minor

README.md

@@ -6,6 +6,9 @@ SnapATAC2: A Python/Rust package for single-cell epigenomics analysis
 ![Continuous integration](https://github.com/kaizhang/SnapATAC2/workflows/test-python-package/badge.svg)
 ![GitHub Repo stars](https://img.shields.io/github/stars/kaizhang/SnapATAC2?style=social)
 
+> [!TIP]
+> Got raw fastq files? Check out our new single-cell preprocessing package [precellar](https://github.com/regulatory-genomics/precellar)!
+
 SnapATAC2 is a flexible, versatile, and scalable single-cell omics analysis framework, featuring:
 
 - Scale to more than 10 million cells.

docs/changelog.md

@@ -7,6 +7,10 @@
   - Support python 3.13.
   - Add Zarr backend support for AnnData.
 
+### Breaking Changes:
+
+  - `pp.import_data` is removed in favor of `pp.import_fragments`.
+
 ## Release 2.8.0 (released December 13, 2024)
 
 ### Features:

snapatac2-python/python/snapatac2/export/__init__.py

@@ -88,7 +88,7 @@ def export_coverage(
     exclude_for_norm: list[str] | Path = None,
     min_frag_length: int | None = None,
     max_frag_length: int | None = 2000,
-    counting_strategy: Literal['fragment', 'insertion', 'paired-insertion'] = 'fragment',
+    counting_strategy: Literal['fragment', 'insertion'] = 'fragment',
     smooth_base: int | None = None,
     out_dir: Path = "./",
     prefix: str = "",
@@ -149,14 +149,10 @@ def export_coverage(
         Maximum fragment length to be included in the computation.
     counting_strategy
         The strategy to compute feature counts. It must be one of the following:
-        "fragment", "insertion", or "paired-insertion". "fragment" means the
+        "fragment" or "insertion". "fragment" means the
         feature counts are assigned based on the number of fragments that overlap
         with a region of interest. "insertion" means the feature counts are assigned
         based on the number of insertions that overlap with a region of interest.
-        "paired-insertion" is similar to "insertion", but it only counts the insertions
-        once if the pair of insertions of a fragment are both within the same region
-        of interest [Miao24]_.
-        Note that this parameter has no effect if input are single-end reads.
     smooth_base
         Length of the smoothing window in bases for the output of the bigwig/bedgraph file.
     out_dir

snapatac2-python/python/snapatac2/preprocessing/_mnn_correct.py

@@ -29,7 +29,9 @@ def mnc_correct(
     data
         Matrice or AnnData object. Matrices should be shaped like n_obs x n_vars.
     batch
-        Batch labels for cells. If a string, labels will be obtained from `obs`.
+        Batch labels for cells, stored as a list of strings, where each string
+        corresponds to the batch label for a cell. Alternatively, `batch` can be
+        a string, and in this case labels will be obtained from `.obs[`batch`]`.
     n_neighbors
         Number of mutual nearest neighbors.
     n_clusters
@@ -70,6 +72,10 @@ def mnc_correct(
 
     if isinstance(batch, str):
         batch = adata.obs[batch]
+    elif isinstance(batch, list):
+        assert len(batch) == mat.shape[0], "When `batch` is a list of strings,  \
+            it is interpreted as the batch labels of cells and it must \
+            have the same length as the number of cells."
 
     if groupby is None:
         mat = _mnc_correct_main(mat, batch, n_iter, n_neighbors, n_clusters)