Merge pull request #166 from MannLabs/feature_release_0_5

Release 0.5.0

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.5
+current_version = 0.5.0
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<build>\d+))?

HISTORY.md

@@ -1,5 +1,13 @@
 # Changelog
 
+# 0.5.0
+* ADD plot Sample Distribution Histogram
+* 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
+* ENH upgrade to pandas 2.0.0
+
 # 0.4.5
 * FIX loading of Data on Windows
 

alphastats/DataSet_Plot.py

@@ -18,6 +18,7 @@
 from alphastats.plots.VolcanoPlot import VolcanoPlot
 from alphastats.plots.IntensityPlot import IntensityPlot
 from alphastats.plots.ClusterMap import ClusterMap
+from alphastats.plots.SampleHistogram import SampleHistogram
 from alphastats.utils import ignore_warning, check_for_missing_values
 
 
@@ -290,6 +291,14 @@ def plot_clustermap(
         )
         return  clustermap.plot
 
+    def plot_samplehistograms(self):
+        """Plots the Denisty distribution of each sample
+
+        Returns:
+            plotly: Plotly Graph Object
+        """
+        return SampleHistogram(dataset=self).plot()
+
     @check_for_missing_values
     def plot_dendrogram(
         self, linkagefun=lambda x: scipy.cluster.hierarchy.linkage(x, "complete")

alphastats/DataSet_Preprocess.py

@@ -10,6 +10,7 @@
 import itertools
 
 
+
 class Preprocess:
     def _remove_sampels(self, sample_list):
         # exclude samples for analysis
@@ -166,7 +167,7 @@ def reset_preprocessing(self):
         self.create_matrix()
         print("All preprocessing steps are reset.")
 
-    def _compare_preprocessing_modes(self, func, params_for_func):
+    def _compare_preprocessing_modes(self, func, params_for_func) -> list:
         dataset = self
         imputation_methods = ["mean", "median", "knn"]
         normalization_methods = ["zscore", "quantile", "vst"]
@@ -195,18 +196,31 @@ def _compare_preprocessing_modes(self, func, params_for_func):
 
     def _log2_transform(self):
         self.mat = np.log2(self.mat + 0.1)
-        self.preprocessing_info.update({"Log2 Transformed": True})
+        self.preprocessing_info.update({"Log2-transformed": True})
+        print("Data has been log2-transformed.")
+
+    def batch_correction(self, batch:str):
+        """Correct for technical bias/batch effects
+        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
 
+        Args:
+            batch (str): column name in the metadata describing the different batches
+        """
+        import combat
+        from combat.pycombat import pycombat
+        data = self.mat.transpose()
+        series_of_batches = self.metadata.set_index(self.sample).reindex(data.columns.to_list())[batch]
+        self.mat = pycombat(data=data, batch=series_of_batches).transpose()
 
     @ignore_warning(RuntimeWarning)
     def preprocess(
         self,
-        log2_transform=True,
-        remove_contaminations=False,
-        subset=False,
-        normalization=None,
-        imputation=None,
-        remove_samples=None,
+        log2_transform: bool=True,
+        remove_contaminations: bool=False,
+        subset: bool=False,
+        normalization: str=None,
+        imputation: str=None,
+        remove_samples: list=None,
     ):
         """Preprocess Protein data
 
@@ -251,6 +265,9 @@ def preprocess(
         """
         if remove_contaminations:
             self._filter()
+
+        if remove_samples is not None:
+            self._remove_sampels(sample_list=remove_samples)
 
         if subset:
             self.mat = self._subset()
@@ -264,8 +281,5 @@ def preprocess(
         if imputation is not None:
             self._imputation(method=imputation)
 
-        if remove_samples is not None:
-            self._remove_sampels(sample_list=remove_samples)
-
         self.mat = self.mat.loc[:, (self.mat != 0).any(axis=0)]
         self.preprocessed = True