cellarr 0.4.1.dev2__tar.gz → 0.5.1__tar.gz

cellarr-0.5.1/.github/workflows/publish-pypi.yml

@@ -0,0 +1,52 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Publish to PyPI
+
+on:
+  push:
+    tags: "*"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.11
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install tox
+
+      - name: Test with tox
+        run: |
+          tox
+
+      - name: Build docs
+        run: |
+          tox -e docs
+
+      - run: touch ./docs/_build/html/.nojekyll
+
+      - name: GH Pages Deployment
+        uses: JamesIves/github-pages-deploy-action@v4
+        with:
+          branch: gh-pages # The branch the action should deploy to.
+          folder: ./docs/_build/html
+          clean: true # Automatically remove deleted files from the deploy branch
+
+      - name: Build Project and Publish
+        run: |
+          python -m tox -e clean,build
+
+      - name: Publish package
+        uses: pypa/gh-action-pypi-publish@v1.12.2
+        with:
+          user: __token__
+          password: ${{ secrets.PYPI_PASSWORD }}

cellarr-0.5.1/.github/workflows/run-tests.yml

@@ -0,0 +1,33 @@
+name: Run tests
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+
+    name: Python ${{ matrix.python-version }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "pip"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install tox
+
+      - name: Test with tox
+        run: |
+          tox

{cellarr-0.4.1.dev2 → cellarr-0.5.1}/.pre-commit-config.yaml

@@ -33,7 +33,7 @@ repos:
 
 - repo: https://github.com/astral-sh/ruff-pre-commit
   # Ruff version.
-  rev: v0.8.2
+  rev: v0.8.3
   hooks:
     - id: ruff
       args: [--fix, --exit-non-zero-on-fix]

{cellarr-0.4.1.dev2 → cellarr-0.5.1}/CHANGELOG.md

@@ -1,5 +1,15 @@
 # Changelog
 
+## Version 0.5.1
+
+- Support csc matrices in layers, although not common ran into a situation where the
+anndata object was stored from R.
+
+## Version 0.5.0
+
+- Construct cellarr TileDB files on HPC environments based on slurm
+(reference: [#61](https://github.com/BiocPy/cellarr/pull/61))
+
 ## Version 0.4.0
 
 - chore: Remove Python 3.8 (EOL).

{cellarr-0.4.1.dev2 → cellarr-0.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cellarr
-Version: 0.4.1.dev2
+Version: 0.5.1
 Summary: TileDB-based array storage for genomics data collections.
 Home-page: https://github.com/BiocPy/cellarr
 Author: Jayaram Kancherla
@@ -166,7 +166,8 @@ A minimal manifest file (json) must contain the following fields
 - `"python_env"`: A set of commands to activate the Python environment containing this package and its dependencies.
 
 Here’s an example of the manifest file:
-```json
+
+```py
 manifest = {
     "files": your/list/of/files,
     "python_env": """
@@ -187,14 +188,18 @@ which python
         }
     ],
 }
+
+import json
+json.dump(manifest, open("your/path/to/manifest.json", "w"))
 ```
+
 For more options, check out the [README](./src/cellarr/slurm/README.md).
 
 - Step 2: Submit the job
 Once your manifest file is ready, you can submit the necessary jobs using the `cellarr_build` CLI. Run the following command:
 
 ```sh
-cellarr_build --input-manifest your/path/to/test_manifest.json --output-dir your/path/to/output --memory-per-job 8 --cpus-per-task 2
+cellarr_build --input-manifest your/path/to/manifest.json --output-dir your/path/to/output --memory-per-job 8 --cpus-per-task 2
 ```
 
 ### Query a `CellArrDataset`

{cellarr-0.4.1.dev2 → cellarr-0.5.1}/README.md

@@ -133,7 +133,8 @@ A minimal manifest file (json) must contain the following fields
 - `"python_env"`: A set of commands to activate the Python environment containing this package and its dependencies.
 
 Here’s an example of the manifest file:
-```json
+
+```py
 manifest = {
     "files": your/list/of/files,
     "python_env": """
@@ -154,14 +155,18 @@ which python
         }
     ],
 }
+
+import json
+json.dump(manifest, open("your/path/to/manifest.json", "w"))
 ```
+
 For more options, check out the [README](./src/cellarr/slurm/README.md).
 
