pertpy 0.9.4__tar.gz → 0.10.0__tar.gz

{pertpy-0.9.4 → pertpy-0.10.0}/.github/pull_request_template.md

@@ -4,9 +4,9 @@
 
 <!-- Please fill in the appropriate checklist below (delete whatever is not relevant). These are the most common things requested on pull requests (PRs). -->
 
--   [ ] Referenced issue is linked
--   [ ] If you've fixed a bug or added code that should be tested, add tests!
--   [ ] Documentation in `docs` is updated
+- [ ] Referenced issue is linked
+- [ ] If you've fixed a bug or added code that should be tested, add tests!
+- [ ] Documentation in `docs` is updated
 
 **Description of changes**
 

{pertpy-0.9.4 → pertpy-0.10.0}/.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: "0.9.4 🌈"
-tag-template: 0.9.4
+name-template: "0.10.0 🌈"
+tag-template: 0.10.0
 exclude-labels:
     - "skip-changelog"
 

{pertpy-0.9.4 → pertpy-0.10.0}/.github/workflows/build.yml

@@ -16,10 +16,10 @@ jobs:
         steps:
             - uses: actions/checkout@v4
 
-            - name: Set up Python 3.11
+            - name: Set up Python
               uses: actions/setup-python@v5
               with:
-                  python-version: "3.11"
+                  python-version: "3.12"
                   cache: "pip"
                   cache-dependency-path: "**/pyproject.toml"
 

{pertpy-0.9.4 → pertpy-0.10.0}/.github/workflows/release.yml

@@ -13,10 +13,10 @@ jobs:
             - name: Checkout code
               uses: actions/checkout@v4
 
-            - name: Set up Python 3.11
+            - name: Set up Python 3.12
               uses: actions/setup-python@v5
               with:
-                  python-version: "3.11"
+                  python-version: "3.12"
 
             - name: Install hatch
               run: pip install hatch

{pertpy-0.9.4 → pertpy-0.10.0}/.github/workflows/test.yml

@@ -21,19 +21,16 @@ jobs:
             fail-fast: false
             matrix:
                 include:
-                    - os: ubuntu-latest
-                      python: "3.10"
-                      run_mode: "slow"
-                    - os: ubuntu-latest
+                    - os: ubuntu-22.04 # ubuntu-latest is currently broken for joblib
                       python: "3.12"
                       run_mode: "slow"
-#                    - os: ubuntu-latest
-#                      python: "3.12"
-#                      run_mode: "fast"
-#                    - os: ubuntu-latest
-#                      python: "3.12"
-#                      run_mode: slow
-#                      pip-flags: "--pre"
+                    - os: ubuntu-22.04
+                      python: "3.12"
+                      run_mode: "fast"
+                    # - os: ubuntu-latest
+                    #   python: "3.12"
+                    #   run_mode: slow
+                    #   pip-flags: "--pre"
 
         env:
             OS: ${{ matrix.os }}

{pertpy-0.9.4 → pertpy-0.10.0}/.gitignore

@@ -137,6 +137,9 @@ dmypy.json
 # Jetbrains IDE
 .idea/
 
+# VSCode
+.vscode
+
 # Coala
 *.orig
 
@@ -155,3 +158,11 @@ lightning_logs/*
 */lightning_logs/*
 
 node_modules
+
+# lamindb
+test.ipynb
+test-perturbation
+test-bug
+
+# uv
+uv.lock

