enhancements to the different pubchem rest tools

bgruening · bgruening · commit 96778de37eb2 · 2014-06-23T10:44:26.000+02:00
diff --git a/rest_tool/readfile.py b/rest_tool/readfile.py
@@ -1,14 +1,25 @@
 #!/usr/bin/env python
 
 import io
-import urllib2, urllib, httplib
-def getListFromFile(file):
+import urllib2
+import urllib
+import httplib
+
+def getListFromFile( infile ):
     idlist=[]
-    for line in file:
-        if int(line):
-            idlist.append(line.strip())
+    for line in infile:
+        line = line.strip()
+        if line.isdigit():
+            idlist.append( line )
     return idlist
 
+def getListString( args ):
+    if args.id_type_ff == "file":
+        list_string = ",".join( getListFromFile(open(args.id_value, "r")) )
+    else:
+        list_string = args.id_value.strip().replace("__cr____cn__", ",")
+    return list_string
+
 def getresult(url):
     try:
         connection = urllib2.urlopen(url)
@@ -17,17 +28,8 @@ def getresult(url):
     else:
         return connection.read().rstrip()
 
-def getListString(args):
-    if args.id_type_ff == "file":
-        #build comma list
-        list_string=",".join(getListFromFile(open(args.id_value,"r")))
-    else:
-        print (args.id_value)
-        list_string=args.id_value.strip().replace("__cr____cn__", ",")
-    return list_string
-
 def store_result_get(url, outfile):
-    data=getresult(url)
+    data = getresult(url)
     outfile.write(data)
     outfile.close()
 
diff --git a/rest_tool/rest_tool.py b/rest_tool/rest_tool.py
@@ -2,7 +2,6 @@
 
 import sys, os
 import argparse
-
 import readfile
 
 txt_output=["cids", "aids", "sids", "synonyms" ]
@@ -33,7 +32,7 @@ def main(args):
         url+="xml"
     if args.operation in check_for_id_type and not args.id_type is None:
         url+="?"+args.operation+"_type="+args.id_type
-    print(url)
+    print('The constructed REST URL is: %s' % url)
     data=readfile.getresult(url)
     outfile=args.outfile
     outfile.write(data)
diff --git a/rest_tool/rest_tool.xml b/rest_tool/rest_tool.xml
@@ -1,5 +1,5 @@
-<tool id="rest_tool" name="Fetch Data from pubchem" version="0.1.0">
-    <description>Fetch pubchem data</description>
+<tool id="pubchem_rest_tool" name="Fetch Data from PubChem" version="0.1.0">
+    <description>(Compounds, Substances and Assay)</description>
     <version_command>echo "0.1.0"</version_command>
     <macros>
         <import>rest_tool_macros.xml</import>
@@ -122,7 +122,6 @@
                 #end if
         #end if
     </command>
-
     <inputs>
         <conditional name="choose_action">
             <param name="action" multiple="false" type="select" label="Choose Use Case">
@@ -132,21 +131,20 @@
                 <option value="advanced" selected="True">Advanced</option>
             </param>
             <when value="search">
-                    <param name="input_type_search" multiple="false" type="select" label="Search for">
-                        <expand macro="acs_options" />
-                    </param>
-                    <param name="input_type" multiple="false" type="select" label="Search By">
-                        <option value="name">Name</option>
-                    </param>
-                    <param format="txt" name="search_name" type="text" label="Enter the Name" />
+                <param name="input_type_search" multiple="false" type="select" label="Search for">
+                    <expand macro="acs_options" />
+                </param>
+                <param name="input_type" multiple="false" type="select" label="Search By">
+                    <option value="name">Name</option>
+                </param>
+                <param format="txt" name="search_name" type="text" label="Enter the Name" />
             </when>
             <when value="specific_data">
                 <expand macro="field_or_file" />
                 <conditional name="choose_acs">
                     <param name="input_type" multiple="false" type="select" label="Input Type">
                         <expand macro="acs_options" />
                     </param>
-        
                     <when value="assay">
                         <expand macro="conditional_operation_assay" />
                     </when>
@@ -172,7 +170,6 @@
                     <when value="activity">
                         <param format="txt" name="activity" type="text" label="Enter the activity" />
                     </when>
-            
                     <when value="target">
                         <param name="target_identifier_type" multiple="false" type="select" label="Choose target identifier">
                             <option value="gi">GI</option>
@@ -261,18 +258,24 @@
         </test>
     </tests>
     <help>
+
 **What it does**
 
-This tool fetches data from pubchem. Pubchem offers a very mighty search tool called rest interface. See https://pubchem.ncbi.nlm.nih.gov/pug_rest/PUG_REST.html.
+This tool fetches data from pubchem via the PubChem REST API. 
+More information are available under:
 
-and https://pubchem.ncbi.nlm.nih.gov/pug_rest/PUG_REST_Tutorial.html
+ - https://pubchem.ncbi.nlm.nih.gov/pug_rest/PUG_REST.html.
+ - https://pubchem.ncbi.nlm.nih.gov/pug_rest/PUG_REST_Tutorial.html
 
 This tool simplifies the use of this interface by offering the user almost every possibility in every step.
 
