Small suggestions

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 default_language_version:
   python: python3
-exclude: '\.(tsv|fasta|gb)$|^ingest/vendored/|'
+exclude: '\.(tsv|fasta|gb)$|^ingest/vendored/'
 repos:
   - repo: https://github.com/pre-commit/sync-pre-commit-deps
     rev: v0.0.3

ingest/README.md

@@ -8,6 +8,20 @@ If you have another data source or private data that needs to be
 formatted for the phylogenetic workflow, then you can use a similar
 workflow to curate your own data.
 
+## Running the workflow
+
+You can run the workflow with default parameters using the `nextstrain` cli:
+
+```sh
+nextstrain build .
+```
+
+or at your own risk using `snakemake` directly (if you've got all the typical Nextstrain workflow dependencies):
+
+```sh
+snakemake
+```
+
 ## Config
 
 The config directory contains all of the default configurations for

ingest/Snakefile

@@ -14,15 +14,14 @@ include: "rules/curate.smk"
 rule clean:
     params:
         targets = [
-            ".snakemake",
             "benchmarks",
             "data",
             "logs",
             "results",
             ]
     shell:
         """
-        rm -rfv {params.targets}
+        rm -rv {params.targets}
         """
 
 # Import custom rules provided via the config.

ingest/profiles/default/config.yaml

@@ -0,0 +1,3 @@
+cores: all
+printshellcmds: true
+ri: true

nextclade/README.md

@@ -23,3 +23,22 @@ FIXME CITE WHO PAPER HERE.
 * If any changes are needed to the clade-defining mutations, add
   changes to `defaults/clades.tsv` and re-run the workflow
 * Repeat as needed
+
+## Using local ingest data
+
+By default, this workflow pulls starting sequences and metadata from Nextstrain's AWS s3 bucket.
+If you want to use data from a local ingest run, just copy the data over:
+
+```sh
+cp -r ../ingest/results data
+```
+
+## Testing the dataset locally
+
+You can test the dataset locally by serving it, e.g. with `npx serve`:
+
+```sh
+npx serve ./dataset --cors
+```
+
+And then navigating to the following URL in your browser: <https://clades.nextstrain.org/?dataset-url=http://localhost:3000>

nextclade/Snakefile

@@ -15,7 +15,6 @@ include: "rules/assemble_dataset.smk"
 rule clean:
     params:
         targets = [
-            ".snakemake",
             "auspice",
             "benchmarks",
             "data",
@@ -26,5 +25,5 @@ rule clean:
         ]
     shell:
         """
-        rm -rfv {params.targets}
+        rm -rv {params.targets}
         """

nextclade/defaults/auspice_config.json

@@ -1,5 +1,5 @@
 {
-  "title": "Real-time tracking of rubella virus full genome virus evolution",
+  "title": "Rubella E1 gene Nextclade reference tree",
   "maintainers": [
     {
       "name": "John SJ Anderson",
@@ -20,6 +20,11 @@
       "title": "Genotype",
       "type": "categorical"
     },
+    {
+      "key": "date",
+      "title": "Collection Date",
+      "type": "temporal"
+    },
     {
       "key": "region",
       "title": "Region",
@@ -29,6 +34,41 @@
       "key": "country",
       "title": "Country",
       "type": "categorical"
+    },
+    {
+      "key": "division",
+      "title": "Division",
+      "type": "categorical"
+    },
+    {
+      "key": "location",
+      "title": "Location",
+      "type": "categorical"
+    },
+    {
+      "key": "length",
+      "title": "Length",
+      "type": "continuous"
+    },
+    {
+      "key": "date_released",
+      "title": "Date Released",
+      "type": "temporal"
+    },
+    {
+      "key": "author",
+      "title": "Author",
+      "type": "categorical"
+    },
+    {
+      "key": "host",
+      "title": "Host",
+      "type": "categorical"
+    },
+    {
+      "key": "institution",
+      "title": "Institution",
+      "type": "categorical"
     }
   ],
   "geo_resolutions": ["country", "region"],

nextclade/defaults/colors.tsv

@@ -81,4 +81,3 @@ clade	1G	#DFA43B
 clade	1H	#E68434
 clade	1I	#E2582C
 clade	1J	#DB2823
-

nextclade/defaults/nextclade-dataset/README.md

@@ -37,4 +37,3 @@ This dataset supports:
 
 Read more about Nextclade datasets in the Nextclade documentation:
 <https://docs.nextstrain.org/projects/nextclade/en/stable/user/datasets.html>
-