pymethyl2sam 0.1.2__py3-none-any.whl

pymethyl2sam-0.1.2.dist-info/METADATA

@@ -0,0 +1,267 @@
+Metadata-Version: 2.4
+Name: pymethyl2sam
+Version: 0.1.2
+Summary: Simulate DNA methylation and generate synthetic NGS reads with methylation tags.
+Author-email: Yoni Weissler <yoni.weissler@gmail.com>
+License: MIT
+Project-URL: Homepage, https://github.com/yoni-w/pymethyl2sam
+Project-URL: Repository, https://github.com/yoni-w/pymethyl2sam
+Project-URL: Documentation, https://pymethyl2sam.readthedocs.io
+Project-URL: Issues, https://github.com/yoni-w/pymethyl2sam/issues
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+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
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Operating System :: MacOS :: MacOS X
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: pysam>=0.21.0
+Requires-Dist: numpy>=1.21.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: click>=8.0.0
+Requires-Dist: typing-extensions>=4.0.0
+Requires-Dist: importlib-metadata>=8.7.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: pylint>=3.2.0; extra == "dev"
+Requires-Dist: pre-commit>=3.2.0; extra == "dev"
+Requires-Dist: sphinx>=6.0.0; extra == "dev"
+Requires-Dist: sphinx-rtd-theme>=1.2.0; extra == "dev"
+Requires-Dist: coverage[toml]>=7.0.0; extra == "dev"
+
+# pymethyl2sam
+
+A Python package for simulating DNA methylation and generating synthetic NGS reads with methylation tags (MM/ML) in SAM/BAM format.
+
+## Overview
+
+pymethyl2sam provides a comprehensive framework for simulating DNA methylation patterns and generating synthetic next-generation sequencing reads with proper methylation tags. The package supports both stochastic (random) and deterministic (pattern-based) read generation modes, making it suitable for testing methylation analysis pipelines and educational purposes.
+
+## Features
+
+- **Dual Read Generation Modes**: Random (stochastic) and pattern-based (deterministic) simulation
+- **Flexible Methylation Modeling**: Support for fully, partially, or unmethylated sites
+- **Valid SAM/BAM Output**: Generates properly formatted files with MM/ML methylation tags
+- **Configurable Parameters**: Coverage, read length, error rates, strand bias
+- **Zero-based Coordinates**: Consistent with bioinformatics conventions
+- **Extensible Architecture**: Modular, layered design for easy extension
+
+## Installation
+
+### From PyPI (when available)
+```bash
+pip install pymethyl2sam
+```
+
+### From Source
+```bash
+git clone https://github.com/yoni-w/pymethyl2sam.git
+cd pymethyl2sam
+pip install -e .
+```
+
+### Development Installation
+```bash
+git clone https://github.com/yoni-w/pymethyl2sam.git
+cd pymethyl2sam
+pip install -e ".[dev]"
+```
+
+## Quick Start
+
+### Basic Usage (Random Mode)
+
+```python
+from pymethyl2sam import MethylationSimulator
+from pymethyl2sam.core import MethylationSite
+from pymethyl2sam.core.genomics import StrandOrientation
+from pymethyl2sam.core.reference_genome import Hg38ReferenceGenome
+from pymethyl2sam.core.sequencing import ReadGenerator, RandomStrategy
+from pymethyl2sam.simulator import SequencedChromosome, SequencedRegion
+
+# Create simulator with random read generation
+simulator = MethylationSimulator(
+    chromosomes=[
+        SequencedChromosome(
+            name="chr1",
+            length=20_000,
+            regions=[
+                SequencedRegion(
+                    start=10100,
+                    end=10450,
+                    read_generator=ReadGenerator(strategy=RandomStrategy()),
+                )
+            ],
+            cpg_sites=[
+                MethylationSite(position=10100, methylation_prob=1.0),
+                MethylationSite(position=10149, methylation_prob=1.0),
+                MethylationSite(position=10155, methylation_prob=0.0),
+                MethylationSite(position=10200, methylation_prob=0.0),
+                MethylationSite(position=10220, methylation_prob=1.0),
+            ],
+        )
+    ],
+    reference_genome=Hg38ReferenceGenome(),
+)
+
+# Generate reads and write to BAM
+simulator.simulate_reads("output.bam")
+```
+
+### Pattern-Based Simulation
+
+```python
+from pymethyl2sam import MethylationSimulator
