fix(datasets): add clone trajectory data sets

Signed-off-by: Cameron Smith <cameron.ray.smith@gmail.com>

Author: cameronraysmith

src/pyrovelocity/io/datasets.py

@@ -24,6 +24,9 @@
     "pancreas",
     "bonemarrow",
     "pbmc68k",
+    "larry_mono_clone_trajectory",
+    "larry_neu_clone_trajectory",
+    "larry_multilineage_clone_trajectory",
 ]
 
 
@@ -301,6 +304,77 @@ def larry_multilineage(
     return adata
 
 
+@beartype
+def larry_mono_clone_trajectory(
+    file_path: str | Path = "data/external/larry_mono_clone_trajectory.h5ad",
+) -> anndata._core.anndata.AnnData:
+    """
+    Pre-computed clone trajectory data for the LARRY monocyte lineage.
+
+    This contains the output of get_clone_trajectory applied to the larry_mono dataset.
+    The clone trajectory information is used for visualizing clonal progression
+    and calculating trajectory alignment with velocity predictions.
+
+    Returns:
+        AnnData object with clone trajectory information
+    """
+    url = "https://storage.googleapis.com/pyrovelocity/data/larry_mono_clone_trajectory.h5ad"
+    adata = sc.read(file_path, backup_url=url, sparse=True, cache=True)
+    expected_hash = (
+        "7bd6e4e9e9f7a830aeab2b342990cfedcf30eb0da5c5bfac4a76b8c7a4ab9142"
+    )
+    _check_hash(file_path, expected_hash)
+    return adata
+
+
+@beartype
+def larry_neu_clone_trajectory(
+    file_path: str | Path = "data/external/larry_neu_clone_trajectory.h5ad",
+) -> anndata._core.anndata.AnnData:
+    """
+    Pre-computed clone trajectory data for the LARRY neutrophil lineage.
+
+    This contains the output of get_clone_trajectory applied to the larry_neu dataset.
+    The clone trajectory information is used for visualizing clonal progression
+    and calculating trajectory alignment with velocity predictions.
+
+    Returns:
+        AnnData object with clone trajectory information
+    """
+    url = "https://storage.googleapis.com/pyrovelocity/data/larry_neu_clone_trajectory.h5ad"
+    adata = sc.read(file_path, backup_url=url, sparse=True, cache=True)
+    expected_hash = (
+        "f2e48b7ec1ed99ba6355e74afaaac8e9e97f9c0cad12dd0f09a0afb53c1c5d0a"
+    )
+    _check_hash(file_path, expected_hash)
+    return adata
+
+
+@beartype
+def larry_multilineage_clone_trajectory(
+    file_path: str
+    | Path = "data/external/larry_multilineage_clone_trajectory.h5ad",
+) -> anndata._core.anndata.AnnData:
+    """
+    Pre-computed clone trajectory data for the LARRY multilineage dataset.
+
+    This contains the concatenated output of get_clone_trajectory applied to
+    both larry_mono and larry_neu datasets. Using this pre-computed trajectory
+    ensures consistent fate analysis across both lineages without recomputing
+    trajectories separately.
+
+    Returns:
+        AnnData object with clone trajectory information
+    """
+    url = "https://storage.googleapis.com/pyrovelocity/data/larry_multilineage_clone_trajectory.h5ad"
+    adata = sc.read(file_path, backup_url=url, sparse=True, cache=True)
+    expected_hash = (
+        "d5c99fd45ab7f17c4a78cb7dc58c6bd3a3dd3ade89d10a8d8adf1b7be0a84cc7"
+    )
+    _check_hash(file_path, expected_hash)
+    return adata
+
+
 @beartype
 def pancreas(
     file_path: str | Path = "data/external/pancreas.h5ad",