Working for APPBEL (removed binary characters from .bel and nested...

Working for APPBEL (removed binary characters from .bel and nested association(split to 2 senetnces)

xBEL2CellD.py

@@ -109,7 +109,7 @@ def get_details_from_element(node, index, statement_num, evidence, expStatementF
                     f.write(element + "\n")
                     f.close()
             if parameter is not None:
-                belnamespace = parameter.get(ns_tag("ns"))
+                belnamespace = parameter.get(ns_tag("ns"))if parameter.get(ns_tag("ns")) is not None else ""
                 namespaceDict = NT.getNamespaceDict()
                 miriamnamespace = belnamespace
                 if namespaceDict.has_key(belnamespace):
@@ -158,6 +158,7 @@ def get_details_from_element(node, index, statement_num, evidence, expStatementF
 
 def convertXBEL(filepath):
     # create new output file 1.nodes.txt 2.reactions.txt
+    print filepath
     nodeFile = "outputs/nodes.txt"
     nFile = open(nodeFile, "w")
     nFile.write("IDENTIFIER\tTYPE\tNAME\tURN\tSPECIES\tDISEASE\tCELL\tTISSUE\tCELLSTRUCTURE\tCELLLINE\tOTHER_ANNOTATION\n")
@@ -166,36 +167,37 @@ def convertXBEL(filepath):
     rFile = open(reactionFile, "w")
     rFile.write("IDENTIFIER\tTYPE\tREACTANTS\tMODIFIERS\tPRODUCTS\tMODIFIER_TYPE\tSPECIES\tANNOTATIONS\n")
     rFile.close()
-    tree = ET.parse(filepath)
-    root = tree.getroot()
-
-    # create new files
-    f = open("outputs/additional/toMapEntities.txt", "w")
-    f.close()
-
-    f = open("outputs/additional/toMapReactions.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
-    totalSpecies = 0
-    expStatementFile = "outputs/additional/exceptionalStatements.txt"
-    file = open(expStatementFile, 'w')
-    file.write("GROUP|STATEMENT_NUMBER|DETAILS|NODEINFO|EVIDENCE\n")
-    file.close()
-    evidence = ""
-    speciesMap={}
-    for index, statementGr in enumerate(root.iter(tag=ns_tag('statementGroup'))):
-        for statement_num, statement in enumerate(statementGr.findall(ns_tag('statement'))):
-            print "\n\n\n############################################"
-            print "GROUP" + str(index + 1) + " :: STATEMENT  " + str(statement_num + 1) + " \t\t\t**" + str(reactionIdentifier)
-            print "############################################"
-            reactionIdentifier += 1  # statement number
-            try:
+    try:
+        tree = ET.parse(filepath)
+        root = tree.getroot()
+
+        # create new files
+        f = open("outputs/additional/toMapEntities.txt", "w")
+        f.close()
+
+        f = open("outputs/additional/toMapReactions.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
+        totalSpecies = 0
+        expStatementFile = "outputs/additional/exceptionalStatements.txt"
+        file = open(expStatementFile, 'w')
+        file.write("GROUP|STATEMENT_NUMBER|DETAILS|NODEINFO|EVIDENCE\n")
+        file.close()
+        evidence = ""
+        speciesMap={}
+        for index, statementGr in enumerate(root.iter(tag=ns_tag('statementGroup'))):
+            for statement_num, statement in enumerate(statementGr.findall(ns_tag('statement'))):
+                print "\n\n\n############################################"
+                print "GROUP" + str(index + 1) + " :: STATEMENT  " + str(statement_num + 1) + " \t\t\t**" + str(reactionIdentifier)
+                print "############################################"
+                reactionIdentifier += 1  # statement number
+
                 ##annotation for evidence statement: pubmedid, journal, evidence , species , cellLine
                 annoGroup = statement.find(ns_tag('annotationGroup'))
                 # get_node_info_recursive(annoGroup)
@@ -204,6 +206,7 @@ def convertXBEL(filepath):
                 evidence = annoGroup.find(ns_tag("evidence")).text if annoGroup is not None else evidence
                 citation = annoGroup.find(ns_tag("citation")) if annoGroup is not None else citation
                 referenceType = citation.get(ns_tag("type")) if annoGroup is not None else referenceType
+                referenceType=namespaceDict.get(referenceType) if namespaceDict.get(referenceType) is not None else referenceType
                 reference = citation.find(ns_tag("reference")).text if annoGroup is not None else reference
                 annoMap = get_annotation_details(annoGroup) if annoGroup is not None else annoMap
                 species = getAnnoElement(annoMap, "SPECIES")
@@ -215,7 +218,7 @@ def convertXBEL(filepath):
                 annoEntry = species + "\t" + disease + "\t" + cell + "\t" + tissue + "\t" + cellstructure + "\t" + cellline
                 keyList = annoMap.keys()
                 otherKeys = set(keyList) - set(['SPECIES', 'DISEASE', 'CELL', 'TISSUE', 'CELLSTRUCTURE', 'CELLLINE'])
-                print otherKeys
+                #print otherKeys
                 otherAnnotation = [each + ":" + annoMap[each] for each in otherKeys]
                 print "EVIDENCE: " + evidence
                 print "------RELATIONSHIP------\n" + relationship
@@ -293,7 +296,7 @@ def convertXBEL(filepath):
                         f = open("outputs/additional/toMapReactions.txt", "a")
                         f.write(relationship + "\n")
                         f.close()
-                reactionEntry = "r" + str(reactionIdentifier) + "\t" + relationship + "\t" + reactant + "\t" + modifier + "\t" + product + "\t" + modifierType + "\t" + species+"\t"+ namespaceDict[referenceType] + ":" + reference + "\n"
+                reactionEntry = "r" + str(reactionIdentifier) + "\t" + relationship + "\t" + reactant + "\t" + modifier + "\t" + product + "\t" + modifierType + "\t" + species+"\t"+ referenceType + ":" + reference + "\n"
                 print reactionEntry
                 rFile = open(reactionFile, "a")
                 rFile.write(reactionEntry)
@@ -301,12 +304,13 @@ def convertXBEL(filepath):
                 rFile.close()
                 # if reactionIdentifier==25:
                 #     exit()
-            except Exception as ex:
-                print " !!!EXCEPTION!!! : " + str(ex)
+    except Exception as ex:
+        print " !!!EXCEPTION!!! : " + str(ex.args)
 
-                exit()
+        exit()
 
 
 # Convert file
 # /home/alex/PhD/Bel2CellD/full_abstract3.xbel
-convertXBEL('/home/alex/PhD/Bel2CellD/small_corpus.xbel')
+#/home/alex/PhD/Bel2CellD/small_corpus.xbel
+convertXBEL('/home/alex/PhD/APP/Aetionomy_AD.xbel')