Update README, versioning, and improve workflow and code readability

.github/workflows/python-package.yml

@@ -2,52 +2,48 @@ name: Python package
 
 on:
   push:
-    branches: [ "main", "master" ]
+    branches: [ "main" ]
   pull_request:
-    branches: [ "main", "master" ]
+    branches: [ "main" ]
 
 jobs:
   build:
-
     runs-on: ${{ matrix.os-version }}
     name: ${{ matrix.os-version }} (${{ matrix.python-version }})
 
     strategy:
       fail-fast: false
       matrix:
         os-version: ["ubuntu-latest"]
-        python-version: ["3.9", "3.10", "3.11"] #, "3.12"]
+        python-version: ["3.11"]
 
     steps:
-    - uses: actions/checkout@v3
-    - name: "Set up Python ${{ matrix.python-version }}"
-      uses: actions/setup-python@v3
-      with:
-        python-version: ${{ matrix.python-version }}
-        cache: 'pip'
-    - name: "Install flake8"
-      run: |
-        pip install flake8
-    - 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: "Install miniconda"
-      uses: conda-incubator/setup-miniconda@v3
-      with:
-        miniconda-version: "latest"
-        auto-update-conda: true
-        python-version: ${{ matrix.python-version }}
-        channels: conda-forge,bioconda
-        environment-file: environment.yml
-    # - name: "Install pytest"
-    #   shell: bash -l {0}
-    #   run: |
-    #     python -m pip install --upgrade pip
-    #     pip install setuptools wheel build pytest
-    # - name: "Test with pytest"
-    #   shell: bash -l {0}
-    #   run: |
-    #     pytest -s
+      - uses: actions/checkout@v3
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v3
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Cache pip dependencies
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ matrix.python-version }}-${{ hashFiles('**/requirements.txt', 'environment.yml') }}
+
+      - name: Install flake8
+        run: pip install flake8
+
+      - name: Lint with flake8
+        run: |
+          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+          flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+
+      - name: Install miniconda
+        uses: conda-incubator/setup-miniconda@v3
+        with:
+          miniconda-version: "latest"
+          auto-update-conda: true
+          python-version: ${{ matrix.python-version }}
+          channels: conda-forge,bioconda
+          environment-file: environment.yml

pyproject.toml

@@ -1,7 +1,7 @@
 [tool.poetry]
 name = "ScreenPro2"
 description = "Flexible analysis of high-content CRISPR screening"
-version = "0.6.0"
+version = "0.6.1"
 authors = [
 	"Abolfazl Arab <abolfazl.arab@ucsf.edu>",
 	"Nick Youngblut <nick.youngblut@arcinstitute.org>",

screenpro/assays/__init__.py

@@ -71,8 +71,8 @@ def _calculateGrowthFactor(self, untreated, treated, db_rate_col):
         growth_factors = []
         # calculate growth factor for gamma, tau, or rho score per replicates
         for replicate in adat.obs.replicate.unique():
-            db_untreated = adat.obs.query(f'condition == "{untreated}" & replicate == {str(replicate)}')[db_rate_col][0]
-            db_treated = adat.obs.query(f'condition == "{treated}" & replicate == {str(replicate)}')[db_rate_col][0]
+            db_untreated = adat.obs.query(f'condition == "{untreated}" & replicate == {str(replicate)}')[db_rate_col].iloc[0]
+            db_treated = adat.obs.query(f'condition == "{treated}" & replicate == {str(replicate)}')[db_rate_col].iloc[0]
 
             growth_factors.append(('gamma', db_untreated, replicate, f'gamma_replicate_{replicate}'))
             growth_factors.append(('tau', db_treated, replicate, f'tau_replicate_{replicate}'))

screenpro/ngs/cas9.py

@@ -154,10 +154,9 @@ def map_to_library_single_guide(df_count, library, return_type='all', verbose=Fa
         )
 
     if verbose:
-        print("% mapped reads",
-            100 * \
-            res_map.to_pandas()['count'].fillna(0).sum() / \
-            int(res.select(pl.sum("count")).to_pandas()['count'])
+        print(
+            "% mapped reads",
+            100 * res_map['count'].sum() / res["count"].sum()
         )
 
     if return_type == 'unmapped':
@@ -221,17 +220,17 @@ def map_to_library_dual_guide(df_count, library, get_recombinant=False, return_t
     if verbose:
         print("% mapped reads",
             100 * \
-            res_map.to_pandas()['count'].fillna(0).sum() / \
-            int(res.select(pl.sum("count")).to_pandas()['count'])
+            res_map['count'].sum() / \
+            res["count"].sum()
         )
 
     if get_recombinant:
 
         if verbose:
             print("% unmapped reads",
                 100 * \
-                res_unmap.to_pandas()['count'].fillna(0).sum() / \
-                int(res.select(pl.sum("count")).to_pandas()['count'])
+                res_unmap['count'].sum() / \
+                res["count"].sum()
             )
 
         sgRNA_table = pd.concat([
@@ -253,8 +252,8 @@ def map_to_library_dual_guide(df_count, library, get_recombinant=False, return_t
         if verbose:
             print("% fully remapped recombination events",
                 100 * \
-                res_recomb_events.drop_nulls().to_pandas()['count'].fillna(0).sum() / \
-                int(res.select(pl.sum("count")).to_pandas()['count'])
+                res_recomb_events.drop_nulls()['count'].sum() / \
+                res['count'].sum()
             )
 
     if return_type == 'unmapped':