Merge pull request #22 from instituteofcancerresearch/python-dev

Python dev

.github/workflows/dev_tests.yml

@@ -1,62 +1,38 @@
 name: SOPRANO (Dev) Tests
 
 on:
-  push:
-    branches:
-      - python-dev
   pull_request:
     branches:
       - python-dev
 
 jobs:
-  lint:
-    strategy:
-      matrix:
-        os: ["ubuntu-latest"]
-        python-version: ["3.11"]
-    name: lint with python ${{ matrix.python-version }} on ${{ matrix.os }}
-    runs-on: ${{ matrix.os }}
-    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 ruff and black
-        run: |
-          python -m pip install --upgrade pip
-          pip install ruff black
-      - name: Lint check with ruff
-        run: |
-          ruff --format=github --target-version=py311 --line-length 79 .
-      - name: Style check with black
-        run: |
-          black ./ --check --line-length 79
   test:
-    strategy:
-      matrix:
-        os: ["ubuntu-latest"]
-        python-version: ["3.11"]
-    name: test with python ${{ matrix.python-version }} on ${{ matrix.os }}
-    runs-on: ${{ matrix.os }}
+    name: Development tests
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash -l {0}
     steps:
       - uses: actions/checkout@v3
-      - uses: mamba-org/setup-micromamba@v1
+      - name: Setup miniconda
+        uses: conda-incubator/setup-miniconda@v2
         with:
-          environment-file: src/SOPRANO/local.yml
-          init-shell: bash
+          auto-update-conda: true
+          miniforge-variant: Mambaforge
+          channels: conda-forge
+          python-version: 3.11
+          activate-environment: soprano-dev
+          environment-file: src/SOPRANO/ci_linux.yml
+          use-mamba: true
       - name: Install SOPRANO
-        shell: bash -l {0}
         run: |
-          micromamba activate soprano-dev
+          conda activate soprano-dev
           pip install -e .[ci]
       - name: Test conda environment
-        shell: bash -l {0}
         run: |
-          micromamba activate soprano-dev
-          pytest tests/test_configuration
+          conda activate soprano-dev
+          pytest -s tests/test_configuration
       - name: Test units
-        shell: bash -l {0}
         run: |
-          micromamba activate soprano-dev
-          pytest tests/test_units
+          conda activate soprano-dev
+          pytest -s tests/test_units

.github/workflows/lint_and_style.yml

@@ -0,0 +1,23 @@
+name: Lint and style check
+
+on: [ push ]
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Setup python
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.11
+      - name: Install ruff and black
+        run: |
+          python -m pip install --upgrade pip
+          pip install ruff black
+      - name: Lint check with ruff
+        run: |
+          ruff --target-version=py311 --line-length 79 .
+      - name: Style check with black
+        run: |
+          black ./ --check --line-length 79

.github/workflows/main_tests.yml

@@ -1,69 +1,42 @@
-name: SOPRANO (Main) Tests
+name: SOPRANO Tests
 
 on:
-  push:
-    branches:
-      - python
-      - master
   pull_request:
     branches:
       - python
-      - master
+      - main
 
 jobs:
-  lint:
-    strategy:
-      matrix:
-        os: ["ubuntu-latest"]
-        python-version: ["3.11"]
-    name: lint with python ${{ matrix.python-version }} on ${{ matrix.os }}
-    runs-on: ${{ matrix.os }}
-    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 ruff and black
-        run: |
-          python -m pip install --upgrade pip
-          pip install ruff black
-      - name: Lint check with ruff
-        run: |
-          ruff --format=github --target-version=py311 --line-length 79 .
-      - name: Style check with black
-        run: |
-          black ./ --check --line-length 79
   test:
     strategy:
       matrix:
-        os: ["ubuntu-latest", "macos-latest"]
-        python-version: ["3.11"]
-    name: test with python ${{ matrix.python-version }} on ${{ matrix.os }}
+        os: [ "ubuntu-latest", "macos-latest" ]
+    name: Development tests on ${{ matrix.os }}
     runs-on: ${{ matrix.os }}
+    defaults:
+      run:
+        shell: bash -l {0}
     steps:
       - uses: actions/checkout@v3
-      - uses: mamba-org/setup-micromamba@v1
+      - name: Setup miniconda
+        uses: conda-incubator/setup-miniconda@v2
         with:
-          environment-file: src/SOPRANO/local.yml
-          init-shell: bash
+          auto-update-conda: true
+          miniforge-variant: Mambaforge
+          channels: conda-forge
+          python-version: 3.11
+          activate-environment: soprano-dev
+          environment-file: src/SOPRANO/ci_osx.yml  # additional coreutils
+          use-mamba: true
       - name: Install SOPRANO
-        shell: bash -l {0}
         run: |
-          micromamba activate soprano-dev
+          conda activate soprano-dev
           pip install -e .[ci]
       - name: Test conda environment
-        shell: bash -l {0}
         run: |
-          micromamba activate soprano-dev
-          pytest tests/test_configuration
+          conda activate soprano-dev
+          pytest -s tests/test_configuration
       - name: Test units
-        shell: bash -l {0}
         run: |
-          micromamba activate soprano-dev
-          pytest tests/test_units
-#      - name: Test integration # TODO: Need to think about this
-#        shell: bash -l {0}
-#        run: |
-#          micromamba activate soprano-dev
-#          pytest tests/test_integrations
+          conda activate soprano-dev
+          pytest -s tests/test_units

