From a6dc06d0c8deec0e712e495c02479db01c986527 Mon Sep 17 00:00:00 2001
From: Jaclyn Taroni <19534205+jaclyn-taroni@users.noreply.github.com>
Date: Sat, 23 Nov 2024 11:28:12 -0500
Subject: [PATCH 1/7] Add bash script for grabbing processed EWS data from
 OpenScPCA

---
 .../download-and-rename-openscpca-data.sh     | 68 +++++++++++++++++++
 1 file changed, 68 insertions(+)
 create mode 100755 scRNA-seq-advanced/setup/ewing-sarcoma/download-and-rename-openscpca-data.sh

diff --git a/scRNA-seq-advanced/setup/ewing-sarcoma/download-and-rename-openscpca-data.sh b/scRNA-seq-advanced/setup/ewing-sarcoma/download-and-rename-openscpca-data.sh
new file mode 100755
index 00000000..396f89f1
--- /dev/null
+++ b/scRNA-seq-advanced/setup/ewing-sarcoma/download-and-rename-openscpca-data.sh
@@ -0,0 +1,68 @@
+#!/bin/bash
+
+set -euo pipefail
+
+# Profile to use with the download script
+PROFILE=${PROFILE:-openscpca}
+# Release to download
+RELEASE=${RELEASE:-2024-08-22}
+
+# Set the working directory to the directory of this file
+cd "$(dirname "${BASH_SOURCE[0]}")"
+
+# Set up directories
+ewing_data_dir="../../data/ewing-sarcoma"
+annotations_dir="${ewing_data_dir}/annotations"
+processed_dir="${ewing_data_dir}/processed"
+
+# Create directories if they don't exist yet
+mkdir -p "${annotations_dir}"
+mkdir -p "${processed_dir}"
+
+# Get download data script from OpenScPCA for convenience
+curl -O \
+    -L https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/a3d8a2c9144e8edb3894a7beeb89cdc6c3e6d681/download-data.py
+# Make executable
+chmod +x download-data.py
+
+# Download Ewing sarcoma tumor samples
+./download-data.py \
+    --samples 'SCPCS000490,SCPCS000492,SCPCS000493,SCPCS000494,SCPCS000495,SCPCS000496,SCPCS000749' \
+    --format SCE \
+    --release ${RELEASE} \
+    --data-dir ${ewing_data_dir} \
+    --profile ${PROFILE}
+
+# # Download Ewing sarcoma metadata
+./download-data.py \
+    --projects SCPCP000015 \
+    --metadata-only \
+    --release ${RELEASE} \
+    --data-dir ${ewing_data_dir} \
+    --profile ${PROFILE}
+
+# Remove existing files from processed directory
+if [ -z "$( ls -A ${processed_dir} )" ]; then
+   echo "No processed files yet!"
+else
+   rm -r ${processed_dir}/*
+fi
+
+# Move files from release folder
+mv ${ewing_data_dir}/${RELEASE}/SCPCP000015/* ${processed_dir}
+mv "${processed_dir}/single_cell_metadata.tsv" "${annotations_dir}/ewing_sarcoma_sample_metadata.tsv"
+
+# Remove PDX samples from metadata
+Rscript - << EOF
+
+sample_metadata_df <- readr::read_tsv("${annotations_dir}/ewing_sarcoma_sample_metadata.tsv")
+sample_metadata_df |>
+    dplyr::filter(stringr::str_detect(sample_type, "xenograft", negate = TRUE)) |>
+    readr::write_tsv("${annotations_dir}/ewing_sarcoma_sample_metadata.tsv")
+
+EOF
+
+# Clean up download data script
+rm download-data.py
+# Clean up the remnants of download structure
+rm -r ${ewing_data_dir}/${RELEASE}

From 179aaeccbf1e2f3ea3da91661905dd84f624b6e5 Mon Sep 17 00:00:00 2001
From: Jaclyn Taroni <19534205+jaclyn-taroni@users.noreply.github.com>
Date: Sat, 23 Nov 2024 11:29:56 -0500
Subject: [PATCH 2/7] Add EWS data to S3 sync script