+from pymethyl2sam.core import MethylationSite
+from pymethyl2sam.core.genomics import StrandOrientation
+from pymethyl2sam.core.reference_genome import Hg38ReferenceGenome
+from pymethyl2sam.core.sequencing import ReadGenerator, PatternStrategy
+from pymethyl2sam.simulator import SequencedChromosome, SequencedRegion
+
+# Create simulator with pattern-based read generation
+simulator = MethylationSimulator(
+    chromosomes=[
+        SequencedChromosome(
+            name="chr1",
+            length=20_000,
+            regions=[
+                SequencedRegion(
+                    start=10100,
+                    end=10250,
+                    read_generator=ReadGenerator(
+                        read_length=150,
+                        strategy=PatternStrategy.from_offsets(
+                            offsets=[0] * 10,
+                            orientation=StrandOrientation.RANDOM,
+                        ),
+                    ),
+                )
+            ],
+            cpg_sites=[
+                MethylationSite(position=10100, methylation_prob=1.0),
+                MethylationSite(position=10149, methylation_prob=1.0),
+                MethylationSite(position=10155, methylation_prob=0.0),
+                MethylationSite(position=10200, methylation_prob=0.0),
+                MethylationSite(position=10220, methylation_prob=1.0),
+            ],
+        )
+    ],
+    reference_genome=Hg38ReferenceGenome(),
+)
+
+# Generate reads and write to BAM
+simulator.simulate_reads("pattern_output.bam")
+```
+
+## Architecture
+
+The package is organized in layers by functional responsibility:
+
+- **core/**: Domain logic for methylation modeling, sequencing, and errors
+- **simulator/**: Orchestration of read and methylation simulation
+- **io/**: Parsers and I/O for FASTA, BED, YAML, JSON
+- **utils/**: Logging, constants, shared helpers
+
+### Core Components
+
+- `MethylationSimulator`: Main class for orchestrating simulation
+- `SequencedChromosome`: Represents a chromosome with defined regions and methylation sites
+- `SequencedRegion`: Defines genomic regions where reads should be generated
+- `ReadGenerator`: Handles read generation with different strategies (Random/Pattern)
+- `MethylationSite`: Represents individual methylation sites with probabilities
+- `ReferenceGenomeProvider`: Interface for accessing reference genome sequences
+
+## Configuration Examples
+
+### YAML Configuration Files
+
+See `examples/config_random.yaml` and `examples/templates_pattern.yaml` for configuration file examples.
+
+## Coordinate System
+
+All genomic coordinates follow zero-based, half-open intervals `[start, end)`:
+
+- A 5-base interval starting at position 100 is `[100, 105)`
+- Read coordinates and methylation positions adhere to this system
+- MM/ML tags follow strand-specific SAM/BAM conventions
+
+## Testing
+
+Run the test suite:
+
+```bash
+pytest
+```
+
+Run with coverage:
+
+```bash
+pytest --cov=pymethyl2sam --cov-report=html
+```
+
+## Development
+
+### Code Formatting
+
+```bash
+black src/ tests/
+```
+
+### Linting
+
+```bash
+pylint src/pymethyl2sam/
+```
+
+### Pre-commit Hooks
+
+```bash
+pre-commit install
+```
+
+## Examples
+
+See the `examples/` directory for complete working examples:
+
+- `simulate_cpgs.py`: Demonstrates both random and pattern-based simulation
+- `config_random.yaml`: YAML configuration for random mode
+- `templates_pattern.yaml`: YAML template for pattern-based simulation
+
+## Documentation
+
+For detailed API documentation, visit: https://pymethyl2sam.readthedocs.io
+
+## License
+
+This project is licensed under the MIT License - see the LICENSE file for details.
+
+## Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Add tests for new functionality
+5. Ensure all tests pass
+6. Submit a pull request
+
+## Citation
+
+If you use pymethyl2sam in your research, please cite:
+
+```
+pymethyl2sam: A Python package for simulating DNA methylation and generating synthetic NGS reads
+Yoni Weissler, 2025
+```
+
+## Support
+
+- **Issues**: https://github.com/yoni-w/pymethyl2sam/issues
+- **Documentation**: https://pymethyl2sam.readthedocs.io
+- **Email**: yoni.weissler@gmail.com

