Merge pull request #10 from infocusp/build_workflows

workflows

.github/workflows/publish-to-pypi.yml

@@ -0,0 +1,51 @@
+name: Publish package to PyPI
+
+on:
+  push:
+    tags:
+      - 'v*' # Push events to tag which starts with v.
+
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.9"
+    - name: Install pypa/build
+      run: >-
+        python3 -m
+        pip install
+        build
+        --user
+    - name: Build a binary wheel and a source tarball
+      run: python3 -m build
+    - name: Store the distribution packages
+      uses: actions/upload-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+   publish-to-pypi:
+    name: >-
+      Publish to PyPI
+    if: startsWith(github.ref, 'refs/tags/')  # only publish to PyPI on tag pushes
+    needs:
+    - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/pyscalr
+    permissions:
+      id-token: write  # IMPORTANT: mandatory for trusted publishing
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Publish to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/run_isort.yml

@@ -0,0 +1,20 @@
+name: "Import checker"
+
+on:
+  - push
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python 3.9
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.9
+    - name: Install isort
+      run: pip install isort
+    - name: Run isort
+      run: isort . --settings-path .isort.cfg

.github/workflows/run_pytest.yml

@@ -0,0 +1,27 @@
+name: Run Unit Test via Pytest
+
+on:
+  pull_request:
+      branches:
+        - main
+  push:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9"]
+
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+      - name: Running test cases
+        run: pytest -v -s

.github/workflows/run_yapf.yml

@@ -0,0 +1,14 @@
+name: YAPF Formatting Check
+
+on: [push]
+
+jobs:
+  formatting-check:
+    name: Formatting Check
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: run YAPF
+      uses: AlexanderMelde/yapf-action@master
+      with:
+        args: --verbose

.pre-commit-config.yaml

@@ -9,11 +9,3 @@ repos:
     hooks:
     -   id: isort
         args: ['--settings-path', '.isort.cfg']
--   repo: local
-    hooks:
-      - id: pytest
-        name: Running test cases in pipeline...
-        entry: pytest -s -v
-        language: system
-        pass_filenames: false
-        stages: [commit]

pyproject.toml

@@ -0,0 +1,39 @@
+[build-system]
+requires = ["hatchling", "hatch-requirements-txt"]
+build-backend = "hatchling.build"
+
+[project]
+name = "scaLR"
+version = "0.0.1"
+requires-python = ">=3.9"
+authors = [
+  { name="Infocusp", email="saurabh@infocusp.com" },
+]
+description = "scaLR: Single cell analysis using low resource."
+readme = "README.md"
+classifiers = [
+    "Programming Language :: Python :: 3.9",
+    "Operating System :: OS Independent",
+    "Intended Audience :: Science/Research"
+]
+
+dynamic = ["dependencies"]
+[tool.hatch.build.targets.wheel]
+packages = ["scalr"]
+
+[tool.hatch.metadata.hooks.requirements_txt]
+files = ["requirements.txt"]
+
+[tool.hatch.build]
+exclude = [
+  "docs/*",
+  "tutorials/*",
+  "tests/*",
+]
+
+license = {file = "LICENSE"}
+
+[project.urls]
+Repository = "https://github.com/infocusp/scaLR.git"
+Homepage = "https://github.com/infocusp/scaLR"
+Issues = "https://github.com/infocusp/scaLR/issues"

scalr/analysis/__init__.py

@@ -7,4 +7,3 @@
 from .gene_recall_curve import GeneRecallCurve
 from .heatmap import Heatmap
 from .roc_auc import RocAucCurve
-

scalr/analysis/dge_pseudobulk.py

@@ -162,12 +162,11 @@ def plot_volcano(self, dge_results_df: DataFrame, cell_type: str,
         dge_results_df['-log10(pvalue)'] = -np.log10(dge_results_df['pvalue'])
 
         upregulated_gene = (dge_results_df['log2FoldChange'] >= log2_fold_chnage
-                           ) & (dge_results_df['-log10(pvalue)'] >=
-                                (neg_log10_pval))
-        downregulated_gene = (dge_results_df['log2FoldChange'] <=
-                              (-log2_fold_chnage)) & (
-                                  dge_results_df['-log10(pvalue)'] >=
-                                  (neg_log10_pval))
+                           ) & (dge_results_df['-log10(pvalue)']
+                                >= (neg_log10_pval))
+        downregulated_gene = (dge_results_df['log2FoldChange'] <= (
+            -log2_fold_chnage)) & (dge_results_df['-log10(pvalue)']
+                                   >= (neg_log10_pval))
 
         unsignificant_gene = dge_results_df['-log10(pvalue)'] <= (
             neg_log10_pval)

