methylseg 0.1.8__tar.gz

methylseg-0.1.8/LICENSE

@@ -0,0 +1,28 @@
+BSD 3-Clause License
+
+Copyright (c) 2026, Clement Lab
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

methylseg-0.1.8/PKG-INFO

@@ -0,0 +1,320 @@
+Metadata-Version: 2.4
+Name: methylseg
+Version: 0.1.8
+Summary: Methylation segmentation utilities used in the TCGA methylation analysis repo.
+Project-URL: Documentation, https://clementlab.github.io/MethylSeg/
+Project-URL: Repository, https://github.com/clementlab/MethylSeg
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cthmm>=0.0.3
+Requires-Dist: hmmlearn>=0.3.3
+Requires-Dist: joblib>=1.5
+Requires-Dist: matplotlib>=3.8
+Requires-Dist: numba>=0.60
+Requires-Dist: numpy>=1.26
+Requires-Dist: pandas>=2.2
+Requires-Dist: panel>=1.4
+Requires-Dist: plotly>=5.24
+Requires-Dist: pybedtools>=0.12.0
+Requires-Dist: pyarrow>=17.0
+Requires-Dist: PyYAML>=6.0
+Requires-Dist: scikit-learn>=1.5
+Requires-Dist: seaborn>=0.13
+Requires-Dist: tqdm>=4.66
+Requires-Dist: umap-learn>=0.5
+Requires-Dist: gdown>=6.0
+Requires-Dist: nbformat>=4.2.0
+Provides-Extra: docs
+Requires-Dist: ipykernel; extra == "docs"
+Requires-Dist: myst-parser>=4.0; extra == "docs"
+Requires-Dist: nbsphinx>=0.9.6; extra == "docs"
+Requires-Dist: Sphinx>=7.4.7; extra == "docs"
+Requires-Dist: sphinx-autobuild>=2024.4.16; extra == "docs"
+Requires-Dist: sphinx-rtd-theme>=2.0.0; extra == "docs"
+Provides-Extra: test
+Requires-Dist: pytest>=8.0; extra == "test"
+Dynamic: license-file
+
+# MethylSeg
+
+![logo](https://raw.githubusercontent.com/clementlab/MethylSeg/main/logo.png)
+
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.22904886.svg)](https://doi.org/10.5281/zenodo.22904886)
+
+MethylSeg is a Python toolkit for identifying methylation domains from
+whole-genome bisulfite sequencing (WGBS) and microarray methylation data. It
+supports data preparation, methylation-state model training, genome
+segmentation, region cleaning, and visualization.
+
+This introduces the standard workflow. For the complete API reference
+and example notebooks, see the [MethylSeg documentation](https://clementlab.github.io/MethylSeg/).
+
+> [!IMPORTANT]
+> Microarray support has currently been tested with Illumina HumanMethylation450 BeadChip (HM450K) data. Other methylation microarrays, such as Illumina HumanMethylation27 and MethylationEPIC, can be used, but array-specific defaults are not yet available and these platforms have not been formally tested.
+
+## Hardware requirements
+
+Memory usage depends on the input data type and dataset size. The following
+values were observed during testing:
+
+| Data type | Typical memory usage | Recommended system memory |
+| --- | ---: | ---: |
+| WGBS | ~12 GB average; up to ~15 GB peak | ≥16 GB |
+| HM450K | <1 GB | ≥8 GB |
+
+> [!NOTE]
+> Numba has known compatibility issues on ARM-based systems. See the
+> [Troubleshooting guide](https://github.com/clementlab/MethylSeg/blob/main/TROUBLESHOOTING.md)
+> for installation guidance.
+
+## Installation
+
+Install from PyPI
+
+```bash
+python -m pip install methylseg
+```
+
+or install the current version from GitHub:
+
+```bash
+python -m pip install "git+https://github.com/clementlab/MethylSeg.git"
+```
+
+## Reference files
+
+### Sample data
+
+Three reference samples are available for use in tutorials and testing.
