for Philip

parse_extra_col.py

#!/usr/bin/python_

import sys,os


def main():
    basedir = "/cluster/work/grlab/projects/projects2018-germlinesqtl/PM_transQTL_analysis/ensembl-vep"
    filename = "mergedQTL_v3_VEP_output.vep.txt"
    fullpath = os.path.join(basedir, filename)

    full_delimiter = "\t"
    extra_col_delimiter = ";"

    with open(fullpath, 'r') as file:
        for line in file.readlines():
            line = line.strip()
            parts = line.split(full_delimiter)
            if line[0] == "#":
                # header line
                extra_col = parts.index("Extra")
            else:
                # body lines
                val = parts[extra_col]
                extra_col_parts = val.split(extra_col_delimiter)
                new_col = parts[:extra_col] + parts[extra_col+1:] + extra_col_parts
                print("\t".join(new_col))


if __name__ == "__main__":
    main()