Added system call to sort the results file and remove exact dupes.

svn path=/; revision=66

diff --git a/preecej/perl_singletons/reactome_chebi_mapping/reactome_chebi_mapping.pl b/preecej/perl_singletons/reactome_chebi_mapping/reactome_chebi_mapping.pl
index bb44688064b3b157a5583d338cfdd322a0b2e98b..46b3cf52e15aa186675ae7a614d4a8d8abe551f8 100755 (executable)
--- a/preecej/perl_singletons/reactome_chebi_mapping/reactome_chebi_mapping.pl
+++ b/preecej/perl_singletons/reactome_chebi_mapping/reactome_chebi_mapping.pl
@@ -38,9 +38,10 @@ use GO::Parser;
 
 # set paths to data files
 my $data_path = "/home/preecej/Documents/Projects/Reactome/";
-my $chebi_obo_file = "chebi_sample.obo";
-my $reactome_file = "RiceReferenceMolecules_sample.txt";
-my $mapped_output_file = "reactome_chebi_mapping.txt";
+my $chebi_obo_file = "chebi.obo";
+my $reactome_file = "RiceReferenceMolecules.txt";
+my $mapped_output_file = "reactome_chebi_mapping_complete.txt";
+my $sorted_output_file = "reactome_chebi_mapping_complete_sorted.txt";
 
 # options
 my $allow_obsolete_terms = 1;
@@ -317,6 +318,9 @@ sub create_mapfile
         print OUTPUT_FILE "$_\n" foreach @map_results;
         
         close OUTPUT_FILE;
+        
+        # sort on all cols (keep the header at the top), remove exact dupes
+        system "awk 'NR == 1; NR > 1 {print \$0 | \"sort\"}' $data_path$mapped_output_file | uniq > $data_path$sorted_output_file";        
     } else {
         print "\n\nSorry, there are no mapped results.\n\n";
     }