Skip to content

Change parallel processing for assemble_reads.py #31

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 7, 2022
Merged

Change parallel processing for assemble_reads.py #31

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 12 additions & 6 deletions secapr/assemble_reads.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,8 +61,14 @@ def add_arguments(parser):
default=1,
help='For parallel processing you can set the number of cores you want to run the assembly on.'
)
parser.add_argument(
'--instances',
type=int,
default=1,
help='How many parallel assemblies to run at a time. This will multiply the cores and max_memory arguments (for each SPAdes run). For example, max_memory=4, cores=2 and instances=4 will use 8 threads and 16 GB.'
)

def assembly_spades(sorted_fastq_files,n_library_numbers,output_folder,id_sample,kmer,cores,max_memory,args):
def assembly_spades(sorted_fastq_files,n_library_numbers,output_folder,id_sample,kmer,args):
print("De-novo assembly with spades of sample %s:" %id_sample)
command = [
"spades.py",
Expand Down Expand Up @@ -160,7 +166,7 @@ def process_subfolder(pool_args):
print(('#' * 50))
print(("Processing sample %s" % sample_id))
start = time.time()
assembly_spades(sorted_fastq_files, n_library_numbers, sample_output_folder, sample_id, kmer, 1, max_memory, args)
assembly_spades(sorted_fastq_files, n_library_numbers, sample_output_folder, sample_id, kmer, args)
contig_file = os.path.join(sample_output_folder, 'contigs.fasta')
new_contig_file = '%s/../../%s.fa' % (sample_output_folder, sample_id)
mv_contig = "cp %s %s" % (contig_file, new_contig_file)
Expand All @@ -177,11 +183,11 @@ def main(args):
out_dir = os.path.join(out_folder,'stats')
if not os.path.exists(out_dir):
os.makedirs(out_dir)
cores = args.cores
instances = args.instances
subfolder_list = [subfolder for subfolder, __, __ in os.walk(input_folder) if os.path.basename(subfolder) != os.path.basename(input_folder)]
if cores > 1:
print(("Running in parallel on %d cores" %cores))
pool = multiprocessing.Pool(cores)
if instances > 1:
print(("Running assemblies in parallel as %d instances" %instances))
pool = multiprocessing.Pool(instances)
pool_args = [[subfolder,args] for subfolder in subfolder_list]
contig_count_df_list = list(pool.map(partial(process_subfolder), pool_args))
pool.close()
Expand Down