update 8 : add input files for dictionary : namespace map and entities and reactions

inputs/EntityDictFile.txt

+proteinAbundance    PROTEIN
+pathology   PHENOTYPE
+biologicalProcess   PHENOTYPE
+rnaAbundance    RNA
+microRNAAbundance RNA
\ No newline at end of file

inputs/namespaceDictFile.txt

@@ -3,4 +3,5 @@ PubMed  urn:miriam:pubmed
 GO  urn:miriam:go
 MESHPP   urn:miriam:mesh.2012
 MESHCL  urn:miriam:mesh.2012
-MESHD   urn:miriam:mesh.2012
\ No newline at end of file
+MESHD   urn:miriam:mesh.2012
+CHEBIID urn:miriam:chebi:CHEBI
\ No newline at end of file

inputs/reactionDictFile.txt

+increases   UNKNOWKN_POSTIVE_INFLUENCE
+directlyIncreases   POSTIVE_INFLUENCE
\ No newline at end of file

namespaceTranslator.py

@@ -21,6 +21,25 @@ def getNamespaceDict():
         namespaceDict[nspace[0]]=nspace[1]
     return namespaceDict
 
+
+
+#LOAD NAMESPACE DICTIONARY
+def getEntityDict():
+    entityDict={}
+    for line in open("inputs/EntityDictFile.txt",'r'):
+        nspace=line.split()
+        entityDict[nspace[0]]=nspace[1]
+    return entityDict
+
+
+#LOAD reaction DICTIONARY
+def getReactionDict():
+    reactionDict={}
+    for line in open("inputs/reactionDictFile.txt",'r'):
+        nspace=line.split()
+        reactionDict[nspace[0]]=nspace[1]
+    return reactionDict
+
 #Get GOID from GOOSE
 def getGoIDfromTerm(term):
     cnx = MySQLdb.connect(user='go_select', passwd='amigo', host='mysql-amigo.ebi.ac.uk', db='go_latest', port=4085)
@@ -29,4 +48,4 @@ def getGoIDfromTerm(term):
     cursor.execute(query)
     row=cursor.fetchone()
     cnx.close()
-    return row
+    return row
\ No newline at end of file

xBEL2CellD.py

@@ -66,10 +66,23 @@ def get_details_from_element(node, index, statement_num, evidence, expStatementF
         elementName = ""  # function@TERM
         elementAnnotation = ""  # ns@PARAMETER+text
         details = "EMPTY"
+
+
+        entityDict=NT.getEntityDict()
+
         if term is not None:
-            elementName = term.get(ns_tag('function'))
+            element = term.get(ns_tag('function'))
             parameter = term.find(ns_tag("parameter"))
-
+            if element in entityDict.keys():
+                elementName=entityDict[element]
+            else:
+                elementName=element
+                #LOAD entity DIctionary
+                alreadyIn=[line.strip() for line in open("outputs/additional/toMapEntities.txt","r")]
+                if element not in alreadyIn:
+                    f=open("outputs/additional/toMapEntities.txt","a")
+                    f.write(element+"\n")
+                    f.close()
             if parameter is not None:
                 belnamespace=parameter.get(ns_tag("ns"))
                 namespaceDict=NT.getNamespaceDict()
@@ -101,8 +114,7 @@ def get_details_from_element(node, index, statement_num, evidence, expStatementF
                         details = get_details_from_element(term, index, statement_num, evidence, expStatementFile)
                         return details
         else:
-            print remove_ns_tag(
-                node.tag).upper() + " is nested WITH A STATEMENT ## add as modifier to nested statement(reaction)"
+            print remove_ns_tag(node.tag).upper() + " is nested WITH A STATEMENT ## add as modifier to nested statement(reaction)"
             print "----PRINTING NODE INFO RECURSIVELY"
 
             entry = str(index+1) + "|" + str(statement_num+1) + "|" + str(elementName + " :" + elementAnnotation) + "|" +str(get_node_info_recursive(term)).replace('|',' ') +"|" + str(evidence.encode('utf-8').replace("\r\n","")+"\n")
@@ -127,10 +139,13 @@ def convertXBEL(filepath):
     tree = ET.parse(filepath)
     root = tree.getroot()
 
-    #LOAD namespace DIctionary
-    f=open("outputs/additional/toAddNamespaces.txt","w")
+    #create new files
+    f=open("outputs/additional/toMapEntities.txt","w")
     f.close()
+
+    #LOAD namespace DIctionary
     namespaceDict=NT.getNamespaceDict()
+    reactionDict=NT.getReactionDict()
 
     # get all statement nodes, annotation and sub nodes (complex, or composite structures)
     reactionIdentifier = 0
@@ -175,6 +190,14 @@ def convertXBEL(filepath):
                         nFile.write(nodeEntry)
                         nFile.close()
                 print "\n-----REACTION-----\n"
+                if relationship in reactionDict.keys():
+                    relationship=reactionDict[relationship]
+                else:
+                    alreadyIn=[line.strip() for line in open("outputs/additional/toMapReactions.txt","r")]
+                    if element not in alreadyIn:
+                        f=open("outputs/additional/toMapReactions.txt","a")
+                        f.write(element+"\n")
+                        f.close()
                 reactionEntry= "r" + str(reactionIdentifier) + "\t" + relationship + "\t" + reactant + "\t" + modifier + "\t" + product + "\t" + namespaceDict[referenceType] + ":" + reference+"\n"
                 print reactionEntry
                 rFile=open(reactionFile,"a")
@@ -185,6 +208,6 @@ def convertXBEL(filepath):
                 print "TO DO : Nested statement: Add as modifier"
 
 
-#COnvert file
+#Convert file
 #/home/alex/PhD/Bel2CellD/full_abstract3.xbel
 convertXBEL('/home/alex/PhD/Bel2CellD/small_corpus.xbel')
\ No newline at end of file