getDisagreementMD-NM-tagEditDistance.py

import sys
import re
import pysam


def extractDisagreement(bam):
    samfile = pysam.AlignmentFile(bam, "rb")
    for read in samfile.fetch():
        NMdef = read.get_tag("NM")/read.query_alignment_length
        MDdef = sum([len(item) for item in re.split('[0-9^]', read.get_tag("MD"))])/read.query_alignment_length
        if NMdef - MDdef > 0.2:
            print('\t'.join(
                    [
                    str(read.get_tag("NM")),
                    str(sum([len(item) for item in re.split('[0-9^]', read.get_tag("MD"))])),
                    read.get_tag("MD"),
                    read.cigarstring,
                    ])
                    )