From 7006f5966d9f6bf67d0d8d76a8731d2e0384407a Mon Sep 17 00:00:00 2001
From: John SJ Anderson <janders4@fredhutch.org>
Date: Fri, 28 Jun 2024 15:40:06 -0700
Subject: [PATCH] Add description file with standard attributions [#24]

---
 phylogenetic/config/description.md | 21 +++++++++++++++++++++
 phylogenetic/rules/export.smk      |  2 ++
 2 files changed, 23 insertions(+)
 create mode 100644 phylogenetic/config/description.md

diff --git a/phylogenetic/config/description.md b/phylogenetic/config/description.md
new file mode 100644
index 0000000..8016742
--- /dev/null
+++ b/phylogenetic/config/description.md
@@ -0,0 +1,21 @@
+We gratefully acknowledge the authors, originating and submitting
+laboratories of the genetic sequences and metadata for sharing their
+work. Please note that although data generators have generously shared
+data in an open fashion, that does not mean there should be free
+license to publish on this data. Data generators should be cited where
+possible and collaborations should be sought in some circumstances.
+Please try to avoid scooping someone else's work. Reach out if
+uncertain.
+
+#### Underlying data
+
+We curate sequence data and metadata from NCBI as starting point for
+our analyses. Curated sequences and metadata are available as flat
+files at:
+
+- [data.nextstrain.org/files/workflows/seasonal-cov/sequences.fasta.zst](https://data.nextstrain.org/files/workflows/seasonal-cov/sequences.fasta.zst)
+- [data.nextstrain.org/files/workflows/seasonal-cov/metadata.tsv.zs](https://data.nextstrain.org/files/workflows/seasonal-cov/metadata.tsv.zs)
+
+Screenshots may be used under a
+[CC-BY-4.0 license](https://creativecommons.org/licenses/by/4.0/) and
+attribution to nextstrain.org must be provided.
diff --git a/phylogenetic/rules/export.smk b/phylogenetic/rules/export.smk
index 11a45bd..62aff1b 100644
--- a/phylogenetic/rules/export.smk
+++ b/phylogenetic/rules/export.smk
@@ -13,6 +13,7 @@ rule export:
         branch_lengths="results/{virus}/branch_lengths.json",
         nt_muts="results/{virus}/nt_muts.json",
         aa_muts="results/{virus}/aa_muts.json",
+        description="config/description.md",
         auspice_config="config/auspice_config.json",
     output:
         auspice_json="auspice/seasonal-cov_{virus}.json",
@@ -29,6 +30,7 @@ rule export:
           --metadata {input.metadata:q} \
           --node-data {input.branch_lengths:q} {input.nt_muts:q} {input.aa_muts:q}  \
           --include-root-sequence \
+          --description {input.description:q} \
           --auspice-config {input.auspice_config:q} \
           --title {params.auspice_title:q} \
           --include-root-sequence \