bam2tensor 2.0__tar.gz → 2.1__tar.gz

bam2tensor-2.1/.gitattributes

@@ -0,0 +1 @@
+* text=auto eol=lf

{bam2tensor-2.0 → bam2tensor-2.1}/CLAUDE.md

@@ -23,8 +23,8 @@ nox --session=pre-commit
 # Run tests directly
 uv run pytest
 
-# Run tests with coverage
-uv run pytest --cov
+# Run tests with coverage (via nox)
+nox --session=tests
 
 # Format code
 uv run black src tests
@@ -40,7 +40,7 @@ uv run mypy src
 
 ```
 src/bam2tensor/
-  __init__.py      # Package version (2.0)
+  __init__.py      # Package version (2.1)
   __main__.py      # Click CLI entry point
   embedding.py     # GenomeMethylationEmbedding class (FASTA parsing, CpG indexing)
   functions.py     # Core extraction: extract_methylation_data_from_bam()
@@ -129,7 +129,6 @@ xdoctest validates code examples in docstrings. Important rules:
 ## CI/CD
 
 - GitHub Actions runs tests on Ubuntu and macOS with Python 3.12
-- SonarCloud integration for quality metrics
 - Automated docs deployment to GitHub Pages
 
 ## Common Tasks

{bam2tensor-2.0 → bam2tensor-2.1}/CONTRIBUTING.md

@@ -99,7 +99,7 @@ Open a [pull request] to submit changes to this project.
 Your pull request needs to meet the following guidelines for acceptance:
 
 - The Nox test suite must pass without errors and warnings.
-- Include unit tests. This project maintains 100% code coverage.
+- Include unit tests.
 - If your changes add functionality, update the documentation accordingly.
 
 Feel free to submit early, though—we can always iterate on this.

{bam2tensor-2.0 → bam2tensor-2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bam2tensor
-Version: 2.0
+Version: 2.1
 Summary: Convert bisulfite-seq and EM-seq BAM files to sparse tensor representations of DNA methylation
 Project-URL: Homepage, https://github.com/mcwdsi/bam2tensor
 Project-URL: Repository, https://github.com/mcwdsi/bam2tensor
@@ -21,6 +21,8 @@ Description-Content-Type: text/markdown
 
 # bam2tensor
 
+**Author:** [Nick Semenkovich](https://nick.semenkovich.com/) (semenko@alum.mit.edu)
+
 [![PyPI](https://img.shields.io/pypi/v/bam2tensor.svg)][pypi status]
 [![Status](https://img.shields.io/pypi/status/bam2tensor.svg)][pypi status]
 [![Python Version](https://img.shields.io/pypi/pyversions/bam2tensor)][pypi status]
@@ -221,8 +223,8 @@ bam2tensor \
 ```
 Usage: bam2tensor [OPTIONS]
 
-  Extract read-level methylation data from an aligned .bam file and export
-  the data as a SciPy sparse matrix.
+  Extract read-level methylation data from an aligned bisulfite-seq or EM-seq
+  .bam file and export the data as a SciPy sparse matrix.
 
