From 033c5452a60249b1a0c893c7de3fd5731848486a Mon Sep 17 00:00:00 2001
From: Dominik Brilhaus <brilhaus@nfdi4plants.org>
Date: Thu, 25 Jan 2024 14:10:56 +0100
Subject: [PATCH] replace TAIR10 ref with the one used "back then"

---
 .gitattributes                                |  1 +
 .../protocols/download-reference.md           | 23 +++++++++++++++++++
 ...Arabidopsis_thaliana.TAIR10.28.cdna.all.fa |  3 +++
 .../Araport11_genes.201606.cdna.fasta         |  3 ---
 4 files changed, 27 insertions(+), 3 deletions(-)
 create mode 100644 studies/arabidopsis-reference/protocols/download-reference.md
 create mode 100644 studies/arabidopsis-reference/resources/Arabidopsis_thaliana.TAIR10.28.cdna.all.fa
 delete mode 100644 studies/arabidopsis-reference/resources/Araport11_genes.201606.cdna.fasta

diff --git a/.gitattributes b/.gitattributes
index 5be99d5..c4990cb 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -4,3 +4,4 @@ _publication/fpls-09-01709.pdf filter=lfs diff=lfs merge=lfs -text
 _publication/Data[[:space:]]Sheet[[:space:]]1.xlsx filter=lfs diff=lfs merge=lfs -text
 studies/arabidopsis-reference/resources/Araport11_genes.201606.cdna.fasta filter=lfs diff=lfs merge=lfs -text
 runs/kallisto_index/out/kallisto_index filter=lfs diff=lfs merge=lfs -text
+studies/arabidopsis-reference/resources/Arabidopsis_thaliana.TAIR10.28.cdna.all.fa filter=lfs diff=lfs merge=lfs -text
diff --git a/studies/arabidopsis-reference/protocols/download-reference.md b/studies/arabidopsis-reference/protocols/download-reference.md
new file mode 100644
index 0000000..d31d55f
--- /dev/null
+++ b/studies/arabidopsis-reference/protocols/download-reference.md
@@ -0,0 +1,23 @@
+
+# Downloading Arabidopsis TAIR10 fasta
+
+### Download and unzip
+
+```bash
+curl -O ftp://ftp.ensemblgenomes.org/pub/plants/release-28/fasta/arabidopsis_thaliana/cdna/Arabidopsis_thaliana.TAIR10.28.cdna.all.fa.gz
+gunzip Arabidopsis_thaliana.TAIR10.28.cdna.all.fa.gz
+```
+
+### sanity check
+
+count number of genes / gene products
+
+```bash
+grep '>' Arabidopsis_thaliana.TAIR10.28.cdna.all.fa | wc -l
+```
+
+### move
+
+```bash
+mv Arabidopsis_thaliana.TAIR10.28.cdna.all.fa ../resources
+```
diff --git a/studies/arabidopsis-reference/resources/Arabidopsis_thaliana.TAIR10.28.cdna.all.fa b/studies/arabidopsis-reference/resources/Arabidopsis_thaliana.TAIR10.28.cdna.all.fa
new file mode 100644
index 0000000..dce30a4
--- /dev/null
+++ b/studies/arabidopsis-reference/resources/Arabidopsis_thaliana.TAIR10.28.cdna.all.fa
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2924f53c82a7013eeaeb14a6691ba97a65010c540007a3fbeffa40a66ed296e8
+size 73699735
diff --git a/studies/arabidopsis-reference/resources/Araport11_genes.201606.cdna.fasta b/studies/arabidopsis-reference/resources/Araport11_genes.201606.cdna.fasta
deleted file mode 100644
index 51b14af..0000000
--- a/studies/arabidopsis-reference/resources/Araport11_genes.201606.cdna.fasta
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:826d4d9f605007e613e8ba2d2fd186d955a768c5a5cc575998e3f09355137a3d
-size 93036871
-- 
GitLab