From a9b86c123348afad445ddf56cbc21ab63f4a7a61 Mon Sep 17 00:00:00 2001
From: hechth <helge.hecht@recetox.muni.cz>
Date: Wed, 4 Dec 2024 15:19:29 +0100
Subject: [PATCH 1/4] recetox-aplcms: parse parameter line tool Fixes #623

---
 .../recetox_aplcms_parse_parameters.xml       | 147 ++++++++++++++++++
 .../test-data/parse_parameters/test.csv       |   2 +
 2 files changed, 149 insertions(+)
 create mode 100644 tools/recetox_aplcms/recetox_aplcms_parse_parameters.xml
 create mode 100644 tools/recetox_aplcms/test-data/parse_parameters/test.csv

diff --git a/tools/recetox_aplcms/recetox_aplcms_parse_parameters.xml b/tools/recetox_aplcms/recetox_aplcms_parse_parameters.xml
new file mode 100644
index 00000000..215f98b5
--- /dev/null
+++ b/tools/recetox_aplcms/recetox_aplcms_parse_parameters.xml
@@ -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>
\ No newline at end of file
diff --git a/tools/recetox_aplcms/test-data/parse_parameters/test.csv b/tools/recetox_aplcms/test-data/parse_parameters/test.csv
new file mode 100644
index 00000000..3536c620
--- /dev/null
+++ b/tools/recetox_aplcms/test-data/parse_parameters/test.csv
@@ -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

From 0d8ffd53f9eda6cdeeb5d433951c62dc9e587adc Mon Sep 17 00:00:00 2001
From: hechth <helge.hecht@recetox.muni.cz>
Date: Wed, 4 Dec 2024 15:25:05 +0100
Subject: [PATCH 2/4] added edam operations and topics

---
 .../recetox_aplcms_parse_parameters.xml             | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/tools/recetox_aplcms/recetox_aplcms_parse_parameters.xml b/tools/recetox_aplcms/recetox_aplcms_parse_parameters.xml
index 215f98b5..1d05677e 100644
--- a/tools/recetox_aplcms/recetox_aplcms_parse_parameters.xml
+++ b/tools/recetox_aplcms/recetox_aplcms_parse_parameters.xml
@@ -5,11 +5,16 @@
         <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>
+    <edam_operations>
+        <edam_operation>operation_1812</edam_operation>
+    </edam_operations>
+
+    <edam_topics>
+        <edam_topic>topic_3316</edam_topic>
+        <edam_topic>topic_3071</edam_topic>
+    </edam_topics>
+
     <expression type="ecma5.1"><![CDATA[{
         // Read the input CSV file
         var data = $job.row.contents;

From 5a574a196f0876da31350699700e42fd8aea192c Mon Sep 17 00:00:00 2001
From: hechth <helge.hecht@recetox.muni.cz>
Date: Wed, 4 Dec 2024 16:31:19 +0100
Subject: [PATCH 3/4] added additional validation logic

---
 .../recetox_aplcms_parse_parameters.xml       | 33 +++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/tools/recetox_aplcms/recetox_aplcms_parse_parameters.xml b/tools/recetox_aplcms/recetox_aplcms_parse_parameters.xml
index 1d05677e..67afc17d 100644
--- a/tools/recetox_aplcms/recetox_aplcms_parse_parameters.xml
+++ b/tools/recetox_aplcms/recetox_aplcms_parse_parameters.xml
@@ -16,6 +16,30 @@
     </edam_topics>
 
     <expression type="ecma5.1"><![CDATA[{
+        // Expected column names
+        var expectedColumnNames = [
+            "min_run",
+            "sigma_lower",
+            "sigma_higher",
+            "min_sd",
+            "max_sd",
+            "mz_tol",
+            "weighting",
+            "min_pres",
+            "group_threshold"
+        ];
+
+        // Validate column names
+        var columnNames = $job.row.metadata.column_names;
+        if (columnNames.length !== expectedColumnNames.length) {
+            throw new Error("Column count does not match expected count.");
+        }
+        for (var i = 0; i < columnNames.length; i++) {
+            if (columnNames[i] !== expectedColumnNames[i]) {
+                throw new Error("Column names do not match expected names.");
+            }
+        }
+
         // Read the input CSV file
         var data = $job.row.contents;
 
@@ -31,6 +55,15 @@
         for (var i = 0; i < header.length; i++) {
             result[header[i]] = row[i];
         }
+
+        // Validate that the float parameters are valid float values
+        var floatParams = ["min_run", "sigma_lower", "sigma_higher", "min_sd", "max_sd", "mz_tol", "min_pres", "group_threshold"];
+        for (var i = 0; i < floatParams.length; i++) {
+            var param = floatParams[i];
+            if (isNaN(parseFloat(result[param]))) {
+                throw new Error("Parameter " + param + " does not contain a valid float value.");
+            }
+        }
         
         var weighting;
         if (result['weighting'] == 'true') {

From 868f2e020573dc4e33751657c6abcb8880be5c78 Mon Sep 17 00:00:00 2001
From: hechth <helge.hecht@recetox.muni.cz>
Date: Mon, 6 Jan 2025 16:54:29 +0100
Subject: [PATCH 4/4] no idea what this was

---
 tools/recetox_aplcms/parse_parameters.sh | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)
 create mode 100644 tools/recetox_aplcms/parse_parameters.sh

diff --git a/tools/recetox_aplcms/parse_parameters.sh b/tools/recetox_aplcms/parse_parameters.sh
new file mode 100644
index 00000000..e1cd4534
--- /dev/null
+++ b/tools/recetox_aplcms/parse_parameters.sh
@@ -0,0 +1,23 @@
+#!/bin/bash
+# Check if the correct number of arguments is provided
+if [ "$#" -ne 1 ]; then
+    echo "Usage: $0 input.csv"
+    exit 1
+fi
+    
+input_file="$1"
+header=$(head -n 1 "$input_file")
+num_columns=$(echo "$header" | awk -F, '{print NF}')
+    
+# Create a directory to store the output files
+output_dir="split_columns"
+mkdir -p "$output_dir"
+    
+# Split the CSV file into one file per column
+for ((i=1; i<= num_columns; i++)); do
+    column_name=$(echo "$header" | cut -d, -f$i)
+    output_file="$output_dir/${column_name}.txt"
+    tail -n +2 "$input_file" | cut -d, -f$i > "$output_file"
+done
+    
+echo "Columns have been split into separate files in the '$output_dir' directory."
\ No newline at end of file