Skip to content

Added synthetic data download #21

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
chmao1 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Added synthetic data download #21

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
32 changes: 31 additions & 1 deletion variantiq-benchmark/src/build_benchmark_data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@
import tarfile

vcf_download_url="https://nssac.bii.virginia.edu/~dm8qs/variantiq_data"
synthetic_data_download_url="https://nssac.bii.virginia.edu/~cm4su/variantiq_data"
FASTQDUMP=["scif","run","fastq-dump"]

build_benchmark_data=App()
Expand Down Expand Up @@ -56,6 +57,35 @@ def default_action(
before re-downloading them
"""
print(f"Building Benchmark Data: {dataset}")

# ----------------------------------------------------------------------
# SPECIAL CASE: variantiq_synthetic
# ----------------------------------------------------------------------
if dataset == "variantiq-synthetic":
print("Special dataset detected: variantiq-synthetic")

archive_name = "variantiq-synthetic.bz2"
download_url = f"{synthetic_data_download_url}/{archive_name}"
target_file = os.path.join(output_directory, archive_name)

# Download only if not already expanded
if not os.path.exists(target_file) and not os.path.exists(f"{target_file}.expanded"):
print(f"Downloading: {download_url}")
download_url_to_file(download_url, target_file, True)

print("Extracting dataset...")
with tarfile.open(target_file, "r:bz2") as tar:
tar.extractall(path=output_directory)

# Mark as expanded
with open(f"{target_file}.expanded", "w") as fp:
pass

print(f"Removing {target_file}")
os.remove(target_file)

print(f"Dataset ready in: {output_directory}")
return

try:
os.mkdir( output_directory, 0o755 )
Expand Down Expand Up @@ -337,4 +367,4 @@ def process_samples(sample_file,data_def_folder,pipeline_inputs_only,comparison_
populate_sample_folder(row["sample_name"],row['read_files'],row['reference_genome'],row['truth_genome'],row,pipeline_inputs_only,comparison_vcf_only,output_directory,data_def_folder,data_def,dataset)


build_benchmark_data()
build_benchmark_data()
Loading