comparison FilterUncorrectabledPEfastq.py @ 1:6703b98884a2 draft default tip

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rcorrector commit 65ada0f9589f3ffebad1db6636ccb50d58082606"

0:9a0b65ad3c84

read pairs containing at least one corrected read.
Currently, this script only handles paired-end data, and handle either unzipped
or gzipped files on the fly, so long as the gzipped files end with 'gz'.
"""

# import sys
import argparse
import gzip
from itertools import izip_longest
# izip
from os.path import basename


def get_input_streams(r1file, r2file):
    if r1file[-2:] == 'gz':

def grouper(iterable, n, fillvalue=None):
    "Collect data into fixed-length chunks or blocks"
    # grouper('ABCDEFG', 3, 'x') --> ABC DEF Gxx
    args = [iter(iterable)] * n
    return izip_longest(fillvalue=fillvalue, * args)


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="options for filtering and logging rCorrector fastq outputs")
    parser.add_argument('-1', '--left_reads', dest='leftreads', type=str, help='R1 fastq file')

        R2 = grouper(f2, 4)
        counter = 0
        for entry in R1:
            counter += 1
            if counter % 100000 == 0:
                print "%s reads processed" % counter
            head1, seq1, placeholder1, qual1 = [i.strip() for i in entry]
            head2, seq2, placeholder2, qual2 = [j.strip() for j in R2.next()]
            if 'unfixable' in head1 or 'unfixable' in head2:
                unfix_count += 1
            else:
                if 'cor' in head1:
                    r1_cor_count += 1

1:6703b98884a2

read pairs containing at least one corrected read.
Currently, this script only handles paired-end data, and handle either unzipped
or gzipped files on the fly, so long as the gzipped files end with 'gz'.
"""

import argparse
import gzip
from itertools import zip_longest
from os.path import basename


def get_input_streams(r1file, r2file):
    if r1file[-2:] == 'gz':

def grouper(iterable, n, fillvalue=None):
    "Collect data into fixed-length chunks or blocks"
    # grouper('ABCDEFG', 3, 'x') --> ABC DEF Gxx
    args = [iter(iterable)] * n
    return zip_longest(fillvalue=fillvalue, * args)


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="options for filtering and logging rCorrector fastq outputs")
    parser.add_argument('-1', '--left_reads', dest='leftreads', type=str, help='R1 fastq file')

        R2 = grouper(f2, 4)
        counter = 0
        for entry in R1:
            counter += 1
            if counter % 100000 == 0:
                print("%s reads processed" % counter)
            head1, seq1, placeholder1, qual1 = [i.strip() for i in entry]
            head2, seq2, placeholder2, qual2 = [j.strip() for j in next(R2)]
            if 'unfixable' in head1 or 'unfixable' in head2:
                unfix_count += 1
            else:
                if 'cor' in head1:
                    r1_cor_count += 1