Merge pull request #204 from MannLabs/release_0.6.2

Release 0.6.2

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.6.1
+current_version = 0.6.2
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<build>\d+))?

HISTORY.md

@@ -1,6 +1,12 @@
 # Changelog
+
+# 0.6.2
+* FIX preprocessing with VST floats and inf
+* FIX plotly display
+
 # 0.6.1
 * FIX data loading
+
 # 0.6.0
 * ADD mzTAB support
 * ENH color Volcano Plot data points using list of protein names `color_list=your_protein_list`

alphastats/DataSet.py

@@ -146,6 +146,7 @@ def create_matrix(self):
         df.columns = df.columns.str.replace(substring_to_remove, "")
         # transpose dataframe
         mat = df.transpose()
+        mat.replace([np.inf, -np.inf], np.nan, inplace=True)
         # remove proteins with only zero
         self.mat = mat.loc[:, (mat != 0).any(axis=0)]
         self.mat = self.mat.astype(float)
@@ -206,7 +207,7 @@ def overview(self):
         dataset_overview = (
             "Attributes of the DataSet can be accessed using: \n"
             + "DataSet.rawinput:\t Raw Protein data.\n"
-            + "DataSet.mat:\tProcessed data matrix with ProteinIDs/ProteinGroups as columns and samples as rows. All computations are performed on this matrix.\n"
+            + "DataSet.mat:\t\tProcessed data matrix with ProteinIDs/ProteinGroups as columns and samples as rows. All computations are performed on this matrix.\n"
             + "DataSet.metadata:\tMetadata for the samples in the matrix. Metadata will be matched with DataSet.mat when needed (for instance Volcano Plot)."
         )
         print(dataset_overview)

alphastats/DataSet_Plot.py

@@ -115,6 +115,8 @@ def plot_umap(self, group=None, circle=False):
         )
         return dimensionality_reduction.plot
 
+
+    @ignore_warning(RuntimeWarning)
     def plot_volcano(
         self,
         group1,

alphastats/DataSet_Preprocess.py

@@ -81,11 +81,11 @@ def _imputation(self, method):
         logging.info("Imputing data...")
 
         if method == "mean":
-            imp = sklearn.impute.SimpleImputer(missing_values=np.nan, strategy="mean")
+            imp = sklearn.impute.SimpleImputer(missing_values=np.nan, strategy="mean", keep_empty_features=True)
             imputation_array = imp.fit_transform(self.mat.values)
 
         elif method == "median":
-            imp = sklearn.impute.SimpleImputer(missing_values=np.nan, strategy="median")
+            imp = sklearn.impute.SimpleImputer(missing_values=np.nan, strategy="median", keep_empty_features=True)
             imputation_array = imp.fit_transform(self.mat.values)
 
         elif method == "knn":
@@ -145,7 +145,7 @@ def _normalization(self, method):
             )
 
         elif method == "vst":
-            scaler = sklearn.preprocessing.PowerTransformer()
+            scaler = sklearn.preprocessing.PowerTransformer(standardize=False)
             normalized_array = scaler.fit_transform(self.mat.values)
 
         else:
@@ -167,10 +167,17 @@ def reset_preprocessing(self):
         self.create_matrix()
         print("All preprocessing steps are reset.")
 
+    @ignore_warning(RuntimeWarning)
     def _compare_preprocessing_modes(self, func, params_for_func) -> list:
         dataset = self
-        imputation_methods = ["mean", "median", "knn"]
-        normalization_methods = ["zscore", "quantile", "vst"]
+
+        #    normalization_methods = methods["normalization"]
+       # if isinstance(methods, dict):
+        #    imputation_methods = methods["imputation"]
+
+        imputation_methods = ["mean", "median", "knn", "randomforest"]
+        normalization_methods = ["vst","zscore", "quantile" ]
+
         preprocessing_modes = list(itertools.product(normalization_methods, imputation_methods))
 
         results_list = []
@@ -182,7 +189,7 @@ def _compare_preprocessing_modes(self, func, params_for_func) -> list:
             # reset preprocessing
             dataset.reset_preprocessing()
             print(f"Normalization {preprocessing_mode[0]}, Imputation {str(preprocessing_mode[1])}")
-
+            dataset.mat.replace([np.inf, -np.inf], np.nan, inplace=True)
             dataset.preprocess(
                 subset=True,
                 normalization = preprocessing_mode[0],
@@ -192,6 +199,8 @@ def _compare_preprocessing_modes(self, func, params_for_func) -> list:
             res = func(**params_for_func)
             results_list.append(res)
 
