add replacement of 0 to gui

HISTORY.md

@@ -1,5 +1,8 @@
 # Changelog
 
+# 0.7.0
+* ADD parameter for loading 0 values as NaNs
+
 # 0.6.5
 * FIX coloring of plot_sampledistribution issue #229
 * ADD nbformat requirement issue #230

alphastats/gui/pages/02_Import Data.py

@@ -102,6 +102,10 @@ def select_columns_for_loaders(software, software_df:None):
             key="intensity_column",
         )
 
+        st.checkbox("Replace 0 values with NaN/mark as missing values in the Intensity columns. ", value = True,
+                    key="replace_zero_with_nan")
+
+
         st.markdown("Select index column (with ProteinGroups) for further analysis")
 
         st.selectbox(
@@ -117,6 +121,9 @@ def select_columns_for_loaders(software, software_df:None):
             key="intensity_column",
         )
 
+        st.checkbox("Replace 0 values with NaN/mark as missing values in the Intensity columns. ", value = True,
+                    key="replace_zero_with_nan")
+
         st.markdown("Select index column (with ProteinGroups) for further analysis")
 
         st.selectbox(
@@ -126,10 +133,10 @@ def select_columns_for_loaders(software, software_df:None):
         )
 
 
-def load_proteomics_data(uploaded_file, intensity_column, index_column, software):
+def load_proteomics_data(uploaded_file, intensity_column, index_column, replace_zero_with_nan, software):
     """load software file into loader object from alphastats"""
     loader = software_options.get(software)["loader_function"](
-        uploaded_file, intensity_column, index_column
+        uploaded_file, intensity_column, index_column, replace_zero_with_nan,
     )
     return loader
 
@@ -191,6 +198,7 @@ def upload_softwarefile(software):
                 softwarefile_df,
                 intensity_column=st.session_state.intensity_column,
                 index_column=st.session_state.index_column,
+                replace_zero_with_nan=st.session_state.replace_zero_with_nan,
                 software=software,
             )
             st.session_state["loader"] = loader

requirements.txt

@@ -1,7 +1,7 @@
 pandas==2.0.2
-scikit-learn==1.2.2
+scikit-learn==1.3.0
 data_cache>=0.1.6
-plotly==5.15.0
+plotly==5.16.1
 statsmodels==0.14.0
 sklearn_pandas==2.2.0
 pingouin==0.5.3
@@ -22,4 +22,5 @@ combat==0.3.3
 xlsxwriter==3.1.0
 pyteomics==4.6.0
 openpyxl>=3.0.10
-nbformat>=5.0
+nbformat>=5.0
+threadpoolctl>=3.0

tests/test_DataSet.py

@@ -390,7 +390,8 @@ def test_plot_clustermap_with_label_bar(self):
 
 class TestMaxQuantDataSet(BaseTestDataSet.BaseTest):
     def setUp(self):
-        self.loader = MaxQuantLoader(file="testfiles/maxquant/proteinGroups.txt")
+        self.loader = MaxQuantLoader(file="testfiles/maxquant/proteinGroups.txt",
+                                     replace_zero_with_nan=False)
         self.metadata_path = "testfiles/maxquant/metadata.xlsx"
         self.obj = DataSet(
             loader=self.loader,
@@ -406,7 +407,7 @@ def test_load_evidence_wrong_sample_names(self):
         with self.assertRaises(ValueError):
             loader = MaxQuantLoader(
                 file="testfiles/maxquant/proteinGroups.txt",
-                evidence_file="testfiles/maxquant_go/evidence.txt",
+                evidence_file="testfiles/maxquant_go/evidence.txt"
             )
             DataSet(
                 loader=loader, metadata_path=self.metadata_path, sample_column="sample",
@@ -737,16 +738,6 @@ def test_multicova_analysis_invalid_covariates(self):
         )
         self.assertEqual(res.shape[1], 45)
 
-    # def test_perform_gsea(self):
-    #     df = self.obj.perform_gsea(column="disease",
-    #                             group1="healthy",
-    #                                     group2="liver cirrhosis",
-    #                                     gene_sets= 'KEGG_2019_Human')
-
-    #     cholesterol_enhanced = 'Cholesterol metabolism' in df.index.to_list()
-    #     self.assertTrue(cholersterol_enhanced)
-
-
 class TestDIANNDataSet(BaseTestDataSet.BaseTest):
     def setUp(self):
         self.loader = DIANNLoader(file="testfiles/diann/report_final.pg_matrix.tsv")
@@ -843,27 +834,13 @@ def test_volcano_plot_wrongmethod(self):
                 method="wrongmethod",
             )
 
-    # def test_diff_expression_analysis_with_list(self):
-    #     self.obj.preprocess(imputation="knn")
-    #     column="grouping1"
-    #     group1="Healthy"
-    #     group2="Disease"
-    #     group1_samples = self.obj.metadata[self.obj.metadata[column] == group1][
-    #             "sample"
-    #         ].tolist()
-    #     group2_samples = self.obj.metadata[self.obj.metadata[column] == group2][
-    #             "sample"
-    #         ].tolist()
-    #     self.obj.diff_expression_analysis(
-    #         group1=group1_samples,
-    #         group2=group2_samples)
-
 
 class TestFragPipeDataSet(BaseTestDataSet.BaseTest):
     def setUp(self):
         self.loader = FragPipeLoader(
             file="testfiles/fragpipe/combined_proteins.tsv",
             intensity_column="[sample] Razor Intensity",
+            replace_zero_with_nan=False
         )
         self.metadata_path = "testfiles/fragpipe/metadata.xlsx"
         self.obj = DataSet(
@@ -887,7 +864,8 @@ def setUpClass(cls):
             )
 
         cls.cls_loader = SpectronautLoader(
-            file="testfiles/spectronaut/results.tsv", filter_qvalue=False
+            file="testfiles/spectronaut/results.tsv", filter_qvalue=False,
+            replace_zero_with_nan=False
         )
         cls.cls_metadata_path = "testfiles/spectronaut/metadata.xlsx"
         cls.cls_obj = DataSet(
@@ -927,7 +905,8 @@ def setUpClass(cls):
                 "S7 Razor Intensity", "S8 Razor Intensity"
             ],
             index_column="Protein",
-            sep="\t"
+            sep="\t",
+            replace_zero_with_nan=False
         )
         cls.cls_metadata_path = "testfiles/fragpipe/metadata2.xlsx"
         cls.cls_obj = DataSet(