Merge branch 'development' into main_to_dev

.bumpversion.cfg

@@ -3,7 +3,7 @@ current_version = 0.6.7
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<build>\d+))?
-serialize = 
+serialize =
 	{major}.{minor}.{patch}-{release}{build}
 	{major}.{minor}.{patch}
 

.github/dependabot.yml

@@ -6,4 +6,4 @@ updates:
       interval: "weekly"
     target-branch: "developer"
     labels:
-      - "pip dependencies"   
+      - "pip dependencies"

.github/workflows/python-package.yml → .github/workflows/build_and_test.yml

@@ -2,24 +2,27 @@
 # For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
 
 
-name: CI
+name: Build and run tests
 
-
-on: [push, pull_request]
-#  push:
-#    branches: [ "main", "developer"]
-#  pull_request:
-#    branches: [ "main", "developer"]
+on:
+  push:
+    branches: [ main, development ]
+  pull_request:
 
 jobs:
-  build:
-
+  pre-commit:
+    name: Run all pre-commit hooks
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v3
+      - uses: pre-commit/action@v3.0.1
+  build-and-test:
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
       matrix:
         python-version: ["3.8", "3.9", "3.10"]
-
     steps:
     - uses: actions/checkout@v3
     - name: Set up Python ${{ matrix.python-version }}
@@ -34,7 +37,7 @@ jobs:
         pip install dictdiffer
     - name: Test installation
       run: |
-        pip install -e.
+        pip install -e .
     - name: Run tests
       run: |
         coverage run -m unittest

.gitignore

@@ -5,4 +5,4 @@ alphastats.egg-info
 _build
 build
 dist
-.coverage
+.coverage

.pre-commit-config.yaml

@@ -0,0 +1,14 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v2.3.0
+  hooks:
+    - id: check-yaml
+    - id: end-of-file-fixer
+    - id: trailing-whitespace
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  rev: v0.4.0
+  hooks:
+    - id: ruff-format
+#    - id: ruff

.readthedocs.yaml

@@ -14,4 +14,4 @@ sphinx:
 # Explicitly set the version of Python and its requirements
 python:
   install:
-    - requirements: docs/requirements_docs.txt
+    - requirements: docs/requirements_docs.txt

CITATION.cff

@@ -3,7 +3,7 @@ message: "If you use this software, please cite both the article from preferred-
 authors:
   - family-names: Krismer
     given-names: Elena
-    orcid: 
+    orcid:
 title: "AlphaPeptStats: an open-source Python package for automated and scalable statistical analysis of mass spectrometry-based proteomics "
 version: 0.6.5
 doi: "10.1093/bioinformatics/btad461"
@@ -17,13 +17,11 @@ preferred-citation:
     - family-names: Bludau
       given-names: Isabell
     - family-names: Strauss
-      given-names: Maximilian T. 
+      given-names: Maximilian T.
     - family-names: Mann
       given-names: Matthias
   title: "AlphaPeptStats: an open-source Python package for automated and scalable statistical analysis of mass spectrometry-based proteomics"
   type: article
   year: 2023
   doi: "10.1093/bioinformatics/btad461"
   journal: "Bioinformatics"
-
-

Dockerfile

@@ -21,4 +21,4 @@ HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
 
 WORKDIR "/app/alphastats/gui"
 
-ENTRYPOINT ["streamlit", "run", "AlphaPeptStats.py", "--server.port=8501", "--server.address=0.0.0.0"]
+ENTRYPOINT ["streamlit", "run", "AlphaPeptStats.py", "--server.port=8501", "--server.address=0.0.0.0"]

HISTORY.md

@@ -17,7 +17,7 @@
 # 0.6.3
 * ENH download metadata template in the GUI
 * ENH multicova analysis
-* ENH filter data completeness `dataset.preprocess(data_completeness=0.7)` 
+* ENH filter data completeness `dataset.preprocess(data_completeness=0.7)`
 * ADD `GenericLoader` for not supported data formats
 
 # 0.6.2
@@ -46,7 +46,7 @@
 
 # 0.5.0
 * ADD plot Sample Distribution Histogram
-* ADD paired-ttest option 
+* ADD paired-ttest option
 * ENH add option to remove samples in GUI
 * ADD pyComBat Batch correction Behdenna A, Haziza J, Azencot CA and Nordor A. (2020) pyComBat, a Python tool for batch effects correction in high-throughput molecular data using empirical Bayes methods. bioRxiv doi: 10.1101/2020.03.17.995431
 * remove iteration utilities, remove C++ dependency
@@ -71,7 +71,7 @@
 * ADD functionionality `dataset.reset_preprocessing()` to reset all preprocessing steps
 
