#276: apply pre-commit end-of-file-fixer, trailing-whitespace, check…

.bumpversion.cfg

@@ -3,7 +3,7 @@ current_version = 0.6.6
 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"

.gitignore

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

.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

@@ -13,7 +13,7 @@
 # 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
@@ -42,7 +42,7 @@
 
 # 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
@@ -67,7 +67,7 @@
 * 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
 
@@ -129,18 +129,3 @@
 * 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
 ```

alphastats/DataSet.py

@@ -72,15 +72,15 @@ 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)
             self.intensity_column = intensity_column
@@ -163,7 +163,7 @@ def create_matrix(self):
             # 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_Plot.py

@@ -122,7 +122,7 @@ def plot_umap(self, group: str = None, circle: bool = False):
         )
         return dimensionality_reduction.plot
 
-    
+
     @ignore_warning(RuntimeWarning)
     def plot_volcano(
         self,
@@ -134,7 +134,7 @@ def plot_volcano(
         min_fc:float=1.0,
         alpha:float=0.05,
         draw_line:bool=True,
-        perm:int=100, 
+        perm:int=100,
         fdr:float=0.05,
         compare_preprocessing_modes:bool=False,
         color_list:list=[]
@@ -178,7 +178,7 @@ def plot_volcano(
                 min_fc=min_fc,
                 alpha=alpha,
                 draw_line=draw_line,
-                perm=perm, 
+                perm=perm,
                 fdr=fdr,
                 color_list=color_list
             )

alphastats/DataSet_Statistics.py

@@ -23,7 +23,7 @@ def _calculate_foldchange(self, mat_transpose:pd.DataFrame, group1_samples:list,
                 mat_transpose[group1_samples].T.mean().values
                 - mat_transpose[group2_samples].T.mean().values
             )
-        
+
         else:
             fc = (
                 mat_transpose[group1_samples].T.mean().values
@@ -32,7 +32,7 @@ def _calculate_foldchange(self, mat_transpose:pd.DataFrame, group1_samples:list,
             fc = np.log2(fc)
 
         return pd.DataFrame({"log2fc": fc, self.index_column: mat_transpose.index})
-    
+
     def _add_metadata_column(self, group1_list: list, group2_list: list):
 
         # create new column in metadata with defined groups
@@ -55,7 +55,7 @@ def _add_metadata_column(self, group1_list: list, group2_list: list):
         self.metadata = metadata
 
         return column, "group1", "group2"
-    
+
     @ignore_warning(RuntimeWarning)
     def diff_expression_analysis(
             self,
@@ -89,11 +89,11 @@ def diff_expression_analysis(
             * ``'ll'``: the log-likelihood of the estimation
         """
         df = DifferentialExpressionAnalysis(
-            dataset=self, 
-            group1=group1, 
-            group2=group2, 
+            dataset=self,
+            group1=group1,
+            group2=group2,
             column=column, method=method,
-            perm=perm, 
+            perm=perm,
             fdr=fdr
         ).perform()
         return df
@@ -160,7 +160,7 @@ def anova(self, column:str, protein_ids="all", tukey: bool=True) -> pd.DataFrame
             * ``'A vs. B Tukey test'``: Tukey-HSD corrected p-values (each combination represents a column)
         """
         return Anova(dataset=self, column=column, protein_ids=protein_ids, tukey=tukey).perform()
-        
+
 
     @lru_cache(maxsize=20)
     def ancova(self, protein_id:str, covar: Union[str, list], between:str) -> pd.DataFrame:
@@ -211,7 +211,7 @@ def multicova_analysis(
         Returns:
             pd.DataFrame: Multicova Analysis results
         """
-        
+
         res, plot_list= MultiCovaAnalysis(
             dataset=self,
             covariates=covariates,
@@ -222,5 +222,3 @@ def multicova_analysis(
             plot=True
         ).calculate()
         return res, plot_list
-
-