smftools 0.2.5__tar.gz → 0.3.1__tar.gz

{smftools-0.2.5 → smftools-0.3.1}/.github/workflows/ci.yml

@@ -2,9 +2,13 @@ name: CI
 
 on:
   push:
-    branches: ["main"]
+    branches: ["main", "0.3.0"]
   pull_request:
-    branches: ["main"]
+    branches: ["main", "0.3.0"]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
 
 jobs:
   format:
@@ -13,21 +17,16 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ["3.12"]
-
     steps:
-      - name: Check out repository
-        uses: actions/checkout@v4
-
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-
+          cache: pip
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          python -m pip install ruff
-
+          python -m pip install "ruff==0.8.6"
       - name: Check formatting with ruff
         run: ruff format --check .
 
@@ -37,40 +36,31 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ["3.12"]
-
     steps:
-      - name: Check out repository
-        uses: actions/checkout@v4
-
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-
+          cache: pip
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          python -m pip install ruff
-
+          python -m pip install "ruff==0.8.6"
       - name: Lint with ruff
-        run: ruff check .
+        run: ruff check --output-format=github .
 
   smoke:
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.10"]
-
+        python-version: ["3.10", "3.12"]
     steps:
-      - name: Check out repository
-        uses: actions/checkout@v4
-
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-
+          cache: pip
       - name: Install system deps for pysam
         run: |
           sudo apt-get update
@@ -81,35 +71,48 @@ jobs:
             liblzma-dev \
             libcurl4-openssl-dev \
             pkg-config
-
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
           python -m pip install .[dev]
-
       - name: Run smoke tests
         run: pytest -m smoke -q
 
+  docs:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+      - name: Install docs deps
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install .[docs]
+      - name: Build docs
+        run: sphinx-build -W -b html docs/source docs/_build/html
+
   build:
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
       matrix:
         python-version: ["3.10", "3.11", "3.12"]
-
     steps:
-      - name: Check out repository
-        uses: actions/checkout@v4
-
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-
+          cache: pip
       - name: Install build tooling
         run: |
           python -m pip install --upgrade pip
-          python -m pip install build
-
+          python -m pip install build twine
       - name: Build package
         run: python -m build
+      - name: Check dist metadata
+        run: twine check dist/*

{smftools-0.2.5 → smftools-0.3.1}/AGENTS.md

@@ -11,6 +11,15 @@ This file tells coding agents (including OpenAI Codex) how to work in this repo.
 - Read existing patterns before inventing new ones.
 - Don’t refactor broadly unless asked.
 - If you’re unsure about intended behavior, look for tests/docs first.
+- Ignore all files in any directory named "archived".
+
+## Project dependencies
+- A core set of dependencies is required for the project.
+- Various optional dependencies are provided for:
+    - Optional functional modules of the package (ont, plotting, ml-base, ml-extended, scanpy, qc)
+    - If a Python version of a CLI tool is preferred (Such as for Samtools, Bedtools, BedGraphToBigWig).
+    - For potential performance boosts in computation (torch)
+    - All dependencies can be installed with `pip install -e ".[all]"`
 
 ## Setup
 - Create env (pick one):
@@ -38,6 +47,7 @@ This file tells coding agents (including OpenAI Codex) how to work in this repo.
   - Use type hints for new/modified functions where reasonable.
   - Use Google style docstring format.
   - Avoid heavy dependencies unless necessary.
+  - Use typing.TYPE_CHECKING and annotations.
 
