--- a/ensembl2symbol.xml	Fri Jun 18 20:23:19 2021 +0000
+++ b/ensembl2symbol.xml	Thu Jul 29 20:48:10 2021 +0000
@@ -4,9 +4,9 @@
       <import>macros.xml</import>
   </macros>
   <expand macro="requirements" />
-  <stdio> 
-    <exit_code range="1" level="fatal" description="Repeated Unique IDs"/> 
-  </stdio> 
+  <stdio>
+    <exit_code range="1" level="fatal" description="Repeated Unique IDs"/>
+  </stdio>
   <command detect_errors="exit_code"><![CDATA[
   ensembl2symbol.py
     -s=$species
@@ -21,10 +21,12 @@
      <option value="mouse">Mus musculus</option>
      <option value="rat">Rattus norvegicus</option>
      <option value="fruitfly">Drosophila melanogaster</option>
+     <option value="thale-cress">Arabidopsis thaliana</option>
+     <option value="nematode">Caenorhabditis elegans</option>
     </param>
     <param name="geneAnnot" type="data" format="tabular" label="Select the Dataset from your History containing the ENSEMBLIDs"/>
-    <param name="uniqId" type="text" size="30" value="" label="Unique Gene FeatureID" help="Name of the column in your dataset containing unique FeatureIDs."/> 
-    <param name="ensemblId" type="text" size="30" value="" label="ENSEMBLID" help="Name of the column containing the ENSEMBLIDs to use for linking to gene symbols."/> 
+    <param name="uniqId" type="text" size="30" value="" label="Unique Gene FeatureID" help="Name of the column in your dataset containing unique FeatureIDs."/>
+    <param name="ensemblId" type="text" size="30" value="" label="ENSEMBLID" help="Name of the column containing the ENSEMBLIDs to use for linking to gene symbols."/>
   </inputs>
   <outputs>
     <data format="tabular" name="output" label="${tool.name} on ${on_string}: ENSEMBL to GeneSymbol Annotation File"/>
@@ -32,95 +34,101 @@
   <tests>
     <test>
       <param name="species" value="rat"/>
-      <param name="geneAnnot" value="gene_annotation_file_01fhl.tsv"/>
+      <param name="geneAnnot" value="gene_annotation.tsv"/>
       <param name="uniqId" value="UniqueID"/>
       <param name="ensemblId" value="GeneName"/>
-      <param name="Output" value="ensembl2symbol_annotation_file_01fhl.tsv"/>
+      <output name="output" value="ensembl2symbol_annotation.tsv"/>
     </test>
   </tests>
   <help><![CDATA[
 
 **Tool Description**
 
-  This tool takes a dataset containing unique FeatureIDs and ENSEMBLIDs and provides gene symbols. The link from the ENSEMBLIDs to gene symbols is made using Biomart. The tool adds the following columns to the input dataset:  GeneSymbol, Score, Selected,  and Tie. The GeneSymbol column contains the short identifiers (typically 3 letter abbreviations) of the gene name. The Score column contains a value that represents how well the ENSEMBLID matched the returned GeneSymbol using the PyPi package Gene 3.0.0 (https://www.ncbi.nlm.nih.gov/pubmed/23175613). The Selected column = 'Yes' when an ENSEMBLID uniquely matches a GeneSymbol or when that row has the highest Score value.  The Selected column = 'No' in the absence of a unique match for rows lower than the maximum score. If there is a tie in the Score the alphabetically first value is selected and the Tie column has a value of Yes. We note that FeatureID may not be unique in the resulting output dataset.
+This tool takes an annotation data file containing unique FeatureIDs and Ensembl IDs and adds
+gene symbols. The link from the Ensembl IDs to gene symbols is made using mygene
+(https://mygene.info/). The tool adds the following columns to the input annotation data file:
+GeneSymbol, Score, Selected and Tie.
+
+The GeneSymbol column contains the short-form abbreviation for the gene. The Score column
+contains a value generated by mygene indicating how well the Ensembl ID matched the returned gene
+symbol(s) (https://genomebiology.biomedcentral.com/articles/10.1186/s13059-016-0953-9). For
+cases where an Ensembl ID uniquely matches to a gene symbol, the Selected column = ‘Yes”. For
+cases where an Ensembl ID matches to more than one gene symbol, the Selected column = ‘Yes’ for
+the gene symbol with the best Score value. If there is a tie, the alphabetically first gene
+symbol is selected and the Tie column = ‘Yes’. We note that FeatureID may not be unique in the
+resulting output dataset.
 
