Add setup script and updates for wilms data

components/dictionary.txt

@@ -485,6 +485,7 @@ VST
 Wattenberg
 Wickham
 Wickham's
+Wilms
 WIPO
 WNT
 xenograft

scRNA-seq-advanced/setup/ewing-sarcoma/README.md

@@ -2,12 +2,12 @@ The shell script in this directory downloads processed `SingleCellExperiment` ob
 
 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.
+By default, it will use your currently active AWS profile (falling back to one called `openscpca` if not set) and download data from the `2024-11-25` OpenScPCA release.
 
 You can alter the AWS profile or release with the following:
 
 ```sh
-PROFILE={profile} RELEASE={release} ./download-openscpca-data.sh
+AWS_PROFILE={profile} RELEASE={release} ./download-openscpca-data.sh
 ```
 
 Replacing `{profile}` and `{release}` with a profile with OpenScPCA access and valid release, respectively.

scRNA-seq-advanced/setup/ewing-sarcoma/download-openscpca-data.sh

@@ -2,8 +2,8 @@
 
 set -euo pipefail
 
-# Profile to use with the download script
-PROFILE=${PROFILE:-openscpca}
+# AWS profile to use with the download script
+AWS_PROFILE=${AWS_PROFILE:-openscpca}
 # Release to download
 RELEASE=${RELEASE:-2024-11-25}
 
@@ -31,15 +31,15 @@ chmod +x download-data.py
     --format SCE \
     --release ${RELEASE} \
     --data-dir ${ewing_data_dir} \
-    --profile ${PROFILE}
+    --profile ${AWS_PROFILE}
 
 # # Download Ewing sarcoma metadata
 ./download-data.py \
     --projects SCPCP000015 \
     --metadata-only \
     --release ${RELEASE} \
     --data-dir ${ewing_data_dir} \
-    --profile ${PROFILE}
+    --profile ${AWS_PROFILE}
 
 # Remove existing files from processed directory
 if [ -z "$( ls -A ${processed_dir} )" ]; then

scRNA-seq-advanced/setup/wilms-tumor/README.md

@@ -0,0 +1,13 @@
+The shell script in this directory downloads processed `SingleCellExperiment` object for the `SCPCS000203` sample from `SCPCP000006` (Wilms tumor) using the data download mechanism from OpenScPCA.
+
+You may want to run it with your OpenScPCA conda environment activated.
+
+By default, it will use your currently active AWS profile (falling back to one called `openscpca` if not set) and download data from the `2024-11-25` OpenScPCA release.
+
+You can alter the AWS profile or release with the following:
+
+```sh
+AWS_PROFILE={profile} RELEASE={release} ./download-openscpca-data.sh
+```
+
+Replacing `{profile}` and `{release}` with a profile with OpenScPCA access and valid release, respectively.

scRNA-seq-advanced/setup/wilms-tumor/download-openscpca-data.sh

@@ -0,0 +1,50 @@
+#!/bin/bash
+
+set -euo pipefail
+
+# AWS profile to use with the download script
+AWS_PROFILE=${AWS_PROFILE:-openscpca}
+# Release to download
+RELEASE=${RELEASE:-2024-11-25}
+
+# Set the working directory to the directory of this file
+cd "$(dirname "${BASH_SOURCE[0]}")"
+
+# Define ScPCA project id
+project_id="SCPCP000006"
+
+# Set up directories
+wilms_data_dir="../../data/wilms-tumor"
+processed_dir="${wilms_data_dir}/processed"
+
+# Create directories if they don't exist yet
+mkdir -p "${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 Wilms tumor samples
+./download-data.py \
+    --samples 'SCPCS000203' \
+    --format SCE \
+    --release ${RELEASE} \
+    --data-dir ${wilms_data_dir} \
+    --profile ${AWS_PROFILE}
+
+# Remove existing files from processed directory
+if [ -z "$( ls -A ${processed_dir} )" ]; then
+   echo "No processed files yet!"
+else
+   rm -r ${processed_dir}/*
+fi
+
+# Move processed files from release folder into processed_dir
+mv ${wilms_data_dir}/${RELEASE}/${project_id}/* ${processed_dir}
+
+# Clean up download data script
+rm download-data.py
+# Clean up the remnants of download structure
+rm -r ${wilms_data_dir}/${AWS_PROFILE}

scripts/link-data.sh

@@ -42,6 +42,7 @@ mkdir -p scRNA-seq-advanced/data/rms/integrated
 mkdir -p scRNA-seq-advanced/data/rms/annotations
 mkdir -p scRNA-seq-advanced/data/pancreas
 mkdir -p scRNA-seq-advanced/data/hodgkins
+mkdir -p scRNA-seq-advanced/data/wilms-tumor/processed
 
 # Machine learning module directory
 mkdir -p machine-learning/data
@@ -94,6 +95,7 @@ link_locs=(
   scRNA-seq-advanced/data/rms/annotations/rms_sample_metadata.tsv
   scRNA-seq-advanced/data/pancreas/processed
   scRNA-seq-advanced/gene-sets
+  scRNA-seq-advanced/data/wilms-tumor/processed
   machine-learning/data/open-pbta
   pathway-analysis/data/leukemia
   pathway-analysis/data/medulloblastoma

scripts/syncup-s3.sh

@@ -45,6 +45,7 @@ sync_dirs=(
   scRNA-seq-advanced/data/rms/integrated
   scRNA-seq-advanced/data/pancreas/processed
   scRNA-seq-advanced/gene-sets
+  scRNA-seq-advanced/data/wilms-tumor/processed
   machine-learning/data/open-pbta/processed
   pathway-analysis/data/leukemia
   pathway-analysis/data/medulloblastoma