Update file description

CHANGELOG.md

@@ -27,5 +27,7 @@
 
 * Added integrated test resource (PR #5).
 
+* Updated file description in yaml file (PR #15).
+
 ## BUGFIXES
 

src/api/file_integrated.yaml

@@ -1,7 +1,7 @@
 type: file
 example: "resources_test/task_cyto_batch_integration/starter_file/integrated.h5ad"
 label: Integrated
-summary: "Integrated dataset"
+summary: "Integrated dataset which batch effect was corrected by an algorithm"
 info:
   format:
     type: h5ad

src/api/file_unintegrated.yaml

@@ -1,9 +1,11 @@
 #TODO: Change to the required and/or optional fields of the anndata
 type: file
 example: "resources_test/task_cyto_batch_integration/starter_file/unintegrated.h5ad"
-label: "Unintegrated"
-summary: "Unintegrated dataset"
-
+label: Unintegrated
+summary: |
+  The complete unintegrated dataset, including all cells' metadata (columns) from the 
+  unintegrated_censored dataset. 
+  The cells in this dataset are the same to those in the unintegrated_censored dataset.
 info:
   format:
     type: h5ad

src/api/file_unintegrated_censored.yaml

@@ -1,8 +1,14 @@
 #TODO: Change to the required and/or optional fields of the anndata
 type: file
 example: "resources_test/task_cyto_batch_integration/starter_file/unintegrated_censored.h5ad"
-label: "Unintegrated Censored"
-summary: "Unintegrated dataset"
+label: Unintegrated Censored
+summary: |
+  An unintegrated dataset with certain columns (cells metadata), such as the donor information, hidden.
+  These columns are intentionally hidden to prevent bias.
+  The batch correction algorithm should not have to rely on these information 
+  to properly integrate different batches.
+  This dataset is used as the input for the batch correction algorithm. 
+  The cells therein are identical to those in the unintegrated dataset. 
 info:
   format:
     type: h5ad

src/api/file_validation.yaml

@@ -3,10 +3,16 @@ example: "resources_test/task_cyto_batch_integration/starter_file/validation.h5a
 label: Validation
 summary: Hold-out dataset for validation. 
 description: |
-  Samples that were held out and will later be used only to assess whether
-  the batch integration was successful. E.g. if a donor from batch 2 was corrected towards batch 1,
-  but also actually measured in batch 1 (without being used as input to the algorithm).
-
+  Dataset containing cells from samples that were held out for evaluating batch integration output. 
+  The cells that are in this dataset are not present in the unintegrated or unintegrated_censored datasets.
+  For example, if samples from donor A are present in batch 1 and 2, the sample from batch 1
+  may be used as input for the batch correction algorithm (and thus present in unintegrated
+  and unintegrated_censored datasets). 
+  The sample from batch 2, may not be included as an input for the batch correction algorithm,
+  but is needed to validate whether whether the algorithm managed to correct the batch effect
+  in batch 2 towards batch 1.
+  This sample will then be included in this dataset (but not in unintegrated
+  and unintegrated_censored datasets).  
 info:
   format:
     type: h5ad