umierrorcorrect2 0.30.0__tar.gz

umierrorcorrect2-0.30.0/.gitignore

@@ -0,0 +1,227 @@
+*.pyc
+.DS_Store
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+*.sam
+results*/
+.vscode/
+.claude/
+CLAUDE.md
+test_data/
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml*.fastq.gz
+*.fastq.gz

umierrorcorrect2-0.30.0/LICENSE.txt

@@ -0,0 +1,8 @@
+Copyright (c) 2019-2023 Tobias Osterlund
+Copyright (c) 2026 Stefan Filges
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

umierrorcorrect2-0.30.0/PKG-INFO

@@ -0,0 +1,104 @@
+Metadata-Version: 2.4
+Name: umierrorcorrect2
+Version: 0.30.0
+Summary: Pipeline for analyzing barcoded amplicon sequencing data with Unique Molecular Identifiers (UMI)
+Project-URL: Homepage, https://github.com/sfilges/umierrorcorrect
+Project-URL: Documentation, https://github.com/sfilges/umierrorcorrect/wiki
+Project-URL: Repository, https://github.com/sfilges/umierrorcorrect
+Author-email: Stefan Filges <stefan.filges@pm.me>, Tobias Osterlund <tobias.osterlund@gu.se>
+License-Expression: MIT
+License-File: LICENSE.txt
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.10
+Requires-Dist: loguru>=0.7.0
+Requires-Dist: matplotlib
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: pysam>=0.8.4
+Requires-Dist: scipy
+Requires-Dist: typer[all]>=0.9.0
+Provides-Extra: dev
+Requires-Dist: mypy; extra == 'dev'
+Requires-Dist: pre-commit; extra == 'dev'
+Requires-Dist: pytest; extra == 'dev'
+Requires-Dist: pytest-cov; extra == 'dev'
+Requires-Dist: ruff; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: sphinx; extra == 'docs'
+Requires-Dist: sphinx-rtd-theme; extra == 'docs'
+Provides-Extra: fast
+Requires-Dist: numba>=0.57.0; extra == 'fast'
+Description-Content-Type: text/markdown
+
+# UMIErrorCorrect2
+
+[![PyPI version](https://badge.fury.io/py/umierrorcorrect2.svg)](https://badge.fury.io/py/umierrorcorrect2)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+
+A modern, high-performance pipeline for analyzing barcoded amplicon sequencing data with Unique Molecular Identifiers (UMI).
+
+This package is a **complete modernization** of the original [UMIErrorCorrect](https://github.com/stahlberggroup/umierrorcorrect) published in *Clinical Chemistry* (2022).
+
+## Key Features
+
+- **High Performance**: Parallel processing of genomic regions and fastp-based preprocessing.
+- **Modern Tooling**: Built with `typer`, `pydantic`, `loguru`, and `hatch`.
+- **Easy Installation**: Fully PEP 621 compliant, installable via `pip` or `uv`.
+- **Comprehensive**: From raw FASTQ to error-corrected VCFs and consensus statistics.
+- **Robust**: Extensive test suite and type safety.
+
+## Dependencies
+
+- `fastp` for preprocessing
+- `bwa` for alignment
+
+## Installation
+
+Use [uv](https://github.com/astral-sh/uv) for lightning-fast installation:
+
+```bash
+uv pip install umierrorcorrect2
+```
+
+Or standard pip:
+
+```bash
+pip install umierrorcorrect2
+```
+
+## Quick Start
+
+The command-line tool is named `umierrorcorrect`. Run the full pipeline on a single sample:
+
+```bash
+umierrorcorrect batch \
+    -r1 sample_R1.fastq.gz \
+    -r2 sample_R2.fastq.gz \
+    -r hg38.fa \
+    -o results/ \
+    -ul 12 \
+    -sl 16 \
+    --fastp
+```
+
+For detailed instructions, see the **[User Guide](docs/USER_GUIDE.md)** or run:
+
+```bash
+umierrorcorrect --help
+```
+
+## Documentation
+
+- [User Guide](docs/USER_GUIDE.md): Detailed usage instructions for all commands.
+- [Implementation Details](docs/IMPLEMENTATION.md): Architecture and design overview.
+- [Docker Guide](docs/docker.md): Running with containers.
+
+## Citation
+
+> Osterlund T., Filges S., Johansson G., Stahlberg A. *UMIErrorCorrect and UMIAnalyzer: Software for Consensus Read Generation, Error Correction, and Visualization Using Unique Molecular Identifiers*, Clinical Chemistry, 2022. [doi:10.1093/clinchem/hvac136](https://doi.org/10.1093/clinchem/hvac136)

