diff --git a/CHANGELOG.md b/CHANGELOG.md
index 31b8988f..06fa5e2f 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -248,3 +248,7 @@
   as scalars instead of lists, as required by `file_score.yaml` (PR #130).
 
 * Clean up stale mock parameters and dead code (PR #133).
+
+
+* Fix bug in `average_batch_r2` where the R2 was computed on all cell types of a donor at once
+  instead of on each cell type separately (PR #127).
diff --git a/src/metrics/average_batch_r2/script.py b/src/metrics/average_batch_r2/script.py
index 6788bf69..a0d82436 100644
--- a/src/metrics/average_batch_r2/script.py
+++ b/src/metrics/average_batch_r2/script.py
@@ -60,13 +60,13 @@
         s2_view_ct = s2_view[s2_view.obs["cell_type"] == ct]
         if (
             s1_view_ct.shape[0] < 20 or s2_view_ct.shape[0] < 20
-        ):  # Skip Rˆ2 calculation if there are less than 10 cells
+        ):  # Skip Rˆ2 calculation if there are less than 20 cells
             print(
                 f"Warning: Rˆ2 not computed for donor {donor} cell type {ct}. Too few cells were present: {s1_view_ct.shape[0]} for split 1 and {s2_view_ct.shape[0]} for split 2"
             )
             continue
 
-        r2_list, marker_list = batch_r2(s1_view, s2_view)
+        r2_list, marker_list = batch_r2(s1_view_ct, s2_view_ct)
 
         marker_list = [ct + "_" + donor + "_" + x for x in marker_list]
         r2_info = [*r2_info, *marker_list]