 ## Testing expectations
 - New functionality must include tests.

{smftools-0.2.5 → smftools-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: smftools
-Version: 0.2.5
+Version: 0.3.1
 Summary: Single Molecule Footprinting Analysis in Python.
 Project-URL: Source, https://github.com/jkmckenna/smftools
 Project-URL: Documentation, https://smftools.readthedocs.io/
@@ -29,7 +29,7 @@ License: MIT License
         SOFTWARE.
 License-File: LICENSE
 Keywords: anndata,chromatin-accessibility,machine-learning,nanopore,protein-dna-binding,single-locus,single-molecule-footprinting
-Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Development Status :: 3 - Alpha
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -41,38 +41,42 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
-Classifier: Programming Language :: Python :: 3.14
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: Topic :: Scientific/Engineering :: Visualization
 Requires-Python: >=3.10
 Requires-Dist: anndata>=0.10.0
 Requires-Dist: biopython>=1.79
-Requires-Dist: captum
 Requires-Dist: click
-Requires-Dist: fastcluster
-Requires-Dist: hydra-core
-Requires-Dist: igraph
-Requires-Dist: leidenalg
-Requires-Dist: lightning
-Requires-Dist: multiqc
-Requires-Dist: networkx>=3.2
 Requires-Dist: numpy<2,>=1.22.0
-Requires-Dist: omegaconf
 Requires-Dist: pandas>=1.4.2
-Requires-Dist: pod5>=0.1.21
-Requires-Dist: pybedtools>=0.12.0
-Requires-Dist: pybigwig>=0.3.24
-Requires-Dist: pyfaidx>=0.8.0
-Requires-Dist: pysam>=0.19.1
-Requires-Dist: scanpy>=1.9
-Requires-Dist: scikit-learn>=1.0.2
 Requires-Dist: scipy>=1.7.3
-Requires-Dist: seaborn>=0.11
-Requires-Dist: shap
-Requires-Dist: torch>=1.9.0
 Requires-Dist: tqdm
-Requires-Dist: upsetplot
-Requires-Dist: wandb
+Provides-Extra: all
+Requires-Dist: captum; extra == 'all'
+Requires-Dist: fastcluster; extra == 'all'
+Requires-Dist: hydra-core; extra == 'all'
+Requires-Dist: leidenalg; extra == 'all'
+Requires-Dist: lightning; extra == 'all'
+Requires-Dist: matplotlib>=3.6.2; extra == 'all'
+Requires-Dist: multiqc; extra == 'all'
+Requires-Dist: networkx>=3.2; extra == 'all'
+Requires-Dist: omegaconf; extra == 'all'
+Requires-Dist: pod5>=0.1.21; extra == 'all'
+Requires-Dist: pybedtools>=0.12.0; extra == 'all'
+Requires-Dist: pybigwig>=0.3.24; extra == 'all'
+Requires-Dist: pynndescent>=0.5.10; extra == 'all'
+Requires-Dist: pysam>=0.19.1; extra == 'all'
+Requires-Dist: scikit-learn>=1.0.2; extra == 'all'
+Requires-Dist: seaborn>=0.11; extra == 'all'
+Requires-Dist: shap; extra == 'all'
+Requires-Dist: torch>=1.9.0; extra == 'all'
+Requires-Dist: umap-learn>=0.5.5; extra == 'all'
+Requires-Dist: upsetplot; extra == 'all'
+Requires-Dist: wandb; extra == 'all'
+Provides-Extra: cluster
+Requires-Dist: fastcluster; extra == 'cluster'
+Requires-Dist: igraph; extra == 'cluster'
+Requires-Dist: leidenalg; extra == 'cluster'
 Provides-Extra: dev
 Requires-Dist: pre-commit; extra == 'dev'
 Requires-Dist: pytest; extra == 'dev'
@@ -81,20 +85,52 @@ Requires-Dist: ruff; extra == 'dev'
 Provides-Extra: docs
 Requires-Dist: ipython>=7.20; extra == 'docs'
 Requires-Dist: matplotlib!=3.6.1; extra == 'docs'
-Requires-Dist: myst-nb>=1; extra == 'docs'
-Requires-Dist: myst-parser>=2; extra == 'docs'
+Requires-Dist: myst-nb<2,>=1; extra == 'docs'
+Requires-Dist: myst-parser<3,>=2; extra == 'docs'
 Requires-Dist: nbsphinx>=0.9; extra == 'docs'
 Requires-Dist: pyyaml; extra == 'docs'
 Requires-Dist: readthedocs-sphinx-search; extra == 'docs'
 Requires-Dist: setuptools; extra == 'docs'
-Requires-Dist: sphinx-autodoc-typehints>=1.25.2; extra == 'docs'
-Requires-Dist: sphinx-book-theme>=1.1.0; extra == 'docs'
-Requires-Dist: sphinx-click; extra == 'docs'
-Requires-Dist: sphinx-copybutton; extra == 'docs'
+Requires-Dist: sphinx-autodoc-typehints<4,>=1.25.2; extra == 'docs'
+Requires-Dist: sphinx-book-theme<2,>=1.1; extra == 'docs'
+Requires-Dist: sphinx-click<7,>=5; extra == 'docs'
+Requires-Dist: sphinx-copybutton<0.6,>=0.5; extra == 'docs'
 Requires-Dist: sphinx-design; extra == 'docs'
-Requires-Dist: sphinx>=7; extra == 'docs'
-Requires-Dist: sphinxcontrib-bibtex; extra == 'docs'
-Requires-Dist: sphinxext-opengraph; extra == 'docs'
+Requires-Dist: sphinx<8,>=7; extra == 'docs'
+Requires-Dist: sphinxcontrib-bibtex<3,>=2; extra == 'docs'
+Requires-Dist: sphinxext-opengraph<0.10,>=0.9; extra == 'docs'
+Provides-Extra: misc
+Requires-Dist: networkx>=3.2; extra == 'misc'
+Requires-Dist: upsetplot; extra == 'misc'
+Provides-Extra: ml-base
+Requires-Dist: scikit-learn>=1.0.2; extra == 'ml-base'
+Requires-Dist: tensorly; extra == 'ml-base'
+Requires-Dist: torch>=1.9.0; extra == 'ml-base'
+Provides-Extra: ml-extended
+Requires-Dist: captum; extra == 'ml-extended'
+Requires-Dist: hydra-core; extra == 'ml-extended'
+Requires-Dist: lightning; extra == 'ml-extended'
+Requires-Dist: omegaconf; extra == 'ml-extended'
+Requires-Dist: shap; extra == 'ml-extended'
+Requires-Dist: wandb; extra == 'ml-extended'
+Provides-Extra: ont
+Requires-Dist: pod5>=0.1.21; extra == 'ont'
+Provides-Extra: plotting
+Requires-Dist: matplotlib>=3.6.2; extra == 'plotting'
+Requires-Dist: seaborn>=0.11; extra == 'plotting'
+Provides-Extra: pybedtools
+Requires-Dist: pybedtools>=0.12.0; extra == 'pybedtools'
+Provides-Extra: pybigwig
+Requires-Dist: pybigwig>=0.3.24; extra == 'pybigwig'
+Provides-Extra: pysam
+Requires-Dist: pysam>=0.19.1; extra == 'pysam'
+Provides-Extra: qc
+Requires-Dist: multiqc; extra == 'qc'
+Provides-Extra: torch
+Requires-Dist: torch>=1.9.0; extra == 'torch'
+Provides-Extra: umap
+Requires-Dist: pynndescent>=0.5.10; extra == 'umap'
+Requires-Dist: umap-learn>=0.5.5; extra == 'umap'
 Description-Content-Type: text/markdown
 