 # 0.4.0
-* SAM implementation from Isabel (MultiCova) 
+* SAM implementation from Isabel (MultiCova)
 * Volcano Plot with permutation based FDR line
 * Bug fix when reseting matrix and saving info
 
@@ -133,18 +133,3 @@
 * remove dependency for Microsoft Visual Studio C++ (dash_bio) (Windows PCs)
 * clustermap with seaborn, adding bar labels is possible
 * save plotting data, preprocessing, method in figure object (accessible using figure.plotting_data, figure.method, figure.preprocessing)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-

README.md

@@ -51,28 +51,28 @@ An open-source Python package for downstream mass spectrometry downstream data a
 ## Citation
 Publication: [AlphaPeptStats: an open-source Python package for automated and scalable statistical analysis of mass spectrometry-based proteomics](https://doi.org/10.1093/bioinformatics/btad461)
 > **Citation:** <br>
-> Krismer, E., Bludau, I.,  Strauss M. & Mann M. (2023). AlphaPeptStats: an open-source Python package for automated and scalable statistical analysis of mass spectrometry-based proteomics. Bioinformatics 
+> Krismer, E., Bludau, I.,  Strauss M. & Mann M. (2023). AlphaPeptStats: an open-source Python package for automated and scalable statistical analysis of mass spectrometry-based proteomics. Bioinformatics
 > https://doi.org/10.1093/bioinformatics/btad461
 
 ---
 ## Installation
 
-AlphaPeptStats can be used as 
- * python library (pip-installation), or 
- * Graphical User Interface (either pip-installation or one-click installer). 
- 
+AlphaPeptStats can be used as
+ * python library (pip-installation), or
+ * Graphical User Interface (either pip-installation or one-click installer).
+
 Further we provide a Dockerimage for the GUI.
 
 ### Pip Installation
 
-AlphaStats can be installed in an existing Python 3.8/3.9/3.10 environment with a single `bash` command. 
+AlphaStats can be installed in an existing Python 3.8/3.9/3.10 environment with a single `bash` command.
 
 ```bash
 pip install alphastats
 ```
 
 In case you want to use the Graphical User Interface, use following command in the command line:
- 
+
 ```bash
 alphastats gui
 ```
@@ -116,6 +116,24 @@ AlphaStats was developed by the [Mann Group at the University of Copenhagen](htt
 
 If you like this software, you can give us a [star](https://github.com/MannLabs/alphapeptstats/stargazers) to boost our visibility! All direct contributions are also welcome. Feel free to post a new [issue](https://github.com/MannLabs/alphapeptstats/issues) or clone the repository and create a [pull request](https://github.com/MannLabs/alphapeptstats/pulls) with a new branch. For an even more interactive participation, check out the [discussions](https://github.com/MannLabs/alphapeptstats/discussions) and the [the Contributors License Agreement](misc/CLA.md).
 
+
+### Notes for developers
+#### pre-commit hooks
+It is highly recommended to use the provided pre-commit hooks, as the CI pipeline enforces all checks therein to
+pass in order to merge a branch.
+
+The hooks need to be installed once by
+```bash
+pip install -r requirements_dev.txt
+pre-commit install
+```
+You can run the checks yourself using:
+```bash
+pre-commit run --all-files
+```
+
+
+
 ---
 ## Changelog
 

alphastats/DataSet.py

@@ -72,17 +72,19 @@ def __init__(self, loader, metadata_path=None, sample_column=None):
         self.create_matrix()
         self._check_matrix_values()
         self.metadata = None
-        
+
         if metadata_path is not None:
             self.sample = sample_column
             self.load_metadata(file_path=metadata_path)
             self._remove_misc_samples_in_metadata()
 
         else:
             self._create_metadata()
-        
+
         if self.loader == "Generic":
-            intensity_column = loader._extract_sample_names(metadata=self.metadata, sample_column=self.sample)
+            intensity_column = loader._extract_sample_names(
+                metadata=self.metadata, sample_column=self.sample
+            )
             self.intensity_column = intensity_column
 