-The input consists mainly of the following: Input IDs Operation Options
+The input consists mainly of the following inpouts:
+
+ - Input IDs 
+ - Operation
+ - Options
 
-The tool has three simple use cases and one more complex use case (choose 'advanced')
 
-The outputformat will be, if possible tabular separated files. If not possible, you will get txt or xml files. 
+The outputformat will be, if possible tabular separated files. If not possible, you will get txt or xml files for further processing.
     </help>
 </tool>
diff --git a/rest_tool/rest_tool_advanced.py b/rest_tool/rest_tool_advanced.py
@@ -5,69 +5,78 @@
 
 import readfile
 import rest_tool_functions
-#dictionary for the output format
 
-dict_output={"cids" :"xml", "aids" : "xml", "sids" : "xml", "description": "xml", "summary" : "xml", "record" : "csv", "classification": "xml", "targets" : "txt", "xrefs" : "txt", "synonyms" : "txt", "property": "csv", "doseresponse" : "csv" }
-
-#alles andere ist xml
+#dictionary for the allowed output formats
+dict_output={"cids" :"xml", 
+    "aids" : "xml", 
+    "sids" : "xml",
+    "description": "xml", 
+    "summary" : "xml",
+    "record" : "csv", 
+    "classification": "xml", 
+    "targets" : "txt", 
+    "xrefs" : "txt", 
+    "synonyms" : "txt", 
+    "property": "csv", 
+    "doseresponse" : "csv"
+    }
 check_for_id_type=["cids", "aids", "sids"]
 
 dic_key_value_type={"assay": "AID", "compound" : "CID", "substance": "SID" }
 dic_key_value_operation={"aids": "AID", "cids" : "CID", "sids": "SID" }
 
 post_id_types=["inchi", "sdf", "smiles"]
-
 id_dict={"compound": "cid", "assay": "aid", "substance" : "sid" }
 
-    
-def main(args):
-    url="http://pubchem.ncbi.nlm.nih.gov/rest/pug/"+args.type+"/"
-    url+=args.id_type+"/"
-    # check if we are post then skip this part otherwise put the ids in the url
+def main( args ):
+    url = "http://pubchem.ncbi.nlm.nih.gov/rest/pug/%s/%s/" % (args.type, args.id_type)
+    # check if we are POST then skip this part otherwise insert the ids into the url
     if not args.id_type in post_id_types:
-        if args.id_type ==id_dict[args.type]:
-            url+=readfile.getListString(args)+"/"
+        if args.id_type == id_dict[args.type]:
+            url += readfile.getListString(args) + "/"
         else:
-            url+=args.id_value+"/"
+            url += args.id_value + "/"
+
+    url += args.operation + "/"
+    if args.operation in ["target", "property", "xrefs"]:
+        url += args.operation_value + "/"
 
-    url+=args.operation+"/"
-    if args.operation == "target" or args.operation == "property" or args.operation == "xrefs":
-        url+=args.operation_value+"/"
-    
-    create_dict_tsv=False
+    create_dict_tsv = False
     if args.operation == "xrefs":
         if "," in args.operation_value:
-            url+="xml"
+            url += "xml"
         else:
-            url+="txt"
+            url += "txt"
     else:
         if args.operation in check_for_id_type:
             # dont create dictionary if they are the same
             if dic_key_value_type[args.type] == dic_key_value_operation[args.operation]:
-                url+="txt"
+                url += "txt"
             else:
-                url+="xml"
-                create_dict_tsv=True
+                url += "xml"
+                create_dict_tsv = True
         else:
-            url+=dict_output[args.operation]
+            url += dict_output[args.operation]
     if args.operation in check_for_id_type and args.id_type not in post_id_types:
-            url+="?%s_type=%s" % (args.operation, args.ids_operation_type)
-    print(url)
+            url += "?%s_type=%s" % (args.operation, args.ids_operation_type)
+    print('The constructed REST URL is: %s' % url)
 
