Sample size calculation

meta_individual_column.csv

@@ -0,0 +1,144 @@
+Sample,Group,Batch,Individual
+AD01_C1_INSOLUBLE_01,AD,C1,AD01_
+AD01_C1_INSOLUBLE_02,AD,C1,AD01_
+AD01_C1_INSOLUBLE_03,AD,C1,AD01_
+AD01_C2_INSOLUBLE_01,AD,C2,AD01_
+AD02_C1_INSOLUBLE_01,AD,C1,AD02_
+AD02_C1_INSOLUBLE_02,AD,C1,AD02_
+AD02_C2_INSOLUBLE_01,AD,C2,AD02_
+AD03_C1_INSOLUBLE_01,AD,C1,AD03_
+AD03_C1_INSOLUBLE_02,AD,C1,AD03_
+AD03_C1_INSOLUBLE_03,AD,C1,AD03_
+AD03_C2_INSOLUBLE_01,AD,C2,AD03_
+AD04_C1_INSOLUBLE_01,AD,C1,AD04_
+AD04_C2_INSOLUBLE_01,AD,C2,AD04_
+AD05_C2_INSOLUBLE_01,AD,C2,AD05_
+AD06_C1_INSOLUBLE_01,AD,C1,AD06_
+AD07_C1_INSOLUBLE_01,AD,C1,AD07_
+AD07_C1_INSOLUBLE_02,AD,C1,AD07_
+AD07_C1_INSOLUBLE_03,AD,C1,AD07_
+AD07_C2_INSOLUBLE_01,AD,C2,AD07_
+AD08_C2_INSOLUBLE_01,AD,C2,AD08_
+AD09_C1_INSOLUBLE_01,AD,C1,AD09_
+AD10_C1_INSOLUBLE_01,AD,C1,AD10_
+AD10_C2_INSOLUBLE_01,AD,C2,AD10_
+AD11_C2_INSOLUBLE_01,AD,C2,AD11_
+AD12_C2_INSOLUBLE_01,AD,C2,AD12_
+AD13_C2_INSOLUBLE_01,AD,C2,AD13_
+AD14_C2_INSOLUBLE_01,AD,C2,AD14_
+AD15_C2_INSOLUBLE_01,AD,C2,AD15_
+AD16_C2_INSOLUBLE_01,AD,C2,AD16_
+AD17_C2_INSOLUBLE_01,AD,C2,AD17_
+AD18_C2_INSOLUBLE_01,AD,C2,AD18_
+AD19_C2_INSOLUBLE_01,AD,C2,AD19_
+AD20_C1_INSOLUBLE_01,AD,C1,AD20_
+AD21_C1_INSOLUBLE_01,AD,C1,AD21_
+AD21_C2_INSOLUBLE_01,AD,C2,AD21_
+AD22_C1_INSOLUBLE_01,AD,C1,AD22_
+AD23_C1_INSOLUBLE_01,AD,C1,AD23_
+AD23_C1_INSOLUBLE_02,AD,C1,AD23_
+AD23_C2_INSOLUBLE_01,AD,C2,AD23_
+AD24_C1_INSOLUBLE_01,AD,C1,AD24_
+AD24_C1_INSOLUBLE_02,AD,C1,AD24_
+AD25_C1_INSOLUBLE_01,AD,C1,AD25_
+AD26_C1_INSOLUBLE_01,AD,C1,AD26_
+AD27_C1_INSOLUBLE_01,AD,C1,AD27_
+AD27_C1_INSOLUBLE_02,AD,C1,AD27_
+AD28_C2_INSOLUBLE_01,AD,C2,AD28_
+AD29_C1_INSOLUBLE_01,AD,C1,AD29_
+AD30_C1_INSOLUBLE_01,AD,C1,AD30_
+AD30_C1_INSOLUBLE_02,AD,C1,AD30_
+AD30_C2_INSOLUBLE_01,AD,C2,AD30_
+AD31_C2_INSOLUBLE_01,AD,C2,AD31_
+AD32_C2_INSOLUBLE_01,AD,C2,AD32_
+AD33_C2_INSOLUBLE_01,AD,C2,AD33_
+AD34_C1_INSOLUBLE_01,AD,C1,AD34_
+AD34_C1_INSOLUBLE_02,AD,C1,AD34_
+AD35_C1_INSOLUBLE_01,AD,C1,AD35_
+AD35_C1_INSOLUBLE_02,AD,C1,AD35_
+AD36_C1_INSOLUBLE_01,AD,C1,AD36_
+AD37_C1_INSOLUBLE_01,AD,C1,AD37_
+AD37_C2_INSOLUBLE_01,AD,C2,AD37_
+AD38_C1_INSOLUBLE_01,AD,C1,AD38_
+AD38_C1_INSOLUBLE_02,AD,C1,AD38_
+AD38_C1_INSOLUBLE_03,AD,C1,AD38_
+AD39_C2_INSOLUBLE_01,AD,C2,AD39_
+AD40_C2_INSOLUBLE_01,AD,C2,AD40_
+AD41_C2_INSOLUBLE_01,AD,C2,AD41_
+AD42_C2_INSOLUBLE_01,AD,C2,AD42_
+AD43_C1_INSOLUBLE_01,AD,C1,AD43_
+AD44_C1_INSOLUBLE_01,AD,C1,AD44_
+AD44_C1_INSOLUBLE_02,AD,C1,AD44_
+AD44_C1_INSOLUBLE_03,AD,C1,AD44_
+AD44_C1_INSOLUBLE_04,AD,C1,AD44_
