refactor: avoid duplicate mappings (#131)

Co-authored-by: Boris Jurič <[email protected]>
Co-authored-by: Alex Kanitz <[email protected]>

.github/workflows/ci.yml

@@ -12,21 +12,18 @@ jobs:
     steps:
 
       - name: check out repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: set up miniconda and env
         uses: conda-incubator/setup-miniconda@v2
         with:
-          auto-update-conda: true
+          python-version: "3.9"
           mamba-version: "*"
-          channels: conda-forge,defaults
-          environment-file: environment.yml
+          auto-update-conda: true
           activate-environment: htsinfer
+          environment-file: environment-dev.yml
           auto-activate-base: false
 
-      - name: update env with dev packages
-        run: mamba env update --file environment-dev.yml
-
       - name: display env info
         run: |
           conda info -a
@@ -50,7 +47,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: [ '3.7', '3.8', '3.9' ]
+        python-version: [ '3.8', '3.9', '3.10' ]
 
     name: unit-testing-Python-${{ matrix.python-version }}
 
@@ -63,16 +60,12 @@ jobs:
         uses: conda-incubator/setup-miniconda@v2
         with:
           python-version: ${{ matrix.python-version }}
-          auto-update-conda: true
           mamba-version: "*"
-          channels: conda-forge,defaults
-          environment-file: environment.yml
+          auto-update-conda: true
           activate-environment: htsinfer
+          environment-file: environment-dev.yml
           auto-activate-base: false
 
-      - name: update env with dev packages
-        run: mamba env update --file environment-dev.yml
-
       - name: display env info
         run: |
           conda info -a
@@ -100,29 +93,25 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: [ '3.7', '3.8', '3.9' ]
+        python-version: [ '3.8', '3.9', '3.10' ]
 
     name: integration-testing-Python-${{ matrix.python-version }}
 
     steps:
 
       - name: check out repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: set up miniconda and env
         uses: conda-incubator/setup-miniconda@v2
         with:
           python-version: ${{ matrix.python-version }}
-          auto-update-conda: true
           mamba-version: "*"
-          channels: conda-forge,defaults
-          environment-file: environment.yml
+          auto-update-conda: true
           activate-environment: htsinfer
+          environment-file: environment-dev.yml
           auto-activate-base: false
 
-      - name: update env with dev packages
-        run: mamba env update --file environment-dev.yml
-
       - name: display env info
         run: |
           conda info -a
@@ -171,4 +160,4 @@ jobs:
         run: |
           echo "Push indicator: ${{ steps.docker.outputs.push-indicator }}"
           echo "# Set to 'true' if image was pushed, empty string otherwise"
-          test "${{ steps.docker.outputs.push-indicator }}" == "true"
+          test "${{ steps.docker.outputs.push-indicator }}" == "true"

