Skip to content

fix: prefix whole gene ids in grRules in addIdentifierPrefix #758

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
edkerk merged 2 commits into from
Oct 7, 2026
Merged

fix: prefix whole gene ids in grRules in addIdentifierPrefix #758

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c83d1c5
fix: prefix whole gene ids in grRules in addIdentifierPrefix
edkerk Oct 6, 2026
3477970
Update documentation
edkerk Oct 7, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 18 additions & 4 deletions conversion/addIdentifierPrefix.m
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,10 +60,8 @@
currField = strcat(currPrefix, currField);
hasChanged(toChangeIdx(i)) = true;

if strcmp(currName,'genes')
model.grRules = regexprep(model.grRules, '(\<[0-9_a-zA-Z])', 'G_$1');
model.grRules = regexprep(model.grRules, ' G_or ', ' or ');
model.grRules = regexprep(model.grRules, ' G_and ', ' and ');
if strcmp(currName,'genes') && isfield(model,'grRules')
model.grRules = cellfun(@(r) prefixGenes(r,currPrefix), model.grRules, 'UniformOutput', false);
end
model.(currName) = currField;
end
Expand All @@ -72,3 +70,19 @@
hasChanged = modelFields(hasChanged,:);
hasChanged = append('model.', hasChanged(:,1), ' (', hasChanged(:,2), ' prefix)');
end


function rule = prefixGenes(rule, prefix)
% Prefix every gene in a grRule, leaving "and", "or" and brackets alone. A
% gene is everything between spaces and brackets, so ids that contain
% "-", "." or ":" get one prefix, not one per word.
[tokens, separators] = regexp(rule, '[^\s()]+', 'match', 'split');
out = separators{1};
for i = 1:numel(tokens)
if ~any(strcmpi(tokens{i}, {'and','or'}))
tokens{i} = [prefix tokens{i}];
end
out = [out tokens{i} separators{i+1}]; %#ok<AGROW>
end
rule = out;
end
42 changes: 29 additions & 13 deletions doc/conversion/addIdentifierPrefix.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,9 @@ <h2><a name="_cross"></a>CROSS-REFERENCE INFORMATION <a href="#_top"><img alt="^
</ul>
<!-- crossreference -->


<h2><a name="_subfunctions"></a>SUBFUNCTIONS <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2>
<ul style="list-style-image:url(../matlabicon.gif)">
<li><a href="#_sub1" class="code">function rule = prefixGenes(rule, prefix)</a></li></ul>

<h2><a name="_source"></a>SOURCE CODE <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2>
<div class="fragment"><pre>0001 <a name="_sub0" href="#_subfunctions" class="code">function [model, hasChanged]=addIdentifierPrefix(model,varargin)</a>
Expand Down Expand Up @@ -137,18 +139,32 @@ <h2><a name="_source"></a>SOURCE CODE <a href="#_top"><img alt="^" border="0" sr
0060 currField = strcat(currPrefix, currField);
0061 hasChanged(toChangeIdx(i)) = true;
0062
0063 <span class="keyword">if</span> strcmp(currName,<span class="string">'genes'</span>)
0064 model.grRules = regexprep(model.grRules, <span class="string">'(\&lt;[0-9_a-zA-Z])'</span>, <span class="string">'G_$1'</span>);
0065 model.grRules = regexprep(model.grRules, <span class="string">' G_or '</span>, <span class="string">' or '</span>);
0066 model.grRules = regexprep(model.grRules, <span class="string">' G_and '</span>, <span class="string">' and '</span>);
0067 <span class="keyword">end</span>
0068 model.(currName) = currField;
0069 <span class="keyword">end</span>
0070 <span class="keyword">end</span>
0071
0072 hasChanged = modelFields(hasChanged,:);
0073 hasChanged = append(<span class="string">'model.'</span>, hasChanged(:,1), <span class="string">' ('</span>, hasChanged(:,2), <span class="string">' prefix)'</span>);
0074 <span class="keyword">end</span></pre></div>
0063 <span class="keyword">if</span> strcmp(currName,<span class="string">'genes'</span>) &amp;&amp; isfield(model,<span class="string">'grRules'</span>)
0064 model.grRules = cellfun(@(r) <a href="#_sub1" class="code" title="subfunction rule = prefixGenes(rule, prefix)">prefixGenes</a>(r,currPrefix), model.grRules, <span class="string">'UniformOutput'</span>, false);
0065 <span class="keyword">end</span>
0066 model.(currName) = currField;
0067 <span class="keyword">end</span>
0068 <span class="keyword">end</span>
0069
0070 hasChanged = modelFields(hasChanged,:);
0071 hasChanged = append(<span class="string">'model.'</span>, hasChanged(:,1), <span class="string">' ('</span>, hasChanged(:,2), <span class="string">' prefix)'</span>);
0072 <span class="keyword">end</span>
0073
0074
0075 <a name="_sub1" href="#_subfunctions" class="code">function rule = prefixGenes(rule, prefix)</a>
0076 <span class="comment">% Prefix every gene in a grRule, leaving &quot;and&quot;, &quot;or&quot; and brackets alone. A</span>
0077 <span class="comment">% gene is everything between spaces and brackets, so ids that contain</span>
0078 <span class="comment">% &quot;-&quot;, &quot;.&quot; or &quot;:&quot; get one prefix, not one per word.</span>
0079 [tokens, separators] = regexp(rule, <span class="string">'[^\s()]+'</span>, <span class="string">'match'</span>, <span class="string">'split'</span>);
0080 out = separators{1};
0081 <span class="keyword">for</span> i = 1:numel(tokens)
0082 <span class="keyword">if</span> ~any(strcmpi(tokens{i}, {<span class="string">'and'</span>,<span class="string">'or'</span>}))
0083 tokens{i} = [prefix tokens{i}];
0084 <span class="keyword">end</span>
0085 out = [out tokens{i} separators{i+1}]; <span class="comment">%#ok&lt;AGROW&gt;</span>
0086 <span class="keyword">end</span>
0087 rule = out;
0088 <span class="keyword">end</span></pre></div>
<hr><address>Generated by <strong><a href="http://www.artefact.tk/software/matlab/m2html/" title="Matlab Documentation in HTML">m2html</a></strong> &copy; 2005</address>
</body>
</html>
11 changes: 11 additions & 0 deletions testing/function_tests/tConversion.m
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,17 @@ function identifierPrefixRoundTrip(testCase)
testCase.verifyEqual(mr.genes, testCase.model.genes);
end

function identifierPrefixKeepsGenesWithPunctuationWhole(testCase)
% A gene id with "-", "." or ":" gets one prefix in grRules, the
% same one it gets in model.genes, so the two still match.
m = testCase.model;
m.genes = [m.genes; {'5-HT1A'; 'b2:1'}];
m.grRules{1} = '5-HT1A and (b2:1 or 5-HT1A)';
[mp, ~] = addIdentifierPrefix(m, 'fields', {'genes'});
testCase.verifyEqual(mp.grRules{1}, 'G_5-HT1A and (G_b2:1 or G_5-HT1A)');
testCase.verifyTrue(all(ismember(getGenesFromGrRules(mp.grRules(1)), mp.genes)));
end

function removeIdentifierPrefixSkipsMissingFields(testCase)
% A model missing an optional field (genes, metNames, rxnNames,
% id) must not make the default field list throw; it should
Expand Down
Loading