+            print("\t")
+
         return results_list
 
     def _log2_transform(self):
@@ -272,11 +281,13 @@ def preprocess(
         if subset:
             self.mat = self._subset()
 
-        if log2_transform:
+        if log2_transform and self.preprocessing_info.get("Log2-transformed") is False:
             self._log2_transform()
 
         if normalization is not None:
             self._normalization(method=normalization)
+            self.mat = self.mat.replace([np.inf, -np.inf], np.nan)
+            #self.mat[:] = np.nan_to_num(self.mat)
 
         if imputation is not None:
             self._imputation(method=imputation)

alphastats/__init__.py

@@ -1,5 +1,5 @@
 __project__ = "alphastats"
-__version__ = "0.6.1"
+__version__ = "0.6.2"
 __license__ = "Apache"
 __description__ = "An open-source Python package for Mass Spectrometry Analysis"
 __author__ = "Mann Labs"

alphastats/plots/DimensionalityReduction.py

@@ -134,6 +134,7 @@ def _plot(self, sample_names, group_color):
             labels=self.labels,
             color=group_color,
             hover_data=[components[self.dataset.sample]],
+            template="simple_white+alphastats_colors"
         )
 
         # rename hover_data_0 to sample

alphastats/plots/IntensityPlot.py

@@ -4,9 +4,30 @@
 import numpy as np
 import plotly.graph_objects as go
 import plotly.express as px
+import plotly
 
 from alphastats.plots.PlotUtils import plotly_object, PlotUtils
 
+plotly.io.templates["alphastats_colors"] = plotly.graph_objects.layout.Template(
+    layout=plotly.graph_objects.Layout(
+        paper_bgcolor="rgba(0,0,0,0)",
+        plot_bgcolor="rgba(0,0,0,0)",
+        colorway=[
+            "#009599",
+            "#005358",
+            "#772173",
+            "#B65EAF",  # pink
+            "#A73A00",
+            "#6490C1",
+            "#FF894F",
+            "#2B5E8B",
+            "#A87F32",
+        ],
+    )
+)
+
+plotly.io.templates.default = "simple_white+alphastats_colors"
+
 
 class IntensityPlot(PlotUtils):
     def __init__(self,
@@ -115,23 +136,26 @@ def _prepare_data(self):
     def _plot(self):
         if self.method == "violin":
             fig = px.violin(
-                self.prepared_df, y=self.protein_id, x=self.group, color=self.group, labels={self.protein_id: self.y_label}
+                self.prepared_df, y=self.protein_id, x=self.group, color=self.group, labels={self.protein_id: self.y_label},
+                template="simple_white+alphastats_colors"
             )
 
         elif self.method == "box":
             fig = px.box(
-                self.prepared_df, y=self.protein_id, x=self.group, color=self.group, labels={self.protein_id: self.y_label}
+                self.prepared_df, y=self.protein_id, x=self.group, color=self.group, labels={self.protein_id: self.y_label},
+                template="simple_white+alphastats_colors"
             )
 
         elif self.method == "scatter":
             fig = px.scatter(
-                 self.prepared_df, y=self.protein_id, x=self.group, color=self.group, labels={self.protein_id: self.y_label}
+                 self.prepared_df, y=self.protein_id, x=self.group, color=self.group, labels={self.protein_id: self.y_label},
+                 template="simple_white+alphastats_colors"
             )
 
