diff add_kegg_pathway_info.xml @ 2:2c218a253d56 draft default tip

"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
author malex
date Thu, 29 Jul 2021 20:48:10 +0000
parents ec9ee8edb84d
children
line wrap: on
line diff
--- a/add_kegg_pathway_info.xml	Fri Jun 18 20:23:19 2021 +0000
+++ b/add_kegg_pathway_info.xml	Thu Jul 29 20:48:10 2021 +0000
@@ -28,14 +28,14 @@
         -gid=$dataSets.geneUniqId
         -gn=$dataSets.geneName
         -gkid=$dataSets.geneKeggId
-        -go=$geneOutput
-        -kg2p=$gene_keggID2pathID
         -mka=$dataSets.metKeggAnnot
         -mid=$dataSets.metUniqId
         -mn=$dataSets.metName
         -mkid=$dataSets.metKeggId
+        -kg2p=$gene_keggID2pathID
+        -km2p=$met_keggID2pathID
+        -go=$geneOutput
         -mo=$metOutput
-        -km2p=$met_keggID2pathID
       #end if
       -p=$pathways
   ]]></command>
@@ -48,19 +48,20 @@
      <option value="ath">Arabidopsis thaliana</option>
      <option value="sce">Saccharomyces cerevisiae</option>
      <option value="eco">Escherichia coli</option>
+     <option value="cel">Caenorhabditis elegans</option>
     </param>
     <conditional name="dataSets">
       <param name="whichDataSet" type="select" display="radio" label="Select the Datasets you want to add KEGG pathway information to.  Note: datasets must contain KEGGIDs.">
         <option value="both" selected="true">Gene Expression + Metabolomic Files with KEGGIDs</option>
-        <option value="geneDataset">Gene Expression File with KEGGIDs</option> 
+        <option value="geneDataset">Gene Expression File with KEGGIDs</option>
         <option value="metDataset">Metabolomic File with KEGGIDs</option>
-        <validator type="no_options" message="You must select at least one option." /> 
+        <validator type="no_options" message="You must select at least one option." />
       </param>
       <when value="both">
         <param name="geneKeggAnnot" type="data" format="tabular" label="Gene to KEGGID Link File" help="Select the Gene to KEGGID Link File that contains KEGG identifiers from your history"/>
-        <param name="geneUniqId" type="text" size="30" value="" label="Gene unique FeatureID" help="Name of the column in your Gene to KEGGID Link File that contains unique FeatureIDs."/> 
+        <param name="geneUniqId" type="text" size="30" value="" label="Gene unique FeatureID" help="Name of the column in your Gene to KEGGID Link File that contains unique FeatureIDs."/>
         <param name="geneName" type="text" size="30" value="" label="Gene Symbol" help="Name of the column in your Gene to KEGGID Link File that contains Gene Symbols."/>
-        <param name="geneKeggId" type="text" size="30" value="" label="Gene KEGGID" help="Name of the column in your Gene to KEGGID Link File that contains KEGGIDs."/> 
+        <param name="geneKeggId" type="text" size="30" value="" label="Gene KEGGID" help="Name of the column in your Gene to KEGGID Link File that contains KEGGIDs."/>
         <param name="metKeggAnnot" type="data" format="tabular" label="Metabolite to KEGGID Link File" help="Select the Metabolite to KEGGID Link File that contains KEGG identifiers from your history"/>
         <param name="metUniqId" type="text" size="30" value="" label="Metabolite unique FeatureID" help="Name of the column in your Metabolite to KEGGID Link File that contains unique FeatureIDs."/>
         <param name="metName" type="text" size="30" value="" label="Metabolite Names" help="Name of the column in your Metabolite to KEGGID Link File that contains Metabolite Names."/>
@@ -68,9 +69,9 @@
       </when>
       <when value="geneDataset">
         <param name="geneKeggAnnot" type="data" format="tabular" label="Gene to KEGGID Link File" help="Select the Gene to KEGGID Link File that contains KEGG identifiers from your history"/>
-        <param name="geneUniqId" type="text" size="30" value="" label="Gene unique FeatureID" help="Name of the column in your Gene to KEGGID Link File that contains unique FeatureIDs."/> 
+        <param name="geneUniqId" type="text" size="30" value="" label="Gene unique FeatureID" help="Name of the column in your Gene to KEGGID Link File that contains unique FeatureIDs."/>
         <param name="geneName" type="text" size="30" value="" label="Gene Symbol" help="Name of the column in your Gene to KEGGID Link File that contains Gene Symbols."/>
-        <param name="geneKeggId" type="text" size="30" value="" label="Gene KEGGID" help="Name of the column in your Gene to KEGGID Link File that contains KEGGIDs."/> 
+        <param name="geneKeggId" type="text" size="30" value="" label="Gene KEGGID" help="Name of the column in your Gene to KEGGID Link File that contains KEGGIDs."/>
       </when>
       <when value="metDataset">
         <param name="metKeggAnnot" type="data" format="tabular" label="Metabolite to KEGGID Link File" help="Select the Metabolite to KEGGID Link File that contains KEGG identifiers from your history"/>
@@ -99,29 +100,46 @@
     <test>
       <param name="species" value="rno"/>
       <param name="whichDataSet" value="both"/>
-      <param name="geneKeggAnnot" value="gene_to_keggId_link_01fhl.tsv"/>
+      <param name="geneKeggAnnot" value="gene_to_keggId_link.tsv"/>
       <param name="geneUniqId" value="UniqueID"/>
       <param name="geneName" value="GeneSymbol"/>
-      <param name="geneKeggId" value="KEGGID"/>
-      <param name="metKeggAnnot" value="metabolite_to_keggId_link_01fhl.tsv"/>
+      <param name="geneKeggId" value="KEGG_ID"/>
+      <param name="metKeggAnnot" value="metabolite_to_keggId_link.tsv"/>
       <param name="metUniqId" value="UniqueID"/>
       <param name="metName" value="MetName"/>
-      <param name="metKeggId" value="KEGGID"/>
-      <output name="kgen2pathway" file="KGEN2PATHWAY"/>
-      <output name="kmet2pathway" file="KMET2PATHWAY"/>
-      <output name="pathways" file="PATHWAYS"/>
-      <output name="output" file="kegg_downloader_table"/>
+      <param name="metKeggId" value="KEGG_ID"/>
+      <output name="gene_keggID2pathID" file="geneKeggId2pathwayId.tsv" compare="diff" lines_diff="10000"/>
+      <output name="met_keggID2pathID" file="metaboliteKeggId2pathwayId.tsv" compare="diff" lines_diff="10000"/>
+      <output name="geneOutput" file="gene_kegg_pathway.tsv" compare="diff" lines_diff="10000"/>
+      <output name="metOutput" file="metabolite_kegg_pathway.tsv" compare="diff" lines_diff="10000"/>
+      <output name="pathways" file="pathwayId2pathwayNames.tsv" compare="diff" lines_diff="10000"/>
     </test>
   </tests>
   <help><![CDATA[
 