         # save preprocessing settings
@@ -104,7 +106,6 @@ def _check_loader(self, loader):
             loader : loader
         """
         if not isinstance(
-
             loader,
             (
                 AlphaPeptLoader,
@@ -113,9 +114,8 @@ def _check_loader(self, loader):
                 FragPipeLoader,
                 SpectronautLoader,
                 GenericLoader,
-                mzTabLoader
+                mzTabLoader,
             ),
-
         ):
             raise LoaderError(
                 "loader must be from class: AlphaPeptLoader, MaxQuantLoader, DIANNLoader, FragPipeLoader or SpectronautLoader"
@@ -158,12 +158,14 @@ def create_matrix(self):
         df = df.set_index(self.index_column)
 
         if isinstance(self.intensity_column, str):
-            regex_find_intensity_columns = self.intensity_column.replace("[sample]", ".*")
+            regex_find_intensity_columns = self.intensity_column.replace(
+                "[sample]", ".*"
+            )
             df = df.filter(regex=(regex_find_intensity_columns), axis=1)
             # remove Intensity so only sample names remain
             substring_to_remove = regex_find_intensity_columns.replace(".*", "")
             df.columns = df.columns.str.replace(substring_to_remove, "")
-        
+
         else:
             df = df[self.intensity_column]
         # transpose dataframe

alphastats/DataSet_Pathway.py

@@ -94,7 +94,6 @@ def _extract_protein_ids(entry):
         return protein_id_concentate
 
     def _get_ptm_proteins(self, sample=None):
-
         if self.evidence_df is None:
             raise ValueError(
                 "No informations about PTMs."

alphastats/DataSet_Plot.py

@@ -122,22 +122,21 @@ def plot_umap(self, group: str = None, circle: bool = False):
         )
         return dimensionality_reduction.plot
 
-
     @ignore_warning(RuntimeWarning)
     def plot_volcano(
         self,
         group1: Union[str, list],
         group2: Union[str, list],
-        column:str=None,
-        method:str="ttest",
-        labels:bool=False,
-        min_fc:float=1.0,
-        alpha:float=0.05,
-        draw_line:bool=True,
-        perm:int=100, 
-        fdr:float=0.05,
-        compare_preprocessing_modes:bool=False,
-        color_list:list=[]
+        column: str = None,
+        method: str = "ttest",
+        labels: bool = False,
+        min_fc: float = 1.0,
+        alpha: float = 0.05,
+        draw_line: bool = True,
+        perm: int = 100,
+        fdr: float = 0.05,
+        compare_preprocessing_modes: bool = False,
+        color_list: list = [],
     ):
         """Plot Volcano Plot
 
@@ -178,9 +177,9 @@ def plot_volcano(
                 min_fc=min_fc,
                 alpha=alpha,
                 draw_line=draw_line,
-                perm=perm, 
+                perm=perm,
                 fdr=fdr,
-                color_list=color_list
+                color_list=color_list,
             )
 
             return volcano_plot.plot
@@ -221,14 +220,22 @@ def plot_sampledistribution(
             df = df.merge(self.metadata, how="inner", on=[self.sample])
 
         if method == "violin":
-            fig = px.violin(df, x=self.sample, y="Intensity", color=color,
-                            template="simple_white+alphastats_colors"
-                            )
+            fig = px.violin(
+                df,
+                x=self.sample,
+                y="Intensity",
+                color=color,
+                template="simple_white+alphastats_colors",
+            )
 
         elif method == "box":
-            fig = px.box(df, x=self.sample, y="Intensity", color=color,
-                         template="simple_white+alphastats_colors"
-                         )
+            fig = px.box(
+                df,
+                x=self.sample,
+                y="Intensity",
+                color=color,
+                template="simple_white+alphastats_colors",
+            )
 
         else:
             raise ValueError(
@@ -390,7 +397,7 @@ def plot_imputed_values(self):
             color="Imputation",
             opacity=0.8,
             hover_data=plot_df.columns,
-            template="simple_white+alphastats_colors"
+            template="simple_white+alphastats_colors",
         )
 
         pass

alphastats/DataSet_Preprocess.py

@@ -8,7 +8,7 @@
 import sklearn.impute
 import streamlit as st
 
-from sklearn.experimental import enable_iterative_imputer #noqa
+from sklearn.experimental import enable_iterative_imputer  # noqa
 from alphastats.utils import ignore_warning