Merge branch 'main' into fix-543

.conda/meta.yaml

@@ -16,12 +16,12 @@ build:
 
 requirements:
  host:
- - python >=3.9
+ - python >=3.10
  - hatchling
  - hatch-vcs
 
  run:
- - python >=3.9
+ - python >=3.10
  - anndata >=0.9
  - awkward >=2.1.0
  - mudata >=0.2.3

.github/workflows/conda.yaml

@@ -22,7 +22,7 @@ jobs:
  matrix:
  include:
  - os: ubuntu-latest
- python: "3.9"
+ python: "3.12"
 
  env:
  OS: ${{ matrix.os }}

.github/workflows/test.yaml

@@ -24,7 +24,7 @@ jobs:
  matrix:
  include:
  - os: ubuntu-latest
- python: "3.9"
+ python: "3.10"
  - os: ubuntu-latest
  python: "3.12"
  - os: ubuntu-latest

.pre-commit-config.yaml

@@ -12,7 +12,7 @@ repos:
  - id: prettier
  exclude: '^\.conda'
  - repo: https://github.com/astral-sh/ruff-pre-commit
- rev: v0.6.1
+ rev: v0.6.2
  hooks:
  - id: ruff
  types_or: [python, pyi, jupyter]

CHANGELOG.md

@@ -23,6 +23,10 @@ and this project adheres to [Semantic Versioning][].
 
 - Fix that pl.clonotype_network couldn't use non-standard obsm key ([#545](https://github.com/scverse/scirpy/pull/545)).
 
+### Other changes
+
+- Drop support for Python 3.9 (in accordance with [SPEC0](https://scientific-python.org/specs/spec-0000/))
+
 ## v0.17.2
 
 ### Fixes

README.md

@@ -47,7 +47,7 @@ Please refer to the [documentation][link-docs]. In particular, the
 
 ## Installation
 
-You need to have Python 3.9 or newer installed on your system. If you don't have
+You need to have Python 3.10 or newer installed on your system. If you don't have
 Python installed, we recommend installing [Mambaforge](https://github.com/conda-forge/miniforge#mambaforge).
 
 There are several alternative options to install scirpy:

docs/tutorials/tutorial_3k_tcr.ipynb

@@ -3048,7 +3048,7 @@
  " method=\"wilcoxon\",\n",
  " )\n",
  " fig, axs = plt.subplots(1, 2, figsize=(8, 4))\n",
- " for ct, ax in zip(clonotypes_top_modularity, axs):\n",
+ " for ct, ax in zip(clonotypes_top_modularity, axs, strict=False):\n",
  " sc.pl.rank_genes_groups_violin(tmp_ad, groups=[ct], n_genes=15, ax=ax, show=False, strip=False)"
  ]
  },

pyproject.toml

@@ -7,7 +7,7 @@ name = 'scirpy'
 dynamic = ["version"]
 description = "Python library for single-cell adaptive immune receptor repertoire (AIRR) analysis"
 readme = "README.md"
-requires-python = '>= 3.9'
+requires-python = '>= 3.10'
 license = {file = "LICENSE"}
 authors = [
  {name = "Gregor Sturm"},
@@ -20,7 +20,7 @@ urls.Documentation = "https://scirpy.readthedocs.io/"
 urls.Source = "https://github.com/scverse/scirpy"
 urls.Home-page = "https://github.com/scverse/scirpy"
 dependencies = [
- 'anndata>=0.9',
+ 'anndata>=0.9,<0.10.9', # TODO remove constraint
  'awkward>=2.1.0',
  'mudata>=0.2.3',
  'scanpy>=1.9.3',

src/scirpy/datasets/_processing_scripts/wu2020.py

@@ -92,7 +92,7 @@ def _load_adata(path):
 adatas = p.map(_load_adata, mtx_paths)
 p.close()
 
-adatas, adatas_airr = zip(*adatas)
+adatas, adatas_airr = zip(*adatas, strict=False)
 
 adata = anndata.concat(adatas)
 

src/scirpy/get/__init__.py

@@ -19,13 +19,13 @@
 @DataHandler.inject_param_docs()
 def airr(
  adata: DataHandler.TYPE,
- airr_variable: Union[str, Sequence[str]],
- chain: Union[ChainType, Sequence[ChainType]] = ("VJ_1", "VDJ_1", "VJ_2", "VDJ_2"),
+ airr_variable: str | Sequence[str],
+ chain: ChainType | Sequence[ChainType] = ("VJ_1", "VDJ_1", "VJ_2", "VDJ_2"),
  *,
  airr_mod: str = "airr",
  airr_key: str = "airr",
  chain_idx_key: str = "chain_indices",
-) -> Union[pd.DataFrame, pd.Series]:
+) -> pd.DataFrame | pd.Series:
  """\
  Retrieve AIRR variables for each cell, given a specific chain.
 
