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

ingest: Remove use of ncov-ingest geolocation rules #79

Merged
merged 1 commit into from
Mar 4, 2025
Merged

ingest: Remove use of ncov-ingest geolocation rules #79

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
4 changes: 0 additions & 4 deletions ingest/defaults/config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,10 +34,6 @@ ncbi_datasets_fields:

# Config parameters related to the curate pipeline
curate:
# URL pointed to public generalized geolocation rules
# For the Nextstrain team, this is currently
# 'https://raw.githubusercontent.com/nextstrain/ncov-ingest/master/source-data/gisaid_geoLocationRules.tsv'
geolocation_rules_url: 'https://raw.githubusercontent.com/nextstrain/ncov-ingest/master/source-data/gisaid_geoLocationRules.tsv'
# The path to the local geolocation rules within the pathogen repo
# The path should be relative to the ingest directory.
local_geolocation_rules: 'defaults/geolocation-rules.tsv'
Expand Down
27 changes: 2 additions & 25 deletions ingest/rules/curate.smk
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,29 +13,6 @@ Parameters are expected to be defined in `config.curate`.
"""


rule fetch_general_geolocation_rules:
output:
general_geolocation_rules="data/general-geolocation-rules.tsv",
params:
geolocation_rules_url=config["curate"]["geolocation_rules_url"],
shell:
"""
curl {params.geolocation_rules_url} > {output.general_geolocation_rules}
"""


rule concat_geolocation_rules:
input:
general_geolocation_rules="data/general-geolocation-rules.tsv",
local_geolocation_rules=config["curate"]["local_geolocation_rules"],
output:
all_geolocation_rules="data/all-geolocation-rules.tsv",
shell:
"""
cat {input.general_geolocation_rules} {input.local_geolocation_rules} >> {output.all_geolocation_rules}
"""


def format_field_map(field_map: dict[str, str]) -> str:
"""
Format dict to `"key1"="value1" "key2"="value2"...` for use in shell commands.
Expand All @@ -46,7 +23,7 @@ def format_field_map(field_map: dict[str, str]) -> str:
rule curate:
input:
sequences_ndjson="data/sequences.ndjson",
all_geolocation_rules="data/all-geolocation-rules.tsv",
geolocation_rules=config["curate"]["local_geolocation_rules"],
annotations=config["curate"]["annotations"],
output:
metadata="data/all_metadata.tsv",
Expand Down Expand Up @@ -90,7 +67,7 @@ rule curate:
--authors-field {params.authors_field} \
--default-value {params.authors_default_value} \
| augur curate apply-geolocation-rules \
--geolocation-rules {input.all_geolocation_rules} \
--geolocation-rules {input.geolocation_rules} \
| ./scripts/fix-zika-strain-names.py \
| augur curate apply-record-annotations \
--annotations {input.annotations} \
Expand Down