 Options:
   --version                       Show the version and exit.
@@ -230,19 +232,27 @@ Options:
                                   process.  [required]
   --genome-name TEXT              A custom string referring to your genome
                                   name, used to save a cache file (e.g. hg38,
-                                  hg38-no-alt, etc.).  [required]
+                                  hg39-no-alt, etc.).
   --expected-chromosomes TEXT     A comma-separated list of chromosomes to
                                   expect in the .fa genome. Defaults to hg38
-                                  chromosomes (chr1-chr22, chrX, chrY).
-  --reference-fasta PATH          Reference genome FASTA file (critical to
-                                  determine CpG sites).  [required]
+                                  chromosomes.
+  --reference-fasta FILE          Reference genome fasta file (critical to
+                                  determine CpG sites).
   --quality-limit INTEGER         Quality filter for aligned reads (default =
-                                  20).
+                                  20)
   --verbose                       Verbose output.
   --skip-cache                    De-novo generate CpG sites (slow).
   --debug                         Debug mode (extensive validity checking +
                                   debug messages).
   --overwrite                     Overwrite output file if it exists.
+  --output-dir DIRECTORY          Output directory for .methylation.npz files.
+                                  Defaults to same directory as the input BAM.
+  --download-reference [t2t-chm13|hg19|hg38|mm10]
+                                  Download and cache a known reference genome
+                                  (e.g. hg38, hg19, mm10, T2T-CHM13). Use
+                                  --list-genomes to see options.
+  --list-genomes                  List available reference genomes for
+                                  download and exit.
   --help                          Show this message and exit.
 ```
 
@@ -523,7 +533,7 @@ If you encounter any problems, please [file an issue] with:
 
 ## Credits
 
-This project is developed and maintained by [Nick Semenkovich (@semenko)], as part of the Medical College of Wisconsin's [Data Science Institute].
+**Created and maintained by [Nick Semenkovich](https://nick.semenkovich.com/) ([@semenko](https://github.com/semenko))**, as part of the Medical College of Wisconsin's [Data Science Institute].
 
 This project was generated from [Statistics Norway]'s [SSB PyPI Template].
 

{bam2tensor-2.0 → bam2tensor-2.1}/README.md

@@ -1,5 +1,7 @@
 # bam2tensor
 
+**Author:** [Nick Semenkovich](https://nick.semenkovich.com/) (semenko@alum.mit.edu)
+
 [![PyPI](https://img.shields.io/pypi/v/bam2tensor.svg)][pypi status]
 [![Status](https://img.shields.io/pypi/status/bam2tensor.svg)][pypi status]
 [![Python Version](https://img.shields.io/pypi/pyversions/bam2tensor)][pypi status]
@@ -200,8 +202,8 @@ bam2tensor \
 ```
 Usage: bam2tensor [OPTIONS]
 
-  Extract read-level methylation data from an aligned .bam file and export
-  the data as a SciPy sparse matrix.
+  Extract read-level methylation data from an aligned bisulfite-seq or EM-seq
+  .bam file and export the data as a SciPy sparse matrix.
 
 Options:
   --version                       Show the version and exit.
@@ -209,19 +211,27 @@ Options:
                                   process.  [required]
   --genome-name TEXT              A custom string referring to your genome
                                   name, used to save a cache file (e.g. hg38,
-                                  hg38-no-alt, etc.).  [required]
+                                  hg39-no-alt, etc.).
   --expected-chromosomes TEXT     A comma-separated list of chromosomes to
                                   expect in the .fa genome. Defaults to hg38
-                                  chromosomes (chr1-chr22, chrX, chrY).
-  --reference-fasta PATH          Reference genome FASTA file (critical to
-                                  determine CpG sites).  [required]
+                                  chromosomes.
+  --reference-fasta FILE          Reference genome fasta file (critical to
+                                  determine CpG sites).
   --quality-limit INTEGER         Quality filter for aligned reads (default =
-                                  20).
+                                  20)
   --verbose                       Verbose output.
   --skip-cache                    De-novo generate CpG sites (slow).
   --debug                         Debug mode (extensive validity checking +
                                   debug messages).
   --overwrite                     Overwrite output file if it exists.
+  --output-dir DIRECTORY          Output directory for .methylation.npz files.
+                                  Defaults to same directory as the input BAM.
+  --download-reference [t2t-chm13|hg19|hg38|mm10]
+                                  Download and cache a known reference genome
+                                  (e.g. hg38, hg19, mm10, T2T-CHM13). Use
+                                  --list-genomes to see options.
+  --list-genomes                  List available reference genomes for
+                                  download and exit.
   --help                          Show this message and exit.
 ```
 
@@ -502,7 +512,7 @@ If you encounter any problems, please [file an issue] with:
 
 ## Credits
 
-This project is developed and maintained by [Nick Semenkovich (@semenko)], as part of the Medical College of Wisconsin's [Data Science Institute].
+**Created and maintained by [Nick Semenkovich](https://nick.semenkovich.com/) ([@semenko](https://github.com/semenko))**, as part of the Medical College of Wisconsin's [Data Science Institute].
 
 This project was generated from [Statistics Norway]'s [SSB PyPI Template].
 

{bam2tensor-2.0 → bam2tensor-2.1}/docs/conf.py

@@ -20,8 +20,8 @@ sys.path.insert(0, os.path.abspath("../src"))
 # -- Project information -----------------------------------------------------
 
 project = "Bam2Tensor"
-copyright = "2023-2026, Nick Semenkovich"
-author = "Nick Semenkovich"
+copyright = "2023-2026, Nick Semenkovich (https://nick.semenkovich.com/)"
+author = "Nick Semenkovich (https://nick.semenkovich.com/)"
 
 # -- General configuration ---------------------------------------------------
 

{bam2tensor-2.0 → bam2tensor-2.1}/docs/reference.md

@@ -13,14 +13,30 @@ delete the .rst file afterwards.
 
 ```{eval-rst}
 bam2tensor package
-=============================================================================
+==================
 
 
+bam2tensor.embedding module
+---------------------------
+
+.. automodule:: bam2tensor.embedding
+   :members:
+   :show-inheritance:
+   :undoc-members:
+
 bam2tensor.functions module
------------------------------------------------------------------------------
+---------------------------
 
 .. automodule:: bam2tensor.functions
    :members:
+   :show-inheritance:
    :undoc-members:
+
+bam2tensor.reference module
+---------------------------
+
+.. automodule:: bam2tensor.reference
+   :members:
    :show-inheritance:
+   :undoc-members:
 ```

{bam2tensor-2.0 → bam2tensor-2.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "bam2tensor"
-version = "2.0"
+version = "2.1"
 description = "Convert bisulfite-seq and EM-seq BAM files to sparse tensor representations of DNA methylation"
 authors = [{ name = "Nick Semenkovich", email = "semenko@alum.mit.edu" }]
 license = "MIT"

{bam2tensor-2.0 → bam2tensor-2.1}/src/bam2tensor/__init__.py

@@ -50,4 +50,4 @@ See Also:
     - https://mcwdsi.github.io/bam2tensor for full documentation
 """
 
-__version__ = "2.0"
+__version__ = "2.1"

{bam2tensor-2.0 → bam2tensor-2.1}/src/bam2tensor/__main__.py

@@ -360,6 +360,7 @@ def main(
 
     # ── Header ──────────────────────────────────────────────────────────
     print(f"bam2tensor v{__version__}")
+    print("By Nick Semenkovich <semenko@alum.mit.edu>.")
     print("=" * 72)
 
     # ── Configuration ───────────────────────────────────────────────────

{bam2tensor-2.0 → bam2tensor-2.1}/uv.lock

@@ -62,7 +62,7 @@ wheels = [
 
 [[package]]
 name = "bam2tensor"
-version = "1.5"
+version = "2.0"
 source = { editable = "." }
 dependencies = [
     { name = "biopython" },

bam2tensor-2.0/.gitattributes

@@ -1,3 +0,0 @@
-* text=auto eol=lf
-*.ipynb filter=nbstripout
-*.ipynb diff=ipynb

bam2tensor-2.0/.prettierignore

@@ -1,4 +0,0 @@
-# Ignore this files since they are reindented with json.dump() and that does not
-# match the prettier format.
-.cookiecutter.json
-.cruft.json

bam2tensor-2.0/sonar-project.properties

@@ -1,11 +0,0 @@
-sonar.projectKey=mcwdsi_bam2tensor
-sonar.organization=mcwdsi
-sonar.host.url=https://sonarcloud.io
-
-sonar.sources=src/bam2tensor
-sonar.tests=tests
-
-sonar.python.version=3.10
-sonar.python.coverage.reportPaths=coverage.xml
-
-sonar.sourceEncoding=UTF-8