Tool for GC annotation

tools/rename_annotated_feature/.shed.yml

@@ -0,0 +1,12 @@
+name: rename_annotated_feature
+owner: recetox
+description: Update column names in an abundance table using a annotation table with spectral matching results
+homepage_url: https://github.com/RECETOX/galaxytools/
+long_description: |
+  Renames column features in the abundance table based on corresponding annotations. 
+  It operates in two modes: 'single' and 'multiple'. In 'single' mode, it selects the 
+  highest scoring match for renaming, while in 'multiple' mode, it includes all matches with scores. 
+categories:
+  - Metabolomics
+remote_repository_url: "https://github.com/RECETOX/galaxytools/tree/master/tools/rename_annotated_feature"
+type: unrestricted

tools/rename_annotated_feature/macros.xml

@@ -0,0 +1,26 @@
+<macros>
+    <token name="@TOOL_VERSION@">1.0.0</token>
+    <xml name="creator">
+    <creator>
+        <person
+            givenName="Wudmir"
+            familyName="Rojas"
+            url="https://github.com/wverastegui"
+            identifier="0000-0001-7036-9987" />
+        <person
+            givenName="Helge"
+            familyName="Hecht"
+            url="https://github.com/hechth"
+            identifier="0000-0001-6744-996X" />
+        <organization
+            url="https://www.recetox.muni.cz/"
+            email="GalaxyToolsDevelopmentandDeployment@space.muni.cz"
+            name="RECETOX MUNI"/>
+    </creator>
+    </xml>
+    <token name="@HELP@"><![CDATA[
+        This tool uses an annotations table to rename columns in an abundance table. It accepts paths to these tables, 
+        a renaming mode ("single" or "multiple"), and an output path for the CSV result. 'Single' mode renames based on
+        the highest match, 'multiple' mode renames based on all matches.
+    ]]></token>
+</macros>

tools/rename_annotated_feature/rename_annotated_feature.py

@@ -0,0 +1,94 @@
+import argparse
+from collections import defaultdict
+from typing import Tuple
+
+import pandas as pd
+
+
+def parse_arguments() -> argparse.Namespace:
+    """Parses command-line arguments.
+
+    Returns:
+        argparse.Namespace: Namespace with argument values as attributes.
+    """
+    parser = argparse.ArgumentParser(description='Rename annotated feature.')
+    parser.add_argument('--annotations_table_path', type=str, required=True, help='Path to the annotations table file.')
+    parser.add_argument('--abundance_table_path', type=str, required=True, help='Path to the abundance table file.')
+    parser.add_argument('--mode', type=str, choices=['single', 'multiple'], default='single', help='Mode to use for renaming. Can be "single" or "multiple".')
+    parser.add_argument('--output_path', type=str, default='output.csv', help='Path to the output CSV file.')
+    return parser.parse_args()
+
+
+def load_tables(annotations_table_path: str, abundance_table_path: str) -> Tuple[pd.DataFrame, pd.DataFrame]:
+    """Loads annotation and abundance tables from files.
+
+    Args:
+        annotations_table_path (str): Path to the annotations table file.
+        abundance_table_path (str): Path to the abundance table file.
+
+    Returns:
+        Tuple[pd.DataFrame, pd.DataFrame]: Tuple of DataFrames for annotations and abundance tables.
+    """
+    annotations_table = pd.read_table(annotations_table_path)
+    abundance_table = pd.read_table(abundance_table_path)
+
+    annotations_table.columns = annotations_table.columns.str.strip()
+    abundance_table.columns = abundance_table.columns.str.strip()
+
+    return annotations_table, abundance_table
+
+
+def rename_single(annotations_table: pd.DataFrame, abundance_table: pd.DataFrame) -> None:
+    """Renames columns in abundance table based on single best match in annotations table.
+
+    Args:
+        annotations_table (pd.DataFrame): DataFrame of annotations.
+        abundance_table (pd.DataFrame): DataFrame of abundance data.
+    """
+    scores_col = annotations_table.columns[-1]
+    ref_idxs = annotations_table.groupby("query")[scores_col].idxmax()
+    results = annotations_table.loc[ref_idxs]
+
+    queries = results["query"]
+    refs = results["reference"]
+
+    mapping = dict(zip(queries, refs))
+    abundance_table.rename(columns=mapping, inplace=True)
+
+
+def rename_multiple(annotations_table: pd.DataFrame, abundance_table: pd.DataFrame) -> None:
+    """Renames columns in abundance table based on multiple matches in annotations table.
+
+    Args:
+        annotations_table (pd.DataFrame): DataFrame of annotations.
+        abundance_table (pd.DataFrame): DataFrame of abundance data.
+    """
+    queries = annotations_table["query"]
+    refs = annotations_table["reference"]
+
+    mapping = defaultdict(list)
+    for query, ref in zip(queries, refs):
+        mapping[query].append(ref)
+
+    for query, refs in mapping.items():
+        new_column_name = ', '.join(refs)
+        if query in abundance_table.columns:
+            abundance_table.rename(columns={query: new_column_name}, inplace=True)
+
+
+def main() -> None:
+    """Main function to parse arguments, load tables, rename columns, and save output."""
+    args = parse_arguments()
+
+    annotations_table, abundance_table = load_tables(args.annotations_table_path, args.abundance_table_path)
+
+    if args.mode == "single":
+        rename_single(annotations_table, abundance_table)
+    else:
+        rename_multiple(annotations_table, abundance_table)
+
+    abundance_table.to_csv(args.output_path, sep="\t", index=False)
+
+
+if __name__ == "__main__":
+    main()

