comparison extract_aln_ends.py @ 14:570a7de9f151 draft

read from bam; fix header issue

13:258b6f9e19ab

("forward-reverse") direction.

By default output is written to stdout.

Input:
* sam file containing alignments (paired-end sequencing)

Output:
* bed6 file containing outer coordinates (sorted by read id)

Example usage:

parser = argparse.ArgumentParser(description=tool_description,
                                 epilog=epilog,
                                 formatter_class=DefaultsRawDescriptionHelpFormatter)
# positional arguments
parser.add_argument(
    "sam",
    help="Path to sam file containing alignments.")
# optional arguments
parser.add_argument(
    "-o", "--outfile",
    help="Write results to this file.")
# misc arguments

    help="Print lots of debugging information",
    action="store_true")
parser.add_argument(
    '--version',
    action='version',
    version='0.1.0')

args = parser.parse_args()

if args.debug:
    logging.basicConfig(level=logging.DEBUG, format="%(asctime)s - %(filename)s - %(levelname)s - %(message)s")
elif args.verbose:
    logging.basicConfig(level=logging.INFO, format="%(filename)s - %(levelname)s - %(message)s")
else:
    logging.basicConfig(format="%(filename)s - %(levelname)s - %(message)s")
logging.info("Parsed arguments:")
logging.info("  sam: '{}'".format(args.sam))
if args.outfile:
    logging.info("  outfile: enabled writing to file")
    logging.info("  outfile: '{}'".format(args.outfile))
logging.info("")

    fn_sorted = tmpdir + "/sorted.bam"
    fn_fixedmates = tmpdir + "/fixedmates.bam"

    # sort by id
    logging.debug("calling samtools sort")
    pysam.sort(args.sam, "-n", "-o{}".format(fn_sorted), "-T sortprefix")

    # fix mate information
    # also removes secondary and unmapped reads
    logging.debug("calling samtools fixmates")
    pysam.fixmate("-r", fn_sorted, fn_fixedmates)

14:570a7de9f151

("forward-reverse") direction.

By default output is written to stdout.

Input:
* alignments in SAM or BAM format (paired-end sequencing)

Output:
* bed6 file containing outer coordinates (sorted by read id)

Example usage:

parser = argparse.ArgumentParser(description=tool_description,
                                 epilog=epilog,
                                 formatter_class=DefaultsRawDescriptionHelpFormatter)
# positional arguments
parser.add_argument(
    "infile",
    help="Path to alignments in SAM or BAM format.")
# optional arguments
parser.add_argument(
    "-o", "--outfile",
    help="Write results to this file.")
# misc arguments

    help="Print lots of debugging information",
    action="store_true")
parser.add_argument(
    '--version',
    action='version',
    version='0.2.0')

args = parser.parse_args()

if args.debug:
    logging.basicConfig(level=logging.DEBUG, format="%(asctime)s - %(filename)s - %(levelname)s - %(message)s")
elif args.verbose:
    logging.basicConfig(level=logging.INFO, format="%(filename)s - %(levelname)s - %(message)s")
else:
    logging.basicConfig(format="%(filename)s - %(levelname)s - %(message)s")
logging.info("Parsed arguments:")
logging.info("  infile: '{}'".format(args.infile))
if args.outfile:
    logging.info("  outfile: enabled writing to file")
    logging.info("  outfile: '{}'".format(args.outfile))
logging.info("")

    fn_sorted = tmpdir + "/sorted.bam"
    fn_fixedmates = tmpdir + "/fixedmates.bam"

    # sort by id
    logging.debug("calling samtools sort")
    pysam.sort(args.infile, "-n", "-o{}".format(fn_sorted), "-T sortprefix")

    # fix mate information
    # also removes secondary and unmapped reads
    logging.debug("calling samtools fixmates")
    pysam.fixmate("-r", fn_sorted, fn_fixedmates)