fixed bug in lca-reconstruct of ambiguous states

cassiopeia/data/utilities.py

@@ -72,6 +72,7 @@ def get_lca_characters(
                 else:
                     lca_vec[i] = all_states[0]
             else:
+                all_ambiguous = np.all([is_ambiguous_state(s) for s in all_states])
                 chars = set.intersection(
                     *map(
                         set,
@@ -83,6 +84,10 @@ def get_lca_characters(
                 )
                 if len(chars) == 1:
                     lca_vec[i] = list(chars)[0]
+                if all_ambiguous:
+                    # if we only have ambiguous states, we set the LCA state
+                    # to be the intersection.
+                    lca_vec[i] = tuple(chars)
     return lca_vec
 
 

test/data_tests/data_utilities_test.py

@@ -316,6 +316,17 @@ def test_lca_characters_ambiguous(self):
         )
         self.assertEqual(ret_vec, [1, 2, 3, 0, 5])
 
+    def test_lca_characters_ambiguous2(self):
+
+        s1 = [(4, 62), (3, 10), (3, 10, 16), (0, 3), (0, 2, 3), (0, 2, 3), (0, 4, 7), (0, 2, 23), (0, 1, 4, 44)]
+        s2 = [4, 3, -1, 0, 0, 0, (0, 7), (0, 2), (0, 4)]
+
+        expected_reconstruction = [4, 3, (3, 10, 16), 0, 0, 0, (0, 7), (0, 2), (0, 4)]
+        ret_vec = data_utilities.get_lca_characters(
+            [s1, s2], missing_state_indicator=-1
+        )
+        self.assertEqual(ret_vec, expected_reconstruction)
+
     def test_lca_characters_ambiguous_and_missing(self):
         vecs = [
             [(1, 1), (0, 2), (3, 0), (4,), (5,)],