Skip to content

Commit

Permalink
recetox-aplcms: parse parameter line tool
Browse files Browse the repository at this point in the history 
Fixes #623
  • Loading branch information
@hechth
hechth committed Dec 4, 2024
1 parent 129488b commit a9b86c1
Show file tree
Hide file tree
Showing 2 changed files with 149 additions and 0 deletions.
147 changes: 147 additions & 0 deletions tools/recetox_aplcms/recetox_aplcms_parse_parameters.xml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,147 @@
<tool id="recetox_aplcms_parse_parameters" name="recetox-aplcms - parse parameters" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.01" license="MIT" tool_type="expression">
<description>tool to parse parameters from a csv row for parameter searches, to be used in workflows only.</description>

<macros>
<token name="@TOOL_VERSION@">0.1.0</token>
<token name="@VERSION_SUFFIX@">0</token>
</macros>
<!-- TODO: please annotate this tool with topics and operations from http://edamontology.org -->
<!-- TODO: for more information see: https://galaxy-iuc-standards.readthedocs.io/en/latest/best_practices/tool_xml.html#edam-topics-and-operations -->

<requirements>
</requirements>
<expression type="ecma5.1"><![CDATA[{
// Read the input CSV file
var data = $job.row.contents;
// Split the data into lines
var lines = data.trim().split('\n');
// Get the header and the first data row
var header = lines[0].split(',');
var row = lines[1].split(',');
// Create a dictionary with column names as keys and row values as values
var result = {};
for (var i = 0; i < header.length; i++) {
result[header[i]] = row[i];
}
var weighting;
if (result['weighting'] == 'true') {
weighting = true;
} else {
weighting = false;
}
return {
'min_run': parseFloat(result['min_run']),
'sigma_lower': parseFloat(result['sigma_lower']),
'sigma_higher': parseFloat(result['sigma_higher']),
'min_sd': parseFloat(result['min_sd']),
'max_sd': parseFloat(result['max_sd']),
'mz_tol': parseFloat(result['mz_tol']),
'weighting': weighting,
'min_pres': parseFloat(result['min_pres']),
'group_threshold': parseFloat(result['group_threshold'])
};
}]]></expression>

<inputs>
<param argument="--row" type="data" format="csv" label="Row of a CSV with the parameters, with header." help="Header has to be: [min_run,sigma_lower,sigma_higher,min_sd,max_sd,mz_tol,weighting,min_pres,group_threshold
]" load_contents="64000"/>
</inputs>
<outputs>
<output name="min_run" type="float" label="min_run of ${on_string}" from="min_run" />
<output name="sigma_lower" type="float" label="sigma_lower of ${on_string}" from="sigma_lower" />
<output name="sigma_higher" type="float" label="sigma_higher of ${on_string}" from="sigma_higher" />
<output name="min_sd" type="float" label="min_sd of ${on_string}" from="min_sd" />
<output name="max_sd" type="float" label="max_sd of ${on_string}" from="max_sd" />
<output name="mz_tol" type="float" label="mz_tol of ${on_string}" from="mz_tol" />
<output name="weighting" type="boolean" label="weighting of ${on_string}" from="weighting" />
<output name="min_pres" type="float" label="min_pres of ${on_string}" from="min_pres" />
<output name="group_threshold" type="float" label="group_threshold of ${on_string}" from="group_threshold" />
</outputs>
<tests>
<!-- Hint: You can use [ctrl+alt+t] after defining the inputs/outputs to auto-scaffold some basic test cases. -->

<test>
<!--TODO: auto-generated test case. Please fill in the required values-->
<param name="row" value="parse_parameters/test.csv"/>
<output name="min_run">
<assert_contents>
<has_text text="3.1"/>
</assert_contents>
</output>
<output name="sigma_lower">
<assert_contents>
<has_text text="0.5"/>
</assert_contents>
</output>
<output name="sigma_higher">
<assert_contents>
<has_text text="1.5"/>
</assert_contents>
</output>
<output name="min_sd">
<assert_contents>
<has_text text="0.1"/>
</assert_contents>
</output>
<output name="max_sd">
<assert_contents>
<has_text text="0.9"/>
</assert_contents>
</output>
<output name="mz_tol">
<assert_contents>
<has_text text="0.01"/>
</assert_contents>
</output>
<output name="weighting">
<assert_contents>
<has_text text="true"/>
</assert_contents>
</output>
<output name="min_pres">
<assert_contents>
<has_text text="0.8"/>
</assert_contents>
</output>
<output name="group_threshold">
<assert_contents>
<has_text text="0.7"/>
</assert_contents>
</output>
</test>
</tests>
<help><![CDATA[
.. class:: infomark
**What it does**
This tool parses parameters from a CSV row for parameter searches. It splits the CSV file into separate files for each column, excluding the header. This tool is intended to be used in workflows only.
Usage
.....
**Input**
- **Row of a CSV with the parameters, with header**: The input CSV file containing the parameters. The header row should contain the column names.
**Output**
- **min_run**: The minimum run value extracted from the specified column.
- **sigma_lower**: The sigma lower value extracted from the specified column.
- **sigma_higher**: The sigma higher value extracted from the specified column.
- **min_sd**: The minimum standard deviation value extracted from the specified column.
- **max_sd**: The maximum standard deviation value extracted from the specified column.
- **mz_tol**: The mz tolerance value extracted from the specified column.
- **weighting**: The weighting value extracted from the specified column.
- **min_pres**: The minimum presence value extracted from the specified column.
- **group_threshold**: The group threshold value extracted from the specified column.
]]></help>
<citations>
</citations>
</tool>
2 changes: 2 additions & 0 deletions tools/recetox_aplcms/test-data/parse_parameters/test.csv
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
min_run,sigma_lower,sigma_higher,min_sd,max_sd,mz_tol,weighting,min_pres,group_threshold
3.1,0.5,1.5,0.1,0.9,0.01,true,0.8,0.7

0 comments on commit a9b86c1

Please sign in to comment.