% % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % %
%                                                                           %
% File:            dna.dtr                                                  %
% Purpose:         a finite state transducer for DNA sequences              %
% Author:          Gerald Gazdar, March 1994                                %
% Email:           geraldg@cogs.sussex.ac.uk                                %
% Address:         COGS, Sussex University, Brighton BN1 9QH, UK            %
% Related files:   dfst2.dtr, dfst3.dtr                                     %
% Version:         1.00                                                     %
%                                                                           %
%      Copyright (c) University of Sussex 1994.  All rights reserved.       %
%                                                                           %
% % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % %

% This initial transducer is just a simple DATR FST -- it does
% not attempt to capture any of the fancy CFL and IL phenomena

# vars $purn : a g .                % purines
# vars $pyrm : c t .                % pyrimidines
# vars $base : a g c t .            % any nucleotide base

DNA:

        <> == '???'
        <$pyrm c a a t> == <caat>   % beginning of caat sequence
        <caat $base>    == <caat>   % discard bases until you see

        <caat t a t a $base a a c a t g>

                                    % then start mapping to amino acids

                        == AminoAcids:<a t g>.

AminoAcids:

        <> == '???'

        <a a $purn> == lys <>       % lysine
        <a a $pyrm> == asn <>       % asparagine

        <a c $base> == thr <>       % threonine

        <a g $purn> == arg <>       % arginine
        <a g $pyrm> == ser <>       % serine

        <a t a>     == ile <>       % isoleucine
        <a t g>     == met <>       % methionine
        <a t $pyrm> == ile <>       % isoleucine

        <c a $purn> == gln <>       % glutamine
        <c a $pyrm> == his <>       % histidine

        <c c $base> == pro <>       % proline

        <c g $base> == arg <>       % arginine

        <c t $base> == leu <>       % leucine

        <g a $purn> == glu <>       % glutamic acid
        <g a $pyrm> == asp <>       % aspartic acid

        <g c $base> == ala <>       % alanine

        <g g $base> == gly <>       % glycine

        <g t $base> == val <>       % valine

        <t a $purn> ==              % end markers
        <t a $pyrm> == tyr <>       % tyrosine

        <t c $base> == ser <>       % serine

        <t g a>     ==              % end marker
        <t g g>     == trp <>       % tryptophan
        <t g $pyrm> == cys <>       % cysteine

        <t t $purn> == leu <>       % leucine
        <t t $pyrm> == phe <>.      % phenylalanine


% % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % %

% Some example theorems:


% DNA:
%
%       <c c a a t c c a t a t a a a a c a t a a t c t t> = ???
%
%       <t c a a t c a c a t t a t a g a a c t t a g t t> = ???
%
%       <c c a a t a t t a t a t a a c a t g t t t c t a a t a g a a> = 
%                                       met   phe   leu   ile   glu ??? 
%
%       <c c a a t a t t a t a t a a c a t g t t t c t a a t a t a a> = 
%                                       met   phe   leu   ile 
%
%       <t c a a t c c a a t t a t a c a a c a t g t t c t t g a t t t g a> = 
%                                             met   phe   leu   ile 
%
%       <c c a a t a t a c c a g t a t a t a a c a t g t t t c t a a t a
%        a t g t t c t t g a t t t a g> = 
%                                                 met   phe   leu   ile
%         met   phe   leu   ile .

% % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % % %

# hide  AminoAcids .

# show 
        <c c a a t c c a t a t a a a a c a t a a t c t t>
        <t c a a t c a c a t t a t a g a a c t t a g t t>
        <c c a a t a t t a t a t a a c a t g t t t c t a a t a g a a>
        <c c a a t a t t a t a t a a c a t g t t t c t a a t a t a a>
        <t c a a t c c a a t t a t a c a a c a t g t t c t t g a t t t g a>
        <c c a a t a t a c c a g t a t a t a a c a t g t t t c t a a t a 
         a t g t t c t t g a t t t a g>.

% The next line is the Revision Control System Id: do not delete it.
% $Id: archive.dtr,v 1.1 1997/04/09 20:40:33 root Exp $