 - Step 2: Submit the job
 Once your manifest file is ready, you can submit the necessary jobs using the `cellarr_build` CLI. Run the following command:
 
 ```sh
-cellarr_build --input-manifest your/path/to/test_manifest.json --output-dir your/path/to/output --memory-per-job 8 --cpus-per-task 2
+cellarr_build --input-manifest your/path/to/manifest.json --output-dir your/path/to/output --memory-per-job 8 --cpus-per-task 2
 ```
 
 ### Query a `CellArrDataset`

{cellarr-0.4.1.dev2 → cellarr-0.5.1}/src/cellarr/utils_anndata.py

@@ -6,7 +6,7 @@ import anndata
 import mopsy
 import numpy as np
 import pandas as pd
-from scipy.sparse import coo_matrix, csr_array, csr_matrix
+from scipy.sparse import coo_matrix, csc_array, csc_matrix, csr_array, csr_matrix
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -119,7 +119,7 @@ def remap_anndata(
 
         if isinstance(mat, np.ndarray):
             mat_coo = coo_matrix(mat)
-        elif isinstance(mat, (csr_array, csr_matrix)):
+        elif isinstance(mat, (csr_array, csr_matrix, csc_matrix, csc_array)):
             mat_coo = mat.tocoo()
         else:
             raise TypeError(f"Unknown matrix type: {type(mat)}.")

{cellarr-0.4.1.dev2 → cellarr-0.5.1}/src/cellarr.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cellarr
-Version: 0.4.1.dev2
+Version: 0.5.1
 Summary: TileDB-based array storage for genomics data collections.
 Home-page: https://github.com/BiocPy/cellarr
 Author: Jayaram Kancherla
@@ -166,7 +166,8 @@ A minimal manifest file (json) must contain the following fields
 - `"python_env"`: A set of commands to activate the Python environment containing this package and its dependencies.
 
 Here’s an example of the manifest file:
-```json
+
+```py
 manifest = {
     "files": your/list/of/files,
     "python_env": """
@@ -187,14 +188,18 @@ which python
         }
     ],
 }
+
+import json
+json.dump(manifest, open("your/path/to/manifest.json", "w"))
 ```
+
 For more options, check out the [README](./src/cellarr/slurm/README.md).
 
 - Step 2: Submit the job
 Once your manifest file is ready, you can submit the necessary jobs using the `cellarr_build` CLI. Run the following command:
 
