Merge pull request #26 from nextstrain/final-final-no-i-mean-it-25

Final tweaks [#25]

ingest/defaults/config.yaml

@@ -128,6 +128,7 @@ curate:
     - full_authors
     - authors
     - institution
+    - url
 nextclade:
   dataset_name: "nextstrain/yellow-fever/prM-E"
   field_map: "defaults/nextclade_field_map.tsv"

ingest/rules/curate.smk

@@ -59,7 +59,7 @@ rule curate:
         all_geolocation_rules="data/all-geolocation-rules.tsv",
         annotations=config["curate"]["annotations"],
     output:
-        metadata="data/all_metadata.tsv",
+        metadata=temp("data/all_metadata_intermediate.tsv"),
         sequences="results/sequences.fasta",
     log:
         "logs/curate.txt",
@@ -116,6 +116,23 @@ rule curate:
         """
 
 
+rule add_genbank_url:
+    input:
+        metadata=temp("data/all_metadata_intermediate.tsv"),
+    output:
+        metadata="data/all_metadata.tsv",
+    log:
+        "logs/add_genbank_url.txt",
+    benchmark:
+        "benchmarks/add_genbank_url.txt",
+    shell:
+        r"""
+        csvtk mutate2 -t \
+          -n url \
+          -e '"https://www.ncbi.nlm.nih.gov/nuccore/" + $accession' \
+          {input.metadata:q} > {output.metadata:q} 2> {log:q}
+        """
+
 rule subset_metadata:
     input:
         metadata="data/all_metadata.tsv",

ingest/rules/nextclade.smk

@@ -64,9 +64,9 @@ rule join_metadata_and_nextclade:
         (
           export SUBSET_FIELDS=`grep -v '^#' {input.nextclade_field_map} | awk '{{print $1}}' | tr '\n' ',' | sed 's/,$//g'`
 
-          csvtk -tl cut -f $SUBSET_FIELDS \
+          csvtk -t cut -f $SUBSET_FIELDS \
               {input.nextclade} \
-          | csvtk -tl rename2 \
+          | csvtk -t rename2 \
               -F \
               -f '*' \
               -p '(.+)' \

phylogenetic/defaults/auspice_config_genome.json

@@ -19,14 +19,9 @@
     },
     {
       "key": "clade",
-      "title": "Genotype (via Nextclade tree)",
+      "title": "Clade (via Nextclade tree)",
       "type": "categorical"
     },
-    {
-      "key": "date",
-      "title": "Date",
-      "type": "temporal"
-    },
     {
       "key": "region",
       "title": "Region",

phylogenetic/defaults/auspice_config_prM-E.json

@@ -19,7 +19,7 @@
     },
     {
       "key": "clade",
-      "title": "Genotype (via Nextclade tree)",
+      "title": "Clade (via Nextclade tree)",
       "type": "categorical"
     },
     {

phylogenetic/defaults/color_orderings.tsv

@@ -225,7 +225,7 @@ region	North America
 
 ################
 
-# genotype assigned by Nextclade
+# clade assigned by Nextclade
 clade	Clade I
 clade	Clade II
 clade	Clade III

phylogenetic/defaults/description.md

@@ -14,20 +14,23 @@ Our bioinformatic processing workflow can be found at
 
 - sequence alignment by [augur align][]
 - phylogenetic reconstruction using [IQTREE-2][]
+- clade assignment using [Nextclade][]
 - ancestral state reconstruction and temporal inference using [TreeTime][]
 
 #### Underlying data
 
 We curate sequence data and metadata from NCBI as starting point for
-our analyses.
+our analyses. We gratefully acknowledge the large contribution of over
+500 sequences from Hill, et al.
 
 ---
 
 Screenshots may be used under a [CC-BY-4.0 license][] and attribution
 to nextstrain.org must be provided.
 
-[CC-BY-4.0 license]: https://creativecommons.org/licenses/by/4.0/
+[github.com/nextstrain/yellow-fever]: https://github.com/nextstrain/yellow-fever
+[augur align]: https://docs.nextstrain.org/projects/augur/en/stable/usage/cli/align.html
 [IQTREE-2]: http://www.iqtree.org/
+[Nextclade]: https://nextstrain.org/fetch/data.clades.nextstrain.org/v3/nextstrain/yellow-fever/prM-E/2024-11-05--09-19-52Z/tree.json
 [TreeTime]: https://github.com/neherlab/treetime
-[augur align]: https://docs.nextstrain.org/projects/augur/en/stable/usage/cli/align.html
-[github.com/nextstrain/yellow-fever]: https://github.com/nextstrain/measles
+[CC-BY-4.0 license]: https://creativecommons.org/licenses/by/4.0/