added ensembl confidence flag

svn path=/; revision=568

diff --git a/Personnel/preecej/python_singletons/incomparanoid.py b/Personnel/preecej/python_singletons/incomparanoid.py
index 256b40d7b0f3f2a5efd2922c3f2f4edd07992f1d..7841bd34b96522b04779b1e357aadcf2c225a530 100755 (executable)
--- a/Personnel/preecej/python_singletons/incomparanoid.py
+++ b/Personnel/preecej/python_singletons/incomparanoid.py
@@ -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 = 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, is_confident) :
 #----------------------------------------------------------------------------------------------------------------------
     """
     open the ensemble plants and rap::irgsp mapping files and generate a hash mapping of reference to projected loci where 
@@ -158,8 +158,8 @@ def create_ens_map(filtering_loci_path, ensembl_input_path, rap_map_path, recip_
                     # swap loc for uniprot, if specified
                     if dict_uniprot_map :
                         os_locus = dict_uniprot_map[os_locus]
-                    # reciprocal identity is >= recip_id%, high confidence
-                    if int(cols[2]) >= recip_id and int(cols[3]) >= recip_id and int(cols[4]) == 1 :
+                    # reciprocal identity is >= recip_id%, optional high confidence
+                    if int(cols[2]) >= recip_id and int(cols[3]) >= recip_id and int(cols[4]) >= is_confident :
                         if os_locus in dict_ens_map :
                             dict_ens_map[os_locus].add(cols[1])
                         else :
@@ -307,6 +307,7 @@ parser.add_argument('-e', '--ensembl_input_path', help='ensembl compara input fi
 parser.add_argument('-i', '--inparanoid_input_path', help='inparanoid supercluster input file')
 parser.add_argument('-m', '--rap_map_path', help='MSU-RAP mapping file')
 parser.add_argument('-r', '--reciprocal_id', type=int, help='reciprocal identity percentage')
+parser.add_argument('-C', '--confidence_high', help='only use ensembl projections marked as high-confidence', action='store_true')
 parser.add_argument('-u', '--uniprot_substitution', help='file path to UniProt substitution data for reference loci')
 # TODO: add an "inparanoid super-cluster vs. conventional input" flag
 
@@ -328,7 +329,7 @@ if 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_ens_map = create_ens_map(args.filtering_loci_path, args.ensembl_input_path, args.rap_map_path, args.reciprocal_id, dict_uniprot_map, 1 if args.confidence_high else 0)
 
 # 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)