Merge branch 'master' into improve-sample-metadata-docs

Author: Tanisha127

malariagen_data/anoph/aim_data.py

@@ -208,6 +208,7 @@ def plot_aim_heatmap(
         show: plotly_params.show = True,
         renderer: plotly_params.renderer = None,
     ) -> plotly_params.figure:
+        aims = self._prep_aims_param(aims=aims)
         # Load AIM calls.
         ds = self.aim_calls(
             aims=aims,

malariagen_data/anoph/snp_data.py

@@ -1,3 +1,4 @@
+import warnings
 from functools import lru_cache
 from typing import Any, Dict, List, Optional, Tuple, Union
 
@@ -1253,6 +1254,12 @@ def _snp_calls(
         if max_cohort_size is not None:
             n_samples = ds.sizes["samples"]
             if n_samples > max_cohort_size:
+                warnings.warn(
+                    f"Cohort downsampled from {n_samples} to {max_cohort_size} "
+                    "samples. Set max_cohort_size=None to disable downsampling.",
+                    UserWarning,
+                    stacklevel=2,
+                )
                 rng = np.random.default_rng(seed=random_seed)
                 loc_downsample = rng.choice(
                     n_samples, size=max_cohort_size, replace=False

tests/anoph/test_dipclust.py

@@ -11,6 +11,9 @@ def random_transcripts_contig(*, api, contig, n):
     df_gff = api.genome_features(attributes=["ID", "Parent"])
     df_transcripts = df_gff.query(f"type == 'mRNA' and contig == '{contig}'")
     transcript_ids = df_transcripts["ID"].dropna().to_list()
+    n = min(n, len(transcript_ids))
+    if n == 0:
+        pytest.skip(f"No mRNA transcripts found for contig '{contig}'")
     transcripts = random.sample(transcript_ids, n)
     return transcripts