From f05ccb0c99d53d3acdcec4f77ddecdbac2cc5122 Mon Sep 17 00:00:00 2001
From: Robrecht Cannoodt <rcannood@gmail.com>
Date: Tue, 9 Jul 2024 14:26:54 +0200
Subject: [PATCH] add dataset processing script

---
 scripts/process_datasets.sh | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)
 create mode 100755 scripts/process_datasets.sh

diff --git a/scripts/process_datasets.sh b/scripts/process_datasets.sh
new file mode 100755
index 00000000..91f7f8cc
--- /dev/null
+++ b/scripts/process_datasets.sh
@@ -0,0 +1,37 @@
+#!/bin/bash
+
+
+cat > /tmp/params.yaml <<'EOF'
+param_list:
+  - id: BREAST
+    input_sc: resources/datasets_raw/BREAST_sc.rds
+    input_sp: resources/datasets_raw/BREAST.rds
+    dataset_id: BREAST
+    dataset_name: "Nicely formatted name"
+    dataset_url: "https://example.com"
+    dataset_reference: "doi identifier"
+    dataset_summary: "A short description of the dataset (1 line)."
+    dataset_description: "A longer description of the dataset."
+    dataset_organism: "mus_musculus/homo_sapiens"
+  - id: HOSTEOSARCOMA
+    input_sc: resources/datasets_raw/HOSTEOSARCOMA_sc.rds
+    input_sp: resources/datasets_raw/HOSTEOSARCOMA.rds
+    dataset_id: HOSTEOSARCOMA
+    dataset_name: "Nicely formatted name"
+    dataset_url: "https://example.com"
+    dataset_reference: "doi identifier"
+    dataset_summary: "A short description of the dataset (1 line)."
+    dataset_description: "A longer description of the dataset."
+    dataset_organism: "mus_musculus/homo_sapiens"
+  # todo: add more
+
+publish_dir: "resources/datasets"
+output_sc: "$id/output_sc.h5ad"
+output_sp: "$id/output_sp.h5ad"
+output_state: "$id/state.yaml"
+EOF
+
+nextflow run . \
+  -main-script target/nextflow/process_datasets/convert/main.nf \
+  -profile docker \
+  -params-file /tmp/params.yaml