+
+```bash
+methylseg download_data_files
+```
+
+The two colon cancer samples were originally generated by Hansen et al. (2011) and were obtained from the data distributed with MethyLasso (Balaramane et al., 2024).
+
+The liver cancer sample, `TCGA-BD-A3EP-01A`, was obtained from the [TCGA-LIHC project through the NCI Genomic Data Commons](https://portal.gdc.cancer.gov/cases/de302b98-250d-42fe-9945-11e1b2bbd3c6).
+
+| Sample name | WGBS filename | HM450K filename |
+| --- | --- | --- |
+| `WGBS_colon-primary-tumor_1` | `WGBS_colon-primary-tumor_1_wgbs.tsv` | `WGBS_colon-primary-tumor_1_450k.beta` |
+| `WGBS_colon-primary-tumor_2` | `WGBS_colon-primary-tumor_2_wgbs.tsv` | `WGBS_colon-primary-tumor_2_450k.beta` |
+| `TCGA-BD-A3EP-01A` | N/A | `TCGA-BD-A3EP-01A_450k.tsv` |
+
+#### References
+
+1. Hansen, K. D., et al. Increased methylation variation in epigenetic domains across cancer types. *Nature Genetics* **43**, 768–775 (2011).
+2. Balaramane, D., Spill, Y. G., Weber, M. & Bardet, A. F. MethyLasso: a segmentation approach to analyze DNA methylation patterns and identify differentially methylated regions from whole-genome datasets. *Nucleic Acids Research* **52**, e98 (2024).
+
+### Pretrained models
+
+Two pretrained models are provided for tutorials, testing, and exploratory
+analysis:
+
+| Model filename | Training data |
+| --- | --- |
+| `wgbs_colon_model` | `WGBS_colon-primary-tumor_1_wgbs.tsv` |
+| `tcga_hm450k_model` | `TCGA-BD-A3EP-01A_450k.tsv` |
+
+Load a pretrained model with `get_pretrained_model`:
+
+```python
+# WGBS model
+wgbs_saved = MethylSegPathway.get_pretrained_model(
+    out_dir=OUTPUT_DIR,
+    resolution="wgbs",
+)
+
+# HM450K model
+hm450k_saved = MethylSegPathway.get_pretrained_model(
+    out_dir=OUTPUT_DIR,
+    resolution="450k",
+)
+```
+
+## Quickstart
+
+The default workflow trains a model on your input, segments the sample,
+cleans the calls, and draws a cleaned methylation state overlay.
+
+Use `resolution="wgbs"` for WGBS count tables or `resolution="450k"` for HM450K
+beta-value tables. Other microarray platforms may require manually configured
+parameters until array-specific defaults are added.
+
+```python
+from pathlib import Path
+
+from methylseg import MethylSegPathway, MethylationStates
+from methylseg.helper_classes import DATA_DIR
+
+reference_dir = DATA_DIR / "reference_files"
+
+# WGBS: replace these with your own sample name and count table.
+# sample_name = "WGBS_colon-primary-tumor_1"
+# sample_file = reference_dir / "WGBS_colon-primary-tumor_1_wgbs.tsv.gz"
+# resolution = "wgbs"
+
+# TCGA/HM450K alternative:
+sample_name = "TCGA-BD-A3EP-01A"
+sample_file = reference_dir / "TCGA-BD-A3EP-01A_450k.tsv.gz"
+resolution = "450k"
+
+sample_info, removed_df = MethylSegPathway.prepare_sample_info(
+    sample_name=sample_name,
+    sample_file=sample_file,
+    resolution=resolution,
+    remove_low_coverage_like_cpgs=True,
+)
+
+pathway = MethylSegPathway(
+    train_sample_info=sample_info,
+    out_dir=Path("out/quickstart") / sample_name,
+)
+
+pathway.run_pathway()
+
+fig = pathway.plot_labels(
+    sample_info=sample_info,
+    sample_info_removed=removed_df,
+    chrom="chr1",
+    region_start=2_200_000,
+    region_end=3_700_000
+)
+```
+
+![quickstart output](https://raw.githubusercontent.com/clementlab/MethylSeg/main/quickstart.png)
+
+`run_pathway(sample_info=sample_info, chroms=["chr1"])` performs fitting,
+segmentation, cleaning, and summary-file writing in one call.