---
 scripts/syncup-s3.sh | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/syncup-s3.sh b/scripts/syncup-s3.sh
index 8f66b434..07063a28 100644
--- a/scripts/syncup-s3.sh
+++ b/scripts/syncup-s3.sh
@@ -37,6 +37,7 @@ sync_dirs=(
   scRNA-seq/data/tabula-muris/alevin-quant/10X_P7_12
   scRNA-seq/data/reference
   scRNA-seq/index/Mus_musculus
+  scRNA-seq-advanced/data/ewing-sarcoma/processed
   scRNA-seq-advanced/data/glioblastoma-10x/raw_feature_bc_matrix
   scRNA-seq-advanced/data/hodgkins/markers
   scRNA-seq-advanced/data/PBMC-TotalSeqB/raw_feature_bc_matrix
@@ -59,6 +60,7 @@ sync_files=(
   scRNA-seq/data/tabula-muris/normalized/TM_normalized.rds
   scRNA-seq/data/tabula-muris/TM_droplet_metadata.csv
   scRNA-seq-advanced/analysis/mouse-liver/markers/cluster07_markers.tsv
+  scRNA-seq-advanced/data/ewing-sarcoma/annotations/ewing_sarcoma_sample_metadata.tsv
   scRNA-seq-advanced/data/rms/annotations/rms_sample_metadata.tsv
   scRNA-seq-advanced/data/reference/hs_mitochondrial_genes.tsv
 )

From 654609f88cc92fdc589b1622efa5ebc86dc33e78 Mon Sep 17 00:00:00 2001
From: Jaclyn Taroni <19534205+jaclyn-taroni@users.noreply.github.com>
Date: Sat, 23 Nov 2024 11:33:00 -0500
Subject: [PATCH 3/7] Add EWS to link data shell script

---
 scripts/link-data.sh | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/scripts/link-data.sh b/scripts/link-data.sh
index 35810556..20e3769c 100644
--- a/scripts/link-data.sh
+++ b/scripts/link-data.sh
@@ -35,6 +35,8 @@ mkdir -p scRNA-seq/data/PBMC-TotalSeqB/normalized/
 # scRNA-seq-advanced module directories
 mkdir -p scRNA-seq-advanced/analysis/mouse-liver
 mkdir -p scRNA-seq-advanced/data/PBMC-TotalSeqB/normalized
+mkdir -p scRNA-seq-advanced/data/ewing-sarcoma/annotations
+mkdir -p scRNA-seq-advanced/data/ewing-sarcoma/processed
 mkdir -p scRNA-seq-advanced/data/glioblastoma-10x
 mkdir -p scRNA-seq-advanced/data/rms/integrated
 mkdir -p scRNA-seq-advanced/data/rms/annotations
@@ -83,6 +85,8 @@ link_locs=(
   scRNA-seq-advanced/data/PBMC-TotalSeqB/raw_feature_bc_matrix
   scRNA-seq-advanced/data/PBMC-TotalSeqB/normalized/PBMC_TotalSeqB_normalized_sce.rds
   scRNA-seq-advanced/data/glioblastoma-10x/raw_feature_bc_matrix
+  scRNA-seq-advanced/data/ewing-sarcoma/annotations/ewing_sarcoma_sample_metadata.tsv
+  scRNA-seq-advanced/data/ewing-sarcoma/processed
   scRNA-seq-advanced/data/hodgkins/markers
   scRNA-seq-advanced/data/reference
   scRNA-seq-advanced/data/rms/processed

From 8484b0bec5b228470c60f0fa3b51015176bfaaa5 Mon Sep 17 00:00:00 2001
From: Jaclyn Taroni <19534205+jaclyn-taroni@users.noreply.github.com>
Date: Sat, 23 Nov 2024 17:41:42 -0500
Subject: [PATCH 4/7] Make name shorter and more accurate