 [![PyPI](https://img.shields.io/pypi/v/smftools.svg)](https://pypi.org/project/smftools)

{smftools-0.2.5 → smftools-0.3.1}/docs/source/installation.md

@@ -2,18 +2,13 @@
 
 ## PyPi version - Easiest starting point
 
-Install smftools from [PyPI](https://pypi.org/project/smftools):
-
-```shell
-pip install smftools
-```
-
-It is recommended to first create and activate a conda environment before installing smftools to ensure dependencies are managed smoothly:
+It is recommended to first create and activate a conda environment before installing smftools to ensure dependencies are managed smoothly. The following sets up a conda environment, activates the environment, and installs the base smftools and uses a Pytorch backend:
 
 ```shell
 conda create -n smftools
 conda activate smftools
-pip install smftools
+pip install --upgrade pip
+pip install smftools[torch]
 ```
 
 Ensure that you can access dorado, modkit, and minimap2 executables from the terminal in this environment.
@@ -24,7 +19,8 @@ For example, if you want to check if dorado is executable, simply run this in th
 dorado
 ```
 
-On Mac OSX, the following can be used to congigure minimap2 (with brew) and BedGraphToBigWig (with wget).
+On Mac OSX, the following can be used to congigure minimap2 (with brew) if you do not want to use the dorado aligner.
+Also, optional samtools (brew), bedtools (brew) and BedGraphToBigWig (with wget) can be installed and configured if you prefer to use the CLI backend. SMFtools also has the option to use a Python backend instead of these CLI backends if you pip install with the optional dependency flags: pysamtools, pybedtools, pybigwig.
 
