Skip to content

SV plugin updates #70

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
nakib103 wants to merge 2 commits into
base: main
Choose a base branch
from
+29 −14
Open

SV plugin updates #70

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b0f5226
SV plugin updates
nakib103 Mar 4, 2026
0ff3a2d
Re-roder if-else logic
nakib103 Mar 5, 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
43 changes: 29 additions & 14 deletions nextflow/vcf_prepper/bin/generate_vep_config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,6 +70,9 @@
"Downstream",
"ClinPred",
]
SV_PLUGINS = [
"CADD"
]
Comment on lines +73 to +75
Copy link
Member

@mluypaert mluypaert Mar 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is CADD really the only plugin we want to run for Structural variants? Should all others be disabled (as this code does)?

Copy link
Contributor Author

@nakib103 nakib103 Mar 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the only other candidate is Phenotype, but we will have separate data store for it soon.

Copy link
Member

@mluypaert mluypaert Mar 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@nakib103 As the phenotype store is still in design, I'd say we should keep the current phenotype plugin enabled until we have access to the new data.

Copy link
Contributor Author

@nakib103 nakib103 Mar 6, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Phenotype plugin data (the GFF3s) has the phenotype for structural variants. But I don't think anyone ever tested/worked on the plugin to see if it works with that data (you might get lots of Pheno against short variants getting attached to the SVs).
But if you already have tested and have good hunch about it I can add the plugin.



def parse_args(args=None):
Expand Down Expand Up @@ -293,6 +296,7 @@ def get_plugin_args(
species: str,
assembly: str,
conservation_data_dir: str = CONSERVATION_DATA_DIR,
structural_variant: bool = False
) -> str:
"""Return plugin configuration line(s) for the requested plugin.

Expand All @@ -305,6 +309,7 @@ def get_plugin_args(
species (str): Species production name.
assembly (str): Assembly name.
conservation_data_dir (str): Directory containing conservation plugin data.
structural_variant (str): Structural variant or not.

Returns:
str|None: Plugin argument string for inclusion in VEP config, or None to skip plugin.
Expand All @@ -318,20 +323,25 @@ def get_plugin_args(
if version < 113:
plugin_data_dir = plugin_data_dir.replace(f"{version}", "113")

if species == "sus_scrofa":
snv = os.path.join(plugin_data_dir, f"ALL_pCADD-PHRED-scores.tsv.gz")
check_plugin_files(plugin, [snv])
if structural_variant:
sv = os.path.join(plugin_data_dir, f"CADD_prescored_variants.tsv.gz")
check_plugin_files(plugin, [sv])

return f"CADD,{snv}"
return f"CADD,{sv}"
else:
if species == "sus_scrofa":
snv = os.path.join(plugin_data_dir, f"ALL_pCADD-PHRED-scores.tsv.gz")
check_plugin_files(plugin, [snv])

snv = os.path.join(
plugin_data_dir, f"CADD_{assembly}_1.7_whole_genome_SNVs.tsv.gz"
)
indels = os.path.join(plugin_data_dir, f"CADD_{assembly}_1.7_InDels.tsv.gz")

check_plugin_files(plugin, [snv, indels])
return f"CADD,{snv}"
else:
snv = os.path.join(
plugin_data_dir, f"CADD_{assembly}_1.7_whole_genome_SNVs.tsv.gz"
)
indels = os.path.join(plugin_data_dir, f"CADD_{assembly}_1.7_InDels.tsv.gz")
check_plugin_files(plugin, [snv, indels])

return f"CADD,{snv},{indels}"
return f"CADD,{snv},{indels}"

if plugin == "REVEL":
data_file = f"/nfs/production/flicek/ensembl/variation/data/REVEL/2021-may/new_tabbed_revel_{assembly.lower()}.tsv.gz"
Expand Down Expand Up @@ -492,6 +502,7 @@ def get_plugins(
assembly: str,
repo_dir: str = REPO_DIR,
conservation_data_dir: str = CONSERVATION_DATA_DIR,
structural_variant: bool = False
) -> list:
"""Assemble plugin argument strings for the species and version.

Expand All @@ -501,17 +512,21 @@ def get_plugins(
assembly (str): Assembly name.
repo_dir (str): Repository directory.
conservation_data_dir (str): Conservation plugin data directory.
structural_variant (str): Structural variant or not.

Returns:
list: List of plugin argument strings to include in the VEP config.
"""
plugin_list = PLUGINS
if structural_variant:
plugin_list = SV_PLUGINS
plugins = []

for plugin in PLUGINS:
for plugin in plugin_list:
plugin_species = get_plugin_species(plugin, repo_dir)
if len(plugin_species) == 0 or species in plugin_species:
plugin_args = get_plugin_args(
plugin, version, species, assembly, conservation_data_dir
plugin, version, species, assembly, conservation_data_dir, structural_variant
)
if plugin_args is not None:
plugins.append(plugin_args)
Expand Down Expand Up @@ -619,7 +634,7 @@ def main(args=None):
else:
print(f"[WARNING] Invalid population config file - {population_data_file}")

plugins = get_plugins(species, version, assembly, repo_dir, conservation_data_dir)
plugins = get_plugins(species, version, assembly, repo_dir, conservation_data_dir, structural_variant)

# write the VEP config file
with open(vep_config, "w") as file:
Expand Down
Loading