README.md

@@ -123,12 +123,14 @@ dependencies via [Conda][conda]:
 git clone https://github.com/zavolanlab/htsinfer
 cd htsinfer
 conda env create --file environment.yml
-conda env update --file environment-dev.yml  # optional: install development/testing dependencies
+# Alternatively, to install with development dependencies,
+# run the following instead
+conda env create --file environment-dev.yml
 ```
 
-Note that creating the environment takes non-trivial time and it is strongly
-recommended that you install [Mamba][mamba] and replace `conda` with `mamba`
-in the previous commands.
+> Note that creating the environment takes non-trivial time and it is strongly
+> recommended that you install [Mamba][mamba] and replace `conda` with `mamba`
+> in the previous command.
 
 Then, activate the `htsinfer` Conda environment with:
 

environment-dev.yml

@@ -1,11 +1,24 @@
 name: htsinfer
 channels:
-  - defaults
+  - conda-forge
+  - bioconda
 dependencies:
-  - coverage>=5.3
-  - flake8>=3.8.4
-  - mypy>=0.782
-  - pylint>=2.4.4
-  - pytest>=6.1.0
+  - biopython >=1.78
+  - coverage >=5.3
+  - cutadapt >=3.5, <=4.2
+  - flake8 >=3.8.4
+  - kallisto >=0.46.1, <= 0.48.0
+  - mypy >=0.782
+  - numpy >=1.22, <1.25
+  - pandas >=1.3.5, <1.4.0
+  - pip >=20.2.3
+  - pyahocorasick >=1.4.0
+  - pydantic >=1.8.1, <2
+  - pylint >=2.4.4
+  - pysam >=0.16.0
+  - pytest >=6.1.0
+  - python >=3.8, <=3.10
+  - star >=2.7.6
   - pip:
     - python-semantic-release>=7.15.0
+    - -e .

environment.yml

@@ -1,18 +1,18 @@
 name: htsinfer
 channels:
-  - defaults
-  - bioconda
   - conda-forge
+  - bioconda
 dependencies:
-  - biopython>=1.78
-  - kallisto>=0.46.1, <= 0.48.0
-  - pandas>=1.0.5
-  - pip>=20.2.3
-  - pyahocorasick>=1.4.0
-  - pydantic>=1.8.1, <2
-  - pysam>=0.16.0
-  - python>3.6, <3.10
-  - star>=2.7.6
-  - cutadapt>=3.5, <=4.2
+  - biopython >=1.78
+  - cutadapt >=3.5, <=4.2
+  - kallisto >=0.46.1, <= 0.48.0
+  - numpy >=1.22, <1.25
+  - pandas >=1.3.5, <1.4.0
+  - pip >=20.2.3
+  - pyahocorasick >=1.4.0
+  - pydantic >=1.8.1, <2
+  - pysam >=0.16.0
+  - python >=3.8, <=3.10
+  - star >=2.7.6
   - pip:
     - -e .

htsinfer/cli.py

@@ -50,6 +50,7 @@ def __call__(
             values,
             option_string=None,
         ) -> None:
+            assert isinstance(values, list)
             if len(values) > 2:
                 parser.print_usage(file=sys.stderr)
                 sys.stderr.write(

htsinfer/get_library_type.py

@@ -21,9 +21,7 @@
     SeqIdFormats,
     Config,
 )
-from htsinfer.get_read_orientation import (
-    GetOrientation,
-)
+from htsinfer.mapping import Mapping
 
 LOGGER = logging.getLogger(__name__)
 
@@ -62,15 +60,15 @@ class GetLibType:
     def __init__(
         self,
         config: Config,
+        mapping: Mapping,
     ):
         """Class constructor."""
         self.path_1: Path = config.args.path_1_processed
         self.path_2: Optional[Path] = config.args.path_2_processed
         self.library_source = config.results.library_source
         self.results: ResultsType = ResultsType()
         self.tmp_dir = config.args.tmp_dir
-        self.get_read_orientation: \
-            GetOrientation = GetOrientation(config=config)
+        self.mapping = mapping
         self.max_distance = config.args.lib_type_max_distance
         self.cutoff = config.args.lib_type_mates_cutoff
 
@@ -126,23 +124,24 @@ def _evaluate_mate_relationship(
                 self.results.relationship = (
                     StatesTypeRelationship.split_mates
                 )
+                self.mapping.library_type.relationship = (
+                    StatesTypeRelationship.split_mates
+                )
         else:
-            self.get_read_orientation.library_type.relationship \
+            self.mapping.library_type.relationship \
                 = StatesTypeRelationship.not_available
-            self.get_read_orientation.library_source = self.library_source
-            _ = self.get_read_orientation.evaluate()
+            self.mapping.library_source = self.library_source
+            self.mapping.evaluate()
             self._align_mates()
 
     def _align_mates(self):
         """Decide mate relationship by alignment."""
 
-        alignment_1 = Path(self.tmp_dir) \
-            / "alignments" / "file_1" / "Aligned.out.sam"
-        alignment_2 = Path(self.tmp_dir) \
-            / "alignments" / "file_2" / "Aligned.out.sam"
+        alignment_1 = self.mapping.star_dirs[0] / 'Aligned.out.sam'
+        alignment_2 = self.mapping.star_dirs[1] / 'Aligned.out.sam'
 
-        samfile1 = pysam.AlignmentFile(alignment_1, 'r')
-        samfile2 = pysam.AlignmentFile(alignment_2, 'r')
+        samfile1 = pysam.AlignmentFile(str(alignment_1), 'r')
+        samfile2 = pysam.AlignmentFile(str(alignment_2), 'r')
 
         previous_seq_id1 = None
         previous_seq_id2 = None
@@ -184,6 +183,10 @@ def _align_mates(self):
             self.results.relationship = (
                 StatesTypeRelationship.split_mates
             )
+            self.mapping.library_type.relationship \
+                = StatesTypeRelationship.split_mates
+            self.mapping.mapped = False
+            self.mapping.star_dirs = []
         else:
             self.results.relationship = (
                 StatesTypeRelationship.not_mates