{pertpy-0.9.4 → pertpy-0.10.0}/.pre-commit-config.yaml

@@ -2,8 +2,8 @@ fail_fast: false
 default_language_version:
     python: python3
 default_stages:
-    - commit
-    - push
+    - pre-commit
+    - pre-push
 minimum_pre_commit_version: 2.16.0
 repos:
     - repo: https://github.com/pre-commit/mirrors-prettier
@@ -11,7 +11,7 @@ repos:
       hooks:
           - id: prettier
     - repo: https://github.com/astral-sh/ruff-pre-commit
-      rev: v0.4.7
+      rev: v0.8.6
       hooks:
           - id: ruff
             args: [--fix, --exit-non-zero-on-fix, --unsafe-fixes]
@@ -27,12 +27,12 @@ repos:
           - id: trailing-whitespace
           - id: check-case-conflict
     - repo: https://github.com/pre-commit/mirrors-mypy
-      rev: v1.10.0
+      rev: v1.14.1
       hooks:
           - id: mypy
             args: [--no-strict-optional, --ignore-missing-imports]
             additional_dependencies:
-                ["types-pkg-resources", "types-requests", "types-attrs"]
+                ["types-setuptools", "types-requests", "types-attrs"]
     - repo: local
       hooks:
           - id: forbid-to-commit

pertpy-0.10.0/.readthedocs.yml

@@ -0,0 +1,18 @@
+version: 2
+build:
+    os: ubuntu-24.04
+    tools:
+        python: "3.12"
+    commands:
+        - asdf plugin add uv
+        - asdf install uv latest
+        - asdf global uv latest
+        - uv venv
+        - uv pip install .[doc,coda,de]
+        - .venv/bin/python -m sphinx -T -b html -d docs/_build/doctrees -D language=en docs $READTHEDOCS_OUTPUT/html
+sphinx:
+    configuration: docs/conf.py
+    fail_on_warning: false
+
+submodules:
+    include: all

{pertpy-0.9.4 → pertpy-0.10.0}/CODE_OF_CONDUCT.md

@@ -14,23 +14,23 @@ religion, or sexual identity and orientation.
 Examples of behavior that contributes to creating a positive environment
 include:
 
--   Using welcoming and inclusive language
--   Being respectful of differing viewpoints and experiences
--   Gracefully accepting constructive criticism
--   Focusing on what is best for the community
--   Showing empathy towards other community members
+- Using welcoming and inclusive language
+- Being respectful of differing viewpoints and experiences
+- Gracefully accepting constructive criticism
+- Focusing on what is best for the community
+- Showing empathy towards other community members
 
 Examples of unacceptable behavior by participants include:
 
--   The use of sexualized language or imagery and unwelcome sexual
-    attention or advances
--   Trolling, insulting/derogatory comments, and personal or political
-    attacks
--   Public or private harassment
--   Publishing others’ private information, such as a physical or
-    electronic address, without explicit permission
--   Other conduct which could reasonably be considered inappropriate in a
-    professional setting
+- The use of sexualized language or imagery and unwelcome sexual
+  attention or advances
+- Trolling, insulting/derogatory comments, and personal or political
+  attacks
+- Public or private harassment
+- Publishing others’ private information, such as a physical or
+  electronic address, without explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
 
 ## Our Responsibilities
 

{pertpy-0.9.4 → pertpy-0.10.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: pertpy
-Version: 0.9.4
+Version: 0.10.0
 Summary: Perturbation Analysis in the scverse ecosystem.
 Project-URL: Documentation, https://pertpy.readthedocs.io
 Project-URL: Source, https://github.com/scverse/pertpy
@@ -44,9 +44,8 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: Topic :: Scientific/Engineering :: Visualization
-Requires-Python: >=3.10
+Requires-Python: <3.13,>=3.10
 Requires-Dist: adjusttext
-Requires-Dist: anndata<0.10.9
 Requires-Dist: blitzgsea
 Requires-Dist: decoupler
 Requires-Dist: lamin-utils
@@ -58,8 +57,8 @@ Requires-Dist: pyarrow
 Requires-Dist: requests
 Requires-Dist: rich
 Requires-Dist: scanpy[leiden]
+Requires-Dist: scikit-learn>=1.4
 Requires-Dist: scikit-misc
-Requires-Dist: scipy
 Requires-Dist: scvi-tools
 Requires-Dist: sparsecca
 Provides-Extra: coda
@@ -69,7 +68,8 @@ Requires-Dist: pyqt5; extra == 'coda'
 Requires-Dist: toytree; extra == 'coda'
 Provides-Extra: de
 Requires-Dist: formulaic; extra == 'de'
-Requires-Dist: pydeseq2; extra == 'de'
+Requires-Dist: formulaic-contrasts>=0.2.0; extra == 'de'
+Requires-Dist: pydeseq2>=v0.5.0pre1; extra == 'de'
 Provides-Extra: dev
 Requires-Dist: pre-commit; extra == 'dev'
 Provides-Extra: doc

