modify bug fix caused by recurrent mutations

friend1ws · Aug 1, 2016 · 6fafaab · 6fafaab
1 parent 4e7938e
commit 6fafaab
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 5 deletions.
diff --git a/lib/genomon_splicing_mutation/run.py b/lib/genomon_splicing_mutation/run.py
@@ -15,7 +15,6 @@ def main(args):
     utils.merge_mut(args.sample_list_file, args.output_prefix + ".mut_merged.txt")
 
     subprocess.call(["junc_utils", "annotate", args.output_prefix + ".SJ_merged.txt", args.output_prefix + ".SJ_merged.annot.txt", args.resource_dir])
-    """
 
     subprocess.call(["junc_utils", "associate", args.output_prefix + ".mut_merged.txt", args.output_prefix + ".SJ_merged.annot.txt",
                      args.output_prefix, args.resource_dir, "--reference_genome", args.reference_genome, "-f", "anno"])
@@ -27,7 +26,8 @@ def main(args):
                                 args.output_prefix + ".splicing_mutation.proc.count_summary.txt",
                                 args.output_prefix + ".splicing_mutation.proc.mut_info.txt", 
                                 args.output_prefix + ".splicing_mutation.proc.SJ_info.txt")
-
+    
+    """
     # true combination    
     print >> sys.stderr, "evaluating true combinations"
 
@@ -37,7 +37,6 @@ def main(args):
     utils.check_significance(args.output_prefix + ".splicing_mutation.proc.count_summary.pruned.txt",
                              args.output_prefix + ".splicing_mutation.proc.count_summary.BIC.txt")
 
-
     utils.summarize_result(args.output_prefix + ".splicing_mutation.proc.count_summary.BIC.txt",
                            args.output_prefix + ".genomon_splicing_mutation.result.txt",
                            args.sample_list_file,

diff --git a/lib/genomon_splicing_mutation/utils.py b/lib/genomon_splicing_mutation/utils.py
@@ -664,6 +664,7 @@ def summarize_result(input_file, output_file, sample_list_file, mut_info_file, S
 
             gene = F[0]
             mutation_states = F[1].split(';')
+            splicing_count_vector = F[2].split(';')
             link_vector = F[3].split(';')
             BIC_min = F[4]
             BIC0 = F[5]
@@ -679,11 +680,13 @@ def summarize_result(input_file, output_file, sample_list_file, mut_info_file, S
 
             for active_link in active_link_vector:
                 mut_id, SJ_id = active_link.split(',')
-
+                current_splicing_counts = splicing_count_vector[int(SJ_id) - 1].split(',')                
+
                 # get sample names
                 sample_names = []
                 for sample_id in mut_id2sample_id[mut_id].split(','):            
-                    sample_names.append(id2sample[sample_id])
+                    if int(current_splicing_counts[int(sample_id) - 1]) > 0:
+                        sample_names.append(id2sample[sample_id])
 
                 # get mutation info
                 mut_info = mut_id2mut_info[gene + '\t' + mut_id]