Skip to content

Commit

Permalink
ingest: Merge Nextclade metadata with augur merge
Browse files Browse the repository at this point in the history
  • Loading branch information
joverlee521 committed Oct 19, 2024
1 parent 1234479 commit 54ca356
Showing 1 changed file with 26 additions and 14 deletions.
40 changes: 26 additions & 14 deletions ingest/rules/nextclade.smk
Original file line number Diff line number Diff line change
Expand Up @@ -54,14 +54,12 @@ if isinstance(config["nextclade"]["field_map"], str):
)


rule join_metadata_clades:
rule nextclade_metadata:
input:
nextclade="results/nextclade.tsv",
metadata="data/subset_metadata.tsv",
output:
metadata="results/metadata.tsv",
nextclade_metadata=temp("results/nextclade_metadata.tsv"),
params:
id_field=config["curate"]["id_field"],
nextclade_id_field=config["nextclade"]["id_field"],
nextclade_field_map=[
f"{old}={new}" for old, new in config["nextclade"]["field_map"].items()
Expand All @@ -74,14 +72,28 @@ rule join_metadata_clades:
--metadata - \
--id-column {params.nextclade_id_field:q} \
--field-map {params.nextclade_field_map:q} \
--output-metadata - \
| tsv-join -H \
--filter-file - \
--key-fields {params.nextclade_id_field} \
--data-fields {params.id_field} \
--append-fields '*' \
--write-all ? \
{input.metadata} \
| tsv-select -H --exclude {params.nextclade_id_field} \
> {output.metadata}
--output-metadata {output.nextclade_metadata:q}
"""


rule join_metadata_and_nextclade:
input:
metadata="data/subset_metadata.tsv",
nextclade_metadata="results/nextclade_metadata.tsv",
output:
metadata="results/metadata.tsv",
params:
metadata_id_field=config["curate"]["id_field"],
nextclade_id_field=config["nextclade"]["id_field"],
shell:
r"""
augur merge \
--metadata \
metadata={input.metadata:q} \
nextclade={input.nextclade_metadata:q} \
--metadata-id-columns \
metadata={params.metadata_id_field:q} \
nextclade={params.nextclade_id_field:q} \
--output-metadata {output.metadata:q} \
--no-source-columns
"""

0 comments on commit 54ca356

Please sign in to comment.