{pertpy-0.9.4 → pertpy-0.10.0}/docs/conf.py

@@ -195,4 +195,7 @@ nbsphinx_thumbnails = {
     "tutorials/notebooks/differential_gene_expression": "_static/tutorials/dge.png",
     "tutorials/notebooks/metadata_annotation": "_static/tutorials/metadata.png",
     "tutorials/notebooks/ontology_mapping": "_static/tutorials/ontology.png",
+    "tutorials/notebooks/norman_use_case": "_static/tutorials/norman.png",
+    "tutorials/notebooks/mcfarland_use_case": "_static/tutorials/mcfarland.png",
+    "tutorials/notebooks/zhang_use_case": "_static/tutorials/zhang.png",
 }

{pertpy-0.9.4 → pertpy-0.10.0}/docs/contributing.md

@@ -132,11 +132,11 @@ in the cookiecutter-scverse template.
 
 Please write documentation for new or changed features and use-cases. This project uses [sphinx][] with the following features:
 
--   the [myst][] extension allows to write documentation in markdown/Markedly Structured Text
--   Google-style docstrings
--   Jupyter notebooks as tutorials through [myst-nb][] (See [Tutorials with myst-nb](#tutorials-with-myst-nb-and-jupyter-notebooks))
--   [Sphinx autodoc typehints][], to automatically reference annotated input and output types
--   Citations (like {cite:p}`Virshup_2023`) can be included with [sphinxcontrib-bibtex](https://sphinxcontrib-bibtex.readthedocs.io/)
+- the [myst][] extension allows to write documentation in markdown/Markedly Structured Text
+- Google-style docstrings
+- Jupyter notebooks as tutorials through [myst-nb][] (See [Tutorials with myst-nb](#tutorials-with-myst-nb-and-jupyter-notebooks))
+- [Sphinx autodoc typehints][], to automatically reference annotated input and output types
+- Citations (like {cite:p}`Virshup_2023`) can be included with [sphinxcontrib-bibtex](https://sphinxcontrib-bibtex.readthedocs.io/)
 
 See the [scanpy developer docs](https://scanpy.readthedocs.io/en/latest/dev/documentation.html) for more information
 on how to write documentation.
@@ -150,10 +150,10 @@ These notebooks come from [pert-tutorials](https://github.com/scverse/pertpy-tut
 
 #### Hints
 
--   If you refer to objects from other packages, please add an entry to `intersphinx_mapping` in `docs/conf.py`. Only
-    if you do so can sphinx automatically create a link to the external documentation.
--   If building the documentation fails because of a missing link that is outside your control, you can add an entry to
-    the `nitpick_ignore` list in `docs/conf.py`
+- If you refer to objects from other packages, please add an entry to `intersphinx_mapping` in `docs/conf.py`. Only
+  if you do so can sphinx automatically create a link to the external documentation.
+- If building the documentation fails because of a missing link that is outside your control, you can add an entry to
+  the `nitpick_ignore` list in `docs/conf.py`
 
