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

Remove automatic Nextclade dataset updates and improve provenance tracking #38

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Remove automatic Nextclade dataset updates and improve provenance tracking #38

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4688d90
updates to clade calling
jpalmer37 Jul 30, 2024
c48a430
minor provenance formatting updates
jpalmer37 Jul 30, 2024
587d2d6
make indentation consistent
jpalmer37 Jul 30, 2024
ca81f6c
minor edits
jpalmer37 Jul 30, 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
37 changes: 22 additions & 15 deletions modules/clade_calling.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,26 +18,27 @@ process clade_calling {

script:
"""
printf -- "process_name: nextclade\\n" >> ${sample_id}_clade_calling_provenance.yml
printf -- "tools:\\n" >> ${sample_id}_clade_calling_provenance.yml
printf -- " - tool_name: nextclade\\n" >> ${sample_id}_clade_calling_provenance.yml
printf -- " tool_version: \$(nextclade --version 2>&1 | cut -d ' ' -f 2)\\n" >> ${sample_id}_clade_calling_provenance.yml
printf -- " subcommand: run\\n" >> ${sample_id}_clade_calling_provenance.yml
printf -- "- process_name: nextclade\\n" >> ${sample_id}_clade_calling_provenance.yml
printf -- " tools:\\n" >> ${sample_id}_clade_calling_provenance.yml
printf -- " - tool_name: nextclade\\n" >> ${sample_id}_clade_calling_provenance.yml
printf -- " tool_version: \$(nextclade --version 2>&1 | cut -d ' ' -f 2)\\n" >> ${sample_id}_clade_calling_provenance.yml
printf -- " subcommand: run\\n" >> ${sample_id}_clade_calling_provenance.yml


if [ `grep "H1" ${ha_consensus_seq}` ]; then
if [ ${params.h1_dataset} == "NO_FILE" ]; then
dataset="flu_h1n1pdm_ha"
nextclade dataset get --name \$dataset --output-dir \$dataset
echo "WARNING: H1 subtype detected in the HA consensus file, but no H1 dataset provided. Please provide an H1 nextclade dataset with the --h1_dataset flag."
exit 10
else
dataset=${params.h1_dataset}
fi
dataset=${params.h1_dataset}
fi
elif [ `grep "H3" ${ha_consensus_seq}` ]; then
if [ ${params.h3_dataset} == "NO_FILE" ]; then
dataset="flu_h3n2_ha"
nextclade dataset get --name \$dataset --output-dir \$dataset
echo "WARNING: H3 subtype detected in the HA consensus file, but no H3 dataset provided. Please provide an H3 nextclade dataset with the --h3_dataset flag."
exit 10
else
dataset=${params.h3_dataset}
fi
dataset=${params.h3_dataset}
fi
elif [ `grep "H5" ${ha_consensus_seq}` ]; then
if [ ${params.h5_dataset} == "NO_FILE" ]; then
echo "WARNING: H5 subtype detected in the HA consensus file, but no H5 dataset provided. Please provide an H5 nextclade dataset with the --h5_dataset flag."
Expand All @@ -46,12 +47,18 @@ process clade_calling {
dataset=${params.h5_dataset}
fi
else
echo "WARNING: None of H1, H3, or H5 were detected in the HA consensus file. No dataset available. Exiting."
echo "WARNING: None of H1, H3, or H5 were detected in the HA consensus file. Exiting."
exit 10
fi

printf -- " databases:\\n" >> ${sample_id}_clade_calling_provenance.yml
printf -- " - database_name: \$(grep 'dbname' \${dataset}/metadata.json | cut -d'\"' -f4) \\n" >> ${sample_id}_clade_calling_provenance.yml
printf -- " database_path: \${dataset} \\n" >> ${sample_id}_clade_calling_provenance.yml
printf -- " database_sha256: \$(sha256sum \${dataset}/tree.json | cut -d' ' -f1) \\n" >> ${sample_id}_clade_calling_provenance.yml


nextclade run \
--input-dataset \$dataset \
--input-dataset \$dataset \
--output-fasta=${sample_id}_nextclade.aligned.fasta.gz \
--output-json=${sample_id}_nextclade.json \
--output-ndjson=${sample_id}_nextclade.ndjson \
Expand Down