# HG changeset patch
# User proteore
# Date 1561623679 14400
# Node ID 34097acf457cdcb70db370651ab1846f6adee973
# Parent  113cce3fc379ca2429430b32878435aed459d4b2
planemo upload commit fb27a6b5de5cd7b269a41be3c85c593b77aa1b18-dirty

diff -r 113cce3fc379 -r 34097acf457c reactome_analysis.py
--- a/reactome_analysis.py	Thu Dec 13 04:17:25 2018 -0500
+++ b/reactome_analysis.py	Thu Jun 27 04:21:19 2019 -0400
@@ -1,7 +1,4 @@
-import os
-import re
-import json
-import argparse
+import os, re, json, argparse, csv
 
 CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
 
@@ -42,22 +39,29 @@
     """
     trash = []
     if identifiers[1] == "list":
-        ids = "\n".join(id_valid(identifiers[0].split())[0])
+        ids = identifiers[0].split()
+        ids = [x.split(";") for x in ids]    
+        ids = [item.strip() for sublist in ids for item in sublist if item != '']
         json_string = os.popen("curl -H \"Content-Type: text/plain\" -d \"$(printf '%s')\" -X POST --url www.reactome.org/AnalysisService/identifiers/\?pageSize\=1\&page\=1" % ids).read()
         if len(id_valid(identifiers[0].split())[1]) > 0:
             trash = id_valid(identifiers[0].split())[1]
     elif identifiers[1] == "file":
         header = identifiers[2]
-        mq = open(identifiers[0]).readlines()
-        if isnumber("int", identifiers[3].replace("c", "")):
-            if header == "true":
-                idens = [x.split("\t")[int(identifiers[3].replace("c", ""))-1] for x in mq[1:]]
-            else:
-                idens = [x.split("\t")[int(identifiers[3].replace("c", ""))-1] for x in mq]
-            ids = "\n".join(id_valid(idens)[0])
-            json_string = os.popen("curl -H \"Content-Type: text/plain\" -d \"$(printf '%s')\" -X POST --url www.reactome.org/AnalysisService/identifiers/\?pageSize\=1\&page\=1 2> stderr" % ids).read()
-            if len(id_valid(idens)[1]) > 0:
-                trash = id_valid(idens)[1]
+        with open(identifiers[0],"r") as mq :
+            file_content = csv.reader(mq,delimiter="\t")
+            file_content = list(file_content)   #csv object to list
+            ncol = identifiers[3]
+            if isnumber("int", ncol.replace("c", "")):
+                if header == "true":
+                    idens = [x for x in [line[int(ncol.replace("c", ""))-1].split(";") for line in file_content[1:]]]
+                else:
+                    idens = [x for x in [line[int(ncol.replace("c", ""))-1].split(";") for line in file_content]] 
+
+                idens = [item.strip() for sublist in idens for item in sublist if item != '']   #flat list of list of lists, remove empty items 
+                ids = "\n".join(id_valid(idens)[0])
+                json_string = os.popen("curl -H \"Content-Type: text/plain\" -d \"$(printf '%s')\" -X POST --url www.reactome.org/AnalysisService/identifiers/\?pageSize\=1\&page\=1 2> stderr" % ids).read()
+                if len(id_valid(idens)[1]) > 0:
+                    trash = id_valid(idens)[1]
     #print(json_string)
     j = json.loads(json_string)
     print ("Identifiers not found: " + str(j["identifiersNotFound"]))
diff -r 113cce3fc379 -r 34097acf457c reactome_analysis.xml
--- a/reactome_analysis.xml	Thu Dec 13 04:17:25 2018 -0500
+++ b/reactome_analysis.xml	Thu Jun 27 04:21:19 2019 -0400
@@ -1,5 +1,5 @@
-<tool id="reactome_analysis" name="Query Reactome pathway database" version="2018.12.12">
-    <description></description>
+<tool id="reactome_analysis" name="Query pathway database" version="2019.06.27">
+    <description>[Reactome]</description>
     <requirements>
     </requirements>
     <stdio>
@@ -20,12 +20,12 @@
     ]]></command>
     <inputs>
         <conditional name="opt">
-            <param name="input" type="select" label="Input identifiers (Uniprot accession number (e.g. P01023), Entrez gene ID (e.g.7157) or gene name (e.g. AQP7)" multiple="False" >
+            <param name="input" type="select" label="Input IDs (UniProt Accession number, Entrez Gene ID, Gene Name)" multiple="False" >
                 <option value="text">Copy/paste your list of IDs </option>
-		        <option value="file" selected="true">Input file containing your identifiers</option>
+		        <option value="file" selected="true">Input file containing your IDs</option>
             </param>
             <when value="text" >
-                <param name="list" type="text" label="Enter list of identifiers" help="IDs must be separated by space into the form field, for example: P31946 P62258">
+                <param name="list" type="text" label="Enter list of IDs" help="IDs must be separated by a space into the form field, for example: P31946 P62258">
                     <sanitizer>
                         <valid initial="string.printable">
                             <remove value="&apos;"/>
@@ -37,15 +37,17 @@
                 </param>
             </when>
             <when value="file" >
-                <param name="file" type="data" format="txt, tabular" label="Input file containing your identifiers" help="Input file is a tab-delimited file with at least one contain containing identifier" />
-                <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does your input file contain header?" />
-		        <param type="text" name="ncol" value="c1" label="Please specify the column number where are your IDs (e.g : Enter c1 for column n°1)" />
+                <param name="file" type="data" format="txt, tabular" label="Input file containing your IDs" help="Input file is a tab-delimited file with at least one contain containing identifier" />
+                <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does file contain header?" />
+		        <param type="text" name="ncol" value="c1" label="Column number of IDs (e.g : Enter c1 for column n°1)">
+                    <validator type="regex" message="Please enter a column number, for example: 'c1' for the first column">[c]{0,1}[0-9]+</validator>
+                </param>
             </when>
         </conditional>
-        <param name="species" type="select" label="Select species">
-            <option value="48887">Human (H. sapiens)</option>
-            <option value="48892">Mouse (M. musculus)</option>
-            <option value="48895">Rat (R. norvegicus)</option>
+        <param name="species" type="select" label="Species (human, mouse, rat)">
+            <option value="48887">Human (Homo sapiens)</option>
+            <option value="48892">Mouse (Mouse musculus)</option>
+            <option value="48895">Rat (Rattus norvegicus)</option>
         </param>
     </inputs>
     <outputs>
@@ -67,13 +69,34 @@
         </test>
     </tests>
     <help><![CDATA[
-Reactome software provides service of creating diagram representing the relations between the biological processes. This tool allows linking to Reactome web service with pre-loaded data from a list of IDs, a file containing IDs or from a column of a complexed file.
+
+**Description**
+
+This tool allows to map your gene/protein list to the Reactome pathway browser (visualize and interact with biological pathways) via a web service with pre-loaded data from your list of IDs
 