 #### Building the docs locally
 

{pertpy-0.9.4 → pertpy-0.10.0}/docs/index.md

@@ -54,8 +54,12 @@ Discussions <https://github.com/scverse/pertpy/discussions>
 references
 ```
 
--   Consider citing [scanpy Genome Biology (2018)] along with original {doc}`references <references>`.
--   A paper for pertpy is in the works.
+## Citation
+
+[Lukas Heumos, Yuge Ji, Lilly May, Tessa Green, Xinyue Zhang, Xichen Wu, Johannes Ostner, Stefan Peidli, Antonia Schumacher, Karin Hrovatin, Michaela Mueller, Faye Chong, Gregor Sturm, Alejandro Tejada, Emma Dann, Mingze Dong, Mojtaba Bahrami, Ilan Gold, Sergei Rybakov, Altana Namsaraeva, Amir Ali Moinfar, Zihe Zheng, Eljas Roellin, Isra Mekki, Chris Sander, Mohammad Lotfollahi, Herbert B. Schiller, Fabian J. Theis
+bioRxiv 2024.08.04.606516; doi: https://doi.org/10.1101/2024.08.04.606516](https://www.biorxiv.org/content/10.1101/2024.08.04.606516v1)
+
+Consider citing [scanpy Genome Biology (2018)] along with the original {doc}`references <references>`.
 
 # Indices and tables
 

{pertpy-0.9.4 → pertpy-0.10.0}/docs/tutorials/index.md

@@ -11,13 +11,25 @@ Many are also designed to work seamlessly in Google colab.
 For questions about the usage of pertpy use the [scverse discourse](https://discourse.scverse.org/).
 :::
 
-## Quick start
+## Quick start: Tool specific tutorials
+
+### Data transformation
 
 ```{eval-rst}
 .. nbgallery::
 
    notebooks/guide_rna_assignment
    notebooks/mixscape
+   notebooks/perturbation_space
+   notebooks/metadata_annotation
+   notebooks/ontology_mapping
+```
+
+### Knowledge inference
+
+```{eval-rst}
+.. nbgallery::
+
    notebooks/augur
    notebooks/sccoda
    notebooks/sccoda_extended
@@ -29,13 +41,24 @@ For questions about the usage of pertpy use the [scverse discourse](https://disc
    notebooks/distance_tests
    notebooks/cinemaot
    notebooks/scgen_perturbation_prediction
-   notebooks/perturbation_space
    notebooks/differential_gene_expression
-   notebooks/metadata_annotation
-   notebooks/ontology_mapping
 ```
 
-### Glossary
+## Use cases
+
+Our use cases showcase a variety of pertpy tools applied to one dataset.
+They are designed to give you a sense of how to use pertpy in a real-world scenario.
+The use cases featured here are those we present in the pertpy [preprint](https://www.biorxiv.org/content/10.1101/2024.08.04.606516v1).
+
+```{eval-rst}
+.. nbgallery::
+
+   notebooks/norman_use_case
+   notebooks/mcfarland_use_case
+   notebooks/zhang_use_case
+```
+
+## Glossary
 
 ```{eval-rst}
 .. tab-set::

{pertpy-0.9.4 → pertpy-0.10.0}/docs/usage/usage.md

@@ -563,9 +563,9 @@ including cell line annotation, bulk RNA and protein expression data.
 
 Available databases for cell line metadata:
 
--   [The Cancer Dependency Map Project at Broad](https://depmap.org/portal/)
--   [The Cancer Dependency Map Project at Sanger](https://depmap.sanger.ac.uk/)
--   [Genomics of Drug Sensitivity in Cancer (GDSC)](https://www.cancerrxgene.org/)
+- [The Cancer Dependency Map Project at Broad](https://depmap.org/portal/)
+- [The Cancer Dependency Map Project at Sanger](https://depmap.sanger.ac.uk/)
+- [Genomics of Drug Sensitivity in Cancer (GDSC)](https://www.cancerrxgene.org/)
 
 ### Compound
 
@@ -573,7 +573,7 @@ The Compound module enables the retrieval of various types of information relate
 
 Available databases for compound metadata:
 
--   [PubChem](https://pubchem.ncbi.nlm.nih.gov/)
+- [PubChem](https://pubchem.ncbi.nlm.nih.gov/)
 
 ### Mechanism of Action
 
@@ -581,7 +581,7 @@ This module aims to retrieve metadata of mechanism of action studies related to
 
 Available databases for mechanism of action metadata:
 
--   [CLUE](https://clue.io/)
+- [CLUE](https://clue.io/)
 
 ### Drug
 
@@ -589,7 +589,7 @@ This module allows for the retrieval of Drug target information.
 
