Merge pull request #197 from MannLabs/revision

Release 0.6.0 Revision
MannLabs · May 31, 2023 · d79a158 · d79a158
2 parents 719ba6c + adab852
commit d79a158
Show file tree

Hide file tree

Showing 26 changed files with 1,713 additions and 38 deletions.
diff --git a/.bumpversion.cfg b/.bumpversion.cfg
@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.5.4
+current_version = 0.6.0
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<build>\d+))?

diff --git a/HISTORY.md b/HISTORY.md
@@ -1,4 +1,7 @@
 # Changelog
+# 0.6.0
+* ADD mzTAB support
+* ENH color Volcano Plot data points using list of protein names `color_list=your_protein_list`
 
 # 0.5.4
 * FIX altair version - binning of streamlit version

diff --git a/alphastats/DataSet.py b/alphastats/DataSet.py
@@ -10,6 +10,7 @@
 from alphastats.loader.FragPipeLoader import FragPipeLoader
 from alphastats.loader.MaxQuantLoader import MaxQuantLoader
 from alphastats.loader.SpectronautLoader import SpectronautLoader
+from alphastats.loader.mzTabLoader import mzTabLoader
 
 from alphastats.DataSet_Plot import Plot
 from alphastats.DataSet_Preprocess import Preprocess
@@ -96,7 +97,7 @@ def _check_loader(self, loader):
             loader : loader
         """
         if not isinstance(
-            loader, (AlphaPeptLoader, MaxQuantLoader, DIANNLoader, FragPipeLoader, SpectronautLoader)
+            loader, (AlphaPeptLoader, MaxQuantLoader, DIANNLoader, FragPipeLoader, SpectronautLoader, mzTabLoader)
         ):
             raise LoaderError(
                 "loader must be from class: AlphaPeptLoader, MaxQuantLoader, DIANNLoader, FragPipeLoader or SpectronautLoader"

diff --git a/alphastats/DataSet_Plot.py b/alphastats/DataSet_Plot.py
@@ -119,15 +119,16 @@ def plot_volcano(
         self,
         group1,
         group2,
-        column=None,
-        method="ttest",
-        labels=False,
-        min_fc=1,
-        alpha=0.05,
-        draw_line=True,
-        perm=100, 
-        fdr=0.05,
-        compare_preprocessing_modes=False
+        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
 
@@ -142,6 +143,7 @@ def plot_volcano(
             draw_line(boolean): whether to draw cut off lines.
             perm(float,optional): number of permutations when using SAM as method. Defaults to 100.
             fdr(float,optional): FDR cut off when using SAM as method. Defaults to 0.05.
+            color_list (list): list with ProteinIDs that should be highlighted.
             compare_preprocessing_modes(bool): Will iterate through normalization and imputation modes and return a list of VolcanoPlots in different settings, Default False.
 
 
@@ -166,7 +168,8 @@ def plot_volcano(
                 alpha=alpha,
                 draw_line=draw_line,
                 perm=perm, 
-                fdr=fdr
+                fdr=fdr,
+                color_list=color_list
             )
 
             return volcano_plot.plot
@@ -241,7 +244,7 @@ def plot_intensity(
             ID (str): ProteinGroup ID
             group (str, optional): A metadata column used for grouping. Defaults to None.
             subgroups (list, optional): Select variables from the group column. Defaults to None.
-            method (str, optional):  Violinplot = "violin", Boxplot = "box", Scatterplot = "scatter". Defaults to "box".
+            method (str, optional):  Violinplot = "violin", Boxplot = "box", Scatterplot = "scatter" or "all". Defaults to "box".
             add_significance (bool, optional): add p-value bar, only possible when two groups are compared. Defaults False.
             log_scale (bool, optional): yaxis in logarithmic scale. Defaults to False.
 

diff --git a/alphastats/__init__.py b/alphastats/__init__.py
@@ -1,5 +1,5 @@
 __project__ = "alphastats"
-__version__ = "0.5.4"
+__version__ = "0.6.0"
 __license__ = "Apache"
 __description__ = "An open-source Python package for Mass Spectrometry Analysis"
 __author__ = "Mann Labs"