tools/rename_annotated_feature/rename_annotated_feature.xml

@@ -0,0 +1,53 @@
+<tool id="rename_annotated_feature" name="Rename Annotated Feature" version="@TOOL_VERSION@+galaxy0" profile="21.09">
+    <description>Rename columns in abundance table based on annotations table</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="creator"/>
+    <requirements>
+        <requirement type="package" version="2.2.1">pandas</requirement>
+    </requirements>
+    <command detect_errors="exit_code"><![CDATA[
+        python3 '${__tool_directory__}/rename_annotated_feature.py'
+        --annotations_table_path '$annotations_table_path' 
+        --abundance_table_path '$abundance_table_path' 
+        --mode '$mode'
+        --output_path '$output_path'
+    ]]></command>
+    <inputs>
+        <param name="annotations_table_path" type="data" format="tabular" label="Annotations table file" help="Path to the annotations table file."/>
+        <param name="abundance_table_path" type="data" format="tabular" label="Abundance table file" help="Path to the abundance table file."/>
+        <param name="mode" type="select" label="Mode to use for renaming" help="Can be single or multiple.">
+            <option value="single" selected="true">Single</option>
+            <option value="multiple">Multiple</option>
+        </param>
+    </inputs>
+    <outputs>
+        <data name="output_path" format="tabular" label="Renamed abundance table"/>
+    </outputs>
+    <tests>
+        <test>
+            <param name="annotations_table_path" value="annotated_table.tsv" ftype="tabular"/>
+            <param name="abundance_table_path" value="abundance_table.tsv" ftype="tabular"/>
+            <param name="mode" value="single"/>
+            <output name="output_path" file="single_mode_output.tsv"/>
+        </test>
+        <test>
+            <param name="annotations_table_path" value="annotated_table.tsv" ftype="tabular"/>
+            <param name="abundance_table_path" value="abundance_table.tsv" ftype="tabular" />
+            <param name="mode" value="multiple"/>
+            <output name="output_path" file="multi_mode_output.tsv"/>
+        </test>
+    </tests>
+    <help>
+        <![CDATA[
+        @HELP@
+        ]]>
+    </help>
+    <!-- Update to the correct citation for this tool -->
+    <citations>
+            <citation type="doi">10.5281/zenodo.7178586</citation>
+            <citation type="doi">10.21105/joss.02411</citation>
+            <citation type="doi">10.1021/ac501530d</citation>            
+    </citations>
+</tool>