 ```shell
 brew install minimap2
@@ -33,6 +29,36 @@ chmod +x bedGraphToBigWig
 sudo mv bedGraphToBigWig /usr/local/bin/
 ```
 
+If you are starting from Nanopore POD5 files, you will need to install with the ont option.
+```shell
+pip install smftools[ont]
+```
+
+If you want multiqc to be performed on your experiment, you will need to use the qc option on install.
+```shell
+pip install smftools[qc]
+```
+
+If you want to use the automated plotting functions, you will need to install the plotting dependencies.
+```shell
+pip install smftools[plotting]
+```
+
+If you prefer to use python backends (or do not have the CLI backends installed) for samtools, bedtools, BedGraphToBigWig, use the following options.
+```shell
+pip install smftools[pysamtools,pybedtools,pybigwig]
+```
+
+If you want to generate UMAPs and perform Leiden clustering, use the following options.
+```shell
+pip install smftools[scanpy,clustering]
+```
+
+If you just want to install the full functionality of smftools, just use the following install option.
+```shell
+pip install smftools[all]
+```
+
 ## Development Version - recommended to use this method for most up to date versions
 
 Clone smftools from source and change into the smftools directory:

smftools-0.3.1/docs/source/release-notes/0.3.0.md

@@ -0,0 +1,4 @@
+(v0.3.0)=
+
+0.3.0 2026-01-20
+Version 0.3.0 Has split the smftools dependencies into its core dependencies, as well as various optional dependencies depending on the user's intended use in order to keep the package as light as possible. The package can now use wither a CLI or a Python based backend for Samtools, Bedtools, and BedGraphToBigWig for smftools load functionality.

{smftools-0.2.5 → smftools-0.3.1}/docs/source/release-notes/index.md

@@ -2,6 +2,11 @@
 
 # Release notes
 
+### Version 0.3.0
+
+```{include} /release-notes/0.3.0.md
+```
+
 ### Version 0.2.3
 
 ```{include} /release-notes/0.2.3.md

smftools-0.3.1/docs/source/requirements.txt

@@ -0,0 +1,16 @@
+sphinx>=7,<8
+sphinx-book-theme>=1.1.0,<2
+sphinx-autodoc-typehints>=1.25.2,<4
+myst-parser>=2,<3
+myst-nb>=1,<2
+sphinx-design
+readthedocs-sphinx-search
+sphinxext-opengraph
+sphinx-copybutton>=0.5,<0.6
+sphinx-click>=5,<7
+nbsphinx>=0.9
+ipython>=7.20
+matplotlib!=3.6.1
+sphinxcontrib-bibtex
+setuptools
+pyyaml

{smftools-0.2.5 → smftools-0.3.1}/docs/source/tutorials/experiment_config.md

@@ -2,7 +2,8 @@
 
 smftools uses an experiment configuration CSV to define paths, modality settings, and workflow
 options. You can start from the repository template (`experiment_config.csv`) and fill in your
-experiment-specific values.
+experiment-specific values. The configuration CSV can override any parameter within the default.yaml
+and modality specific config .yamls found within the config subpackage of smftools.
 
 ## CSV format
 

{smftools-0.2.5 → smftools-0.3.1}/pyproject.toml

@@ -25,7 +25,7 @@ keywords = [
 readme = "README.md"
 classifiers = [
     "License :: OSI Approved :: MIT License",
-    "Development Status :: 2 - Pre-Alpha",
+    "Development Status :: 3 - Alpha",
     "Environment :: Console",
     "Intended Audience :: Developers",
     "Intended Audience :: Science/Research",
@@ -36,39 +36,17 @@ classifiers = [
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
-    "Programming Language :: Python :: 3.14",
     "Topic :: Scientific/Engineering :: Bio-Informatics",
     "Topic :: Scientific/Engineering :: Visualization"
 ]
 dependencies = [
     "anndata>=0.10.0",
     "biopython>=1.79",
-    "captum",
     "click",
-    "fastcluster",
-    "hydra-core",
-    "igraph",
-    "leidenalg",
-    "lightning",
-    "multiqc",
-    "networkx>=3.2",
     "numpy>=1.22.0,<2",
-    "omegaconf",
     "pandas>=1.4.2",
-    "pod5>=0.1.21",
-    "pyfaidx>=0.8.0",
-    "pybedtools>=0.12.0",
-    "pyBigWig>=0.3.24",
-    "pysam>=0.19.1",
-    "scanpy>=1.9",
-    "scikit-learn>=1.0.2",
     "scipy>=1.7.3",
-    "shap",
-    "seaborn>=0.11",
-    "torch>=1.9.0",
     "tqdm",
-    "upsetplot",
-    "wandb"
 ]
 dynamic = ["version"]
 
@@ -81,27 +59,130 @@ smftools = "smftools.cli_entry:cli"
 
 [project.optional-dependencies]
 