diff --git a/alphastats/loader/mzTabLoader.py b/alphastats/loader/mzTabLoader.py
@@ -0,0 +1,29 @@
+from pyteomics import mztab
+from alphastats.loader.BaseLoader import BaseLoader
+
+class mzTabLoader(BaseLoader):
+    def __init__(self, file, intensity_column: str="protein_abundance_[sample]", index_column:str="accession"):
+        """Load mzTab file. Will add contamination column for further analysis.
+
+        Args:
+            file (str): path to mzTab file.
+            intensity_column (str, optional):  columns where the intensity of the proteins are given.. Defaults to "protein_abundance_[sample]".
+            index_column (str, optional): column indicating the protein groups.  Defaults to "accession".
+        """
+        self.filter_columns = []
+        self.gene_names = None
+        self.intensity_column = intensity_column
+        self.index_column = index_column
+        self.confidence_column = None
+        self.evidence_df = None
+        self.gene_names = None
+        self._load_protein_table(file=file)
+        self._add_contamination_column()
+
+
+    def _load_protein_table(self, file):
+        tables = mztab.MzTab(file)
+        self.rawinput = tables.protein_table
+        self.mztab_metadata = tables.metadata
+        self.software = tables.protein_table.search_engine[0]
+
diff --git a/alphastats/plots/IntensityPlot.py b/alphastats/plots/IntensityPlot.py
@@ -128,6 +128,12 @@ def _plot(self):
                  self.prepared_df, y=self.protein_id, x=self.group, color=self.group, labels={self.protein_id: self.y_label}
             )
 
+        elif self.method == "all":
+            fig = px.violin(
+                 self.prepared_df, y=self.protein_id, x=self.group, color=self.group, labels={self.protein_id: self.y_label},
+                 box=True, points="all"
+            )
+
         else:
             raise ValueError(
                 f"{self.method} is not available."

diff --git a/alphastats/plots/VolcanoPlot.py b/alphastats/plots/VolcanoPlot.py
@@ -15,7 +15,8 @@ def __init__(
         column=None, method=None, 
         labels=None, min_fc=None, 
         alpha=None, draw_line=None, 
-        plot=True, perm=100, fdr=0.05
+        plot=True, perm=100, fdr=0.05,
+        color_list=[]
     ):  
         self.dataset = dataset
         self.group1 = group1
@@ -31,6 +32,7 @@ def __init__(
         self.res = None
         self.pvalue_column = None
         self.perm=perm
+        self.color_list = color_list
         self._check_input()
 
         if plot:
@@ -266,6 +268,10 @@ def _annotate_result_df(self):
 
         value = ["down", "up"]
         self.res["color"] = np.select(condition, value, default="non_sig")   
+
+        if len(self.color_list) > 0:
+            self.res["color"] = np.where(self.res[self.dataset.index_column].isin(self.color_list), 
+                                          "color", "no_color")   
 
 
     def _add_labels_plot(self):
@@ -327,6 +333,17 @@ def _draw_fdr_line(self):
             line_shape='spline',
             showlegend=False)
         )
+
+    def _color_data_points(self):
+         # update coloring
+        if len(self.color_list) == 0:
+            color_dict = {"non_sig": "#404040", "up": "#B65EAF", "down": "#009599"}
+
+        else:
+            color_dict = {"no_color": "#404040", "color": "#B65EAF"}
+
+        self.plot = self._update_colors_plotly(self.plot, color_dict=color_dict)
+
 
 
     def _plot(self):
@@ -339,8 +356,7 @@ def _plot(self):
         )
 
         # update coloring
-        color_dict = {"non_sig": "#404040", "up": "#B65EAF", "down": "#009599"}
-        self.plot = self._update_colors_plotly(self.plot, color_dict=color_dict)
+        self._color_data_points()
 
         if self.labels:
             self._add_labels_plot()

diff --git a/docs/Introduction.md b/docs/Introduction.md
@@ -7,6 +7,12 @@
 
 AlphaPeptStats is an open-source package for analyzing mass spectrometry-based proteomics data.
 
-AlphaPeptStats was developed to simplify and standardize the process of analyzing complex datasets. Hereby AlphaPeptStats supports proteomics data generated by `AlphaPept`, `DIA-NN`, `FragPipe`, `MaxQuant` and `Spectronaut`. The tool allows a structured workflow from importing data, preprocessing data to visualization.
+AlphaPeptStats was developed to simplify and standardize the process of analyzing complex datasets. Hereby AlphaPeptStats supports proteomics data generated by `AlphaPept`, `DIA-NN`, `FragPipe`, `MaxQuant` and `Spectronaut` and quantiative proteomics results in `mzTab` format. The tool allows a structured workflow from importing data, preprocessing data to visualization.
 
