Merge pull request #27 from maxibor/dev

Pydamage version 0.80

.github/workflows/pydamage_ci.yml

@@ -10,23 +10,14 @@ jobs:
     if: "!contains(github.event.head_commit.message, '[skip_ci]')"
     steps:
       - uses: actions/checkout@v2
-      - uses: conda-incubator/setup-miniconda@v2
+      - uses: conda-incubator/setup-miniconda@v3
         with:
-          python-version: 3.7
+          auto-update-conda: true
           mamba-version: "*"
           channels: conda-forge,bioconda,defaults
           channel-priority: true
           environment-file: environment.yml
           activate-environment: pydamage
-      - uses: actions/setup-java@v2
-        with:
-          distribution: 'adopt'
-          java-version: '11'
-      - name: Lint with flake8
-        shell: bash -l {0}
-        run: |
-          pip install flake8
-          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
       - name: Test with pytest
         shell: bash -l {0}
         run: |

.readthedocs.yml

@@ -5,6 +5,11 @@
 # Required
 version: 2
 
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "mambaforge-latest"
+
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
   configuration: docs/source/conf.py

conda/meta.yaml

@@ -31,7 +31,6 @@ requirements:
     - tqdm>=4.45.0
     - biopython>=1.78
     - kneed>=0.7.0
-    - pypmml>=0.9.7
 
 test:
   commands:

docs/source/conf.py

@@ -19,7 +19,7 @@
 # -- Project information -----------------------------------------------------
 
 project = "pydamage"
-copyright = "2020, Maxime Borry"
+copyright = "2024, Maxime Borry"
 author = "Maxime Borry"
 
 # The full version, including alpha/beta/rc tags
@@ -42,6 +42,7 @@
     "sphinx.ext.mathjax",
     "sphinx_click.ext",
     "recommonmark",
+    "nbsphinx",
 ]
 
 
@@ -76,7 +77,7 @@
 # You can specify multiple suffix as a list of string:
 #
 # source_suffix = ['.rst', '.md']
-source_suffix = [".rst", ".md", ".ipynb"]
+source_suffix = [".rst", ".md"]
 
 # The master toctree document.
 master_doc = "index"

docs/source/index.rst

@@ -24,6 +24,7 @@ __ homepage_
    CLI
    output
    troubleshooting
+   rescaling
 
 
 

docs/source/output.md

@@ -29,6 +29,15 @@ The tabular outputs are  comma-separated file (`.csv`) with the following column
 
 Same file as above, but with contigs filtered with `qvalue <= 0.05` and `predicted_accuracy >= threshold` with a user defined filtering threshold (default = 0.5), or determined with the [kneedle](https://ieeexplore.ieee.org/document/5961514) method.
 
+
+### `pydamage_rescaled.bam`
+
+The input alignment file with rescaled base quality scores when running `pydamage analyze` with the `-r` or `--rescale` flag.
+
+The rescaled base calling scores are computed for each read containing ancient DNA damage according to the following formula, with `i` the position in the read, `p_err` the original base calling error probability,`p_pydam` the pydamage computed ancient damage probability, and `p_new` the updated base calling error probability.
+
+`p_new(i) = 1 - (1 - p_err(i)) (1 - p_pydam(i))`
+
 ### Plots
 
 The visual output are PNG files, one per reference contig. They show the frequency of observed C to T, and G to A transition at the 5' end of the sequencing data and overlay it with the fitted models for both the null and the damage model, including 95% confidence intervals. Furthermore, it provides a "residuals versus fitted" plot to help evaluate the fit of the pydamage damage model. Finally, the plot contains informtion on the average coverage along the reference and the p-value calculated from the likelihood-ratio test-statistic using a chi-squared distribution.
@@ -43,4 +52,4 @@ The visual output are PNG files, one per reference contig. They show the frequen
 
 * **Visual output**
 
-![pydamage_plot](../img/NZ_JHCB02000011.1.png)
+![pydamage_plot](../img/reference.png)