-dev = ["ruff", "pre-commit", "pytest", "pytest-cov"]
+dev = [
+    "ruff", 
+    "pre-commit", 
+    "pytest", 
+    "pytest-cov"]
 
 docs = [
-    "sphinx>=7",
-    "sphinx-book-theme>=1.1.0",
-    "sphinx-autodoc-typehints>=1.25.2",
-    "myst-parser>=2",
-    "myst-nb>=1",
+    "sphinx>=7,<8",
+    "sphinx-book-theme>=1.1,<2",
+    "sphinx-autodoc-typehints>=1.25.2,<4",
+    "myst-parser>=2,<3",
+    "myst-nb>=1,<2",
     "sphinx-design",
     "readthedocs-sphinx-search",
-    "sphinxext-opengraph",
-    "sphinx-copybutton",
-    "sphinx-click",
+    "sphinxext-opengraph>=0.9,<0.10",
+    "sphinx-copybutton>=0.5,<0.6",
+    "sphinx-click>=5,<7",
     "nbsphinx>=0.9",
     "ipython>=7.20",
     "matplotlib!=3.6.1",
-    "sphinxcontrib-bibtex",
+    "sphinxcontrib-bibtex>=2,<3",
     "setuptools",
     "pyyaml"
 ]
 
+cluster = [
+    "fastcluster",
+    "igraph",
+    "leidenalg",
+]
+
+misc = [
+    "networkx>=3.2",
+    "upsetplot",
+]
+
+ont = [
+    "pod5>=0.1.21",
+]
+
+plotting = [
+    "matplotlib>=3.6.2",
+    "seaborn>=0.11",
+]
+
+pybedtools = [
+    "pybedtools>=0.12.0",
+]
+
+pybigwig = [
+    "pyBigWig>=0.3.24",
+]
+
+pysam = [
+    "pysam>=0.19.1",
+]
+
+ml-base = [
+    "scikit-learn>=1.0.2",
+    "tensorly",
+    "torch>=1.9.0",
+]
+
+ml-extended = [
+    "captum",
+    "hydra-core",
+    "lightning",
+    "omegaconf",
+    "shap",
+    "wandb",
+]
+
+qc = [
+    "multiqc",
+]
+
+umap = [
+    "pynndescent>=0.5.10",
+    "umap-learn>=0.5.5",
+]
+
+torch = [
+    "torch>=1.9.0",
+]
+
+all = [
+    # cluster
+    "fastcluster",
+    "leidenalg",
+
+    # informatics
+    "pybedtools>=0.12.0",
+    "pyBigWig>=0.3.24",
+    "pysam>=0.19.1",
+
+    # misc
+    "networkx>=3.2",
+    "upsetplot",
+
+    # ont
+    "pod5>=0.1.21",
+
+    # plotting
+    "matplotlib>=3.6.2",
+    "seaborn>=0.11",
+
+    # ml
+    "captum",
+    "hydra-core",
+    "lightning",
+    "omegaconf",
+    "scikit-learn>=1.0.2",
+    "shap",
+    "torch>=1.9.0",
+    "wandb",
+
+    # umap
+    "pynndescent>=0.5.10",
+    "umap-learn>=0.5.5",
+
+    # qc
+    "multiqc",
+]
+
 [tool.hatch.build]
 sources = ["src"]
 
@@ -150,4 +231,4 @@ line-ending = "lf"
 
 [tool.ruff.lint]
 select = ["E", "F", "I", "B", "UP", "SIM", "ISC"]
-ignore = ["E501", "F", "B", "UP","SIM"]
+ignore = ["E501", "F", "B", "UP","SIM"]

{smftools-0.2.5 → smftools-0.3.1}/requirements.txt

@@ -1,31 +1,39 @@
-# Essential packages
+# Core
 anndata>=0.10.0
 biopython>=1.79
-captum
 click
+numpy>=1.22.0,<2
+pandas>=1.4.2
+pyfaidx>=0.8.0
+scipy>=1.7.3
+seaborn>=0.11
+tqdm
+
+# Graph / clustering
 fastcluster
-hydra-core
-leidenalg
-lightning
 igraph
 leidenalg
-lightning
-multiqc
 networkx>=3.2
-numpy>=1.22.0,<2
-omegaconf
-pandas>=1.4.2
+
+# Genomics / informatics
 pod5>=0.1.21
 pybedtools>=0.12.0
 pyBigWig>=0.3.24
-pyfaidx>=0.8.0
 pysam>=0.19.1
-scanpy>=1.11
+umap-learn>=0.5.5
+pynndescent>=0.5.10
+
+# ML / modeling
+captum
+hydra-core
+lightning
+omegaconf
 scikit-learn>=1.0.2
-scipy>=1.7.3
-seaborn>=0.11
 shap
+tensorly
 torch>=1.9.0
-tqdm
-upsetplot
 wandb
+
+# QC / viz
+multiqc
+upsetplot