wip

svn path=/; revision=532

diff --git a/Personnel/preecej/python_singletons/map_os_2_at.py b/Personnel/preecej/python_singletons/map_os_2_at.py
index c0e3d8ff68766aeed07616d325b44017affe4169..783c785b17e15f2d54b938326c6a11c255bbae35 100755 (executable)
--- a/Personnel/preecej/python_singletons/map_os_2_at.py
+++ b/Personnel/preecej/python_singletons/map_os_2_at.py
@@ -1,29 +1,34 @@
 #!/bin/python
 
-# open the ensemble plants and rap::irgsp mapping files and generate a 2-col mapping of AT to LOC loci
+# open the ensemble plants and rap::irgsp mapping files and generate a 2-col mapping of AT to LOC loci where reciprocal identity is >= 50% and confidence is high 
 
 path = "/home/preecej/Documents/projects/plant_reactome/plant_reactome_site/projection/rice_to_arabidopsis/"
 
 dict_ens_ids = {}
 
-ENS = open(path + "ensemble_plants_40_ath_to_rice_IRGSP.tab")
+ENS = open(path + "ensembl_plants_40_os_2_at_uniq.tab")
 ENS.readline();
 for line in ENS :
-    words = line.rstrip().split()
-    dict_ens_ids[words[2]] = words[0]
+    cols = line.rstrip().split()
+    if len(cols) == 5 :
+        if int(cols[2]) >= 50 and int(cols[3]) >= 50 and int(cols[4]) == 1 :  # reciprocal identity is >= 50%, high confidence
+            dict_ens_ids[cols[0]] = cols[1]
 ENS.close()
 
-OS_2_AT_MAP = open(path + "ensembl_ortho_os_2_at.tab",'w')
+for k, v in dict_ens_ids.iteritems() :
+    print k, v 
 
-RAP_IRGSP = open(path + "loc_rap_mappings.txt")
-RAP_IRGSP.readline();
-for line in RAP_IRGSP:
-    if line.strip() != "" :
-        words = line.rstrip().split()
-        rap_id = words[1].upper()
-        if rap_id in dict_ens_ids and rap_id != "NONE" :
-            #print dict_ens_ids[rap_id] + "\t" + words[0] 
-            OS_2_AT_MAP.write(words[0] + "\t" + dict_ens_ids[rap_id] + "\n") 
-RAP_IRGSP.close()
-
-OS_2_AT_MAP.close()
+# OS_2_AT_MAP = open(path + "ensembl_ortho_os_2_at.tab",'w')
+# 
+# RAP_IRGSP = open(path + "loc_rap_mappings.txt")
+# RAP_IRGSP.readline();
+# for line in RAP_IRGSP:
+    # if line.strip() != "" :
+        # cols = line.rstrip().split()
+        # rap_id = cols[1].upper()
+        # if rap_id in dict_ens_ids and rap_id != "NONE" :
+            # #print dict_ens_ids[rap_id] + "\t" + cols[0] 
+            # OS_2_AT_MAP.write(cols[0] + "\t" + dict_ens_ids[rap_id] + "\n")
+# RAP_IRGSP.close()
+# 
+# OS_2_AT_MAP.close()