comparison RepEnrich2.py @ 9:2b61c6407efb draft default tip

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/repenrich2 commit 961a14cd73dd8e40b2f30d5e4df136b98cd8f07a

8:567549a49eb2

def run_bowtie(args):
    '''
    write to files to save memory
    '''
    metagenome, fastqfile = args
    b_opt = "-k 1 -p 1 --quiet --no-hd --no-unal"
    command = shlex.split(f"bowtie2 {b_opt} -x {metagenome} {fastqfile}")
    bowtie_align = subprocess.run(command, check=True,
                                  capture_output=True, text=True).stdout
    bowtie_align = bowtie_align.rstrip('\r\n').split('\n')
    with open(f"{metagenome}.reads", "a+") as readfile:
        for line in bowtie_align:

            if read:
                readfile.write(f"{read}\n")


# multimapper parsing
args_list = [(metagenome, fastqfile_1) for metagenome in repeat_list]
if paired_end:
    args_list.extend([(metagenome, fastqfile_2) for
                     metagenome in repeat_list])
with ProcessPoolExecutor(max_workers=cpus) as executor:
    results = executor.map(run_bowtie, args_list)

# Aggregate results (avoiding race conditions)
metagenome_reads = defaultdict(list)  # metagenome: list of multimap reads

# Now we read .reads file to populate metagnomes_reads
for metagenome in repeat_list:
    with open(f"{metagenome}.reads") as readfile:
        for read in readfile:
            metagenome_reads[metagenome].append(read)
        # read are only once in list

9:2b61c6407efb

def run_bowtie(args):
    '''
    write to files to save memory
    '''
    metagenome = args
    b_opt = "-k 1 -p 2 --quiet --no-hd --no-unal"
    if paired_end is True:
        command = shlex.split(f"bowtie2 {b_opt} -x {metagenome}"
                              f" -1 {fastqfile_1} -2 {fastqfile_1}")
    else:
        command = shlex.split(f"bowtie2 {b_opt} -x {metagenome} {fastqfile_1}")
    bowtie_align = subprocess.run(command, check=True,
                                  capture_output=True, text=True).stdout
    bowtie_align = bowtie_align.rstrip('\r\n').split('\n')
    with open(f"{metagenome}.reads", "a+") as readfile:
        for line in bowtie_align:

            if read:
                readfile.write(f"{read}\n")


# multimapper parsing
args_list = [metagenome for metagenome in repeat_list]
with ProcessPoolExecutor(max_workers=cpus) as executor:
    results = executor.map(run_bowtie, args_list)

# Aggregate results (avoiding race conditions)
metagenome_reads = defaultdict(list)  # metagenome: list of multimap reads

# Now we read .reads files to populate metagnomes_reads
for metagenome in repeat_list:
    with open(f"{metagenome}.reads") as readfile:
        for read in readfile:
            metagenome_reads[metagenome].append(read)
        # read are only once in list