Merge branch 'development' into implement_additional_distance_metrics

.cookietemple.yml

@@ -15,5 +15,5 @@ full_name: Lukas Heumos
 email: [email protected]
 project_name: pertpy
 project_short_description: Perturbation Analysis in the Scanpy ecosystem.
-version: 0.5.0
+version: 0.6.0
 license: MIT

.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: "0.5.0 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
-tag-template: 0.5.0 # <<COOKIETEMPLE_FORCE_BUMP>>
+name-template: "0.6.0 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
+tag-template: 0.6.0 # <<COOKIETEMPLE_FORCE_BUMP>>
 exclude-labels:
     - "skip-changelog"
 

.github/workflows/build_package.yml

@@ -9,7 +9,7 @@ jobs:
         strategy:
             matrix:
                 os: [macos-latest, ubuntu-latest]
-                python: ["3.8", "3.10"]
+                python: ["3.9", "3.10"]
 
         steps:
             - uses: actions/checkout@v3

.github/workflows/publish_package.yml

@@ -18,7 +18,7 @@ jobs:
             - name: Set up Python
               uses: actions/setup-python@v4
               with:
-                  python-version: "3.10"
+                  python-version: "3.11"
 
             - name: Install Poetry
               run: |
@@ -30,7 +30,7 @@ jobs:
                   poetry build --ansi
 
             - name: Publish package on PyPI
-              uses: pypa/[email protected].6
+              uses: pypa/[email protected].8
               with:
                   user: __token__
                   password: ${{ secrets.PYPI_TOKEN }}

.gitignore

@@ -149,3 +149,6 @@ cache
 
 # Apple stuff
 .DS_Store
+
+lightning_logs/*
+*/lightning_logs/*

.readthedocs.yml

@@ -3,15 +3,16 @@ version: 2
 sphinx:
     configuration: docs/conf.py
 
-formats:
-    - htmlzip
+formats: []
 
-python:
-    version: 3.8
-    install:
-        - method: pip
-          path: .
-        - requirements: docs/requirements.txt
+build:
+    os: ubuntu-22.04
+    tools:
+        python: "3.10"
+    jobs:
+        post_install:
+            - pip install .
+            - pip install -r docs/requirements.txt
 
 submodules:
     include: all

cookietemple.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.5.0
+current_version = 0.6.0
 
 [bumpversion_files_whitelisted]
 init_file = pertpy/__init__.py

docs/conf.py

@@ -15,8 +15,8 @@
 author = "Lukas Heumos"
 github_repo = "pertpy"
 
-version = "0.5.0"
-release = "0.5.0"
+version = "0.6.0"
+release = "0.6.0"
 
 extensions = [
     "myst_parser",
@@ -33,7 +33,6 @@
     "sphinx_gallery.load_style",
     "sphinx_remove_toctrees",
     "sphinx_design",
-    "sphinxext.opengraph",
 ]
 
 # remove_from_toctrees = ["tutorials/notebooks/*", "api/reference/*"]
@@ -184,4 +183,5 @@
     "tutorials/notebooks/distance_tests": "_static/tutorials/distances_tests.png",
     "tutorials/notebooks/scgen_perturbation_prediction": "_static/tutorials/scgen_perturbation_prediction.png",
     "tutorials/notebooks/scgen_batch_removal": "_static/tutorials/scgen_batch_removal.png",
+    "tutorials/notebooks/ontology_mapping": "_static/tutorials/ontology.png",
 }

docs/contributing.md

@@ -1,7 +1,7 @@
 # Contributor Guide
 
 Thank you for your interest in improving this project.
-This project is open-source under the [Apache2.0 license] and
+This project is open-source under the MIT license and
 highly welcomes contributions in the form of bug reports, feature requests, and pull requests.
 
 Here is a list of important resources for contributors:
@@ -120,7 +120,6 @@ $ nox --session=pre-commit -- install
 It is recommended to open an issue before starting work on anything.
 This will allow a chance to talk it over with the owners and validate your approach.
 
