Deep Learning Workshop

@@ -80,9 +80,22 @@ if __name__ == "__main__":
         for row in reader:
             # print(row)
             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']))
-            if row['feature'] == args.feature:
+            # Features in HGA:
+            # exon
+            # feature
+            # five_prime_utr
+            # gene
+            # Selenocysteine
+            # start_codon
+            # stop_codon
+            # three_prime_utr
+
+            if row['feature'] == "exon":
                 label = row['feature']
+            elif row['feature'] in ["five_prime_utr", "three_prime_utr"]:
+                label = "utr"
             else:
                 label = "other"
             new_row = "{}\t{}\t{}\t{}\t{}\n".format(row['seqname'], row['start'], row['end'], sequence, label)
@@ -90,6 +103,8 @@ if __name__ == "__main__":
             i += 1
             if (i % 100) == 0:
                 print("{} rows processed.".format(i))
+            if i == 10000:
+                break
 
     with open(os.path.join(args.outputPath, args.outputFile), mode="w") as oFile:
         oFile.write("seqname\tstart\tend\tsequence\tlabel\n")