Merge pull request #3 from simpsonlab/add_cyto_fix_script

Add cyto fix script

README.md

@@ -66,6 +66,11 @@ There are two required files for running breakpoint analysis:
 * `metadata` which is a tab separated file containing `sample`, band for `region1` and band for `region2`
 * `cytobands` which contains the genomic regions and their corresponding cytogenetic bands
 
+The cytobands file that is downloaded from the UCSC site requires an
+additional column to work with the analysis pipeline.  The script
+`workflow/scripts/fix_cytoband_file.py` can be used to append the
+additional column.
+
 ### Run the workflow
 The basecaller uses `guppy` and a GPU to convert FAST5 files to FASTQ files.
 ```

workflow/scripts/fix_cytoband_file.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python
+
+"""
+Append a column to the UCSC cytoband file
+"""
+
+import os
+import sys
+import argparse
+import csv
+
+
+def init_args():
+    """
+    Initialize command line arguments
+    """
+    description = 'Append chromosome identifier column to UCSC cytoband file'
+    parser = argparse.ArgumentParser(description=description)
+    parser.add_argument('-f', '--file', required=True,
+        help='full path to UCSC cytoband file')
+    return parser.parse_args()
+
+
+def main():
+    """
+    Main program
+    """
+    args = init_args()
+    fieldnames = ['chrom', 'start', 'end', 'band', 'desc']
+    with open(args.file, 'r') as ifh:
+        reader = csv.DictReader(ifh, delimiter='\t', fieldnames=fieldnames)
+        for line in reader:
+            chr_cyto = ''.join(['chr', line['band']])
+            print('\t'.join([
+                line['chrom'],
+                line['start'],
+                line['end'],
+                line['band'],
+                line['desc'],
+                chr_cyto
+            ]))
+    ifh.close()
+
+
+if __name__ == '__main__':
+    main()
+
+
+#__END__