.gitignore

@@ -74,4 +74,13 @@ src/SOPRANO/data/homo_sapiens/**/Homo_sapiens.GRCh*.fa.gz
 /example_output.txt
 
 # App output files
-pipeline_cache/
+pipeline_cache/
+
+# User defined app sources
+app_sources/
+!app_sources/annotated_inputs/.gitkeep
+!app_sources/coordinate_files/.gitkeep
+!app_sources/immunopeptidomes/.gitkeep
+
+# Ignore release cache file
+src/SOPRANO/data/ensembl.releases

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
 -   repo: https://github.com/python/black
-    rev: 23.7.0
+    rev: 23.9.1
     hooks:
     - id: black
       pass_filenames: true
@@ -13,7 +13,8 @@ repos:
     rev: 'v1.5.1'
     hooks:
     -   id: mypy
+        additional_dependencies: ['types-requests']
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.0.287
+    rev: v0.0.292
     hooks:
     -   id: ruff

docs/APP.md

@@ -35,15 +35,40 @@ export SOPRANO_CACHE=/path/to/my/soprano/cache
 soprano-app
 ```
 
+### Data sources
+
+By default, the application will serve options for the annotated mutation
+and human immunopeptidome files shipped with SOPRANO. Additional files
+can be detected by the application by their placement in the `./app_sources`
+folders:
+
+- `./app_sources/annotated_inputs`
+
+    VEP annotated mutation files placed in this directory will be detected,
+    so long as they have the extension pattern `*anno*`. E.g., `mutations.anno`
+    or `mutations.annotated`.
+
+
+- `./app_sources/immunopeptidomes`
+
+    User defined immunopeptidomes BED files placed in this directory will be 
+    detected, so long as they have the extension `.bed`. E.g., `immuno.bed`.
+
+
+- `./app_sources/coordinate_files`
+
+    User defined BED files that can be used for randomization will be detected,
+    so long as they have the extension `.bed`. E.g., `randoms.bed`.
+
+
 ### Development status
 
 This app is actively being developed (September 2023). The configuration is 
 subject to change, and additional features are soon to be integrated.
 
 _Planned features:_
 
-- Generalization of species. Currently only homo sapiens are supported.
-- Selection of randomization regions. Currently only available via CLI.
+- Generalization of species. Currently only Homo Sapiens are supported.
 - Selection of transcript files. Currently only available via CLI.
 - Interface for linking VEP cache files.
 - Interface for downloading genome references.

docs/CLI.md

@@ -49,17 +49,23 @@ These arguments have short (`-s`) or long (`--long`) argument flags.
     This value should be an integer greater than zero. Defaults to "-1", 
     implying no seed value chosen.
 
+
+- `-s | --species`
 
-- `-r | --reference`
+    The Latin species name associated with genome reference. The default value
+    is for homo_sapiens.
 
-    The name of the genome reference. Currently, this CLI supports GRCh37 and 
-    GRCh38, which may be passed as arguments. By default, GRCh37 is chosen.
 
+- `-a | --assembly`
 
-- `-q | --release`
+    The name of the Ensembl reference genome assembly. The default value is for 
+    GRCh38 (Homo Sapiens).
+
+
+- `-r | --release`
 
     The Ensembl release number of the genome reference
-    file. By default, the CLI will select release 110.
+    file. The default value is 110.
 
 
 - `-t | --transcript`

pyproject.toml

@@ -8,26 +8,30 @@ description = "SOPRANO: Selection On PRotein ANnotated regiOns"
 readme = "README.md"
 authors = [
     { name = "Luis Zapata", email = "[email protected]" },
-    { name = "ICR Scientific Software Group", email = "[email protected]"},
+    { name = "ICR Scientific Software Group", email = "[email protected]" },
 ]
 maintainers = [
     { name = "Luis Zapata", email = "[email protected]" },
-    { name = "ICR Scientific Software Group", email = "[email protected]"},
+    { name = "ICR Scientific Software Group", email = "[email protected]" },
 ]
-requires-python = ">=3.8"
+requires-python = ">=3.10"
 dependencies = [
     "pandas",
     "numpy",
-    "streamlit == 1.27.0"
+    "streamlit == 1.27.0",
+    "requests",
+    "types-requests",
+    "clint"
 ]
 classifiers = [
-  "Development Status :: 3 - Alpha",
-  "License :: OSI Approved :: BSD License",
-  "Programming Language :: Python :: 3 :: Only",
-  "Programming Language :: Python :: 3.11",
-  "Programming Language :: Perl",
-  "Topic :: Scientific/Engineering :: Bio-Informatics",
-  "Intended Audience :: Science/Research"
+    "Development Status :: 3 - Alpha",
+    "License :: OSI Approved :: BSD License",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Perl",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+    "Intended Audience :: Science/Research"
 ]
 dynamic = ["version"]
 
@@ -59,6 +63,7 @@ soprano-run = "SOPRANO.run:run_cli"
 soprano-app = "SOPRANO.run:run_app"
 soprano-get-genome = "SOPRANO.run:download_genome"
 soprano-link-vep = "SOPRANO.run:link_vep_cache"
+soprano-hla2ip = "SOPRANO.run:hla2pip"
 
 [tool.hatch]
 version.source = "vcs"