 --------------------------------------------------------------------------------
 
-**INPUT**
+**Input**
 
-**Dataset with unique FeatureIDs and ENSEMBLIDs**
+**Dataset with unique FeatureID and ENSEMBLID values**
 
-  +-------------+--------------+-----+
-  | FeatureID   | ENSEMBLID    | ... |
-  +=============+==============+=====+
-  | FeatureID_1 | ENS...       | ... |
-  +-------------+--------------+-----+
-  | FeatureID_2 | ENS...       | ... |
-  +-------------+--------------+-----+
-  | FeatureID_3 | ENS...       | ... |
-  +-------------+--------------+-----+
-  | ...         | ...          | ... |
-  +-------------+--------------+-----+
+ +-------------+--------------+-----+
+ | FeatureID   | ENSEMBLID    | ... |
+ +=============+==============+=====+
+ | FeatureID_1 | ENS...       | ... |
+ +-------------+--------------+-----+
+ | FeatureID_2 | ENS...       | ... |
+ +-------------+--------------+-----+
+ | FeatureID_3 | ENS...       | ... |
+ +-------------+--------------+-----+
+ | ...         | ...          | ... |
+ +-------------+--------------+-----+
 
     **NOTE:** This file must contain at least two columns, a column with unique FeatureIDs and a column containing ENSEMBLIDs. Other columns may be present.
 
 **Unique FeatureID**
 
-  Name of the column in your input dataset that has unique FeatureIDs.
+Name of the column in your input dataset that has unique FeatureIDs.
 
 **ENSEMBLID**
 
- Name of the column containing the ENSEMBLIDs.
+Name of the column containing the ENSEMBLIDs.
 
 --------------------------------------------------------------------------------
 
 **OUTPUT**
 
-  The user will get a single output file.
+The user will get a single output file containing the linked gene symbols.
 
 **Output Table**
 
-  +------------+------------+--------------+-------------+-----------+----------+
-  | FeatureID   | ENSEMBLID | ...          | GeneSymbol  | Score     | Selected |
-  +============+============+==============+=============+===========+==========+
-  | FeatureID_1 | ENS...    | ...          | one*        | 13.550056 | Yes      |
-  +------------+------------+--------------+-------------+-----------+----------+
-  | FeatureID_2 | ENS...    | ...          | two*        | 12.984067 | Yes      |
-  +------------+------------+--------------+-------------+-----------+----------+
-  | FeatureID_2 | ENS...    | ...          | three*      | 11.995048 | No       |
-  +------------+------------+--------------+-------------+-----------+----------+
-  | FeatureID_3 | ENS...    | ...          | four*       | 12.549084 | Yes      |
-  +------------+------------+--------------+-------------+-----------+----------+
-  | ...        | ...        | ...          | ...         | ...       | ...      |
-  +------------+------------+--------------+-------------+-----------+----------+
+  +-------------+------------+--------------+-------------+-----------+----------+
+  | FeatureID   | ENSEMBLID  | ...          | GeneSymbol  | Score     | Selected |
+  +=============+============+==============+=============+===========+==========+
+  | FeatureID_1 | ENS...     | ...          | one*        | 13.550056 | Yes      |
+  +-------------+------------+--------------+-------------+-----------+----------+
+  | FeatureID_2 | ENS...     | ...          | two*        | 12.984067 | Yes      |
+  +-------------+------------+--------------+-------------+-----------+----------+
+  | FeatureID_2 | ENS...     | ...          | three*      | 11.995048 | No       |
+  +-------------+------------+--------------+-------------+-----------+----------+
+  | FeatureID_3 | ENS...     | ...          | four*       | 12.549084 | Yes      |
+  +-------------+------------+--------------+-------------+-----------+----------+
+  | ...         | ...        | ...          | ...         | ...       | ...      |
+  +-------------+------------+--------------+-------------+-----------+----------+
 
-  ]]>
-  </help>
+  '*'=refers to the matched gene
+
+  ]]></help>
   <citations>
-    <citation type="bibtex">@article{wu2014mygene,
-    title={MyGene. info: gene annotation query as a service},
-    author={Wu, Chunlei and Mark, Adam and Su, Andrew I},
-    journal={bioRxiv},
-    pages={009332},
-    year={2014},
-    publisher={Cold Spring Harbor Laboratory}
-    }</citation>
     <citation type="bibtex">@ARTICLE{Kirpich17secimtools,
     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>
+    <citation type="bibtex">@article{xim2016mygene,
+    title={High-performance web services for querying gene and variant annotation},
+    author={Xin, J and Mark, A and Afrashiabi, C and Tsueng, G and Juchler, M and Gopal, N and Stupp, GS and Putman, TE and Ainscough, BJ and Griffith, OL and Torkamani, A and Whetzel, PL and Mungall, CJ and Mooney, SD and Su, AI and Wu, C},
+    journal={Genome Biology},
+    year={2016},
     }</citation>
   </citations>
 </tool>