Deep Learning Workshop

@@ -74,6 +74,11 @@ if __name__ == "__main__":
 
     list_rows = []
     i = 0
+    length = 0
+    length_total_exon = 0
+    length_total_utr = 0
+    total_exon = 0
+    total_utr = 0
     # Read HGA csv file
     with open(os.path.join(args.hgaPath, args.hgaFile), mode="r", encoding="utf-8") as csvfile:
         reader = csv.DictReader(csvfile)
@@ -91,22 +96,27 @@ if __name__ == "__main__":
             # start_codon
             # stop_codon
             # three_prime_utr
-
+            length = int(row['end']) - int(row['start']) + 1
             if row['feature'] == "exon":
                 label = row['feature']
+                length_total_exon += length
+                total_exon += 1
             elif row['feature'] in ["five_prime_utr", "three_prime_utr"]:
                 label = "utr"
+                length_total_utr += length
+                total_utr += 1
             else:
                 label = "other"
-            new_row = "{}\t{}\t{}\t{}\t{}\n".format(row['seqname'], row['start'], row['end'], sequence, label)
+            new_row = "{}\t{}\t{}\t{}\t{}\t{}\n".format(row['seqname'], row['start'], row['end'], length, sequence, label)
             list_rows.append(new_row)
             i += 1
             if (i % 100) == 0:
                 print("{} rows processed.".format(i))
             if i == 10000:
                 break
-
+    print("Length media exons {} and utr {}".format(length_total_exon/total_exon, length_total_utr/total_utr))
     with open(os.path.join(args.outputPath, args.outputFile), mode="w") as oFile:
-        oFile.write("seqname\tstart\tend\tsequence\tlabel\n")
+        oFile.write("seqname\tstart\tend\tlength\tsequence\tlabel\n")
         for elem in list_rows:
             oFile.write(elem)
+