Skip to content

Add tqdm progress bar for hmmsearch aggregation #279

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

Open
wwood wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Add tqdm progress bar for hmmsearch aggregation #279

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f4b5a46
Add progress bar for hmmsearch results
wwood Jan 8, 2026
5273853
Update hmmsearch progress tracking
wwood Jan 8, 2026
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: 14 additions & 4 deletions singlem/supplement.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -420,6 +420,10 @@ def run_hmmsearch_on_one_genome(lock, data, matched_transcripts_fna, working_dir
return (total_num_transcripts, failure_genomes, num_transcriptomes, num_found_transcripts)


def _run_hmmsearch_on_one_genome_star(args):
return run_hmmsearch_on_one_genome(*args)


def gather_hmmsearch_results(num_threads, working_directory, old_metapackage, new_genome_transcripts_and_proteins,
hmmsearch_evalue):
# Run hmmsearch using a concatenated set of HMMs from each graftm package in the metapackage
Expand Down Expand Up @@ -454,12 +458,18 @@ def gather_hmmsearch_results(num_threads, working_directory, old_metapackage, ne
# context, otherwise we get deadlock. See
# https://pola-rs.github.io/polars/user-guide/misc/multiprocessing/#example
with get_context('spawn').Pool(num_threads) as pool:
map_result = pool.starmap(
run_hmmsearch_on_one_genome,
[(lock, data, matched_transcripts_fna, working_directory, hmmsearch_evalue, concatenated_hmms) for data in new_genome_transcripts_and_proteins.items()],
map_result = pool.imap_unordered(
_run_hmmsearch_on_one_genome_star,
[(lock, data, matched_transcripts_fna, working_directory, hmmsearch_evalue, concatenated_hmms)
for data in new_genome_transcripts_and_proteins.items()],
chunksize=1)

for (num_transcripts, failure_genomes, num_transcriptomes, num_found_transcripts) in map_result:
for (num_transcripts, failure_genomes, num_transcriptomes, num_found_transcripts) in tqdm(
map_result,
total=len(new_genome_transcripts_and_proteins),
desc="Running hmmsearch",
unit="genome",
):
total_num_transcripts += num_transcripts
total_failure_genomes += failure_genomes
total_num_transcriptomes += num_transcriptomes
Expand Down