tigmint-filter-paf

#!/usr/bin/env python3
"""
Given a PAF-formatted mapping file, output mapping extents BED file
"""
import argparse

def paf_to_molecule_extents(args: argparse.Namespace) -> None:
    "Read through the input PAF file, and output the mapping extents above the length threshold"
    with open(args.PAF, 'r') as fin:
        for line in fin:
            line = line.strip().split("\t")
            ctg_name, ctg_start, ctg_end = line[5], int(line[7]), int(line[8])
            read_name = line[0]
            num_mx = int(line[9])
            if ctg_end - ctg_start >= args.m:
                print(ctg_name, ctg_start, ctg_end, read_name, num_mx, sep="\t")

def main() -> None:
    "Filter input PAF file, output BED file"
    parser = argparse.ArgumentParser(description="Given a PAF-formatted mapping file, "
                                                 "output molecule extents BED")
    parser.add_argument("PAF", help="Input PAF file")
    parser.add_argument("-m", help="Minimum size of output extents (bp)", default=2000, type=int)
    parser.add_argument('--version', action='version', version='tigmint-filter-paf 1.2.9')

    args = parser.parse_args()

    args.PAF = "/dev/stdin" if args.PAF == "-" else args.PAF

    paf_to_molecule_extents(args)

if __name__ == "__main__":
    main()