fix: Remove spliced alignments from DP calculation

.github/workflows/integration_tests.yml

@@ -4,31 +4,26 @@ on: [push]
 
 jobs:
   test:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [ '3.7', '3.8', '3.9', '3.10' ]
+        python-version: [ '3.8', '3.9', '3.10' ]
 
     steps:
-    - uses: actions/checkout@v2
+    - name: Checkout code
+      uses: actions/checkout@v4
+
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4
-      with:
+      uses: actions/setup-python@v5
+        with:
           python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
-      run: |
-        sudo apt-get update
-        sudo apt-get --assume-yes install build-essential libcurl4-openssl-dev libz-dev liblzma-dev
-        python -m pip install --upgrade pip
-        pip install setuptools wheel
-        # this is needed by pybedtools
-        sudo apt-get --assume-yes install bedtools
-        # install python requirements
-        pip install -r requirements.txt
-    - name: Install vafator
-      run: |
-        python setup.py bdist_wheel
-        pip install dist/vafator-*.whl
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+          pip install .
+
     - name: Run integration tests
       run: |
         make clean integration_tests

.github/workflows/release.yml

@@ -6,19 +6,24 @@ on:
 
 jobs:
   deploy:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v2
-    - uses: actions/setup-python@v2
+    - uses: actions/checkout@v4
+
+    - uses: actions/setup-python@v5
+      with:
+          python-version: 3.10
+
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
         pip install setuptools wheel twine
+
     - name: Build and publish
       env:
         TWINE_USERNAME: __token__
         TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
       run: |
         python setup.py sdist bdist_wheel
-        twine upload dist/*
+        twine upload dist/*

.github/workflows/unit_tests.yml

@@ -4,25 +4,31 @@ on: [push]
 
 jobs:
   test:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-latest
+
     strategy:
       matrix:
-        python-version: [ '3.7', '3.8', '3.9', '3.10' ]
+        python-version: ['3.8', '3.9', '3.10']
 
     steps:
-    - uses: actions/checkout@v2
-    - 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
-        pip install setuptools wheel coverage
-        pip install virtualenv tox==3.26.0 tox-wheel==1.0.0 tox-gh-actions
-    - name: Build, install and run unit tests
-      run: |
-        pip install -r requirements.txt
-        coverage run -m unittest discover vafator.tests
-    - name: Upload Coverage to Codecov
-      uses: codecov/codecov-action@v3
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+          pip install .
+          pip install coverage codecov
+
+      - name: Run tests with coverage
+        run: |
+          coverage run -m unittest discover
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4

requirements.txt

@@ -3,4 +3,5 @@ pysam~=0.19.1
 cyvcf2~=0.30.14
 logzero~=1.7.0
 pybedtools~=0.9.0
+numpy>=1.20,<2.0
 scipy>=1.0.0,<2.0.0

vafator/__init__.py

@@ -1,4 +1,4 @@
-VERSION='2.2.0'
+VERSION='2.2.1'
 
 
 AMBIGUOUS_BASES = ['N', 'M', 'R', 'W', 'S', 'Y', 'K', 'V', 'H', 'D', 'B']

vafator/pileups.py

@@ -148,7 +148,7 @@
                     if start > variant_position:
                         break
                 if not match:
                     # TODO: when finds a read with an indel not matching our particular indel it counts it
                     pass
             elif pileup_read.indel == 0:
                 # NOTE: considers all reads without indels to be the reference!
@@ -181,9 +181,10 @@
         all_positions = aggregate_list_per_base(bases, pileup.get_query_positions())
 
         if include_ambiguous_bases:
-            dp = len(bases)
+            dp = len([b for b in bases if b!= ""])
         else:
-            dp = len([b for b in bases if b not in AMBIGUOUS_BASES])
+            # remove ambiguous bases and reads where the position is spliced out
+            dp = len([b for b in bases if b not in AMBIGUOUS_BASES and b != ""])
         ac = Counter(bases)
     except StopIteration:
         # no reads