From 7da438f9b8409507463e402c28da2c602c7bf6bd Mon Sep 17 00:00:00 2001
From: Kai Waldrant <kai@data-intuitive.com>
Date: Thu, 11 Jul 2024 20:50:07 +0200
Subject: [PATCH] update common dataset file

---
 src/api/file_common_dataset.yaml | 34 ++++++++++++++++++++++++++++++--
 1 file changed, 32 insertions(+), 2 deletions(-)

diff --git a/src/api/file_common_dataset.yaml b/src/api/file_common_dataset.yaml
index 0a5a05f..f3bd931 100644
--- a/src/api/file_common_dataset.yaml
+++ b/src/api/file_common_dataset.yaml
@@ -1,15 +1,41 @@
-#TODO: Change to the required and/or optional fields of the anndata
 type: file
 example: "resources_test/common/pancreas/dataset.h5ad"
 info:
   label: "Common Dataset"
   summary: A subset of the common dataset.
   slots:
-    layers: 
+    layers:
       - type: integer
         name: counts
         description: Raw counts
         required: true
+      - type: double
+        name: normalized
+        description: Normalized expression values
+        required: true
+    obs:
+      - type: string
+        name: cell_type
+        description: Cell type information
+        required: true
+      - type: string
+        name: batch
+        description: Batch information
+        required: true
+    var:
+      - type: boolean
+        name: hvg
+        description: Whether or not the feature is considered to be a 'highly variable gene'
+        required: true
+      - type: double
+        name: hvg_score
+        description: A ranking of the features by hvg.
+        required: true
+    obsm:
+      - type: double
+        name: X_pca
+        description: The resulting PCA embedding.
+        required: true
     uns:
       - type: string
         name: dataset_id
@@ -39,3 +65,7 @@ info:
         type: string
         description: The organism of the sample in the dataset.
         required: false
+      - type: string
+        name: normalization_id
+        description: "Which normalization was used"
+        required: true