+AD45_C1_INSOLUBLE_01,AD,C1,AD45_
+AD45_C1_INSOLUBLE_02,AD,C1,AD45_
+AD46_C1_INSOLUBLE_01,AD,C1,AD46_
+AD46_C1_INSOLUBLE_02,AD,C1,AD46_
+AD46_C1_INSOLUBLE_03,AD,C1,AD46_
+AD46_C2_INSOLUBLE_01,AD,C2,AD46_
+AD47_C1_INSOLUBLE_01,AD,C1,AD47_
+AD48_C2_INSOLUBLE_01,AD,C2,AD48_
+AD49_C2_INSOLUBLE_01,AD,C2,AD49_
+CTR01_C1_INSOLUBLE_01,CTR,C1,CTR01
+CTR02_C1_INSOLUBLE_01,CTR,C1,CTR02
+CTR03_C1_INSOLUBLE_01,CTR,C1,CTR03
+CTR04_C1_INSOLUBLE_01,CTR,C1,CTR04
+CTR05_C2_INSOLUBLE_01,CTR,C2,CTR05
+CTR06_C2_INSOLUBLE_01,CTR,C2,CTR06
+CTR07_C1_INSOLUBLE_01,CTR,C1,CTR07
+CTR08_C1_INSOLUBLE_01,CTR,C1,CTR08
+CTR08_C2_INSOLUBLE_01,CTR,C2,CTR08
+CTR09_C2_INSOLUBLE_01,CTR,C2,CTR09
+CTR10_C1_INSOLUBLE_01,CTR,C1,CTR10
+CTR10_C2_INSOLUBLE_01,CTR,C2,CTR10
+CTR11_C2_INSOLUBLE_01,CTR,C2,CTR11
+CTR12_C2_INSOLUBLE_01,CTR,C2,CTR12
+CTR13_C2_INSOLUBLE_01,CTR,C2,CTR13
+CTR14_C2_INSOLUBLE_01,CTR,C2,CTR14
+CTR15_C2_INSOLUBLE_01,CTR,C2,CTR15
+CTR16_C2_INSOLUBLE_01,CTR,C2,CTR16
+CTR17_C2_INSOLUBLE_01,CTR,C2,CTR17
+CTR18_C2_INSOLUBLE_01,CTR,C2,CTR18
+CTR19_C1_INSOLUBLE_01,CTR,C1,CTR19
+CTR20_C1_INSOLUBLE_01,CTR,C1,CTR20
+CTR21_C2_INSOLUBLE_01,CTR,C2,CTR21
+CTR22_C2_INSOLUBLE_01,CTR,C2,CTR22
+CTR23_C2_INSOLUBLE_01,CTR,C2,CTR23
+CTR24_C1_INSOLUBLE_01,CTR,C1,CTR24
+CTR25_C1_INSOLUBLE_01,CTR,C1,CTR25
+CTR26_C2_INSOLUBLE_01,CTR,C2,CTR26
+CTR27_C1_INSOLUBLE_01,CTR,C1,CTR27
+CTR28_C1_INSOLUBLE_01,CTR,C1,CTR28
+CTR28_C1_INSOLUBLE_02,CTR,C1,CTR28
+CTR28_C2_INSOLUBLE_01,CTR,C2,CTR28
+CTR29_C1_INSOLUBLE_01,CTR,C1,CTR29
+CTR29_C1_INSOLUBLE_02,CTR,C1,CTR29
+CTR29_C1_INSOLUBLE_03,CTR,C1,CTR29
+CTR30_C1_INSOLUBLE_01,CTR,C1,CTR30
+CTR30_C1_INSOLUBLE_02,CTR,C1,CTR30
+CTR30_C2_INSOLUBLE_01,CTR,C2,CTR30
+CTR31_C1_INSOLUBLE_01,CTR,C1,CTR31
+CTR31_C2_INSOLUBLE_01,CTR,C2,CTR31
+CTR32_C1_INSOLUBLE_01,CTR,C1,CTR32
+CTR32_C2_INSOLUBLE_01,CTR,C2,CTR32
+CTR33_C1_INSOLUBLE_01,CTR,C1,CTR33
+CTR34_C1_INSOLUBLE_01,CTR,C1,CTR34
+CTR34_C2_INSOLUBLE_01,CTR,C2,CTR34
+CTR35_C1_INSOLUBLE_01,CTR,C1,CTR35
+CTR36_C1_INSOLUBLE_01,CTR,C1,CTR36
+CTR36_C1_INSOLUBLE_02,CTR,C1,CTR36
+CTR37_C1_INSOLUBLE_01,CTR,C1,CTR37
+CTR38_C1_INSOLUBLE_01,CTR,C1,CTR38
+CTR39_C1_INSOLUBLE_01,CTR,C1,CTR39
+CTR40_C1_INSOLUBLE_01,CTR,C1,CTR40
+CTR40_C1_INSOLUBLE_02,CTR,C1,CTR40
+CTR40_C1_INSOLUBLE_03,CTR,C1,CTR40
+CTR41_C1_INSOLUBLE_01,CTR,C1,CTR41
+CTR41_C1_INSOLUBLE_02,CTR,C1,CTR41
+CTR41_C1_INSOLUBLE_03,CTR,C1,CTR41
+CTR42_C1_INSOLUBLE_01,CTR,C1,CTR42
+CTR42_C1_INSOLUBLE_02,CTR,C1,CTR42
+CTR42_C1_INSOLUBLE_03,CTR,C1,CTR42
+CTR43_C2_INSOLUBLE_01,CTR,C2,CTR43
+CTR44_C1_INSOLUBLE_01,CTR,C1,CTR44