 Available databases for drug metadata:
 
--   [chembl](https://www.ebi.ac.uk/chembl/)
+- [chembl](https://www.ebi.ac.uk/chembl/)
 
 ```{eval-rst}
 .. autosummary::

{pertpy-0.9.4 → pertpy-0.10.0}/pertpy/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = "Lukas Heumos"
 __email__ = "lukas.heumos@posteo.net"
-__version__ = "0.9.4"
+__version__ = "0.10.0"
 
 import warnings
 

pertpy-0.10.0/pertpy/_doc.py

@@ -0,0 +1,19 @@
+from textwrap import dedent
+
+
+def _doc_params(**kwds):  # pragma: no cover
+    """\
+    Docstrings should start with "\" in the first line for proper formatting.
+    """
+
+    def dec(obj):
+        obj.__orig_doc__ = obj.__doc__
+        obj.__doc__ = dedent(obj.__doc__.format_map(kwds))
+        return obj
+
+    return dec
+
+
+doc_common_plot_args = """\
+return_fig: if `True`, returns figure of the plot, that can be used for saving.\
+"""

{pertpy-0.9.4 → pertpy-0.10.0}/pertpy/data/_datasets.py

@@ -66,7 +66,7 @@ def sc_sim_augur() -> AnnData:  # pragma: no cover
     output_file_path = settings.datasetdir / output_file_name
     if not Path(output_file_path).exists():
         _download(
-            url="https://figshare.com/ndownloader/files/31645886",
+            url="https://figshare.com/ndownloader/files/49828902",
             output_file_name=output_file_name,
             output_path=settings.datasetdir,
             is_zip=False,

{pertpy-0.9.4 → pertpy-0.10.0}/pertpy/metadata/_cell_line.py

@@ -8,12 +8,15 @@ from lamin_utils import logger
 if TYPE_CHECKING:
     from collections.abc import Iterable
 
+    from matplotlib.pyplot import Figure
+
 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
 from scanpy import settings
 from scipy import stats
 
+from pertpy._doc import _doc_params, doc_common_plot_args
 from pertpy.data._dataloader import _download
 
 from ._look_up import LookUp
@@ -338,8 +341,8 @@ class CellLine(MetaData):
         # then we can compare these keys and fetch the corresponding metadata.
         if query_id not in adata.obs.columns:
             raise ValueError(
-                f"The specified `query_id` {query_id} can't be found in the `adata.obs`.\n"
-                "Ensure that you are using one of the available query IDs present in the adata.obs for the annotation.\n"
+                f"The specified `query_id` {query_id} can't be found in the `adata.obs`. \n"
+                "Ensure that you are using one of the available query IDs present in the adata.obs for the annotation."
                 "If the desired query ID is not available, you can fetch the cell line metadata "
                 "using the `annotate()` function before calling 'annotate_bulk_rna()'. "
                 "This ensures that the required query ID is included in your data, e.g. stripped_cell_line_name, DepMap ID."
@@ -356,9 +359,8 @@ class CellLine(MetaData):
         else:
             reference_id = "DepMap_ID"
             logger.warning(
-                "To annotate bulk RNA data from Broad Institue, `DepMap_ID` is used as default reference and query identifier if no `reference_id` is given.\n"
-                "Ensure that `DepMap_ID` is available in 'adata.obs'.\n"
-                "Alternatively, use `annotate()` to annotate the cell line first "
+                "To annotate bulk RNA data from Broad Institue, `DepMap_ID` is used as default reference and query identifier if no `reference_id` is given."
+                "If `DepMap_ID` isn't available in 'adata.obs', use `annotate()` to annotate the cell line first."
             )
             if self.bulk_rna_broad is None:
                 self._download_bulk_rna(cell_line_source="broad")
@@ -690,6 +692,7 @@ class CellLine(MetaData):
 
         return corr, pvals, new_corr, new_pvals
 
+    @_doc_params(common_plot_args=doc_common_plot_args)
     def plot_correlation(
         self,
         adata: AnnData,
@@ -700,7 +703,8 @@ class CellLine(MetaData):
         metadata_key: str = "bulk_rna_broad",
         category: str = "cell line",
