MAINT: build Python 3.14 wheels; fix to_anndata for anndata 0.13 (#1005)

* MAINT: build Python 3.14 wheels

#1004 upgraded cibuildwheel to a version that supports 3.14, but the
build selector in pyproject.toml still listed cp39-cp313, so no cp314
wheels were produced. Add cp314-* to the selector.

Also note the in1d -> isin fix (#1003) in the ChangeLog.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* BUG: to_anndata fails with anndata >= 0.13

anndata 0.13.0 removed the dtype argument to AnnData(), so
Table.to_anndata() raised TypeError. Cast the matrix before
constructing the AnnData object instead. This also removes the
FutureWarning older anndata versions emitted for dtype=.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

Author: wasade

ChangeLog.md

@@ -7,6 +7,12 @@ biom-2.1.18-dev
 Bug fixes:
 
 * A regression with parse of UTF-8 characters was introduced, reported [here](https://forum.qiime2.org/t/feature-table-gives-ascii-codec-cant-decode-byte-0xc3-in-position-4-error/33858/7)
+* `np.in1d` was removed in NumPy 2.4, replaced with `np.isin`. See issue [#1003](https://github.com/biocore/biom-format/issues/1003)
+* `Table.to_anndata` failed with anndata >= 0.13, which removed the `dtype` argument to `AnnData`. The matrix is now cast prior to construction. See PR [#1005](https://github.com/biocore/biom-format/pull/1005)
+
+General Maintenance:
+
+* Python 3.14 added to CI and wheels are now built for Python 3.14. See PR [#1004](https://github.com/biocore/biom-format/pull/1004)
 
 biom-2.1.17
 -----------

biom/table.py

@@ -4397,10 +4397,13 @@ def to_anndata(self, dense=False, dtype="float32", transpose=True):
         if dense:
             mat = mat.toarray()
 
+        # anndata 0.13 removed the AnnData(dtype=...) argument
+        mat = mat.astype(dtype)
+
         var = self.metadata_to_dataframe("sample")
         obs = self.metadata_to_dataframe("observation")
 
-        adata = anndata.AnnData(mat, obs=obs, var=var, dtype=dtype)
+        adata = anndata.AnnData(mat, obs=obs, var=var)
         # Convention for scRNA-seq analysis in Python
         adata = adata.transpose()
 

pyproject.toml

@@ -84,7 +84,7 @@ test-requires = ["pytest", "numpy"]
 skip = ["*-win32", "*-manylinux_i686", "pp*", "*-musllinux*"]
 
 # Python versions to build
-build = "cp39-* cp310-* cp311-* cp312-* cp313-*"
+build = "cp39-* cp310-* cp311-* cp312-* cp313-* cp314-*"
 
 [tool.pytest.ini_options]
 addopts = ["--ignore=biom/assets/exercise_api.py "]