     if args.id_type in post_id_types:
-        postfile=open(args.id_value,"r")
-        post_value=postfile.read()
-        post_dict={args.id_type : post_value}
-        print(post_dict)
+        postfile = open(args.id_value,"r")
+        post_value = postfile.read()
+        post_dict = {args.id_type : post_value}
+        #print(post_dict)
         readfile.store_result_post(url, post_dict, args.outfile)
-    # check if have to create a tsv file
+    # check if we have to create a tsv file
     elif create_dict_tsv == True:
-        key=dic_key_value_type[args.type]
-        value=dic_key_value_operation[args.operation]
-        dic=rest_tool_functions.get_dict_key_value(url, key, value)
-        rest_tool_functions.write_to_sf(dic, args.outfile, "\t")
+        key = dic_key_value_type[args.type]
+        value = dic_key_value_operation[args.operation]
+        dic = rest_tool_functions.get_dict_key_value( url, key, value )
+        rest_tool_functions.write_to_sf( dic, args.outfile, "\t" )
     else:
         readfile.store_result_get(url, args.outfile)
+
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument('--type', type=str, required=True,
@@ -95,10 +104,5 @@ def main(args):
     parser.add_argument('--outfile', type=argparse.FileType('w'), required=True,
         help="Specify the output file")
 
-
-    if len(sys.argv) < 8:
-        print "Too few arguments..."
-        parser.print_help()
-        exit(1)
     args = parser.parse_args()
     main( args )
diff --git a/rest_tool/rest_tool_assays_with_cids_given_target.py b/rest_tool/rest_tool_assays_with_cids_given_target.py
@@ -5,23 +5,15 @@
 import argparse
 import readfile
 
-#get every aid as a list
-#returns a dictionary with aid as key and as value the list of cids
-def getAllAssayIDs():
-    url="http://pubchem.ncbi.nlm.nih.gov/rest/pug/assay/type/all/aids/TXT"
-    data=readfile.getresult(url)
-    aidlist=readfile.getListFromString(data)
-    return aidlist
-
-
 def getIDofLine(line):
     arr=line.split(">")
     if len(arr) > 1:
-        aid=arr[1].split("<")[0]
+        aid = arr[1].split("<")[0]
         return aid
     else:
         return "-1"
-        
+
+
 #get xml of all aids with cids for an activity
 def getAllCidsForAssayActivity(activity):
     url="http://pubchem.ncbi.nlm.nih.gov/rest/pug/assay/activity/"+activity+"/aids/txt?list_return=listkey"
diff --git a/rest_tool/rest_tool_comp_for_assay.py b/rest_tool/rest_tool_comp_for_assay.py
@@ -6,31 +6,29 @@
 import readfile
 import rest_tool_functions
 
-        
-#get the cids for bioassay aid
+"""
+Get all DICs from belonging to bioassay IDs (AIDs)
+"""
 
-        
 def main(args):
     if args.aid_file is None:
-        aidlist=args.aid.split(",")
+        aidlist = args.aid.split(",")
     else:
-        aidlist=readfile.getListFromFile(args.aid_file)
-    aidliststring=",".join(aidlist)
-    url="http://pubchem.ncbi.nlm.nih.gov/rest/pug/assay/aid/"+aidliststring+"/cids/xml"
-    print(url)
-    dic=rest_tool_functions.get_dict_key_value(url, "AID", "CID")
+        aidlist = readfile.getListFromFile(args.aid_file)
+    aidliststring = ",".join(aidlist)
+    url = "http://pubchem.ncbi.nlm.nih.gov/rest/pug/assay/aid/"+aidliststring+"/cids/xml"
+    print('The constructed REST URL is: %s' % url)
+    dic = rest_tool_functions.get_dict_key_value(url, "AID", "CID")
     rest_tool_functions.write_to_sf(dic, args.outfile, "\t")
-    
+
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument('--aid', type=str, dest="aid", help="AIDs of the BioAssay")
     parser.add_argument('--aid-file', dest="aid_file", type=argparse.FileType('r'),
         help="Specify a file with a list of aids, one per line")
     parser.add_argument('--outfile', type=argparse.FileType('w'),
         help="Specify output file")
-    if len(sys.argv) < 2:
-        print "Too few arguments..."
-        parser.print_help()
-        exit(1)
+
     args = parser.parse_args()
     main( args )
diff --git a/rest_tool/rest_tool_functions.py b/rest_tool/rest_tool_functions.py
