Merge branch 'main' into kra-gha-integration

.github/workflows/ingestion-ci.yml

@@ -21,10 +21,12 @@ jobs:
         python-version: ["3.11"]
 
     steps:
-      # - uses: actions/checkout@v4
-      - name: Download Conda YAML file
-        run: curl -o pipeline_env.yaml https://raw.githubusercontent.com/DendrouLab/panpipes/kra-gha/pipeline_env.yaml
+      - uses: actions/checkout@v4
 
+      - name: File tree
+        if: env.debug == 'true'
+        run: tree
+
       - uses: conda-incubator/setup-miniconda@v3
         with:
           miniforge-version: latest
@@ -33,8 +35,14 @@ jobs:
           channels: conda-forge
           channel-priority: strict
           activate-environment: pipeline_env
-          environment-file: pipeline_env.yaml # consider moving to etc/pipeline_env.yaml
+          environment-file: pipeline_env.yaml
 
+      - name: Install Panpipes
+        shell: bash -el {0}
+        run: |
+          pip install -e .
+          conda list
+          
       - name: Conda info
         if: env.debug == 'true'
         shell: bash -el {0}
@@ -84,7 +92,7 @@ jobs:
 
       - name: File tree
         if: env.debug == 'true'
-        run: tree
+        run: tree teaseq
 
       - name: Review pipeline tasks
         shell: bash -el {0}
@@ -100,4 +108,10 @@ jobs:
 
       - name: File tree
         if: env.debug == 'true'
-        run: tree
+        run: tree teaseq
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: teaseq_unfilt.h5mu
+          path: teaseq/ingest/teaseq_unfilt.h5mu
+          retention-days: 1

.gitignore

@@ -1,8 +1,165 @@
-dist/
-panpipes/__pycache__
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
 build/
-panpipes.egg-info
-*.pyc
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# panpipes specific
 .history
 panpipes/.DS_Store
 .DS_Store

.readthedocs.yaml

@@ -1,32 +1,13 @@
-# .readthedocs.yaml
-# Read the Docs configuration file
-# 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:
   os: ubuntu-22.04
   tools:
     python: "3.11"
-    # You can also specify other tool versions:
-    # nodejs: "19"
-    # rust: "1.64"
-    # golang: "1.19"
 
-# Build documentation in the "docs/" directory with Sphinx
 sphinx:
    configuration: docs/conf.py
 
-# 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:
    install:
    - requirements: docs/requirements.txt

CHANGELOG.md

@@ -1,5 +1,5 @@
-Releases
-===========
+
+# Releases
 
 ## [latest]
 
@@ -17,30 +17,30 @@ Releases
 ## v0.4.1
 
 ### added
+
 - added example multiome submission file 10X_h5
 - added example multiome submission file cellranger
 - workflows & tutorials for `qc_spatial`, `preprocess_spatial`, and `deconvolution_spatial` to readthedocs
 - tutorial for `vis`
 - added PCA parameters in pipeline_preprocess.py for PROT modality to fix issue #120
 - added full control of dimred params for all modalities in pipeline_preprocess.py
 - more info on custom genes format files added to documentation
-- parsing summary files for cellranger multi version < 7 
+- parsing summary files for cellranger multi version < 7
 - added checks for n_pcs in run_neighbors_method_choice
 - added filtering by HVF for atac
 
-
 ### fixed
 
 - changed typo in tutorial paths for clustering and deconvolution
-- fix io to read cellranger outs folder for atac. 
-- fixes to refmap workflow 
+- fix io to read cellranger outs folder for atac.
+- fixes to refmap workflow
 - typos & capitalization in the pipeline.yml files of `qc_spatial`, `preprocess_spatial`, and `deconvolution_spatial`, `vis`
-- remove `assay`, `sample_prefix`, and `modalities` parameters from the `qc_spatial` pipeline.yml 
+- remove `assay`, `sample_prefix`, and `modalities` parameters from the `qc_spatial` pipeline.yml
 - remove `sample_prefix` and `modalities` parameters from the `preprocess_spatial` pipeline.yml
 - fixed error in `preprocess_spatial` when `filtering: run: False`
     -> now able to run no filtering without needing to save the MuData in `filtered.data` before running the pipeline
 - fixed error in `vis`
-    - change PARAMS['custom_markers_minimal'] -> PARAMS['custom_markers']['files']['minimal']
+  - change PARAMS['custom_markers_minimal'] -> PARAMS['custom_markers']['files']['minimal']
 - fix to avoid rerunning HVF and explicitly check X layer before normalization in pipeline_preprocess.py
 - fix plotting of umaps after batch correction
 - fix fetching string scvi if present in mudata for wnn
@@ -49,54 +49,55 @@ Releases
 - fixed filtering HVG for rna
 - moved pynndescent to PyPi dependencies
 
-
 ### dependencies
 
 ## v0.4.0
 
 Big Change! the submission files for the `ingest` workflow have now changed! we require the paths to the Gene expression (RNA/GEX) and Protein (ADT) to have the following headers.
 
-
 | sample_id | rna_path    | rna_filetype | prot_path    | prot_filetype |
 | --------- | ----------- | ------------ | ------------ | ------------- |
 | sampleX   | path/to/rna | 10X_h5       | path/to/prot | 10x_h5        |
 |           |             |              |              |               |
 
-
 See tutorials for examples of submission files.
 
-
 ### added
+
 - merged PR #111:
   - LSI in panpipes_preprocess is run on the highly variable features
   - n_comp for LSI
+
 ### fixed
+
 - changed all instances of ADT into PROT
 - changed all instances of GEX to RNA
 - changed the params to fix plotting as mentioned in issue #41
 - typo in readme
 - set default seaborn <=0.12.2 to avoid issue #104, #126
 
-### dependencies
-
 ## v0.3.1
-- set default matplotlib<=3.7.3 to avoid issue #104. 
+
+- set default matplotlib<=3.7.3 to avoid issue #104.
 
 ## v0.3.0
+
 ### added
+
 - Spatial data analysis is now included in panpipes
-    - panpipes qc_spatial
-    - panpipes preprocess_spatial
-    - panpipes_deconvolution_spatial
+  - panpipes qc_spatial
+  - panpipes preprocess_spatial
+  - panpipes_deconvolution_spatial
 
 ### fixed
+
 - make sure columns from individual modalities that are not in the multimodal outer obs can be used to
 
 ### dependencies
+
 - additional dependencies: squidpy, cell2location, openpyxl
 
 ## v0.2.0
-- First public version of panpipes
-    - contains qc_mm, preprocess, intergration, clustering
-
 
+- First public version of panpipes
+- contains qc_mm, preprocess, intergration, clustering