Skip to content
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

Jump to bottom

Use user provided thread count for masking #866

Closed
wants to merge 2 commits into from
Closed

Use user provided thread count for masking #866

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e63a2a7
Use user provided thread count
ChillarAnand Aug 2, 2024
82716fb
Add logs for each step
ChillarAnand Aug 3, 2024
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
12 changes: 9 additions & 3 deletions scripts/k2
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@ import tempfile
import threading
import urllib
import urllib.error
import datetime
from urllib.error import HTTPError, ContentTooShortError
import urllib.parse
import urllib.request
Expand Down Expand Up @@ -482,9 +483,8 @@ def spawn_masking_subprocess(output_file, protein=False):
argv = masking_binary + " -outfmt fasta | sed -e '/^>/!s/[a-z]/x/g'"
if masking_binary.find("k2mask") >= 0:
# k2mask can run multithreaded
argv = masking_binary + " -outfmt fasta -threads {} -r x".format(
multiprocessing.cpu_count() // 2
)
threads = int(os.environ.get("KRAKEN2_NUM_THREADS", multiprocessing.cpu_count()))
argv = masking_binary + " -outfmt fasta -threads {} -r x".format(threads)

p = subprocess.Popen(
argv, shell=True, stdin=subprocess.PIPE, stdout=output_file
Expand Down Expand Up @@ -1131,6 +1131,7 @@ def build_kraken2_db(args):
os.remove("accmap.tmp")
move("seqid2taxid.map.tmp", "seqid2taxid.map")
LOG.info("Created sequence ID to taxonomy ID map\n")
start = datetime.datetime.now()
estimate_capacity_binary = find_kraken2_binary("estimate_capacity")
argv = [estimate_capacity_binary, "-S", construct_seed_template(args)]
if args.protein:
Expand All @@ -1157,11 +1158,13 @@ def build_kraken2_db(args):
proc.stdin.write(data)
estimate = proc.communicate()[0].decode()
required_capacity = (int(estimate.strip()) + 8192) / args.load_factor
end = datetime.datetime.now()
LOG.info(
"Estimated hash table requirement: {:s}\n".format(
format_bytes(required_capacity * 4)
)
)
LOG.info("Time to estimate hash table requirement: {:s}\n".format(str(end - start)))
if args.max_db_size:
if args.max_db_size < required_capacity * 4:
args.max_db_size = int(args.max_db_size / 4)
Expand All @@ -1173,6 +1176,7 @@ def build_kraken2_db(args):
if os.path.isfile("hash.k2d"):
LOG.info("Hash table already present, skipping build\n")
else:
start = datetime.datetime.now()
LOG.info("Starting database build\n")
build_db_bin = find_kraken2_binary("build_db")
argv = [
Expand Down Expand Up @@ -1216,6 +1220,8 @@ def build_kraken2_db(args):
move("taxo.k2d.tmp", "taxo.k2d")
move("opts.k2d.tmp", "opts.k2d")
LOG.info("Finished building database\n")
end = datetime.datetime.now()
LOG.info("Time to build database: {:s}\n".format(str(end - start)))


# Parses RDP sequence data to create Kraken taxonomy
Expand Down