umierrorcorrect2-0.30.0/README.md

@@ -0,0 +1,68 @@
+# UMIErrorCorrect2
+
+[![PyPI version](https://badge.fury.io/py/umierrorcorrect2.svg)](https://badge.fury.io/py/umierrorcorrect2)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+
+A modern, high-performance pipeline for analyzing barcoded amplicon sequencing data with Unique Molecular Identifiers (UMI).
+
+This package is a **complete modernization** of the original [UMIErrorCorrect](https://github.com/stahlberggroup/umierrorcorrect) published in *Clinical Chemistry* (2022).
+
+## Key Features
+
+- **High Performance**: Parallel processing of genomic regions and fastp-based preprocessing.
+- **Modern Tooling**: Built with `typer`, `pydantic`, `loguru`, and `hatch`.
+- **Easy Installation**: Fully PEP 621 compliant, installable via `pip` or `uv`.
+- **Comprehensive**: From raw FASTQ to error-corrected VCFs and consensus statistics.
+- **Robust**: Extensive test suite and type safety.
+
+## Dependencies
+
+- `fastp` for preprocessing
+- `bwa` for alignment
+
+## Installation
+
+Use [uv](https://github.com/astral-sh/uv) for lightning-fast installation:
+
+```bash
+uv pip install umierrorcorrect2
+```
+
+Or standard pip:
+
+```bash
+pip install umierrorcorrect2
+```
+
+## Quick Start
+
+The command-line tool is named `umierrorcorrect`. Run the full pipeline on a single sample:
+
+```bash
+umierrorcorrect batch \
+    -r1 sample_R1.fastq.gz \
+    -r2 sample_R2.fastq.gz \
+    -r hg38.fa \
+    -o results/ \
+    -ul 12 \
+    -sl 16 \
+    --fastp
+```
+
+For detailed instructions, see the **[User Guide](docs/USER_GUIDE.md)** or run:
+
+```bash
+umierrorcorrect --help
+```
+
+## Documentation
+
+- [User Guide](docs/USER_GUIDE.md): Detailed usage instructions for all commands.
+- [Implementation Details](docs/IMPLEMENTATION.md): Architecture and design overview.
+- [Docker Guide](docs/docker.md): Running with containers.
+
+## Citation
+
+> Osterlund T., Filges S., Johansson G., Stahlberg A. *UMIErrorCorrect and UMIAnalyzer: Software for Consensus Read Generation, Error Correction, and Visualization Using Unique Molecular Identifiers*, Clinical Chemistry, 2022. [doi:10.1093/clinchem/hvac136](https://doi.org/10.1093/clinchem/hvac136)

