Merge remote-tracking branch 'origin/master' into batch_correct

.github/workflows/ci-test.yml

@@ -14,7 +14,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest]
-        python-version: ['3.7', '3.8', '3.9']
+        python-version: ['3.8', '3.9', '3.10', '3.11']
 
     steps:
     - uses: actions/checkout@v2
@@ -48,10 +48,6 @@ jobs:
     - name: One sample input test
       run: |
         bash tests/run_one_sample.sh
-    - name: Hashing CITE-Seq pipeline test
-      run: |
-        bash tests/run_hashing_citeseq.sh
-        pytest tests/test_hashing_citeseq.py
     - name: iNMF test
       run: |
         bash tests/run_inmf.sh

.readthedocs.yml

@@ -1,6 +1,35 @@
+# Read the Docs configuration file for Sphinx projects
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version and other tools you might need
 build:
-  image: latest
+  os: ubuntu-22.04
+  tools:
+    python: "3.9"
+    # You can also specify other tool versions:
+    # nodejs: "20"
+    # rust: "1.70"
+    # golang: "1.20"
+
+# Build documentation in the "docs/" directory with Sphinx
 sphinx:
   configuration: docs/conf.py
+  # You can configure Sphinx to use a different builder, for instance use the dirhtml builder for simpler URLs
+  # builder: "dirhtml"
+  # Fail on all warnings to avoid broken references
+  # fail_on_warning: true
+
+# Optionally build your docs in additional formats such as PDF and ePub
+# formats:
+#    - pdf
+#    - epub
+
+# Optional but recommended, declare the Python requirements required
+# to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
 python:
-  version: 3.8
+  install:
+    - requirements: docs/requirements.txt

docs/api/index.rst

@@ -85,6 +85,7 @@ Cluster Algorithms
     cluster
     louvain
     leiden
+    split_one_cluster
     spectral_louvain
     spectral_leiden
 

docs/conf.py

@@ -23,22 +23,22 @@
 # -- Project information -----------------------------------------------------
 
 project = "Pegasus"
-copyright = "2022 Genentech, Inc. All rights reserved."
+copyright = "2024 Genentech, Inc. All rights reserved."
 author = (
     "Yiming Yang, Joshua Gould and Bo Li"
 )
 
 # The short X.Y version
-version = "1.7"
+version = "1.9"
 # The full version, including alpha/beta/rc tags
-release = "1.7.1"
+release = "1.9.0"
 
 
 # -- General configuration ---------------------------------------------------
 
 # If your documentation needs a minimal Sphinx version, state it here.
 #
-#needs_sphinx = '1.7'
+#needs_sphinx = '1.8'
 
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom

docs/index.rst

@@ -10,7 +10,7 @@
 Release Highlights in Current Stable
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. include:: release_notes/version_1_7.rst
+.. include:: release_notes/version_1_9.rst
 
 .. toctree::
    :maxdepth: 1

docs/release_notes.rst

@@ -6,6 +6,16 @@ Release Notes
 .. note::
     Also see the release notes of `PegasusIO <https://pegasusio.readthedocs.io/en/stable/release_notes.html>`__.
 
+Version 1.9
+~~~~~~~~~~~~~
+
+.. include:: release_notes/version_1_9.rst
+
+Version 1.8
+~~~~~~~~~~~~~
+
+.. include:: release_notes/version_1_8.rst
+
 Version 1.7
 ~~~~~~~~~~~~~
 

docs/release_notes/version_1_8.rst

@@ -0,0 +1,21 @@
+1.8.1 :small:`August 23, 2023`
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+* Bug fix in cell marker JSON files for ``infer_cell_types`` function.
+
+1.8.0 :small:`July 21, 2023`
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+**New Feature and Improvement**
+
+* Updata ``human_immune`` and ``human_lung`` marker sets.
+* Add ``mouse_liver`` marker set.
+* Add `split_one_cluster <./api/pegasus.split_one_cluster.html>`_ function to subcluster one cluster into a specified number of subclusters.
+* Update **neighbors** function to set ``use_cache=False`` by default, and adjust K to ``min(K, int(sqrt(n_samples)))``. [PR `272 <https://github.com/lilab-bcb/pegasus/pull/272>`_]
+* In **infer_doublets** function, argument ``manual_correction`` now accepts a float number threshold specified by users for cut-off. [PR `275 <https://github.com/lilab-bcb/pegasus/pull/275>`_]
+
+**Bug Fix**
+
+* Fix divide by zero issue in ``integrative_nmf`` function. [PR `258 <https://github.com/lilab-bcb/pegasus/pull/258>`_]
+* Compatibility with Pandas v2.0. [PR `261 <https://github.com/lilab-bcb/pegasus/pull/261>`_]
+* Allow ``infer_doublets`` to use any count matrix with key name specified by users. [PR `268 <https://github.com/lilab-bcb/pegasus/pull/268>`_ Thanks to `Donghoon Lee <https://github.com/hoondy>`_]

docs/release_notes/version_1_9.rst

@@ -0,0 +1,14 @@
+1.9.0 :small:`January 19, 2024`
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+**New Feature and Improvement**
+
+* ``calculate_z_score`` works with sparse count matrix. [PR `276 <https://github.com/lilab-bcb/pegasus/pull/276>`_ Thanks to `Jayaram Kancherla <https://github.com/jkanche>`_]
+* Plotting functions (``scatter``, ``dotplot``, ``violin``, ``heatmap``) now give warnings on genes/attributes not existing in the data, and skip them in the plots.
+* Improve ``heatmap``:
+
+  * Add ``show_sample_name`` parameter for cases of pseudo-bulk data, nanoString DSP data, etc.
+  * Use Scipy's linkage (``scipy.cluster.hierarchy.linkage``) for dendrograms to use its optimal ordering feature for better results (see ``groupby_optimal_ordering`` parameter).
+
+* Update human lung and mouse immune markers used by ``infer_cell_types`` function.
+* Expose ``online_batch_size`` parameter in ``nmf`` and ``integrative_nmf`` functions.

docs/requirements.txt

@@ -14,7 +14,6 @@ natsort
 joblib
 psutil
 numba
-importlib_metadata; python_version < '3.8'
 umap-learn
 forceatlas2-python
 pyarrow

pegasus/__init__.py

@@ -65,6 +65,7 @@
     de_analysis,
     markers,
     write_results_to_excel,
+    cluster_specific_markers,
     find_markers,
     infer_path,
     calc_signature_score,

pegasus/annotate_cluster/annotate_cluster.py

@@ -278,7 +278,9 @@ def infer_cell_types(
             * ``'mouse_immune'`` for mouse immune cells;
             * ``'human_brain'`` for human brain cells;
             * ``'mouse_brain'`` for mouse brain cells;
-            * ``'human_lung'`` for human lung cells.
+            * ``'human_lung'`` for human lung cells;
+            * ``'mouse_lung'`` for mouse lung cells;
+            * ``'mouse_liver'`` for mouse liver cells.
         * If ``Dict``, it refers to a Python dictionary describing the markers.
 
     de_test: ``str``, optional, default: ``"mwu"``
@@ -320,6 +322,8 @@ def infer_cell_types(
         human_brain="human_brain_cell_markers.json",
         mouse_brain="mouse_brain_cell_markers.json",
         human_lung="human_lung_cell_markers.json",
+        mouse_lung="mouse_lung_cell_markers.json",
+        mouse_liver="mouse_liver_cell_markers.json",
     )
 
     if isinstance(markers, str):