-[apache2.0 license]: https://opensource.org/licenses/Apache2.0
 [code of conduct]: https://github.com/theislab/pertpy/CODE_OF_CONDUCT.md
 [documentation]: https://pertpy.readthedocs.io/
 [issue tracker]: https://github.com/theislab/pertpy/issues

docs/requirements.txt

@@ -1,18 +1,16 @@
-Sphinx
+sphinx
 sphinx-automodapi
 sphinx-autodoc-annotation
+sphinx-autodoc-typehints
+sphinx-design
+sphinx-gallery
 sphinx_last_updated_by_git
 sphinxcontrib-spelling
-sphinx-autodoc-typehints
-sphinx_gallery<0.11
-sphinxcontrib-bibtex
+sphinx-copybutton
 nbsphinx
 nbsphinx-link
-sphinx-copybutton
 furo
 myst-parser
-sphinx-remove-toctrees
-sphinx-design
-sphinxext-opengraph
 ete3
 pyqt5
+sphinx-remove-toctrees

docs/tutorials/index.md

@@ -28,6 +28,7 @@ For questions about the usage of pertpy use [Github Discussions].
    notebooks/distance_tests
    notebooks/scgen_perturbation_prediction
    notebooks/scgen_batch_removal
+   notebooks/ontology_mapping
 ```
 
 ### Glossary

docs/usage/usage.md

@@ -99,7 +99,7 @@ Example implementation:
 import pertpy as pt
 import scanpy as sc
 
-mdata = pt.data.papalexi_2021()
+mdata = pt.dt.papalexi_2021()
 gdo = mdata.mod['gdo']
 gdo.layers['counts'] = gdo.X.copy()
 sc.pp.log1p(gdo)
@@ -112,50 +112,6 @@ pt.pl.guide.heatmap(gdo, layer='assigned_guides')
 
 ## Tools
 
-### Cell type prioritization
-
-#### Augur
-
-The Python implementation of [Augur R package](https://github.com/neurorestore/Augur)
-Skinnider, M.A., Squair, J.W., Kathe, C. et al. [Cell type prioritization in single-cell data](https://doi.org/10.1038/s41587-020-0605-1). Nat Biotechnol 39, 30–34 (2021).
-
-Augur aims to rank or prioritize cell types according to their response to experimental perturbations given high dimensional single-cell sequencing data.
-The basic idea is that in the space of molecular measurements cells reacting heavily to induced perturbations are
-more easily separated into perturbed and unperturbed than cell types with little or no response.
-This separability is quantified by measuring how well experimental labels (eg. treatment and control) can be predicted within each cell type.
-Augur trains a machine learning model predicting experimental labels for each cell type in multiple cross validation runs and
-then prioritizes cell type response according to metric scores measuring the accuracy of the model.
-For categorical data the area under the curve is the default metric and for numerical data the concordance correlation coefficient
-is used as a proxy for how accurate the model is which in turn approximates perturbation response.
-
-Example implementation:
-
-```python
-import pertpy as pt
-
-adata = pt.dt.sc_sim_augur()
-ag = pt.tl.Augur(estimator="random_forest_classifier")
-adata = ag.load(adata)
-adata, results = ag.predict(adata)
-
-# metrics for each cell type
-results['summary_metrics']
-```
-
-See [augur tutorial](https://pertpy.readthedocs.io/en/latest/tutorials/notebooks/augur.html) for a more elaborate tutorial.
-
-```{eval-rst}
-.. currentmodule:: pertpy
-```
-
-```{eval-rst}
-.. autosummary::
-    :toctree: tools
-    :nosignatures:
-
-    tools.Augur
-```
-
 ### Pooled CRISPR screens
 
 #### Mixscape
@@ -219,7 +175,7 @@ Example implementation:
 import pertpy as pt
 import scanpy as sc
 
-adata = pt.data.stephenson_2021_subsampled()
+adata = pt.dt.stephenson_2021_subsampled()
 adata.obs['COVID_severity'] = adata.obs['Status_on_day_collection_summary'].copy()
 adata.obs[['patient_id', 'COVID_severity']].drop_duplicates()
 adata = adata[adata.obs['Status'] != 'LPS'].copy()
@@ -319,8 +275,8 @@ all_results, new_mcps = dl.multilevel_modeling(ct_subs=ct_subs,
 
 ### Distances and Permutation Tests
 
-General purpose functions for distances and permutation tests. Reimplements
-functions from [scperturb](http://projects.sanderlab.org/scperturb/) package.
+General purpose functions for distances and permutation tests.
+Reimplements functions from [scperturb](http://projects.sanderlab.org/scperturb/) package.
 