tutorials/analysis/differential_gene_expression/dge_lmem_main.py

@@ -29,35 +29,40 @@
 
 from scalr.analysis import DgeLMEM
 
+
 def main(config):
-    test_data = sc.read_h5ad(config['full_datapath'],backed='r')
-    dirpath= config['dirpath']
-    dge_type= config['dge_type']
-    assert (dge_type=='DgeLMEM') and ('lmem_params' in config),(
+    test_data = sc.read_h5ad(config['full_datapath'], backed='r')
+    dirpath = config['dirpath']
+    dge_type = config['dge_type']
+    assert (dge_type == 'DgeLMEM') and ('lmem_params' in config), (
         f"Check '{dge_type}' and 'lmem_params' in dge_config file")
-        
+
     lmem_params = config['lmem_params']
-    dge = DgeLMEM(
-        fixed_effect_column = lmem_params['fixed_effect_column'],
-        fixed_effect_factors = lmem_params['fixed_effect_factors'],
-        group = lmem_params['group'],
-        celltype_column = lmem_params.get('celltype_column',None),
-        cell_subsets = lmem_params.get('cell_subsets',None),
-        min_cell_threshold = lmem_params.get('min_cell_threshold',10),
-        n_cpu = lmem_params.get('n_cpu',6),
-        gene_batch_size = lmem_params.get('gene_batch_size',1000),
-        coef_threshold = lmem_params.get('coef_threshold',0),
-        p_val = lmem_params.get('p_val',0.05),
-        y_lim_tuple = lmem_params.get('y_lim_tuple',None),
-        save_plot = lmem_params.get('save_plot',True),
-        stdout = True)
-        
-    dge.generate_analysis(test_data,dirpath)
+    dge = DgeLMEM(fixed_effect_column=lmem_params['fixed_effect_column'],
+                  fixed_effect_factors=lmem_params['fixed_effect_factors'],
+                  group=lmem_params['group'],
+                  celltype_column=lmem_params.get('celltype_column', None),
+                  cell_subsets=lmem_params.get('cell_subsets', None),
+                  min_cell_threshold=lmem_params.get('min_cell_threshold', 10),
+                  n_cpu=lmem_params.get('n_cpu', 6),
+                  gene_batch_size=lmem_params.get('gene_batch_size', 1000),
+                  coef_threshold=lmem_params.get('coef_threshold', 0),
+                  p_val=lmem_params.get('p_val', 0.05),
+                  y_lim_tuple=lmem_params.get('y_lim_tuple', None),
+                  save_plot=lmem_params.get('save_plot', True),
+                  stdout=True)
+
+    dge.generate_analysis(test_data, dirpath)
+
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description='Dge analysis : LMEM method')
-    parser.add_argument('--config','-c',type=str,required=True,help='Path to input dge_config.yaml file')
+    parser.add_argument('--config',
+                        '-c',
+                        type=str,
+                        required=True,
+                        help='Path to input dge_config.yaml file')
     argument = parser.parse_args()
-    with open(argument.config,'r') as config_file:
+    with open(argument.config, 'r') as config_file:
         config = yaml.safe_load(config_file)
-    main(config)
+    main(config)

tutorials/analysis/differential_gene_expression/dge_pseudobulk_main.py

@@ -18,33 +18,40 @@
 
 from scalr.analysis import DgePseudoBulk
 
+
 def main(config):
-    test_data = sc.read_h5ad(config['full_datapath'],backed='r')
-    dirpath= config['dirpath']
-    dge_type= config['dge_type']
-    assert (dge_type=='DgePseudoBulk') and ('psedobulk_params' in config),(
+    test_data = sc.read_h5ad(config['full_datapath'], backed='r')
+    dirpath = config['dirpath']
+    dge_type = config['dge_type']
+    assert (dge_type == 'DgePseudoBulk') and ('psedobulk_params' in config), (
         f"Check '{dge_type}' and 'psedobulk_params' in dge_config file")
-        
+
     psedobulk_params = config['psedobulk_params']
-    dge = DgePseudoBulk(
-        celltype_column = psedobulk_params.get('celltype_column'),
-        design_factor = psedobulk_params['design_factor'],
-        factor_categories = psedobulk_params['factor_categories'],
-        sum_column = psedobulk_params['sum_column'],
-        cell_subsets = psedobulk_params.get('cell_subsets',None),
-        min_cell_threshold = psedobulk_params.get('min_cell_threshold',10),
-        fold_change = psedobulk_params.get('fold_change',1.5),
-        p_val = psedobulk_params.get('p_val',0.05),
-        y_lim_tuple = psedobulk_params.get('y_lim_tuple',None),
-        save_plot = psedobulk_params.get('save_plot',True),
-        stdout = True)
-
-    dge.generate_analysis(test_data,dirpath)
+    dge = DgePseudoBulk(celltype_column=psedobulk_params.get('celltype_column'),
+                        design_factor=psedobulk_params['design_factor'],
+                        factor_categories=psedobulk_params['factor_categories'],
+                        sum_column=psedobulk_params['sum_column'],
+                        cell_subsets=psedobulk_params.get('cell_subsets', None),
+                        min_cell_threshold=psedobulk_params.get(
+                            'min_cell_threshold', 10),
+                        fold_change=psedobulk_params.get('fold_change', 1.5),
+                        p_val=psedobulk_params.get('p_val', 0.05),
+                        y_lim_tuple=psedobulk_params.get('y_lim_tuple', None),
+                        save_plot=psedobulk_params.get('save_plot', True),
+                        stdout=True)
+
+    dge.generate_analysis(test_data, dirpath)
+
 
 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description='Dge analysis : psedobulk method')
-    parser.add_argument('--config','-c',type=str,required=True,help='Path to input dge_config.yaml file')
+    parser = argparse.ArgumentParser(
+        description='Dge analysis : psedobulk method')
+    parser.add_argument('--config',
+                        '-c',
+                        type=str,
+                        required=True,
+                        help='Path to input dge_config.yaml file')
     argument = parser.parse_args()
-    with open(argument.config,'r') as config_file:
+    with open(argument.config, 'r') as config_file:
         config = yaml.safe_load(config_file)
-    main(config)
+    main(config)