added projection prefix option

svn path=/; revision=562

diff --git a/Personnel/preecej/python_singletons/incomparanoid.py b/Personnel/preecej/python_singletons/incomparanoid.py
index 31465fa568b84324950ea2b9ec259f32cae6b957..a2988049b6e4c2d0a91bc1523b682bcba1d302bf 100755 (executable)
--- a/Personnel/preecej/python_singletons/incomparanoid.py
+++ b/Personnel/preecej/python_singletons/incomparanoid.py
@@ -71,7 +71,7 @@ def create_dict_uniprot_map(uniprot_substitution_path) :
     return dict_uniprot_map
 
 #----------------------------------------------------------------------------------------------------------------------
-def create_inp_map(inparanoid_input_path, dict_uniprot_map) :
+def create_inp_map(inparanoid_input_path, dict_uniprot_map, projection_prefix) :
 #----------------------------------------------------------------------------------------------------------------------
     """
     open the inparanoid file (which is already loci-filtered for curated reference set) and generate a 2-col mapping of PRJ to LOC loci
@@ -90,7 +90,7 @@ def create_inp_map(inparanoid_input_path, dict_uniprot_map) :
         # swap loc for uniprot, if specified
         if dict_uniprot_map :
             os_locus = dict_uniprot_map[os_locus]
-        prj_locus = cols[1].rsplit("_",1)[0].rsplit(".",1)[0] # remove any isoform suffixes (i.e. '.#', '_T0#')
+            prj_locus = (projection_prefix if projection_prefix else "") + cols[1].rsplit("_",1)[0].rsplit(".",1)[0] # remove any isoform suffixes (i.e. '.#', '_T0#')
         if os_locus in dict_inp_map :
             dict_inp_map[os_locus].add(prj_locus)
         else :
@@ -108,7 +108,7 @@ def create_inp_map(inparanoid_input_path, dict_uniprot_map) :
 
 
 #----------------------------------------------------------------------------------------------------------------------
-def create_ens_map(filtering_loci_path, ensembl_input_path, rap_map_path, recip_id, dict_uniprot_map) :
+def create_ens_map(filtering_loci_path, ensembl_input_path, rap_map_path, recip_id, dict_uniprot_map, projection_prefix) :
 #----------------------------------------------------------------------------------------------------------------------
     """
     open the ensemble plants and rap::irgsp mapping files and generate a hash mapping of reference to projected loci where 
@@ -161,9 +161,9 @@ def create_ens_map(filtering_loci_path, ensembl_input_path, rap_map_path, recip_
                     # reciprocal identity is >= recip_id%, high confidence
                     if int(cols[2]) >= recip_id and int(cols[3]) >= recip_id and int(cols[4]) == 1 :
                         if os_locus in dict_ens_map :
-                            dict_ens_map[os_locus].add(cols[1])
+                            dict_ens_map[os_locus].add((projection_prefix if projection_prefix + ":" else "") + cols[1])
                         else :
-                            dict_ens_map[os_locus] = set([cols[1]])
+                            dict_ens_map[os_locus] = set([(projection_prefix if projection_prefix else "") + cols[1]])
     ENS.close()
 
     for k, v in dict_ens_map.iteritems() :
@@ -291,6 +291,7 @@ parser.add_argument('-u', '--uniprot_substitution', help='substitute UniProt for
 # TODO: add an "inparanoid super-cluster vs. conventional input" flag
 
 # output settings
+parser.add_argument('-p', '--projection_prefix', help='add a platform-specific prefix to the projectied protein identifiers', default='')
 parser.add_argument('-c', '--comparison_file_path', help='output file containing statistical comparisons')
 parser.add_argument('-E', '--ensembl_output_path', help='output file containing flat (1-to-many) ensemble ortho pairs')
 parser.add_argument('-I', '--inparanoid_output_path', help='output file containing flat (1-to-many) inparanoid ortho pairs')
@@ -303,8 +304,8 @@ if args.uniprot_substitution :
     dict_uniprot_map = create_dict_uniprot_map(args.uniprot_substitution)
 
 # create projection maps
-dict_inp_map = create_inp_map(args.inparanoid_input_path, dict_uniprot_map)
-dict_ens_map = create_ens_map(args.filtering_loci_path, args.ensembl_input_path, args.rap_map_path, args.reciprocal_id, dict_uniprot_map)
+dict_inp_map = create_inp_map(args.inparanoid_input_path, dict_uniprot_map, args.projection_prefix)
+dict_ens_map = create_ens_map(args.filtering_loci_path, args.ensembl_input_path, args.rap_map_path, args.reciprocal_id, dict_uniprot_map, args.projection_prefix)
 
 # generate stats and output them
 compare_maps(dict_ens_map, dict_inp_map, args.comparison_file_path, args.ensembl_output_path, args.inparanoid_output_path)