+
+## Input formats
+
+MethylSeg accepts tab-delimited `.tsv` and `.tsv.gz` files containing DNA methylation measurements. Genomic coordinates must use the 0-based, half-open coordinate system, and chromosome names must be consistent throughout each file.
+
+Two BED-like input formats are supported.
+
+### Beta-value format
+
+This format can be used for either WGBS or microarray data. It contains four required columns:
+
+1. chromosome;
+2. CpG start position;
+3. CpG end position; and
+4. methylation beta value.
+
+For microarray data, an optional fifth column containing the probe identifier may be included. Probe identifiers are retained as metadata.
+
+| CpG_chrm | CpG_beg | CpG_end | beta | probe      |
+| -------- | ------: | ------: | ---: | ---------- |
+| chr1     |   15864 |   15866 |  0.0 | cg13869341 |
+| chr1     |   29406 |   29408 |  0.0 | cg12045430 |
+| chr1     |   29424 |   29426 |  0.0 | cg20826792 |
+
+
+### WGBS count format
+
+This format contains five required columns:
+
+1. chromosome;
+2. CpG start position;
+3. CpG end position;
+4. methylated read count; and
+5. total read coverage.
+
+MethylSeg calculates the beta value internally as: 
+$
+\mathrm{beta} = \frac{\mathrm{methylated\ reads}}{\mathrm{total\ coverage}}.
+$
+
+| CpG_chrm | CpG_beg | CpG_end | meth | coverage |
+| -------- | ------: | ------: | ---: | -------: |
+| chr1     |   10468 |   10470 |   14 |       15 |
+| chr1     |   10470 |   10472 |   10 |       10 |
+| chr1     |   10483 |   10485 |   23 |       28 |
+
+
+## Outputs
+
+The final output of MethylSeg consists primarily of BED files containing the
+identified methylation domains. Separate files are generated for each
+methylation state: `HIGH`, `INTERMEDIATE`, `LOW`, and `PMD`.
+
+For each chromosome and state, MethylSeg writes:
+
+| Output | Filename pattern | Description |
+| --- | --- | --- |
+| Raw regions | `segments_{chrom}_{sample_id}_{resolution}_{state}.bed` | Regions produced directly by genome segmentation |
+| Cleaned regions | `clean_regions/segments_cleaned_{chrom}_{sample_id}_{resolution}_{state}.bed` | Regions retained after merging and filtering |
+| Cleaned metadata | `clean_regions/metadata_cleaned_{chrom}_{sample_id}_{resolution}_{state}.tsv` | Additional information about the cleaned regions |
+
+After all requested chromosomes have been processed, MethylSeg also creates
+genome-wide files for each state under `summary_files/`:
+
+| Output | Filename pattern |
+| --- | --- |
+| Genome-wide raw regions | `segments_raw_{state}.bed` |
+| Genome-wide cleaned regions | `segments_cleaned_{state}.bed` |
+| Genome-wide cleaned metadata | `metadata_cleaned_{state}.tsv` |
+
+A simplified output directory has the following structure:
+
+```text
+methylseg_output/
+├── segments_chr1_sample.wgbs_PMD.bed
+├── segments_chr1_sample.wgbs_LOW.bed
+├── clean_regions/
+│   ├── segments_cleaned_chr1_sample.wgbs_PMD.bed
+│   ├── segments_cleaned_chr1_sample.wgbs_LOW.bed
+│   ├── metadata_cleaned_chr1_sample.wgbs_PMD.tsv
+│   └── metadata_cleaned_chr1_sample.wgbs_LOW.tsv
+└── summary_files/
+    ├── segments_raw_PMD.bed
+    ├── segments_raw_LOW.bed
+    ├── segments_cleaned_PMD.bed
+    ├── segments_cleaned_LOW.bed
+    ├── metadata_cleaned_PMD.tsv
+    └── metadata_cleaned_LOW.tsv
+```
+
+Each BED file contains 0-based, half-open genomic coordinates and the assigned
+methylation state. For example, segments_cleaned_PMD.bed may contain:
+
+| Chromosome |     Start |       End | State |
+| ---------- | --------: | --------: | ----- |
+| `chr1`     | 1,261,344 | 1,323,691 | `PMD` |
+| `chr1`     | 2,789,167 | 2,999,312 | `PMD` |
+| `chr1`     | 3,885,138 | 3,916,529 | `PMD` |
+| `chr1`     | 6,167,866 | 6,186,177 | `PMD` |
+
+The BED files themselves are tab-delimited and do not contain a header.
