Added function to Report sizes.

scripts/ReportSizes.py

@@ -13,24 +13,34 @@ from collections import OrderedDict
 def make_report(size_gistic, size_rubic_gains, size_rubic_losses, census_genes, known_genes, reps, sizes, ref_genome, report_file, plot_dir):
     """Make a report of the results produced using input files with different sample sizes."""
     list_stats = []
-    with open(report_file, 'w') as out:
-        dict_stats = {}
-        for i in range(len(size_rubic_gains)):      #loop through sizes
-            size_rep = size_rubic_gains[i].split("Size")[1].split("/gains")[0]
-            size, repetition = size_rep.split(".Rep")
-            for tool in 'GISTIC', 'RUBIC':
-                size_file = (size_rubic_gains[i], size_rubic_losses[i]) if tool == 'RUBIC' else size_gistic[i]
-                parsed_results = parse_regions(size_file, known_genes, census_genes, tool)
-                stats_results = get_stats(parsed_results, size)
-                for stat_list in stats_results[0], stats_results[1]:
-                    converted_stats = [tool] + stat_list[0:2]
-                    for stat in stat_list[2:5]:
-                        converted_stats.append(float(stat))
-                    for stat in stat_list[5:]:
-                        converted_stats.append(float(stat.split(" (")[0]))
-                    list_stats.append(converted_stats)
+    all_results = {}
+    for i in range(len(size_rubic_gains)):      #loop through sizes
+        size_rep = size_rubic_gains[i].split("Size")[1].split("/gains")[0]
+        size, repetition = size_rep.split(".Rep")
+        for tool in 'GISTIC', 'RUBIC':
+            size_file = (size_rubic_gains[i], size_rubic_losses[i]) if tool == 'RUBIC' else size_gistic[i]
+            parsed_results = parse_regions(size_file, known_genes, census_genes, tool)
+            if tool not in all_results.keys():
+                all_results[tool] = [parsed_results]
+            else:
+                all_results[tool] = all_results[tool] + [parsed_results]
+            stats_results = get_stats(parsed_results, size)
+            for stat_list in stats_results[0], stats_results[1]:
+                converted_stats = [tool] + stat_list[0:2]
+                for stat in stat_list[2:5]:
+                    converted_stats.append(float(stat))
+                for stat in stat_list[5:]:
+                    converted_stats.append(float(stat.split(" (")[0]))
+                list_stats.append(converted_stats)
+    overlap_genes(all_results, report_file)
     make_plots(list_stats, reps, sizes, plot_dir)
 
+def overlap_genes(all_results, report_file):
+    for tool in all_results.keys():
+        print(all_results)
+
+
+
 def make_plots(list_stats, reps, sizes, plot_dir):
     plot_y_axis = (['Number of recurrent regions', 'Average size of regions (Kb)', 'Total size (Mb)',
                    'Number of genes', 'Nr. regions with known genes', 'Nr. regions with census genes'])