umierrorcorrect2-0.30.0/pyproject.toml

@@ -0,0 +1,164 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+
+
+name = "umierrorcorrect2"
+dynamic = ["version"]
+description = "Pipeline for analyzing barcoded amplicon sequencing data with Unique Molecular Identifiers (UMI)"
+readme = "README.md"
+license = "MIT"
+requires-python = ">=3.10"
+authors = [
+    { name = "Stefan Filges", email = "stefan.filges@pm.me" },
+    { name = "Tobias Osterlund", email = "tobias.osterlund@gu.se" },
+]
+classifiers = [
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+]
+dependencies = [
+    "pysam>=0.8.4",
+    "scipy",
+    "matplotlib",
+    "loguru>=0.7.0",
+    "typer[all]>=0.9.0",
+    "pydantic>=2.0.0",
+]
+[project.optional-dependencies]
+dev = ["ruff", "pytest", "pytest-cov", "mypy", "pre-commit"]
+docs = ["sphinx", "sphinx-rtd-theme"]
+fast = ["numba>=0.57.0"]
+
+[project.scripts]
+umierrorcorrect = "umierrorcorrect.cli:main_cli"
+
+[project.urls]
+Homepage = "https://github.com/sfilges/umierrorcorrect"
+Documentation = "https://github.com/sfilges/umierrorcorrect/wiki"
+Repository = "https://github.com/sfilges/umierrorcorrect"
+
+[tool.hatch.version]
+path = "umierrorcorrect/version.py"
+
+[tool.hatch.build.targets.sdist]
+include = ["/umierrorcorrect", "/test_data", "/doc"]
+
+[tool.hatch.build.targets.wheel]
+packages = ["umierrorcorrect"]
+
+# Ruff configuration
+[tool.ruff]
+target-version = "py39"
+line-length = 120
+src = ["umierrorcorrect"]
+
+[tool.ruff.lint]
+select = [
+    "E",   # pycodestyle errors
+    "W",   # pycodestyle warnings
+    "F",   # Pyflakes
+    "I",   # isort
+    "B",   # flake8-bugbear
+    "C4",  # flake8-comprehensions
+    "UP",  # pyupgrade
+    "ARG", # flake8-unused-arguments
+    "SIM", # flake8-simplify
+    "S",   # flake8-bandit (security)
+    "PTH", # flake8-use-pathlib
+]
+ignore = [
+    "E501", # line too long (handled by formatter)
+    "S101", # assert usage (ok in tests)
+    "S603", # subprocess calls - expected for CLI tool that runs bwa, pigz, gzip, cutadapt
+    "S607", # partial executable path - expected for CLI tool (e.g., ["bwa", "mem", ...])
+    "S301", # pickle usage - used intentionally for caching in MSA alignment
+]
+fixable = ["ALL"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/*" = ["S101", "ARG", "S311"] # S311: random ok for test data
+"umierrorcorrect/cli.py" = ["ARG001"] # version arg used by typer callback
+"umierrorcorrect/core/consensus.py" = [
+    "ARG001",
+    "SIM108",
+    "SIM201",
+    "B007",
+] # ref arg part of function signature; ternary would reduce readability
+"umierrorcorrect/core/get_cons_info.py" = [
+    "ARG001",
+    "SIM201",
+    "SIM108",
+    "PTH123",
+] # indel_freq args part of API; debug code in __main__
+"umierrorcorrect/core/check_args.py" = [
+    "SIM102",
+] # nested if is clearer for validation errors
+"umierrorcorrect/core/umi_cluster.py" = [
+    "PTH123",
+] # hardcoded debug paths in __main__ block
+"umierrorcorrect/umi_error_correct.py" = [
+    "SIM108",
+] # ternary would reduce readability for complex expressions
+"umierrorcorrect/preprocess.py" = ["SIM108"] # ternary would reduce readability
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+
+# Pytest configuration
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py"]
+python_functions = ["test_*"]
+addopts = ["-v", "--tb=short", "--strict-markers"]
+markers = [
+    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
+    "integration: marks tests as integration tests",
+    "requires_bwa: marks tests that require bwa installed",
+]
+filterwarnings = ["ignore::DeprecationWarning:pysam.*"]
+
+# Coverage configuration
+[tool.coverage.run]
+source = ["umierrorcorrect"]
+branch = true
+omit = ["*/test_*.py", "*/__init__.py"]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "if __name__ == .__main__.:",
+    "raise NotImplementedError",
+]
+show_missing = true
+
+# Mypy configuration
+[tool.mypy]
+python_version = "3.10"
+warn_return_any = false
+warn_unused_configs = true
+allow_redefinition = true
+ignore_missing_imports = true
+exclude = ["tests/", "build/"]
+
+[[tool.mypy.overrides]]
+module = "pysam.*"
+ignore_missing_imports = true
+
+[[tool.mypy.overrides]]
+module = [
+    "umierrorcorrect.core.consensus",
+    "umierrorcorrect.core.umi_cluster",
+    "umierrorcorrect.umi_error_correct",
+    "umierrorcorrect.get_consensus_statistics",
+    "umierrorcorrect.cli",
+    "umierrorcorrect.core.logging_config"
+]
+ignore_errors = true

