Created
March 7, 2024 18:23
-
-
Save huddlej/cde8e98d0a1ceb1546f9068039a433f2 to your computer and use it in GitHub Desktop.
Example subsampling logic for multi-species seasonal flu build
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
custom_rules: | |
- profiles/gisaid/prepare_data.smk | |
metadata_fields: | |
- Isolate_Name | |
- Isolate_Id | |
- Passage_History | |
- Location | |
- Authors | |
- Originating_Lab | |
- Collection_Date | |
- Submission_Date | |
renamed_metadata_fields: | |
- strain | |
- accession | |
- passage | |
- location | |
- authors | |
- originating_lab | |
- date | |
- date_submitted | |
lat-longs: "config/lat_longs.tsv" | |
segments: | |
- ha | |
submission_date_field: date_submitted | |
recency: | |
date_bins: [7, 30, 90] | |
date_bin_labels: ["last week", "last month", "last quarter"] | |
upper_bin_label: older | |
builds: | |
"h3n2": | |
lineage: h3n2 | |
reference: "config/h3n2/{segment}/reference.fasta" | |
annotation: "config/h3n2/{segment}/genemap.gff" | |
tree_exclude_sites: "config/h3n2/{segment}/exclude-sites.txt" | |
clades: "config/h3n2/ha/clades.tsv" | |
subclades: "config/h3n2/ha/subclades.tsv" | |
auspice_config: "config/h3n2/auspice_config.json" | |
enable_lbi: true | |
enable_glycosylation: true | |
subsamples: | |
human: | |
filters: --query "host == 'human'" --subsample-max-sequences 100 --group-by country year month | |
avian: | |
filters: --query "host in ['duck', 'chicken', 'stork']" --subsample-max-sequences 100 --group-by region | |
swine: | |
filters: --query "host == 'swine'" --subsample-max-sequences 100 --group-by region |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
custom_rules: | |
- profiles/gisaid/prepare_data.smk | |
metadata_fields: | |
- Isolate_Name | |
- Isolate_Id | |
- Passage_History | |
- Location | |
- Authors | |
- Originating_Lab | |
- Collection_Date | |
- Submission_Date | |
renamed_metadata_fields: | |
- strain | |
- accession | |
- passage | |
- location | |
- authors | |
- originating_lab | |
- date | |
- date_submitted | |
lat-longs: "config/lat_longs.tsv" | |
segments: | |
- ha | |
submission_date_field: date_submitted | |
recency: | |
date_bins: [7, 30, 90] | |
date_bin_labels: ["last week", "last month", "last quarter"] | |
upper_bin_label: older | |
builds: | |
"h3n2": | |
lineage: h3n2 | |
reference: "config/h3n2/{segment}/reference.fasta" | |
annotation: "config/h3n2/{segment}/genemap.gff" | |
tree_exclude_sites: "config/h3n2/{segment}/exclude-sites.txt" | |
clades: "config/h3n2/ha/clades.tsv" | |
subclades: "config/h3n2/ha/subclades.tsv" | |
auspice_config: "config/h3n2/auspice_config.json" | |
enable_lbi: true | |
enable_glycosylation: true | |
subsamples: | |
specific_strains: | |
filters: --exclude-all --include profiles/gisaid/specific_strains.txt |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment