erge branch 'ASintsova-ci-with-conda' of https://github.com/Microbiol…

…ogyETHZ/mbarq

 Please enter a commit message to explain why this merge is necessary,

.github/workflows/ci-with-conda.yml

@@ -0,0 +1,40 @@
+name: Python Package using Conda
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+jobs:
+  build-linux:
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 5
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.10'
+    - name: Add conda to system path
+      run: |
+        # $CONDA is an environment variable pointing to the root of the miniconda directory
+        echo $CONDA/bin >> $GITHUB_PATH
+    - name: Install dependencies
+      run: |
+        conda install -c conda-forge mamba
+        mamba env update --file mbarq_environment.yaml --name base
+        pip install .
+    - name: Lint with flake8
+      run: |
+        conda install flake8
+        # 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 pytest
+      run: |
+        conda install pytest
+        pytest

mbarq/analysis.py

@@ -383,12 +383,14 @@ def process_results(self, contrasts_run=()):
         self.logger.info('Writing out final results.')
         if not contrasts_run:
             contrasts_run = self.sd.contrasts
-        try:
-            res = pd.concat([pd.read_table(self.output_dir / f"{self.name}_{i}_vs_{self.sd.baseline}.gene_summary.txt")
-                            .assign(contrast=i) for i in contrasts_run])
-        except:
-            print(f"Warning: No such file or directory: {self.output_dir}/{self.name}_{i}_vs_{self.sd.baseline}.gene_summary.txt")
-
+        contrast_dfs = []
+        for con in contrasts_run:
+            try:
+                contrast_dfs.append(pd.read_table(self.output_dir / f"{self.name}_{con}_vs_{self.sd.baseline}.gene_summary.txt")
+                                .assign(contrast=con))
+            except:
+                print(f"Warning: No such file or directory: {self.output_dir}/{self.name}_{con}_vs_{self.sd.baseline}.gene_summary.txt")
+        res = pd.concat(contrast_dfs)
         bc_res = pd.concat([pd.read_table(self.output_dir / f"{self.name}_{i}_vs_{self.sd.baseline}.sgrna_summary.txt")
                         .assign(contrast=i) for i in contrasts_run]).rename({'sgrna': 'barcode', 'Gene': 'Name'}, axis=1)
         fres = res[['id', 'num', 'neg|lfc', 'neg|fdr', 'pos|fdr', 'contrast']]

mbarq_environment.yaml

@@ -5,12 +5,12 @@ channels:
   - defaults
 dependencies:
   - mageck
-  - python==3.8.*
+  - python>=3.8
   - blast==2.9.*
   - bedtools==2.30.*
   - biopython==1.79
-  - numpy=1.22.1
-  - pandas==1.3.3
+  - numpy=1.22
+  - pandas
   - pytest
   - click
   - pip