updates for kmer module, tests and pypi upload

.github/workflows/tests.yml

@@ -0,0 +1,90 @@
+name: Test Suite
+
+on:
+  push:
+  pull_request:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: tests-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    name: Fast tests on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os:
+          - ubuntu-latest
+          - windows-latest
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: "pip"
+
+      - name: Upgrade pip
+        run: python -m pip install --upgrade pip
+
+      - name: Install test dependencies
+        run: python -m pip install pytest
+
+      - name: Install package
+        run: python -m pip install .
+
+      - name: Copy tests to temp directory
+        run: python -c "import pathlib, shutil; src = pathlib.Path(r'${{ github.workspace }}') / 'tests'; dst = pathlib.Path(r'${{ runner.temp }}') / 'tests'; shutil.rmtree(dst, ignore_errors=True); shutil.copytree(src, dst)"
+
+      - name: Run fast test suite
+        working-directory: ${{ runner.temp }}
+        run: python -m pytest tests -m "not benchmark and not integration" -q
+
+  test-heavy:
+    name: Heavy tests on ${{ matrix.os }}
+    if: github.event_name == 'push' && github.ref == 'refs/heads/dev'
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os:
+          - ubuntu-latest
+          - windows-latest
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: "pip"
+
+      - name: Upgrade pip
+        run: python -m pip install --upgrade pip
+
+      - name: Install test dependencies
+        run: python -m pip install pytest
+
+      - name: Install package
+        run: python -m pip install .
+
+      - name: Copy tests to temp directory
+        run: python -c "import pathlib, shutil; src = pathlib.Path(r'${{ github.workspace }}') / 'tests'; dst = pathlib.Path(r'${{ runner.temp }}') / 'tests'; shutil.rmtree(dst, ignore_errors=True); shutil.copytree(src, dst)"
+
+      - name: Run benchmark and integration suites
+        env:
+          RUN_BENCHMARKS: "1"
+          RUN_INTEGRATION: "1"
+        working-directory: ${{ runner.temp }}
+        run: python -m pytest tests -m "benchmark or integration" -q

.vscode/launch.json

@@ -6,7 +6,7 @@
     "configurations": [
         {
             "name": "Python: Current File",
-            "type": "python",
+            "type": "debugpy",
             "request": "launch",
             "program": "${file}",
             "console": "integratedTerminal",

.vscode/settings.json

@@ -1,11 +1,12 @@
 {
     "python.testing.pytestArgs": [
-        "mir"
+        "tests"
     ],
     "python.testing.unittestEnabled": false,
     "python.testing.pytestEnabled": true,
     "[python]": {
         "editor.defaultFormatter": "ms-python.python"
     },
-    "python.formatting.provider": "none"
+    "python-envs.defaultEnvManager": "ms-python.python:conda",
+    "python-envs.defaultPackageManager": "ms-python.python:conda"
 }

CMakeLists.txt

@@ -1,18 +1,31 @@
 cmake_minimum_required(VERSION 3.18)
-project(mir_cdrscore LANGUAGES CXX)
+project(mir_native LANGUAGES CXX)
 
+find_package(Python3 REQUIRED COMPONENTS Interpreter Development.Module)
 find_package(pybind11 CONFIG REQUIRED)
-find_package(Python REQUIRED COMPONENTS Interpreter Development.Module)
 
