def run_porechop(minion_reads, output_directory, threads, logfile=None):
chopped_reads = os.path.join(output_directory, 'minION_chopped.fastq.gz')
cmd = 'porechop -i {minion_reads} -o {chopped_reads} -t {threads}'.format(minion_reads=minion_reads,
chopped_reads=chopped_reads,
threads=threads)
run_cmd(cmd, logfile=logfile)
return chopped_reads
def run_nanoplot(fastq_file, output_directory, threads):
if os.path.isfile(os.path.join(output_directory, 'NanoPlot-report.html')):
return
cmd = 'NanoPlot -t {threads} -o {output_directory} --fastq_rich {fastq_file}'.format(
threads=threads,
output_directory=output_directory,
fastq_file=fastq_file)
run_cmd(cmd)
def correct_illumina(forward_reads, reverse_reads, output_directory, threads, logfile=None):
forward_corrected = os.path.join(output_directory, os.path.split(forward_reads.replace('.fastq.gz', '_corrected.fastq.gz'))[1])
reverse_corrected = os.path.join(output_directory, os.path.split(reverse_reads.replace('.fastq.gz', '_corrected.fastq.gz'))[1])
cmd = 'tadpole.sh in={forward_reads} in2={reverse_reads} out={forward_corrected} out2={reverse_corrected} ' \
'mode=correct threads={threads}'.format(forward_reads=forward_reads,
reverse_reads=reverse_reads,
forward_corrected=forward_corrected,
reverse_corrected=reverse_corrected,
threads=threads)
run_cmd(cmd, logfile=logfile)
return forward_corrected, reverse_corrected
def trim_illumina(forward_reads, reverse_reads, output_directory, threads, logfile=None):
forward_trimmed = os.path.join(output_directory, os.path.split(forward_reads.replace('.fastq.gz', '_trimmed.fastq.gz'))[1])
reverse_trimmed = os.path.join(output_directory, os.path.split(reverse_reads.replace('.fastq.gz', '_trimmed.fastq.gz'))[1])
cmd = 'bbduk.sh in={forward_reads} in2={reverse_reads} out={forward_trimmed} out2={reverse_trimmed} ' \
'qtrim=w trimq=10 ref=adapters minlength=50 threads={threads}'.format(forward_reads=forward_reads,
reverse_reads=reverse_reads,
forward_trimmed=forward_trimmed,
reverse_trimmed=reverse_trimmed,
threads=threads)
run_cmd(cmd, logfile=logfile)
return forward_trimmed, reverse_trimmed
def run_unicycler(forward_reads, reverse_reads, long_reads, output_directory, threads, logfile=None, conservative=False):
if conservative:
runmode = "conservative"
else:
runmode ="normal"
cmd = 'unicycler -1 {forward_reads} -2 {reverse_reads} -l {long_reads} -o {output_directory} -t {threads} ' \
'--no_correct --min_fasta_length 1000 --keep 0 --mode {runmode}'.format(forward_reads=forward_reads,
reverse_reads=reverse_reads,
long_reads=long_reads,
output_directory=output_directory,
threads=threads, runmode=runmode)
run_cmd(cmd, logfile=logfile)
def subsample_via_filtlong(minion_reads, illumina_forward, illumina_reverse, output_directory, target_bases=250000000, logfile=None):
logging.info('Targeting {} bases for read subsampling...'.format(target_bases))
filtered_reads = os.path.join(output_directory, 'length_filtered_reads.fastq')
cmd = 'filtlong -t {target_bases} -1 {illumina_forward} -2 {illumina_reverse} {minion_reads} > {filtered_reads}'.format(target_bases=target_bases, illumina_forward=illumina_forward, illumina_reverse=illumina_reverse, minion_reads=minion_reads, filtered_reads=filtered_reads)
run_cmd(cmd, logfile=logfile)
return filtered_reads