Simple script to split PacBio BAM file into subread files.

split_subreads2dir.py

import os
import sys
import gzip

filetype="txt"

for line in sys.stdin:
    # {movieName}/{holeNumber}/{qStart}_{qEnd} according to https://pacbiofileformats.readthedocs.io/en/3.0/BAM.html
    (movieName,holeNumber,subread)=(line.split()[0].split('/'))
    directory = movieName+'/'+holeNumber[:3]
    if filetype == "gzip":
        outfile = directory+"/"+holeNumber+'.gz'
    else:
        outfile = directory+"/"+holeNumber+'.txt'
    try:
        if filetype == "gzip":
            f=gzip.open(outfile,mode='at', compresslevel=1)
        else:
            f=open(outfile,mode='at')
        f.write(line)
        f.close()
    except:
        os.makedirs(directory, exist_ok=True)
        if filetype == "gzip":
            f=gzip.open(outfile,mode='at', compresslevel=1)
        else:
            f=open(outfile,mode='at')
        f.write(line)
        f.close()