@@ -110,7 +110,7 @@ def _airr_col(
 
 
 @contextmanager
-def obs_context(data: Union[AnnData, MuData], temp_cols: Union[pd.DataFrame, Mapping[str, Any]]):
+def obs_context(data: AnnData | MuData, temp_cols: pd.DataFrame | Mapping[str, Any]):
  """
  Contextmanager that temporarily adds columns to obs.
 
@@ -151,8 +151,8 @@ def obs_context(data: Union[AnnData, MuData], temp_cols: Union[pd.DataFrame, Map
 @DataHandler.inject_param_docs()
 def airr_context(
  data: DataHandler.TYPE,
- airr_variable: Union[str, Sequence[str]],
- chain: Union[ChainType, Sequence[ChainType]] = ("VJ_1", "VDJ_1", "VJ_2", "VDJ_2"),
+ airr_variable: str | Sequence[str],
+ chain: ChainType | Sequence[ChainType] = ("VJ_1", "VDJ_1", "VJ_2", "VDJ_2"),
  *,
  airr_mod: str = "airr",
  airr_key: str = "airr",

src/scirpy/io/_convert_anndata.py

@@ -87,7 +87,7 @@ def to_airr_cells(adata: DataHandler.TYPE, *, airr_mod: str = "airr", airr_key:
  tmp_airr = ak.to_list(params.airr[i : i + CHUNKSIZE])
  tmp_obs = params.adata.obs.iloc[i : i + CHUNKSIZE].to_dict(orient="index")
 
- for (cell_id, row), chains in zip(tmp_obs.items(), tmp_airr):
+ for (cell_id, row), chains in zip(tmp_obs.items(), tmp_airr, strict=False):
  tmp_cell = AirrCell(cast(str, cell_id), logger=logger)
  # add cell-level metadata
  tmp_cell.update(row)

src/scirpy/io/_io.py

@@ -6,7 +6,7 @@
 from collections.abc import Collection, Iterable, Sequence
 from glob import iglob
 from pathlib import Path
-from typing import Any, Union
+from typing import Any
 
 import numpy as np
 import pandas as pd
@@ -46,7 +46,7 @@ def _cdr3_from_junction(junction_aa, junction_nt):
 
 
 def _read_10x_vdj_json(
- path: Union[str, Path],
+ path: str | Path,
  filtered: bool = True,
 ) -> Iterable[AirrCell]:
  """Read IR data from a 10x genomics `all_contig_annotations.json` file"""
@@ -148,7 +148,7 @@ def _read_10x_vdj_json(
 
 
 def _read_10x_vdj_csv(
- path: Union[str, Path],
+ path: str | Path,
  filtered: bool = True,
 ) -> Iterable[AirrCell]:
  """Read IR data from a 10x genomics `_contig_annotations.csv` file"""
@@ -199,7 +199,7 @@ def _read_10x_vdj_csv(
 
 
 @_doc_params(doc_working_model=doc_working_model)
-def read_10x_vdj(path: Union[str, Path], filtered: bool = True, include_fields: Any = None, **kwargs) -> AnnData:
+def read_10x_vdj(path: str | Path, filtered: bool = True, include_fields: Any = None, **kwargs) -> AnnData:
  """\
  Read :term:`AIRR` data from 10x Genomics cell-ranger output.
 
@@ -241,7 +241,7 @@ def read_10x_vdj(path: Union[str, Path], filtered: bool = True, include_fields:
 
 
 @_doc_params(doc_working_model=doc_working_model)
-def read_tracer(path: Union[str, Path], **kwargs) -> AnnData:
+def read_tracer(path: str | Path, **kwargs) -> AnnData:
  """\
  Read data from `TraCeR <https://github.com/Teichlab/tracer>`_ (:cite:`Stubbington2016-kh`).
 
