Add new dataset (#106)

* add dataset processing script

* fix reference

* add goal batch

* update script for cll dataset

* update changelog

---------

Co-authored-by: Givanna Putri <givanna.h@gmail.com>

Author: rcannood

CHANGELOG.md

@@ -64,6 +64,7 @@
 
 * Added Seurat rPCA (PR #95).
 
+* Added processing scripts for CLL dataset (PR #106).
 
 ## MAJOR CHANGES
 

scripts/create_resources/human_cll_mass_cytometry.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+# get the root of the directory
+REPO_ROOT=$(git rev-parse --show-toplevel)
+
+# ensure that the command below is run from the root of the repository
+cd "$REPO_ROOT"
+
+set -e
+
+RAW_DIR=resources_raw/human_cll_mass_cytometry/
+DATASET_ID=human_cll_mass_cytometry
+OUTPUT_DIR=resources/datasets_raw/$DATASET_ID/
+
+mkdir -p $OUTPUT_DIR
+
+# create raw dataset files
+python << HERE
+import anndata as ad
+
+adata = ad.read_h5ad("$RAW_DIR/human_cll_mass_cytometry.h5ad")
+
+# make sure the output is compressed
+adata.write_h5ad("$OUTPUT_DIR/common_dataset.h5ad", compression='gzip')
+HERE
+
+cat > $OUTPUT_DIR/state.yaml << HERE
+id: $DATASET_ID
+output_dataset: !file common_dataset.h5ad
+HERE
+
+# only run this if you have access to the openproblems-data bucket
+aws s3 sync --profile op \
+  resources/datasets_raw/human_cll_mass_cytometry \
+  s3://openproblems-data/resources/task_cyto_batch_integration/datasets_raw/human_cll_mass_cytometry/ \
+  --delete --dryrun