+
+## Citation
+
+If you use MethylSeg, please cite the software using the
+[CITATION.cff](https://github.com/clementlab/MethylSeg/blob/main/CITATION.cff)
+metadata. On GitHub, select **Cite this repository** to copy the citation in APA
+or BibTeX format.
+
+A manuscript describing MethylSeg is in preparation. Its citation will be added
+when available.
+
+## Planned support
+
+See [ROADMAP.md](https://github.com/clementlab/MethylSeg/blob/main/ROADMAP.md)
+
+## Reporting issues
+
+To report a bug, request a feature, or ask a question about MethylSeg, open an
+issue on the [GitHub issue tracker](https://github.com/clementlab/MethylSeg/issues).
+
+When reporting a bug, please include:
+
+- Your MethylSeg version
+- Your Python version and operating system
+- The complete error message or traceback
+- A minimal example that reproduces the problem, when possible
+
+## License
+
+MethylSeg is distributed under the [BSD 3-Clause License](LICENSE.md).

methylseg-0.1.8/README.md

@@ -0,0 +1,282 @@
+# MethylSeg
+
+![logo](https://raw.githubusercontent.com/clementlab/MethylSeg/main/logo.png)
+
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.22904886.svg)](https://doi.org/10.5281/zenodo.22904886)
+
+MethylSeg is a Python toolkit for identifying methylation domains from
+whole-genome bisulfite sequencing (WGBS) and microarray methylation data. It
+supports data preparation, methylation-state model training, genome
+segmentation, region cleaning, and visualization.
+
+This introduces the standard workflow. For the complete API reference
+and example notebooks, see the [MethylSeg documentation](https://clementlab.github.io/MethylSeg/).
+
+> [!IMPORTANT]
+> Microarray support has currently been tested with Illumina HumanMethylation450 BeadChip (HM450K) data. Other methylation microarrays, such as Illumina HumanMethylation27 and MethylationEPIC, can be used, but array-specific defaults are not yet available and these platforms have not been formally tested.
+
+## Hardware requirements
+
+Memory usage depends on the input data type and dataset size. The following
+values were observed during testing:
+
+| Data type | Typical memory usage | Recommended system memory |
+| --- | ---: | ---: |
+| WGBS | ~12 GB average; up to ~15 GB peak | ≥16 GB |
+| HM450K | <1 GB | ≥8 GB |
+
+> [!NOTE]
+> Numba has known compatibility issues on ARM-based systems. See the
+> [Troubleshooting guide](https://github.com/clementlab/MethylSeg/blob/main/TROUBLESHOOTING.md)
+> for installation guidance.
+
+## Installation
+
+Install from PyPI
+
+```bash
+python -m pip install methylseg
+```
+
+or install the current version from GitHub:
+
+```bash
+python -m pip install "git+https://github.com/clementlab/MethylSeg.git"
+```
+
+## Reference files
+
+### Sample data
+
+Three reference samples are available for use in tutorials and testing.
+
+```bash
+methylseg download_data_files
+```
+
+The two colon cancer samples were originally generated by Hansen et al. (2011) and were obtained from the data distributed with MethyLasso (Balaramane et al., 2024).