@@ -351,7 +351,7 @@ def _process_chains(chains, chain_type):
  cell_attributes=f"""`({",".join([f'"{x}"' for x in DEFAULT_AIRR_CELL_ATTRIBUTES])})`""",
 )
 def read_airr(
- path: Union[str, Sequence[str], Path, Sequence[Path], pd.DataFrame, Sequence[pd.DataFrame]],
+ path: str | Sequence[str] | Path | Sequence[Path] | pd.DataFrame | Sequence[pd.DataFrame],
  use_umi_count_col: None = None, # deprecated, kept for backwards-compatibility
  infer_locus: bool = True,
  cell_attributes: Collection[str] = DEFAULT_AIRR_CELL_ATTRIBUTES,
@@ -405,8 +405,8 @@ def read_airr(
  airr_cells = {}
  logger = _IOLogger()
 
- if isinstance(path, (str, Path, pd.DataFrame)):
- path: list[Union[str, Path, pd.DataFrame]] = [path] # type: ignore
+ if isinstance(path, str | Path | pd.DataFrame):
+ path: list[str | Path | pd.DataFrame] = [path] # type: ignore
 
  for tmp_path_or_df in path:
  if isinstance(tmp_path_or_df, pd.DataFrame):
@@ -475,7 +475,7 @@ def _infer_locus_from_gene_names(chain_dict, *, keys=("v_call", "d_call", "j_cal
 
 
 @_doc_params(doc_working_model=doc_working_model)
-def read_bracer(path: Union[str, Path], **kwargs) -> AnnData:
+def read_bracer(path: str | Path, **kwargs) -> AnnData:
  """\
  Read data from `BraCeR <https://github.com/Teichlab/bracer>`_ (:cite:`Lindeman2018`).
 
@@ -546,7 +546,7 @@ def read_bracer(path: Union[str, Path], **kwargs) -> AnnData:
  return from_airr_cells(bcr_cells.values(), **kwargs)
 
 
-def write_airr(adata: DataHandler.TYPE, filename: Union[str, Path], **kwargs) -> None:
+def write_airr(adata: DataHandler.TYPE, filename: str | Path, **kwargs) -> None:
  """Export :term:`IR` data to :term:`AIRR` Rearrangement `tsv` format.
 
  Parameters
@@ -636,7 +636,7 @@ def from_dandelion(dandelion, transfer: bool = False, to_mudata: bool = False, *
 
 
 @_doc_params(doc_working_model=doc_working_model)
-def read_bd_rhapsody(path: Union[str, Path], **kwargs) -> AnnData:
+def read_bd_rhapsody(path: str | Path, **kwargs) -> AnnData:
  """\
  Read :term:`IR` data from the BD Rhapsody Analysis Pipeline.
 

src/scirpy/ir_dist/__init__.py

@@ -34,10 +34,10 @@ def IrNeighbors(*args, **kwargs):
  )
 
 
-MetricType = Union[
- Literal["alignment", "fastalignment", "identity", "levenshtein", "hamming", "normalized_hamming", "tcrdist"],
- metrics.DistanceCalculator,
-]
+MetricType = (
+ Literal["alignment", "fastalignment", "identity", "levenshtein", "hamming", "normalized_hamming", "tcrdist"]
+ | metrics.DistanceCalculator
+)
 
 _doc_metrics = """\
 metric
@@ -77,7 +77,7 @@ def _get_metric_key(metric: MetricType) -> str:
  return "custom" if isinstance(metric, metrics.DistanceCalculator) else metric # type: ignore
 
 
-def _get_distance_calculator(metric: MetricType, cutoff: Union[int, None], *, n_jobs=-1, **kwargs):
+def _get_distance_calculator(metric: MetricType, cutoff: int | None, *, n_jobs=-1, **kwargs):
  """Returns an instance of :class:`~scirpy.ir_dist.metrics.DistanceCalculator`
  given a metric.
 