 ```{eval-rst}
 .. currentmodule:: pertpy
@@ -377,6 +333,48 @@ Available databases for cell line metadata:
 
 ### Response prediction
 
+#### Augur
+
+The Python implementation of [Augur R package](https://github.com/neurorestore/Augur)
+Skinnider, M.A., Squair, J.W., Kathe, C. et al. [Cell type prioritization in single-cell data](https://doi.org/10.1038/s41587-020-0605-1). Nat Biotechnol 39, 30–34 (2021).
+
+Augur aims to rank or prioritize cell types according to their response to experimental perturbations given high dimensional single-cell sequencing data.
+The basic idea is that in the space of molecular measurements cells reacting heavily to induced perturbations are
+more easily separated into perturbed and unperturbed than cell types with little or no response.
+This separability is quantified by measuring how well experimental labels (eg. treatment and control) can be predicted within each cell type.
+Augur trains a machine learning model predicting experimental labels for each cell type in multiple cross validation runs and
+then prioritizes cell type response according to metric scores measuring the accuracy of the model.
+For categorical data the area under the curve is the default metric and for numerical data the concordance correlation coefficient
+is used as a proxy for how accurate the model is which in turn approximates perturbation response.
+
+Example implementation:
+
+```python
+import pertpy as pt
+
+adata = pt.dt.sc_sim_augur()
+ag = pt.tl.Augur(estimator="random_forest_classifier")
+adata = ag.load(adata)
+adata, results = ag.predict(adata)
+
+# metrics for each cell type
+results['summary_metrics']
+```
+
+See [augur tutorial](https://pertpy.readthedocs.io/en/latest/tutorials/notebooks/augur.html) for a more elaborate tutorial.
+
+```{eval-rst}
+.. currentmodule:: pertpy
+```
+
+```{eval-rst}
+.. autosummary::
+    :toctree: tools
+    :nosignatures:
+
+    tools.Augur
+```
+
 #### scGen
 
 Reimplementation of scGen for perturbation response prediction of scRNA-seq data in Jax.
@@ -419,41 +417,46 @@ pred, delta = model.predict(
 pred.obs['condition'] = 'pred'
 ```
 
-See [augur tutorial](https://pertpy.readthedocs.io/en/latest/tutorials/notebooks/scgen_perturbation_prediction.html) for a more elaborate tutorial.
+See [scgen tutorial](https://pertpy.readthedocs.io/en/latest/tutorials/notebooks/scgen_perturbation_prediction.html) for a more elaborate tutorial.
 
-### Representation
+### Perturbation space
+
+Various modules for calculating and evaluating perturbation spaces.
+
+```{eval-rst}
+.. currentmodule:: pertpy
+```
 
 ```{eval-rst}
 .. autosummary::
     :toctree: tools
 
-    tools.kernel_pca
+    tools.DiscriminatorClassifierSpace
+    tools.CentroidSpace
+    tools.DBSCANSpace
+    tools.KMeansSpace
+    tools.PseudobulkSpace
 ```
 
-## Plots
-
-### Preprocessing
-
-```{eval-rst}
-.. autosummary::
-    :toctree: plot
+Example implementation:
 
-    plot.guide
+```python
+import pertpy as pt
 
+# TODO will be added soon.
 ```
 
-### Cell type prioritization
+See [perturbation space tutorial](https://pertpy.readthedocs.io/en/latest/tutorials/notebooks/perturbation_space.html) for a more elaborate tutorial.
 
-#### Augur
+## Plots
+
+### Preprocessing
 
 ```{eval-rst}
 .. autosummary::
     :toctree: plot
 
-    plot.ag.dp_scatter
-    plot.ag.important_features
-    plot.ag.lollipop
-    plot.ag.scatterplot
+    plot.guide
 
 ```
 
@@ -503,6 +506,19 @@ See [augur tutorial](https://pertpy.readthedocs.io/en/latest/tutorials/notebooks
 
 ### Response prediction
 
+#### Augur
+
+```{eval-rst}
+.. autosummary::
+    :toctree: plot
+
+    plot.ag.dp_scatter
+    plot.ag.important_features
+    plot.ag.lollipop
+    plot.ag.scatterplot
+
+```
+
 #### scGen
 
 ```{eval-rst}