 AlphaPeptStats was developed by the [Mann Group at the University of Copenhagen](https://www.biochem.mpg.de/mann) and is freely available with an [Apache License](LICENSE.txt). External Python packages (available in the [requirements](requirements) folder) have their own licenses, which can be consulted on their respective websites.
+
+The workflow consists of:
+1. Import of proteomics data 
+2. Creation of the DataSet, consisting of the imported proteomics data and metadata
+3. Data preprocessing (optional)
+4. Statistical Analysis and Visualization
diff --git a/docs/api_reference/loader.rst b/docs/api_reference/loader.rst
@@ -32,3 +32,9 @@ SpectronautLoader
 .. automodule:: alphastats.loader.SpectronautLoader
     :members:
     :undoc-members:
+
+mzTabLoader
+~~~~~~~~~~~~~~~~~~~~~~
+.. automodule:: alphastats.loader.mzTabLoader
+    :members:
+    :undoc-members:
diff --git a/docs/conf.py b/docs/conf.py
@@ -23,7 +23,7 @@
 author = "Elena Krismer"
 
 # The full version, including alpha/beta/rc tags
-release = "0.5.4"
+release = "0.6.0"
 
 
 # -- General configuration ---------------------------------------------------

diff --git a/docs/import_data.md b/docs/import_data.md
@@ -1,9 +1,23 @@
 # Data import
 
 
-Currently, AlphaStats allows the analysis of four quantitative proteomics software packages: AlphaPept, DIA-NN, FragPipe, MaxQuant and Spectronaut. As the output of these software differs significantly data needs to be loaded in customized loaders.
+Currently, AlphaStats allows the analysis of five quantitative proteomics software packages: AlphaPept, DIA-NN, FragPipe, MaxQuant and Spectronaut. As the output of these software differs significantly data needs to be loaded in customized loaders.
 
+Imported proteomics data and metadata can be combined in a DataSet, which will be used for the downstream analysis.
 
+```python
+import alphastats 
+
+maxquant_data = alphastats.MaxQuantLoader(
+    file="testfiles/maxquant_proteinGroups.txt"
+)
+
+dataset = alphastats.DataSet(
+    loader = maxquant_data, 
+    metadata_path="../testfiles/maxquant/metadata.xlsx", 
+    sample_column="sample"
+)
+```
 
 
 ## Importing data from a Proteomics software
@@ -13,7 +27,7 @@ As we are dealing with wide data, a column represents the intensity for one samp
 
 Upon data import, the proteomics data gets processed in an internal format.
 
-## Additional modifications by AlphaStats
+### Additional modifications by AlphaStats
 
 When importing the data, AlphaStats will identify potential contaminations based on a contaminant library, created by [Frankenfield et al. 2022](https://www.biorxiv.org/content/10.1101/2022.04.27.489766v2.full). This information will be added as an extra column to the imported data and can either be ignored or used for filtering in the preprocessing step.
 
@@ -70,19 +84,49 @@ fragpipe_data = alphastats.FragPipeLoader(file="testfiles/fragpipe_combined_prot
 
 Find more details about the file format [here](https://biognosys.com/content/uploads/2022/12/Spectronaut17_UserManual.pdf).
 
-```python
-import alphastats
-spectronaut_data = alphastats.FragPipeLoader(file="testfiles/spectronaut/results.tsv")
-```
+
 As default alphastats will use "PG.ProteinGroups" and "PG.Quantity" for the analysis. For an ananlysis on a peptide level the "F.PeakArea" and the peptide sequences ("PEP.StrippedSequence") can be used.
 
 ```python
-spectronaut_data = alphastats.FragPipeLoader(
+import alphastats
+spectronaut_data = alphastats.SpectronautLoader(
     file="testfiles/spectronaut/results.tsv",
     intensity_column = "F.PeakArea",
     index_column = "PEP.StrippedSequence"
     )
 ```
 
+### mzTab 
+
+Find more details about the file format [here](https://www.psidev.info/mztab).
+
+```python
+import alphastats
+mztab_data = alphastats.mzTabLoader(
+    file="testfiles/mztab/test.mztab"
+    )
+```
+
+
 ## Preparing metadata
+
 To compare samples across various conditions in the downstream analysis, a metadata file in form of a table (excel, csv, tsv) is required. This file should contain a column with the sample IDs (raw file names) matching the sample names annotated in the output file of your proteomics software. Further, information can be provided like disease and various clinical parameters. Examples of metadata files can be found in the [testfiles-folder](https://github.com/MannLabs/alphastats/tree/main/testfiles).
+
+
+## Creating a DataSet
+
+The whole downstream analysis can be perforemd on the alphastats.DataSet. To create the DataSet you need to provide the loader object as well as the metadata.
+
+```python
+import alphastats 
+
+maxquant_data = alphastats.MaxQuantLoader(
+    file="testfiles/maxquant_proteinGroups.txt"
+)
+
+dataset = alphastats.DataSet(
+    loader = maxquant_data, 
+    metadata_path="../testfiles/maxquant/metadata.xlsx", 
+    sample_column="sample"
+)
+```
diff --git a/docs/index.rst b/docs/index.rst
@@ -22,9 +22,9 @@ The tool allows a structured workflow like importing data, preprocessing data an
    installation.md
    import_data.md
    data_preprocessing.md
-   go_analysis.md
    functions.rst
    workflow_example.rst
+   go_analysis.md
    API <api_reference/index>
 
