view tabular_to_fastq.py @ 3:68f57cc8fad0 draft

"planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tool_collections/galaxy_sequence_utils/tabular_to_fastq commit 31edb920789fbd080260f853bc856be72fa7cfa8"
author devteam
date Fri, 01 Nov 2019 13:27:30 -0400
parents b8cdc0507586
children 2dcfbbf9071a
line wrap: on
line source

# Dan Blankenberg
from __future__ import print_function

import sys


def main():
    input_filename = sys.argv[1]
    output_filename = sys.argv[2]
    identifier_col = int(sys.argv[3]) - 1
    sequence_col = int(sys.argv[4]) - 1
    quality_col = int(sys.argv[5]) - 1

    max_col = max(identifier_col, sequence_col, quality_col)
    num_reads = None
    skipped_lines = 0
    out = open(output_filename, 'w')
    for num_reads, line in enumerate(open(input_filename)):
        fields = line.rstrip('\n\r').split('\t')
        if len(fields) > max_col:
            out.write("@%s\n%s\n+\n%s\n" % (fields[identifier_col], fields[sequence_col], fields[quality_col]))
        else:
            skipped_lines += 1

    out.close()
    if num_reads is None:
        print("Input was empty.")
    else:
        print("%i tabular lines were written as FASTQ reads. Be sure to use the FASTQ Groomer tool on this output before further analysis." % (num_reads + 1 - skipped_lines))


if __name__ == "__main__":
    main()