+
+The liver cancer sample, `TCGA-BD-A3EP-01A`, was obtained from the [TCGA-LIHC project through the NCI Genomic Data Commons](https://portal.gdc.cancer.gov/cases/de302b98-250d-42fe-9945-11e1b2bbd3c6).
+
+| Sample name | WGBS filename | HM450K filename |
+| --- | --- | --- |
+| `WGBS_colon-primary-tumor_1` | `WGBS_colon-primary-tumor_1_wgbs.tsv` | `WGBS_colon-primary-tumor_1_450k.beta` |
+| `WGBS_colon-primary-tumor_2` | `WGBS_colon-primary-tumor_2_wgbs.tsv` | `WGBS_colon-primary-tumor_2_450k.beta` |
+| `TCGA-BD-A3EP-01A` | N/A | `TCGA-BD-A3EP-01A_450k.tsv` |
+
+#### References
+
+1. Hansen, K. D., et al. Increased methylation variation in epigenetic domains across cancer types. *Nature Genetics* **43**, 768–775 (2011).
+2. Balaramane, D., Spill, Y. G., Weber, M. & Bardet, A. F. MethyLasso: a segmentation approach to analyze DNA methylation patterns and identify differentially methylated regions from whole-genome datasets. *Nucleic Acids Research* **52**, e98 (2024).
+
+### Pretrained models
+
+Two pretrained models are provided for tutorials, testing, and exploratory
+analysis:
+
+| Model filename | Training data |
+| --- | --- |
+| `wgbs_colon_model` | `WGBS_colon-primary-tumor_1_wgbs.tsv` |
+| `tcga_hm450k_model` | `TCGA-BD-A3EP-01A_450k.tsv` |
+
+Load a pretrained model with `get_pretrained_model`:
+
+```python
+# WGBS model
+wgbs_saved = MethylSegPathway.get_pretrained_model(
+    out_dir=OUTPUT_DIR,
+    resolution="wgbs",
+)
+
+# HM450K model
+hm450k_saved = MethylSegPathway.get_pretrained_model(
+    out_dir=OUTPUT_DIR,
+    resolution="450k",
+)
+```
+
+## Quickstart
+
+The default workflow trains a model on your input, segments the sample,
+cleans the calls, and draws a cleaned methylation state overlay.
+
+Use `resolution="wgbs"` for WGBS count tables or `resolution="450k"` for HM450K
+beta-value tables. Other microarray platforms may require manually configured
+parameters until array-specific defaults are added.
+
+```python
+from pathlib import Path
+
+from methylseg import MethylSegPathway, MethylationStates
+from methylseg.helper_classes import DATA_DIR
+
+reference_dir = DATA_DIR / "reference_files"
+
+# WGBS: replace these with your own sample name and count table.
+# sample_name = "WGBS_colon-primary-tumor_1"
+# sample_file = reference_dir / "WGBS_colon-primary-tumor_1_wgbs.tsv.gz"
+# resolution = "wgbs"
+
+# TCGA/HM450K alternative:
+sample_name = "TCGA-BD-A3EP-01A"
+sample_file = reference_dir / "TCGA-BD-A3EP-01A_450k.tsv.gz"
+resolution = "450k"
+
+sample_info, removed_df = MethylSegPathway.prepare_sample_info(
+    sample_name=sample_name,
+    sample_file=sample_file,
+    resolution=resolution,
+    remove_low_coverage_like_cpgs=True,
+)
+
+pathway = MethylSegPathway(
+    train_sample_info=sample_info,
+    out_dir=Path("out/quickstart") / sample_name,
+)
+
+pathway.run_pathway()
+
+fig = pathway.plot_labels(
+    sample_info=sample_info,
+    sample_info_removed=removed_df,
+    chrom="chr1",
+    region_start=2_200_000,
+    region_end=3_700_000
+)
+```
+
+![quickstart output](https://raw.githubusercontent.com/clementlab/MethylSeg/main/quickstart.png)
+
+`run_pathway(sample_info=sample_info, chroms=["chr1"])` performs fitting,
+segmentation, cleaning, and summary-file writing in one call.