 ```sh
-cellarr_build --input-manifest your/path/to/test_manifest.json --output-dir your/path/to/output --memory-per-job 8 --cpus-per-task 2
+cellarr_build --input-manifest your/path/to/manifest.json --output-dir your/path/to/output --memory-per-job 8 --cpus-per-task 2
 ```
 
 ### Query a `CellArrDataset`

{cellarr-0.4.1.dev2 → cellarr-0.5.1}/src/cellarr.egg-info/SOURCES.txt

@@ -11,8 +11,8 @@ pyproject.toml
 setup.cfg
 setup.py
 tox.ini
-.github/workflows/pypi-publish.yml
-.github/workflows/pypi-test.yml
+.github/workflows/publish-pypi.yml
+.github/workflows/run-tests.yml
 assets/cellarr.jpg
 assets/cellarr.png
 assets/cellarr.svg

{cellarr-0.4.1.dev2 → cellarr-0.5.1}/tests/test_build.py

@@ -13,6 +13,7 @@ from cellarr import (
     CellMetadataOptions,
 )
 import cellarr
+from scipy import sparse as sp
 
 __author__ = "Jayaram Kancherla"
 __copyright__ = "Jayaram Kancherla"
@@ -460,3 +461,60 @@ def test_build_cellarrdataset_from_frame_withsubset_columns():
         )
         == 0
     )
+
+def test_with_sparse():
+    tempdir = tempfile.mkdtemp()
+
+    adata1 = generate_adata(1000, 100, 10)
+    adata1.layers["counts"] = sp.csr_matrix(adata1.layers["counts"])
+
+    adata2 = generate_adata(100, 1000, 100)
+    adata2.layers["counts"] = sp.csc_matrix(adata2.layers["counts"])
+
+    build_cellarrdataset(
+        output_path=tempdir,
+        files=[adata1, adata2],
+        matrix_options=MatrixOptions(dtype=np.float32),
+    )
+
+    cfp = tiledb.open(f"{tempdir}/assays/counts", "r")
+    gfp = tiledb.open(f"{tempdir}/gene_annotation", "r")
+
+    genes = gfp.df[:]
+
+    assert len(genes) == 1000
+
+    gene_list = ["gene_1", "gene_95", "gene_50"]
+    _genes_from_tile = genes["cellarr_gene_index"].tolist()
+    gene_indices_tdb = sorted([_genes_from_tile.index(x) for x in gene_list])
+
+    adata1_gene_indices = sorted(
+        [adata1.var.index.tolist().index(x) for x in gene_list]
+    )
+
+    adata2_gene_indices = sorted(
+        [adata2.var.index.tolist().index(x) for x in gene_list]
+    )
+
+    assert np.allclose(
+        cfp.multi_index[0, gene_indices_tdb]["data"],
+        adata1.layers["counts"][0, adata1_gene_indices].todense(),
+    )
+    assert np.allclose(
+        cfp.multi_index[1000, gene_indices_tdb]["data"],
+        adata2.layers["counts"][0, adata2_gene_indices].todense(),
+    )
+
+    sfp = tiledb.open(f"{tempdir}/sample_metadata", "r")
+    samples = sfp.df[:]
+    assert len(samples) == 2
+    assert "cellarr_sample_start_index" in samples.columns
+    assert "cellarr_sample_end_index" in samples.columns
+    assert "cellarr_cell_counts" in samples.columns
+    assert "cellarr_original_gene_set" in samples.columns
+
+    cellfp = tiledb.open(f"{tempdir}/cell_metadata", "r")
+    cell_df = cellfp.df[:]
+    assert len(cell_df) == 1100
+    assert "cellarr_sample" in cell_df.columns
+    assert "cellarr_cell_index_in_sample" in cell_df.columns

cellarr-0.4.1.dev2/.github/workflows/pypi-publish.yml

@@ -1,51 +0,0 @@
-# This workflow will install Python dependencies, run tests and lint with a single version of Python
-# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
-
-name: Publish to PyPI
-
-on:
-  push:
-    tags: "*"
-
-jobs:
-  build:
-
-    runs-on: ubuntu-latest
-
-    steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python 3.11
-      uses: actions/setup-python@v5
-      with:
-        python-version: 3.11
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install flake8 pytest tox
-    # - name: Lint with flake8
-    #   run: |
-    #     # stop the build if there are Python syntax errors or undefined names
-    #     flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-    #     # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-    #     # flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-    - name: Test with tox
-      run: |
-        tox
-    - name: Build docs
-      run: |
-        tox -e docs
-    - run: touch ./docs/_build/html/.nojekyll
-    - name: GH Pages Deployment
-      uses: JamesIves/github-pages-deploy-action@4.1.3
-      with:
-        branch: gh-pages # The branch the action should deploy to.
-        folder: ./docs/_build/html
-        clean: true # Automatically remove deleted files from the deploy branch
-    - name: Build Project and Publish
-      run: |
-        python -m tox -e clean,build
-    - name: Publish package
-      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
-      with:
-        user: __token__
-        password: ${{ secrets.PYPI_PASSWORD }}

cellarr-0.4.1.dev2/.github/workflows/pypi-test.yml

@@ -1,40 +0,0 @@
-# This workflow will install Python dependencies, run tests and lint with a single version of Python
-# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
-
-name: Test the library
-
-on:
-  push:
-    branches: [ master ]
-  pull_request:
-    branches: [ master ]
-
-jobs:
-  build:
-
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version: [ '3.9', '3.10', '3.11', '3.12' ]
-
-    name: Python ${{ matrix.python-version }}
-    steps:
-    - uses: actions/checkout@v4
-    - name: Setup Python
-      uses: actions/setup-python@v5
-      with:
-        python-version: ${{ matrix.python-version }}
-        cache: 'pip'
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install flake8 pytest tox
-    # - name: Lint with flake8
-    #   run: |
-    #     # stop the build if there are Python syntax errors or undefined names
-    #     flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-    #     # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-    #     # flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-    - name: Test with tox
-      run: |
-        tox