pymethyl2sam-0.1.2.dist-info/RECORD

@@ -0,0 +1,19 @@
+pymethyl2sam/__init__.py,sha256=i77oQcOBi5jaBcdVUKWuWut75vIk2P_7f3Iu_tQ7ZbU,389
+pymethyl2sam/core/__init__.py,sha256=S1iH9qNjQKZEDq4pZ_FaS7rv5HfngChS5VI8q28sj9U,189
+pymethyl2sam/core/errors.py,sha256=H-_Vk9ke-YzAuHn2FTnRtoNYgfB0ctAraeAjSqMSyIY,7400
+pymethyl2sam/core/genomics.py,sha256=CPtfUkmjow-xrgR6vViGJB1s5Vnn8z9MfsCB_ReiFcE,3325
+pymethyl2sam/core/reference_genome.py,sha256=XJBfz004h0-EEOaW2rLIz3uN9wFATjMBv5txT7aSmyc,3209
+pymethyl2sam/core/sequencing.py,sha256=yg4WZbNccwY66FYUjzD7aSIR85fk-W_3n6N176F5apI,6619
+pymethyl2sam/io/__init__.py,sha256=49n5vuex_Y6jHo-qLnPnfDwt1wx4IX2JDc7NZyrbv3s,128
+pymethyl2sam/io/genome_loader.py,sha256=YE2rXnX9-K57xkxRgtG9Tc_HnkNeC_E4Lq_fAVitPKc,5231
+pymethyl2sam/simulator/__init__.py,sha256=ptElyO2y3E6-QIS8cV1WgKhR_Fq3TwJoBPj0zr1Uvgw,340
+pymethyl2sam/simulator/simulator.py,sha256=IWWypLK9zKvS-yCtyukNd3iZ_P_kI0eQEXqllkZN5y0,7632
+pymethyl2sam/simulator/summary.py,sha256=8X0QpqPt8yKICMBRmcdz8Lp2DYkvfGh1y_2zmZeq-5Q,2501
+pymethyl2sam/utils/__init__.py,sha256=5MyXuQEcjk9RfU87MD2cgUtJEJxkTS8oylT6Yr47MGQ,132
+pymethyl2sam/utils/constants.py,sha256=2ldM9q1tYX78zIylrirqHT1-GXlm7kuQfmm2T5fopE8,1256
+pymethyl2sam/utils/logging.py,sha256=bDUxk6cdhgjmLHiL0mWOOq72lYtYHSFWjwl0Yduk37E,1520
+pymethyl2sam/utils/pysam.py,sha256=4897IPyCn4BV49QtdjcpPKgff7DF9P1fZicErHwaDEk,2834
+pymethyl2sam-0.1.2.dist-info/METADATA,sha256=AUV_3J2YvJISPD3qOEovURoFMUiJE64EJfu0ZF8whAk,8579
+pymethyl2sam-0.1.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+pymethyl2sam-0.1.2.dist-info/top_level.txt,sha256=9LCoHbvPZhQO2KrjnRLsPf2TIzz5u9VPkr1YtbDQ_TY,13
+pymethyl2sam-0.1.2.dist-info/RECORD,,

pymethyl2sam-0.1.2.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

pymethyl2sam-0.1.2.dist-info/top_level.txt

@@ -0,0 +1 @@
+pymethyl2sam