         subset_identifier: str | int | Iterable[str] | Iterable[int] | None = None,
-    ) -> None:
+        return_fig: bool = False,
+    ) -> Figure | None:
         """Visualise the correlation of cell lines with annotated metadata.
 
         Args:
@@ -713,6 +717,8 @@ class CellLine(MetaData):
             subset_identifier: Selected identifiers for scatter plot visualization between the X matrix and `metadata_key`.
                               If not None, only the chosen cell line will be plotted, either specified as a value in `identifier` (string) or as an index number.
                               If None, all cell lines will be plotted.
+            {common_plot_args}
+
         Returns:
             Pearson correlation coefficients and their corresponding p-values for matched and unmatched cell lines separately.
         """
@@ -740,7 +746,7 @@ class CellLine(MetaData):
                 if all(isinstance(id, str) for id in subset_identifier_list):
                     if set(subset_identifier_list).issubset(adata.obs[identifier].unique()):
                         subset_identifier_list = np.where(
-                            np.in1d(adata.obs[identifier].values, subset_identifier_list)
+                            np.isin(adata.obs[identifier].values, subset_identifier_list)
                         )[0]
                     else:
                         raise ValueError("`Subset_identifier` must be found in adata.obs.`identifier`.")
@@ -790,6 +796,10 @@ class CellLine(MetaData):
                     "edgecolor": "black",
                 },
             )
+
+            if return_fig:
+                return plt.gcf()
             plt.show()
+            return None
         else:
-            raise NotImplementedError
+            raise NotImplementedError("Only 'cell line' category is supported for correlation comparison.")

{pertpy-0.9.4 → pertpy-0.10.0}/pertpy/metadata/_compound.py

@@ -42,7 +42,7 @@ class Compound(MetaData):
             adata = adata.copy()
 
         if query_id not in adata.obs.columns:
-            raise ValueError(f"The requested query_id {query_id} is not in `adata.obs`.\n" f"Please check again. ")
+            raise ValueError(f"The requested query_id {query_id} is not in `adata.obs`.\n Please check again.")
 
         query_dict = {}
         not_matched_identifiers = []
@@ -84,7 +84,7 @@ class Compound(MetaData):
         query_df = pd.DataFrame.from_dict(query_dict, orient="index", columns=["pubchem_name", "pubchem_ID", "smiles"])
         # Merge and remove duplicate columns
         # Column is converted to float after merging due to unmatches
-        # Convert back to integers
+        # Convert back to integers afterwards
         if query_id_type == "cid":
             query_df.pubchem_ID = query_df.pubchem_ID.astype("Int64")
             adata.obs = (
@@ -119,8 +119,7 @@ class Compound(MetaData):
 
         The LookUp object provides an overview of the metadata to annotate.
         Each annotate_{metadata} function has a corresponding lookup function in the LookUp object,
-        where users can search the reference_id in the metadata and
-        compare with the query_id in their own data.
+        where users can search the reference_id in the metadata and compare with the query_id in their own data.
 
         Returns:
             Returns a LookUp object specific for compound annotation.

{pertpy-0.9.4 → pertpy-0.10.0}/pertpy/metadata/_metadata.py

@@ -62,7 +62,7 @@ class MetaData:
             if verbosity > 0:
                 logger.info(
                     f"There are {total_identifiers} identifiers in `adata.obs`."
-                    f"However, {len(unmatched_identifiers)} identifiers can't be found in the {metadata_type} annotation,"
+                    f"However, {len(unmatched_identifiers)} identifiers can't be found in the {metadata_type} annotation, "
                     "leading to the presence of NA values for their respective metadata.\n"
                     f"Please check again: *unmatched_identifiers[:verbosity]..."
                 )