 **Tool Description**
 
-  This tool takes a Gene to KEGG Link dataset, a Metabolomic to KEGG Link dataset or both and adds KEGG Pathway Names using KEGGIDs. The tool was designed to take the output from the ''Link Name to KEGGID' tool as input (for example the Gene to KEGGID Link dataset) but other datasets containing KEGGIDs can be used as well.
+  This tool takes a Gene to KEGG Link dataset or a Metabolomic to KEGG Link dataset and adds KEGG Pathway Names using KEGGIDs.
+  The tool was designed to take the output from the 'Link Name to KEGGID' tool as input (for example the Gene to KEGGID Link dataset),
+  but other datasets containing KEGGIDs can be used as well.
+
+
+  If a 'Gene to KEGG ID link File’ is given, the tool outputs the following three files;
+
+	1) a 'Gene KEGG Pathway File' containing the unique FeatureID, Feature_Name, Feature_Type and KEGG_ID columns from the input file plus Pathway_ID and Pathway_Name columns 	containing KEGG pathway identifiers and KEGG pathway names, respectively.  If no pathways are 	linked to the KEGG IDs then these columns return ‘NA’.
+
+	2) a 'GeneKeggID2PathwayID' file containing the KEGG gene identifiers and their associated KEGG pathway identifiers.
 