+
+## Input formats
+
+MethylSeg accepts tab-delimited `.tsv` and `.tsv.gz` files containing DNA methylation measurements. Genomic coordinates must use the 0-based, half-open coordinate system, and chromosome names must be consistent throughout each file.
+
+Two BED-like input formats are supported.
+
+### Beta-value format
+
+This format can be used for either WGBS or microarray data. It contains four required columns:
+
+1. chromosome;
+2. CpG start position;
+3. CpG end position; and
+4. methylation beta value.
+
+For microarray data, an optional fifth column containing the probe identifier may be included. Probe identifiers are retained as metadata.
+
+| CpG_chrm | CpG_beg | CpG_end | beta | probe      |
+| -------- | ------: | ------: | ---: | ---------- |
+| chr1     |   15864 |   15866 |  0.0 | cg13869341 |
+| chr1     |   29406 |   29408 |  0.0 | cg12045430 |
+| chr1     |   29424 |   29426 |  0.0 | cg20826792 |
+
+
+### WGBS count format
+
+This format contains five required columns:
+
+1. chromosome;
+2. CpG start position;
+3. CpG end position;
+4. methylated read count; and
+5. total read coverage.
+
+MethylSeg calculates the beta value internally as: 
+$
+\mathrm{beta} = \frac{\mathrm{methylated\ reads}}{\mathrm{total\ coverage}}.
+$
+
+| CpG_chrm | CpG_beg | CpG_end | meth | coverage |
+| -------- | ------: | ------: | ---: | -------: |
+| chr1     |   10468 |   10470 |   14 |       15 |
+| chr1     |   10470 |   10472 |   10 |       10 |
+| chr1     |   10483 |   10485 |   23 |       28 |
+
+
+## Outputs
+
+The final output of MethylSeg consists primarily of BED files containing the
+identified methylation domains. Separate files are generated for each
+methylation state: `HIGH`, `INTERMEDIATE`, `LOW`, and `PMD`.
+
+For each chromosome and state, MethylSeg writes:
+
+| Output | Filename pattern | Description |
+| --- | --- | --- |
+| Raw regions | `segments_{chrom}_{sample_id}_{resolution}_{state}.bed` | Regions produced directly by genome segmentation |
+| Cleaned regions | `clean_regions/segments_cleaned_{chrom}_{sample_id}_{resolution}_{state}.bed` | Regions retained after merging and filtering |
+| Cleaned metadata | `clean_regions/metadata_cleaned_{chrom}_{sample_id}_{resolution}_{state}.tsv` | Additional information about the cleaned regions |
+
+After all requested chromosomes have been processed, MethylSeg also creates
+genome-wide files for each state under `summary_files/`:
+
+| Output | Filename pattern |
+| --- | --- |
+| Genome-wide raw regions | `segments_raw_{state}.bed` |
+| Genome-wide cleaned regions | `segments_cleaned_{state}.bed` |
+| Genome-wide cleaned metadata | `metadata_cleaned_{state}.tsv` |
+
+A simplified output directory has the following structure:
+
+```text
+methylseg_output/
+├── segments_chr1_sample.wgbs_PMD.bed
+├── segments_chr1_sample.wgbs_LOW.bed
+├── clean_regions/
+│   ├── segments_cleaned_chr1_sample.wgbs_PMD.bed
+│   ├── segments_cleaned_chr1_sample.wgbs_LOW.bed
+│   ├── metadata_cleaned_chr1_sample.wgbs_PMD.tsv
+│   └── metadata_cleaned_chr1_sample.wgbs_LOW.tsv
+└── summary_files/
+    ├── segments_raw_PMD.bed
+    ├── segments_raw_LOW.bed
+    ├── segments_cleaned_PMD.bed
+    ├── segments_cleaned_LOW.bed
+    ├── metadata_cleaned_PMD.tsv
+    └── metadata_cleaned_LOW.tsv
+```
+
+Each BED file contains 0-based, half-open genomic coordinates and the assigned
+methylation state. For example, segments_cleaned_PMD.bed may contain:
+
+| Chromosome |     Start |       End | State |
+| ---------- | --------: | --------: | ----- |
+| `chr1`     | 1,261,344 | 1,323,691 | `PMD` |
+| `chr1`     | 2,789,167 | 2,999,312 | `PMD` |
+| `chr1`     | 3,885,138 | 3,916,529 | `PMD` |
+| `chr1`     | 6,167,866 | 6,186,177 | `PMD` |
+
+The BED files themselves are tab-delimited and do not contain a header.