         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"
+                 box=True, points="all", template= "simple_white+alphastats_colors"
             )
 
         else:

alphastats/plots/PlotUtils.py

@@ -2,6 +2,26 @@
 import seaborn as sns
 import plotly.graph_objects as go
 
+plotly.io.templates["alphastats_colors"] = plotly.graph_objects.layout.Template(
+    layout=plotly.graph_objects.Layout(
+        paper_bgcolor="rgba(0,0,0,0)",
+        plot_bgcolor="rgba(0,0,0,0)",
+        colorway=[
+            "#009599",
+            "#005358",
+            "#772173",
+            "#B65EAF",  # pink
+            "#A73A00",
+            "#6490C1",
+            "#FF894F",
+            "#2B5E8B",
+            "#A87F32",
+        ],
+    )
+)
+
+plotly.io.templates.default = "simple_white+alphastats_colors"
+
 class PlotUtils:
     def __init__(self) -> None:
         pass

alphastats/plots/VolcanoPlot.py

@@ -5,9 +5,28 @@
 import pandas as pd
 import plotly.express as px
 import plotly.graph_objects as go
-
+import plotly
 from functools import lru_cache
 
+plotly.io.templates["alphastats_colors"] = plotly.graph_objects.layout.Template(
+    layout=plotly.graph_objects.Layout(
+        paper_bgcolor="rgba(0,0,0,0)",
+        plot_bgcolor="rgba(0,0,0,0)",
+        colorway=[
+            "#009599",
+            "#005358",
+            "#772173",
+            "#B65EAF",  # pink
+            "#A73A00",
+            "#6490C1",
+            "#FF894F",
+            "#2B5E8B",
+            "#A87F32",
+        ],
+    )
+)
+
+plotly.io.templates.default = "simple_white+alphastats_colors"
 
 class VolcanoPlot(PlotUtils):
     def __init__(
@@ -245,7 +264,7 @@ def _annotate_result_df(self):
         convert pvalue to log10
         add color labels for up and down regulates
         """
-        self.res = self.res[(self.res["log2fc"] < 10) & (self.res["log2fc"] > -10)]
+        self.res = self.res[(self.res["log2fc"] < 20) & (self.res["log2fc"] > -20)]
         self.res["-log10(p-value)"] = -np.log10(self.res[self.pvalue_column])
 
         self.alpha = -np.log10(self.alpha)
@@ -353,6 +372,7 @@ def _plot(self):
             y="-log10(p-value)",
             color="color",
             hover_data=self.hover_data,
+            template= "simple_white+alphastats_colors"
         )
 
         # update coloring

docs/conf.py

@@ -23,7 +23,7 @@
 author = "Elena Krismer"
 
 # The full version, including alpha/beta/rc tags
-release = "0.6.1"
+release = "0.6.2"
 
 
 # -- General configuration ---------------------------------------------------

nbs/getting_started.ipynb

@@ -13,6 +13,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "63ea0375-2937-4689-b1c9-f2186776b329",
    "metadata": {},
@@ -329,6 +330,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "ebcf20a2-458d-480b-8a76-4d38c98aa1a2",
    "metadata": {},
@@ -618,6 +620,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "1b2da0df-dd79-429f-815e-cea5228790dd",
    "metadata": {},
@@ -648,6 +651,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "71235990-e4bc-491f-8828-8f9445dcac3b",
    "metadata": {},
@@ -681,6 +685,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "aefc5fe7-0f97-42d5-acb6-d9a151320627",
    "metadata": {},
@@ -716,6 +721,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "e0efd5a2-22cf-4504-9ce8-0490a7967e92",
    "metadata": {},
@@ -725,6 +731,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "b8244053-e920-447d-a405-7049507733a9",
    "metadata": {},
@@ -751,6 +758,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "1cd24307-cd84-411b-8c3c-dccc3be08dbc",
    "metadata": {},
@@ -787,6 +795,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "bc027a63-318a-475d-a04e-7e27002e2ee2",
    "metadata": {},
@@ -813,6 +822,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "51c7655f-9bb7-4473-be47-563e8ced0e98",
    "metadata": {},
@@ -848,6 +858,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "d4d74bd7-3937-4155-965c-302c7a7795c4",
    "metadata": {},
@@ -874,6 +885,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "4357b5ee-e208-4992-9f52-60ec5eb73758",
    "metadata": {},
@@ -914,6 +926,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "7bdf8679-0451-4f2f-b041-637d134c7ea2",
    "metadata": {},
@@ -958,7 +971,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.7"
+   "version": "3.9.13"
   },
   "vscode": {
    "interpreter": {