Store neighbours as an obsp graph instead of strings

HISTORY.rst

@@ -2,6 +2,31 @@
 History
 =======
 
+1.5.1 (2026-11-07)
+------------------
+* ``st.tl.cci.run`` now uses a spots-by-spots, sparse graph:
+  ``adata.obsp["spot_neighbours"]``. It replaces the comma-joined strings
+  ``adata.obsm["spot_neighbours"]`` and ``adata.obsm["spot_neigh_bcs"]``.
+* With ``use_label``, ``run`` counts cell types over the same graph instead of
+  searching the neighbours a second time (``het.count`` takes it as ``neighbours=``).
+* ``st.tl.cache.write_subset_h5ad`` takes ``obsp_keys``, and
+  ``merge_h5ad_into_adata`` copies ``obsp``, so a cached CCI run keeps its neighbours.
+
+API and Bug Fixes:
+
+* ``stlearn.tl.cci.neighbours.calc_neighbours`` returns that sparse matrix instead
+  of a numba ``List``. ``neighbourhood_matrix`` and
+  ``neighbourhoods_from_barcodes`` are removed.
+* ``LRScorer`` takes a sparse matrix. ``get_scores``, ``adjacency`` and
+  ``flatten_neighbours`` are removed from ``stlearn.tl.cci.scoring``.
+* ``st.tl.cci.run_cci`` and ``get_edges`` read the stored graph directly;
+  ``stlearn.tl.cci.neighbours.get_neighbourhoods`` and the edge helpers in
+  ``stlearn.tl.cci.edges`` are removed. ``get_interaction_matrix`` and
+  ``get_interaction_pvals`` take the graph's CSR arrays (``neigh_indptr``,
+  ``neigh_indices``) instead of a numba ``List``.
+* ``get_edges`` no longer deduplicates edges with a quadratic loop: the arrow
+  plots on large neighbourhoods are seconds faster.
+
 1.5.0 (2026-11-01)
 ------------------
 This release contains changes in cell-cell interaction (CCI) mainly

docs/conf.py

@@ -21,7 +21,7 @@
 exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
 
 TUTORIALS_URL = (
-    "https://github.com/GenomicsMachineLearning/stLearn-tutorials/releases/download/V1.5.0/tutorials.zip"
+    "https://github.com/GenomicsMachineLearning/stLearn-tutorials/releases/download/V1.5.1/tutorials.zip"
 )
 
 

docs/index.rst

@@ -38,6 +38,8 @@ undissociated tissue sample.
 Latest Additions
 ----------------
 
+.. include:: release_notes/1.5.1.rst
+
 .. include:: release_notes/1.5.0.rst
 
 .. include:: release_notes/1.4.1.rst

docs/release_notes/1.5.1.rst

@@ -0,0 +1,24 @@
+1.5.1 (2026-11-07)
+~~~~~~~~~~~~~~~~~~
+
+.. rubric:: Features
+
+* ``st.tl.cci.run`` now uses a spots-by-spots, sparse graph:
+  ``adata.obsp["spot_neighbours"]``. It replaces the comma-joined strings
+  ``adata.obsm["spot_neighbours"]`` and ``adata.obsm["spot_neigh_bcs"]``.
+* With ``use_label``, ``run`` counts cell types over the same graph instead of
+  searching the neighbours a second time (``het.count`` takes it as ``neighbours=``).
+* ``st.tl.cache.write_subset_h5ad`` takes ``obsp_keys``, and
+  ``merge_h5ad_into_adata`` copies ``obsp``, so a cached CCI run keeps its neighbours.
+* ``stlearn.tl.cci.neighbours.calc_neighbours`` returns that sparse matrix instead
+  of a numba ``List``. ``neighbourhood_matrix`` and
+  ``neighbourhoods_from_barcodes`` are removed.
+* ``LRScorer`` takes a sparse matrix. ``get_scores``, ``adjacency`` and
+  ``flatten_neighbours`` are removed from ``stlearn.tl.cci.scoring``.
+* ``st.tl.cci.run_cci`` and ``get_edges`` read the stored graph directly;
+  ``stlearn.tl.cci.neighbours.get_neighbourhoods`` and the edge helpers in
+  ``stlearn.tl.cci.edges`` are removed. ``get_interaction_matrix`` and
+  ``get_interaction_pvals`` take the graph's CSR arrays (``neigh_indptr``,
+  ``neigh_indices``) instead of a numba ``List``.
+* ``get_edges`` no longer deduplicates edges with a quadratic loop: the arrow
+  plots on large neighbourhoods are seconds faster.

docs/release_notes/index.rst

@@ -1,6 +1,8 @@
 Release Notes
 ===================================================
 
+.. include:: 1.5.1.rst
+
 .. include:: 1.5.0.rst
 
 .. include:: 1.4.1.rst

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "stlearn"
-version = "1.5.0"
+version = "1.5.1"
 authors = [
     { name = "Genomics and Machine Learning Lab", email = "andrew.newman@uq.edu.au" },
 ]

stlearn/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = """Genomics and Machine Learning Lab"""
 __email__ = "andrew.newman@uq.edu.au"
-__version__ = "1.5.0"
+__version__ = "1.5.1"
 
 from . import add, datasets, em, io, pl, pp, spatial, tl, types, utils
 from ._settings import settings

stlearn/tl/cache/anndata.py

@@ -3,8 +3,8 @@
 import pandas as pd
 
 
-def write_subset_h5ad(adata, filename, obsm_keys=None, uns_keys=None):
-    """Write only specific obsm and uns components to H5AD"""
+def write_subset_h5ad(adata, filename, obsm_keys=None, uns_keys=None, obsp_keys=None):
+    """Write only specific obsm, obsp and uns components to H5AD"""
 
     # Create a minimal AnnData object with the same structure
     minimal_adata = ad.AnnData(
@@ -32,6 +32,14 @@ def write_subset_h5ad(adata, filename, obsm_keys=None, uns_keys=None):
             else:
                 print(f"Warning: uns['{key}'] not found")
 
+    if obsp_keys:
+        for key in obsp_keys:
+            if key in adata.obsp:
+                minimal_adata.obsp[key] = adata.obsp[key]
+                print(f"Added obsp['{key}'] with {adata.obsp[key].nnz} entries")
+            else:
+                print(f"Warning: obsp['{key}'] not found")
+
     minimal_adata.write_h5ad(filename, compression="gzip", compression_opts=9)
     print(f"Wrote subset to {filename}")
 
@@ -48,4 +56,8 @@ def merge_h5ad_into_adata(adata_main, h5ad_file):
         adata_main.uns[key] = value
         print(f"Added uns['{key}']")
 
+    for key, value in adata_subset.obsp.items():
+        adata_main.obsp[key] = value
+        print(f"Added obsp['{key}'] with {value.nnz} entries")
+
     return adata_main