@@ -116,12 +116,12 @@ def _get_distance_calculator(metric: MetricType, cutoff: Union[int, None], *, n_
 @DataHandler.inject_param_docs(metric=_doc_metrics, cutoff=_doc_cutoff, dist_mat=metrics._doc_dist_mat)
 def _ir_dist(
  adata: DataHandler.TYPE,
- reference: Optional[DataHandler.TYPE] = None,
+ reference: DataHandler.TYPE | None = None,
  *,
  metric: MetricType = "identity",
- cutoff: Union[int, None] = None,
+ cutoff: int | None = None,
  sequence: Literal["aa", "nt"] = "nt",
- key_added: Union[str, None] = None,
+ key_added: str | None = None,
  inplace: bool = True,
  n_jobs: int = -1,
  airr_mod: str = "airr",
@@ -131,7 +131,7 @@ def _ir_dist(
  airr_key_ref: str = "airr",
  chain_idx_key_ref: str = "chain_indices",
  **kwargs,
-) -> Union[dict, None]:
+) -> dict | None:
  """\
  Computes a sequence-distance metric between all unique :term:`VJ <Chain locus>`
  :term:`CDR3` sequences and between all unique :term:`VDJ <Chain locus>`
@@ -257,10 +257,10 @@ def _get_unique_seqs(tmp_adata, chain_type):
 @_doc_params(metric=_doc_metrics, cutoff=_doc_cutoff, dist_mat=metrics._doc_dist_mat)
 def sequence_dist(
  seqs: Sequence[str],
- seqs2: Optional[Sequence[str]] = None,
+ seqs2: Sequence[str] | None = None,
  *,
  metric: MetricType = "identity",
- cutoff: Union[None, int] = None,
+ cutoff: None | int = None,
  n_jobs: int = -1,
  **kwargs,
 ) -> csr_matrix:

src/scirpy/ir_dist/_clonotype_neighbors.py

@@ -1,6 +1,6 @@
 import itertools
 from collections.abc import Mapping, Sequence
-from typing import Literal, Optional, Union
+from typing import Literal
 
 import numpy as np
 import pandas as pd
@@ -19,12 +19,12 @@ class ClonotypeNeighbors:
  def __init__(
  self,
  params: DataHandler,
- params2: Optional[DataHandler] = None,
+ params2: DataHandler | None = None,
  *,
  receptor_arms: Literal["VJ", "VDJ", "all", "any"],
  dual_ir: Literal["primary_only", "all", "any"],
  same_v_gene: bool = False,
- match_columns: Union[None, Sequence[str]] = None,
+ match_columns: None | Sequence[str] = None,
  distance_key: str,
  sequence_key: str,
  n_jobs: int = -1,

src/scirpy/ir_dist/_util.py

@@ -2,7 +2,7 @@
 from collections.abc import Hashable, Mapping, Sequence
 from functools import reduce
 from operator import mul
-from typing import Literal, Optional, Union
+from typing import Literal
 
 import numpy as np
 import pandas as pd
@@ -46,7 +46,7 @@ def merge_coo_matrices(mats: Sequence[coo_matrix], shape=None) -> coo_matrix:
  if not len(mats) or shape is None or reduce(mul, shape) == 0:
  return coo_matrix((0, 0) if shape is None else shape)
 
- data, row, col = zip(*((x.data, x.row, x.col) for x in mats))
+ data, row, col = zip(*((x.data, x.row, x.col) for x in mats), strict=False)
 
  return sp.coo_matrix((np.hstack(data), (np.hstack(row), np.hstack(col))), shape=shape)
 
@@ -174,7 +174,7 @@ def __getitem__(self, i):
 
 
 class DoubleLookupNeighborFinder:
- def __init__(self, feature_table: pd.DataFrame, feature_table2: Optional[pd.DataFrame] = None):
+ def __init__(self, feature_table: pd.DataFrame, feature_table2: pd.DataFrame | None = None):
  """
  A datastructure to efficiently retrieve distances based on different features.
 
@@ -235,8 +235,8 @@ def lookup(
  self,
  object_id: int,
  forward_lookup_table: str,
- reverse_lookup_table: Union[str, None] = None,
- ) -> Union[coo_matrix, np.ndarray]:
+ reverse_lookup_table: str | None = None,
+ ) -> coo_matrix | np.ndarray:
  """Get ids of neighboring objects from a lookup table.
 
  Performs the following lookup:
@@ -285,7 +285,7 @@ def lookup(
  # ... and get column indices directly from sparse row
  # sum concatenates coo matrices
  return merge_coo_matrices(
- (reverse[i] * multiplier for i, multiplier in zip(row.indices, row.data)), # type: ignore
+ (reverse[i] * multiplier for i, multiplier in zip(row.indices, row.data, strict=False)), # type: ignore
  shape=(1, reverse.size),
  )
 
@@ -294,7 +294,7 @@ def add_distance_matrix(
  name: str,
  distance_matrix: sp.csr_matrix,
  labels: Sequence,
- labels2: Optional[Sequence] = None,
+ labels2: Sequence | None = None,
  ):
  """Add a distance matrix.