MD-editDistance-fromBam_1.py

import pysam
import re

def extractMDFromBam(bam):
	'''
	loop over a bam file and get the edit distance to the reference genome
 	mismatches are stored in the MD tag
	scale by aligned read length
	'''
	samfile = pysam.AlignmentFile(bam, "rb")
	return [(read.query_alignment_length - sum([int(item) for item in re.split('[ACTG^]', read.get_tag("MD")) if not item == '']))/read.query_alignment_length  for read in samfile.fetch()]