintf(fidOut,'%c\t',AcidChar);
          fprintf(fidOut,'%.3f\t%.3f\t%.3f\r\n',[Xloc Yloc Zloc]);

        end
      end 

    end
  end

end

% Close files
fclose(fidPDB);
fclose(fidOut);