-  The user will get different outputs from the 'Add KEGG Pathway Info Tool', depending on the input. If a Gene to KEGGID Link dataset is given as input the tool outputs the following three files:  1) a Gene KEGG Pathway dataset containing the FeatureID, Feature_Name, Feature_Type and KEGGID  columns from the input file and KEGG_PathwayIDs and KEGG Pathway Names from KEGG, 2) a GeneKeggID2PathwayID dataset containing all gene KEGGIDs in KEGG and their associated pathway KEGGIDs and 3) a PathwayID2PathwayNames dataset containing all of the pathway KEGGIDs and their associated KEGG pathway names.  
+	3) a 'PathwayID2PathwayNames' file containing all of the KEGG pathway identifiers and theirassociated KEGG pathway names.
+
+  If a 'Metabolite to KEGG ID link File’ is given, the tool outputs the following three files;
 
-  Analoguous files are generated by the tool if a Metabolite to KEGGID Link dataset is input by the user. 
+	1) a ' Metabolite KEGG Pathway File' containing the unique FeatureID, Feature_Name, Feature_Type and KEGG_ID columns from the input file plus Pathway_ID and Pathway_Name 	columns containing KEGG pathway identifiers and KEGG pathway names, respectively.  If no 	pathways are linked to the KEGG IDs then these columns return ‘NA’.
+
+	2) a 'MetaboliteKeggID2PathwayID' file containing the KEGG metabolite identifiers and their associated KEGG pathway identifiers.
+
+	3) a 'PathwayID2PathwayNames' file containing all of the KEGG pathway identifiers and their associated KEGG pathway names.
+
 
   Note: FeatureIDs and KEGGIDs may not be unique in the output.
 
@@ -140,7 +158,7 @@
   +----------+-----------+--------------+---------+--------------+---------+------------+-----+----------+
   | Gene_3   | three     | Gene         | Yes     | three*       | mmu:... | 1.0        | No  | Yes      |
   +----------+-----------+--------------+---------+--------------+---------+------------+-----+----------+
-  | Gene_4   | four      | Gene         | No      | NA           | NA      | NA         | Na  | NA       |
+  | Gene_4   | four      | Gene         | No      | NA           | NA      | NA         | No  | NA       |
   +----------+-----------+--------------+---------+--------------+---------+------------+-----+----------+
   | ...      | ...       | ...          | ...     | ...          | ...     | ...        | ... | ...      |
   +----------+-----------+--------------+---------+--------------+---------+------------+-----+----------+
@@ -156,7 +174,7 @@
   +----------+----------+--------------+---------+--------------+----------+------------+-----+----------+
   | Met_3    | three    | Metabolite   | Yes     | three*       | cpd:...  | 1.0        | No  | Yes      |
   +----------+----------+--------------+---------+--------------+----------+------------+-----+----------+
-  | Met_4    | four     | Metabolite   | No      | NA           | NA       | NA         | Na  | NA       |
+  | Met_4    | four     | Metabolite   | No      | NA           | NA       | NA         | No  | NA       |
   +----------+----------+--------------+---------+--------------+----------+------------+-----+----------+
   | ...      | ...      | ...          | ...     | ...          | ...      | ...        | ... | ...      |
   +----------+----------+--------------+---------+--------------+----------+------------+-----+----------+
@@ -198,7 +216,7 @@
   | ...         | ...          | ...          | ...     | ...          | ...          |
   +-------------+--------------+--------------+---------+--------------+--------------+
 
-
+------------------------------------------------------------------
 
   (5) **Metabolite KEGG Pathway File.** Tabular file with metabolites, feature types, KEGGIDs, PathwayIDs and Pathway Names.
 
@@ -223,17 +241,13 @@
     author = {Alexander S. Kirpich, Miguel Ibarra, Oleksandr Moskalenko, Justin M. Fear, Joseph Gerken, Xinlei Mi, Ali Ashrafi, Alison M. Morse, Lauren M. McIntyre},
     title = {SECIMTools: A suite of Metabolomics Data Analysis Tools},
     journal = {BMC Bioinformatics},
-    year = {in press}
+    year = {2018}
     }</citation>
-    <citation type="bibtex">@article{garcia2010paintomics,
-    title={Paintomics: a web based tool for the joint visualization of transcriptomics and metabolomics data},
-    author={Garc{\'\i}a-Alcalde, Fernando and Garc{\'\i}a-L{\'o}pez, Federico and Dopazo, Joaqu{\'\i}n and Conesa, Ana},
-    journal={Bioinformatics},
-    volume={27},
-    number={1},
-    pages={137--139},
-    year={2010},
-    publisher={Oxford University Press}
+    <citation type="bibtex">@article{Mor2021GaitGM,
+    title={GAIT-GM integrative cross-omics analyses reveal cholinergic defects in a C. elegans model of Parkinson's disease},
+    author={Mor, DE and Huertas, F and Morse, AM and Kaletsky, R and Murphy, CT and Kalia, V and Miller, GW and Moskalenko, O and Conesa, A and McIntyre, LM},
+    journal={BMC Genomics},
+    year={submitted},
     }</citation>
   </citations>
 </tool>