---
 ...ad-and-rename-openscpca-data.sh => download-openscpca-data.sh} | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 rename scRNA-seq-advanced/setup/ewing-sarcoma/{download-and-rename-openscpca-data.sh => download-openscpca-data.sh} (100%)

diff --git a/scRNA-seq-advanced/setup/ewing-sarcoma/download-and-rename-openscpca-data.sh b/scRNA-seq-advanced/setup/ewing-sarcoma/download-openscpca-data.sh
similarity index 100%
rename from scRNA-seq-advanced/setup/ewing-sarcoma/download-and-rename-openscpca-data.sh
rename to scRNA-seq-advanced/setup/ewing-sarcoma/download-openscpca-data.sh

From 2d6914ab1dc1047a756d66f98d472517e63b45de Mon Sep 17 00:00:00 2001
From: Jaclyn Taroni <19534205+jaclyn-taroni@users.noreply.github.com>
Date: Sat, 23 Nov 2024 17:42:07 -0500
Subject: [PATCH 5/7] Add a short README

---
 scRNA-seq-advanced/setup/ewing-sarcoma/README.md | 13 +++++++++++++
 1 file changed, 13 insertions(+)
 create mode 100644 scRNA-seq-advanced/setup/ewing-sarcoma/README.md

diff --git a/scRNA-seq-advanced/setup/ewing-sarcoma/README.md b/scRNA-seq-advanced/setup/ewing-sarcoma/README.md
new file mode 100644
index 00000000..fd45eebf
--- /dev/null
+++ b/scRNA-seq-advanced/setup/ewing-sarcoma/README.md
@@ -0,0 +1,13 @@
+The shell script in this directory downloads processed `SingleCellExperiment` objects and metadata from tumor samples in `SCPCP000015` using the data download mechanism from OpenScPCA.
+
+You may want to run it with your OpenScPCA conda environment activated.
+
+By default, it will use an AWS profile called `openscpca` and download data from the `2024-08-22` OpenScPCA release.
+
+You can alter the AWS profile or release with the following:
+
+```sh
+PROFILE={profile} RELEASE={release} ./download-openscpca-data.sh
+```
+
+Replacing `{profile}` and `{release}` with a profile with OpenScPCA access and valid release, respectively.

From 9dbc28d2f0979c51afd2aa90d1c563cb9101812e Mon Sep 17 00:00:00 2001
From: Jaclyn Taroni <19534205+jaclyn-taroni@users.noreply.github.com>
Date: Mon, 25 Nov 2024 09:47:35 -0500
Subject: [PATCH 6/7] Add OpenScPCA to dictionary

---
 components/dictionary.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/components/dictionary.txt b/components/dictionary.txt
index 3379690a..5c42f78a 100644
--- a/components/dictionary.txt
+++ b/components/dictionary.txt
@@ -315,6 +315,7 @@ oncoproteins
 OPC
 OPCs
 OpenPBTA
+OpenScPCA
 Optimus
 orking
 orthotopic

From 4284c2447bddb88648d31e0177191a0ad1e1bc3c Mon Sep 17 00:00:00 2001
From: Jaclyn Taroni <19534205+jaclyn-taroni@users.noreply.github.com>
Date: Mon, 25 Nov 2024 11:35:39 -0500
Subject: [PATCH 7/7] Apply suggestions from code review

Co-authored-by: Joshua Shapiro <josh.shapiro@ccdatalab.org>
---
 .../setup/ewing-sarcoma/download-openscpca-data.sh              | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scRNA-seq-advanced/setup/ewing-sarcoma/download-openscpca-data.sh b/scRNA-seq-advanced/setup/ewing-sarcoma/download-openscpca-data.sh
index 396f89f1..7ccae206 100755
--- a/scRNA-seq-advanced/setup/ewing-sarcoma/download-openscpca-data.sh
+++ b/scRNA-seq-advanced/setup/ewing-sarcoma/download-openscpca-data.sh
@@ -5,7 +5,7 @@ set -euo pipefail
 # Profile to use with the download script
 PROFILE=${PROFILE:-openscpca}
 # Release to download
-RELEASE=${RELEASE:-2024-08-22}
+RELEASE=${RELEASE:-2024-11-25}
 
 # Set the working directory to the directory of this file
 cd "$(dirname "${BASH_SOURCE[0]}")"