Skip to content

fix-issue-101 feat: use BUSCO_DOWNLOAD_PATH env variable when available #102

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
nextgenusfs merged 1 commit into from
Oct 19, 2026
Merged

fix-issue-101 feat: use BUSCO_DOWNLOAD_PATH env variable when available #102

Show file tree
Hide file tree
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
3 changes: 2 additions & 1 deletion funannotate2/annotate.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -363,7 +363,8 @@ def annotate(args):
else:
# choose best busco species
busco_species = choose_best_busco_species(taxonomy)
# Ensure the BUSCO lineage is available under FUNANNOTATE2_DB,
# Ensure the BUSCO lineage is available under BUSCO_DOWNLOAD_PATH,
# falling back to FUNANNOTATE2_DB i BUSCO_DOWNLOAD_PATH is not set,
# downloading it if needed. In dockerized usage the lineage from a
# previous train/predict run is gone when annotate starts in a fresh
# container, so this guards against the cryptic "<path> is not a
Expand Down
3 changes: 3 additions & 0 deletions funannotate2/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,9 @@
os.path.dirname(env["AUGUSTUS_CONFIG"]), "scripts"
)

if "BUSCO_DOWNLOAD_PATH" in os.environ:
env["BUSCO_DOWNLOAD_PATH"] = os.environ["BUSCO_DOWNLOAD_PATH"]


augustus_species = {
"pea_aphid": {
Expand Down
22 changes: 14 additions & 8 deletions funannotate2/utilities.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -162,9 +162,10 @@ def get_odb_version(downloads_json_file):
def ensure_busco_lineage(species, logger):
"""
Ensure the BUSCO lineage `<species>_<odb_version>` is present under
FUNANNOTATE2_DB, downloading and extracting it from the URL in
downloads.json if missing. The check is a no-op when the directory
already exists, so callers can invoke this idempotently.
BUSCO_DOWNLOAD_PATH, falling back to FUNANNOTATE2_DB if not, downloading
and extracting it from the URL in downloads.json if missing. The check
is a no-op when the directory already exists, so callers can invoke this
idempotently.

Parameters:
- species (str): BUSCO lineage species name (e.g. "fungi", "aspergillus").
Expand All @@ -179,21 +180,26 @@ def ensure_busco_lineage(species, logger):
"""
downloads_json = os.path.join(os.path.dirname(__file__), "downloads_v2.json")
odb_version = get_odb_version(downloads_json)
busco_model_path = os.path.join(
env["FUNANNOTATE2_DB"], f"{species}_{odb_version}"
)

if "BUSCO_DOWNLOAD_PATH" in env:
busco_dir_path = env["BUSCO_DOWNLOAD_PATH"]
else:
busco_dir_path = env["FUNANNOTATE2_DB"]
busco_model_path = os.path.join(busco_dir_path,
f"{species}_{odb_version}"
)
if os.path.isdir(busco_model_path):
return busco_model_path
download_urls = load_json(downloads_json)
busco_url = download_urls["busco"][species][0]
busco_tgz = os.path.join(env["FUNANNOTATE2_DB"], os.path.basename(busco_url))
busco_tgz = os.path.join(busco_dir_path, os.path.basename(busco_url))
logger.info(f"Downloading {species}_{odb_version} model from {busco_url}")
download(busco_url, busco_tgz, wget=False)
if os.path.isfile(busco_tgz):
runSubprocess(
["tar", "-zxf", os.path.basename(busco_tgz)],
logger,
cwd=env["FUNANNOTATE2_DB"],
cwd=busco_dir_path,
)
if os.path.isdir(busco_model_path):
os.remove(busco_tgz)
Expand Down