 ..

diff --git a/docs/requirements_docs.txt b/docs/requirements_docs.txt
@@ -1,4 +1,4 @@
-alphastats==0.5.4
+alphastats==0.6.0
 altair==4.2.0 
 anndata==0.8.0 
 attrs==22.1.0 

diff --git a/release/one_click_linux_gui/control b/release/one_click_linux_gui/control
@@ -1,5 +1,5 @@
 Package: alphastats
-Version: 0.5.4
+Version: 0.6.0
 Architecture: all
 Maintainer: MannLabs
 Description: alphastats

diff --git a/release/one_click_linux_gui/create_installer_linux.sh b/release/one_click_linux_gui/create_installer_linux.sh
@@ -17,7 +17,7 @@ python setup.py sdist bdist_wheel
 # Setting up the local package
 cd release/one_click_linux_gui
 # Make sure you include the required extra packages and always use the stable or very-stable options!
-pip install "../../dist/alphastats-0.5.4-py3-none-any.whl"
+pip install "../../dist/alphastats-0.6.0-py3-none-any.whl"
 
 # Creating the stand-alone pyinstaller folder
 pip install pyinstaller==5.8

diff --git a/release/one_click_macos_gui/Info.plist b/release/one_click_macos_gui/Info.plist
@@ -9,9 +9,9 @@
 	<key>CFBundleIconFile</key>
 	<string>alphapeptstats_logo.icns</string>
 	<key>CFBundleIdentifier</key>
-	<string>alphastats.0.5.4</string>
+	<string>alphastats.0.6.0</string>
 	<key>CFBundleShortVersionString</key>
-	<string>0.5.4</string>
+	<string>0.6.0</string>
 	<key>CFBundleInfoDictionaryVersion</key>
 	<string>6.0</string>
 	<key>CFBundleName</key>

diff --git a/release/one_click_macos_gui/create_installer_macos.sh b/release/one_click_macos_gui/create_installer_macos.sh
@@ -20,7 +20,7 @@ python setup.py sdist bdist_wheel
 
 # Setting up the local package
 cd release/one_click_macos_gui
-pip install "../../dist/alphastats-0.5.4-py3-none-any.whl"
+pip install "../../dist/alphastats-0.6.0-py3-none-any.whl"
 
 # Creating the stand-alone pyinstaller folder
 pip install pyinstaller==5.8

diff --git a/release/one_click_macos_gui/distribution.xml b/release/one_click_macos_gui/distribution.xml
@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="utf-8" standalone="no"?>
 <installer-script minSpecVersion="1.000000">
-    <title>AlphaPeptStats 0.5.4</title>
+    <title>AlphaPeptStats 0.6.0</title>
     <background mime-type="image/png" file="alphapeptstats_logo.png" scaling="proportional"/>
     <welcome file="welcome.html" mime-type="text/html" />
     <conclusion file="conclusion.html" mime-type="text/html" />

diff --git a/release/one_click_windows_gui/alphastats_innoinstaller.iss b/release/one_click_windows_gui/alphastats_innoinstaller.iss
@@ -2,7 +2,7 @@
 ; SEE THE DOCUMENTATION FOR DETAILS ON CREATING INNO SETUP SCRIPT FILES!
 
 #define MyAppName "AlphaPeptStats"
-#define MyAppVersion "0.5.4"
+#define MyAppVersion "0.6.0"
 #define MyAppPublisher "MannLabs"
 #define MyAppURL "https://github.com/MannLabs/alphapeptstats"
 #define MyAppExeName "alphastats_gui.exe"

diff --git a/release/one_click_windows_gui/create_installer_windows.sh b/release/one_click_windows_gui/create_installer_windows.sh
@@ -17,7 +17,7 @@ python setup.py sdist bdist_wheel
 # Setting up the local package
 cd release/one_click_windows_gui
 # Make sure you include the required extra packages and always use the stable or very-stable options!
-pip install "../../dist/alphastats-0.5.4-py3-none-any.whl"
+pip install "../../dist/alphastats-0.6.0-py3-none-any.whl"
 
 # Creating the stand-alone pyinstaller folder
 pip install pyinstaller==5.8