-**For the rows that have more than 1 ID, only the first one is taken into account.**
+-----
+
+**Input** 
+
+A list of gene/protein IDs. List of IDs can be entered either in a copy/paste manner or by selecting a file with your IDs. 
+
+ID types allowed are: UniProt accNumber (e.g. O75391), Entrez gene ID (e.g. 8086) and gene name (e.g. TP53, NUP58...). If you have other type of ID, please use the ID_Converter tool of ProteoRE.
 
-**Supported IDs: Uniprot accession number (e.g. P01023), Entrez gene ID (e.g.7157), gene name (e.g. AQP7). If there is any ID containing invalid characters, it will be removed from the queue and placed in "Invalid identifiers" file.**
+.. class:: warningmark
+	
+In copy/paste mode, the number of IDs considered in input is limited to 5000.
+
+-----
+
+**Parameters**
 
-**Supported species: Human (H. sapiens), Mouse (M. musculus), Rat (Rattus norvegicus)**
+"Select species": can be Human (Homo sapiens), Mouse (Mouse musculus) or Rat (Rattus norvegicus)
+
+-----
+
+**Output**
+
+To access results, click on the "View data" icon (from the item created in your history panel), then click on the "Analyze" button in the central panel will directly display the results in the Reactome pathway browser.  
 
 -----
 
@@ -81,19 +104,21 @@
 
 **Authors** 
 
-Fabregat et al. 2017 PMID: 29145629 (https://www.ncbi.nlm.nih.gov/pubmed/29145629)
+Fabregat et al., The Reactome Pathway Knowledgebase. Nucleic Acids Res. 2018. 46(D1):D649-D655. doi: 10.1093/nar/gkx1132. PubMed PMID: 29145629
 
-Milacic et al. 2012 PMID:24213504 (https://www.ncbi.nlm.nih.gov/pubmed/24243840)
+-----
 
 .. class:: infomark
 
 **Galaxy integration**
 
-T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR
+Lien Nguyen, Florence Combes, Yves Vandenbrouck - CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR
+
+Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux - INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform, FR
 
-Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit,Migale Bioinformatics platform,
+This work has been partially funded through the French National Agency for Research (ANR) IFB project.
 
-Contact support@proteore.org for any questions or concerns about the Galaxy implementation of this tool.
+Help: contact@proteore.org for any questions or concerns about this tool.
     ]]></help>
     <citations>
     </citations>