Deep Learning Workshop

@@ -86,35 +86,37 @@ if __name__ == "__main__":
         for row in reader:
         for row in reader:
             # print(row)
             # print(row)
             filename = os.path.join(args.fastaPath, "Homo_sapiens.GRCh38.dna.chromosome.{}.fa".format(row['seqname']))
             filename = os.path.join(args.fastaPath, "Homo_sapiens.GRCh38.dna.chromosome.{}.fa".format(row['seqname']))
-            # We use only
-            sequence = get_sequence(filename, int(row['start']), int(row['end']))
-            # Features in HGA:
-            # exon
-            # feature
-            # five_prime_utr
-            # gene
-            # Selenocysteine
-            # 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{}\t{}\n".format(row['seqname'], row['start'], row['end'], length, sequence, label)
-            list_rows.append(new_row)
+            if row['feature'] in ["exon", "five_prime_utr", "three_prime_utr"]:
+                # We use only exon, five_prime_utr, and three_prime_utr
+                sequence = get_sequence(filename, int(row['start']), int(row['end']))
+                # Features in HGA:
+                # exon
+                # feature
+                # five_prime_utr
+                # gene
+                # Selenocysteine
+                # 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{}\t{}\n".format(row['seqname'], row['start'], row['end'], length, sequence, label)
+                list_rows.append(new_row)
             i += 1
             i += 1
             if (i % 100) == 0:
             if (i % 100) == 0:
                 print("{} rows processed.".format(i))
                 print("{} rows processed.".format(i))
             if i == 10000:
             if i == 10000:
                 break
                 break
+    print("Count exons {} and utr {}".format(total_exon, total_utr))
     print("Length media exons {} and utr {}".format(length_total_exon/total_exon, length_total_utr/total_utr))
     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:
     with open(os.path.join(args.outputPath, args.outputFile), mode="w") as oFile:
         oFile.write("seqname\tstart\tend\tlength\tsequence\tlabel\n")
         oFile.write("seqname\tstart\tend\tlength\tsequence\tlabel\n")