umierrorcorrect2-0.30.0/umierrorcorrect/align.py

@@ -0,0 +1,104 @@
+#!/usr/bin/env python3
+import subprocess
+import sys
+from pathlib import Path
+
+import pysam
+
+from umierrorcorrect.core.logging_config import get_logger, log_subprocess_stderr
+
+logger = get_logger(__name__)
+
+
+def _cleanup_files(*files: Path) -> None:
+    """Remove files if they exist."""
+    for f in files:
+        if f.exists():
+            f.unlink()
+
+
+def check_bwa_index(reference_file: str | Path) -> None:
+    """Check if BWA index files exists, otherwise create."""
+    ref_path = Path(reference_file)
+    if not ref_path.is_file():
+        logger.error(f"Reference genome file {reference_file} does not exist, exiting")
+        sys.exit(1)
+
+    if not Path(str(reference_file) + ".bwt").is_file():  # check if index exists
+        logger.warning(f"BWA index for reference genome file {reference_file} does not exist")
+        answer = input("Do you want to create a BWA index now? (y/n) ").lower().strip()
+        while answer not in ("y", "yes", "n", "no"):
+            logger.warning("Answer yes or no")
+            answer = input("Do you want to create a BWA index now? (y/n) ").lower().strip()
+        if answer[0] != "y":
+            sys.exit(1)
+        try:
+            logger.info("Creating BWA index...")
+            result = subprocess.run(
+                ["bwa", "index", reference_file],
+                capture_output=True,
+                check=True,
+            )
+            log_subprocess_stderr(result.stderr, "bwa-index")
+        except subprocess.CalledProcessError as e:
+            logger.error(f"bwa index failed: {e.stderr.decode() if e.stderr else 'Unknown error'}")
+            sys.exit(1)
+
+
+def align_bwa(
+    num_threads: int,
+    reference_file: str | Path,
+    fastq_files: list[str | Path],
+    output_path: str | Path,
+    sample_name: str,
+    remove_large_files: bool,
+) -> str | None:
+    """Align reads with BWA to create a SAM file, then convert it to BAM, sort and index the file."""
+    logger.info("Starting alignment with BWA")
+
+    # Validate inputs
+    output_dir = Path(output_path)
+    if not output_dir.is_dir():
+        logger.error(f"Output directory {output_path} does not exist")
+        return None
+
+    if not 1 <= len(fastq_files) <= 2:
+        logger.error(f"Expected 1 or 2 FASTQ files, got {len(fastq_files)}")
+        return None
+
+    check_bwa_index(reference_file)
+
+    output_base = output_dir / sample_name
+    sam_file = output_base.with_suffix(".sam")
+    bam_file = output_base.with_suffix(".bam")
+    sorted_bam = output_base.parent / f"{sample_name}.sorted.bam"
+    logger.info(f"Creating output file: {sorted_bam}")
+
+    bwacommand = ["bwa", "mem", "-t", str(num_threads), str(reference_file), *[str(f) for f in fastq_files]]
+
+    try:
+        with sam_file.open("w") as g:
+            result = subprocess.run(bwacommand, stdout=g, stderr=subprocess.PIPE, check=True)
+            log_subprocess_stderr(result.stderr, "bwa-mem")
+    except subprocess.CalledProcessError as e:
+        logger.error(f"bwa mem failed: {e.stderr.decode() if e.stderr else 'Unknown error'}")
+        _cleanup_files(sam_file)
+        return None
+
+    try:
+        pysam.view("-Sb", "-@", str(num_threads), str(sam_file), "-o", str(bam_file), catch_stdout=False)
+        pysam.sort("-@", str(num_threads), str(bam_file), "-o", str(sorted_bam), catch_stdout=False)
+        pysam.index(str(sorted_bam), catch_stdout=False)
+    except pysam.SamtoolsError as e:
+        logger.error(f"SAM/BAM processing failed: {e}")
+        _cleanup_files(sam_file, bam_file)
+        return None
+    finally:
+        _cleanup_files(sam_file, bam_file)
+
+    if remove_large_files:
+        for fastq in fastq_files:
+            Path(fastq).unlink()
+
+    logger.info("Finished alignment")
+    return str(sorted_bam)