+
+## Citation
+
+If you use MethylSeg, please cite the software using the
+[CITATION.cff](https://github.com/clementlab/MethylSeg/blob/main/CITATION.cff)
+metadata. On GitHub, select **Cite this repository** to copy the citation in APA
+or BibTeX format.
+
+A manuscript describing MethylSeg is in preparation. Its citation will be added
+when available.
+
+## Planned support
+
+See [ROADMAP.md](https://github.com/clementlab/MethylSeg/blob/main/ROADMAP.md)
+
+## Reporting issues
+
+To report a bug, request a feature, or ask a question about MethylSeg, open an
+issue on the [GitHub issue tracker](https://github.com/clementlab/MethylSeg/issues).
+
+When reporting a bug, please include:
+
+- Your MethylSeg version
+- Your Python version and operating system
+- The complete error message or traceback
+- A minimal example that reproduces the problem, when possible
+
+## License
+
+MethylSeg is distributed under the [BSD 3-Clause License](LICENSE.md).

methylseg-0.1.8/methylseg/__init__.py

@@ -0,0 +1,38 @@
+"""Public package exports for the reusable methylseg workflow."""
+
+from .helper_classes import (
+    MethylStateAssignmentMethod,
+    MethylationStates,
+    MethylDataPrep,
+    SampleInfo,
+    HMMType,
+)
+from .methylseg_hmm import (
+    CTMethylSegHMM,
+    MethylSegHMM,
+    StickyCategoricalMethylSegHMM,
+)
+from .methyl_state_assigner import MethylStateAssigner
+from .methyl_state_analyzer import MethylStateAnalyzer
+from .methyl_segmentor import MethylSegmentor
+from .methylseg_pathway import MethylSegPathway
+from .methylseg_config import MethylSegConfig
+from .utils import get_biological_state_colors, get_cluster_colors
+
+__all__ = [
+    "CTMethylSegHMM",
+    "MethylDataPrep",
+    "MethylSegConfig",
+    "MethylSegHMM",
+    "MethylSegPathway",
+    "MethylSegmentor",
+    "MethylStateAnalyzer",
+    "MethylStateAssigner",
+    "MethylStateAssignmentMethod",
+    "MethylationStates",
+    "HMMType",
+    "SampleInfo",
+    "StickyCategoricalMethylSegHMM",
+    "get_biological_state_colors",
+    "get_cluster_colors",
+]

methylseg-0.1.8/methylseg/cli.py

@@ -0,0 +1,32 @@
+from .data_manager import download_data_files
+import argparse
+
+#TODO - add subcommands for pathway running, segmentation and plotting
+def main():
+    """
+    Run the ``methylseg`` command-line interface.
+
+    Returns
+    -------
+    None
+        Parses CLI arguments, executes the requested subcommand, and prints
+        help text when no subcommand is provided.
+    """
+    parser = argparse.ArgumentParser(prog="methylseg")
+
+    subparsers = parser.add_subparsers(dest="command")
+
+    # subcommand: download_data_files
+    dl_parser = subparsers.add_parser("download_data_files")
+    dl_parser.add_argument(
+        "--cleanup_existing",
+        action="store_true",
+        help="Delete existing files before downloading",
+    )
+
+    args = parser.parse_args()
+
+    if args.command == "download_data_files":
+        download_data_files(cleanup_existing=args.cleanup_existing)
+    else:
+        parser.print_help()