-pybind11_add_module(cdrscore MODULE mir/distances/cdrscore.cpp)
-target_compile_features(cdrscore PRIVATE cxx_std_17)
+# --- seqdist_c (mir.distances) — distances + CDR3 scoring ---
+pybind11_add_module(seqdist_c MODULE mir/distances/seqdist.cpp)
+target_compile_features(seqdist_c PRIVATE cxx_std_17)
 if (MSVC)
-  target_compile_options(cdrscore PRIVATE /O2 /DNOMINMAX)
+  target_compile_options(seqdist_c PRIVATE /O2 /DNOMINMAX)
 else()
-  target_compile_options(cdrscore PRIVATE -O3)
+  target_compile_options(seqdist_c PRIVATE -O3)
 endif()
-
-set_target_properties(cdrscore PROPERTIES
+set_target_properties(seqdist_c PROPERTIES
   LIBRARY_OUTPUT_DIRECTORY "${CMAKE_CURRENT_BINARY_DIR}/mir/distances"
 )
-install(TARGETS cdrscore LIBRARY DESTINATION mir/distances)
+install(TARGETS seqdist_c LIBRARY DESTINATION mir/distances)
+
+# --- mirseq (mir.basic) ---
+pybind11_add_module(mirseq MODULE mir/basic/mirseq.cpp)
+target_compile_features(mirseq PRIVATE cxx_std_17)
+if (MSVC)
+  target_compile_options(mirseq PRIVATE /O2 /DNOMINMAX)
+else()
+  target_compile_options(mirseq PRIVATE -O3)
+endif()
+set_target_properties(mirseq PROPERTIES
+  LIBRARY_OUTPUT_DIRECTORY "${CMAKE_CURRENT_BINARY_DIR}/mir/basic"
+)
+install(TARGETS mirseq LIBRARY DESTINATION mir/basic)

README.md

@@ -20,6 +20,12 @@ Requirements:
 - Python 3.11+
 - a C/C++ build toolchain for compiled extensions
 
+Install from PyPI:
+
+```bash
+pip install mirpy-lib
+```
+
 Install from the repository root:
 
 ```bash
@@ -90,6 +96,29 @@ repertoire = Repertoire.load(
 )
 ```
 
+### Mask and match sequences
+
+```python
+from mir.basic.alphabets import (
+    aa_to_reduced,
+    mask,
+    matches,
+    matches_aa_reduced,
+    NT_MASK,
+    AA_MASK,
+)
+
+nt_masked = mask("ATCGAT", (2, 5), NT_MASK)
+assert nt_masked == b"ATNNNT"
+
+aa = "CASTIV"
+reduced = aa_to_reduced(aa)
+
+# Matching ignores mask symbols: N for nucleotides, X for amino-acid alphabets.
+assert matches(mask(aa, 0, AA_MASK), aa, AA_MASK)
+assert matches_aa_reduced(aa, mask(reduced, 3, AA_MASK))
+```
+
 ## Resources
 
 - Example notebooks are available in [notebooks/](https://github.com/antigenomics/mirpy/tree/main/notebooks).

docs/mir.basic.rst

@@ -28,14 +28,6 @@ mir.basic.fast_clust module
    :undoc-members:
    :show-inheritance:
 
-mir.basic.kmers module
-----------------------
-
-.. automodule:: mir.basic.kmers
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
 mir.basic.pgen module
 ---------------------
 
@@ -52,6 +44,22 @@ mir.basic.sampling module
    :undoc-members:
    :show-inheritance:
 
+mir.basic.alphabets module
+--------------------------
+
+.. automodule:: mir.basic.alphabets
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+mir.basic.mirseq module
+-----------------------
+
+.. automodule:: mir.basic.mirseq
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
 mir.basic.segment_usage module
 ------------------------------
 

docs/mir.biomarkers.rst

@@ -12,6 +12,14 @@ mir.biomarkers.fisher_biomarkers_detector module
    :undoc-members:
    :show-inheritance:
 
+mir.biomarkers.kmer_stats module
+--------------------------------
+
+.. automodule:: mir.biomarkers.kmer_stats
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
 Module contents
 ---------------
 

docs/mir.distances.rst

@@ -28,6 +28,22 @@ mir.distances.search module
    :undoc-members:
    :show-inheritance:
 
+mir.distances.seqdist module
+----------------------------
+
+.. automodule:: mir.distances.seqdist
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+mir.distances.seqdist\_c module
+-------------------------------
+
+.. automodule:: mir.distances.seqdist_c
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
 Module contents
 ---------------