protzilla/data_analysis/differential_expression_mann_whitney.py

@@ -4,21 +4,24 @@
 import pandas as pd
 from scipy import stats
 
-from protzilla.data_analysis.differential_expression_helper import _map_log_base, apply_multiple_testing_correction, \
-    merge_differential_expression_and_significant_df, normalize_ptm_df
+from protzilla.data_analysis.differential_expression_helper import (
+    _map_log_base,
+    apply_multiple_testing_correction,
+    normalize_ptm_df,
+)
 from protzilla.utilities.transform_dfs import long_to_wide
 
 
 def mann_whitney_test_on_intensity_data(
-        protein_df: pd.DataFrame,
-        metadata_df: pd.DataFrame,
-        grouping: str,
-        group1: str,
-        group2: str,
-        log_base: str = None,
-        alpha=0.05,
-        multiple_testing_correction_method: str = "Benjamini-Hochberg",
-        p_value_calculation_method: str = "auto"
+    protein_df: pd.DataFrame,
+    metadata_df: pd.DataFrame,
+    grouping: str,
+    group1: str,
+    group2: str,
+    log_base: str = None,
+    alpha=0.05,
+    multiple_testing_correction_method: str = "Benjamini-Hochberg",
+    p_value_calculation_method: str = "auto",
 ) -> dict:
     """
     Perform Mann-Whitney U test on all proteins in the given intensity data frame.
@@ -57,15 +60,26 @@ def mann_whitney_test_on_intensity_data(
         alpha=alpha,
         multiple_testing_correction_method=multiple_testing_correction_method,
         columns_name="Protein ID",
-        p_value_calculation_method=p_value_calculation_method
+        p_value_calculation_method=p_value_calculation_method,
+    )
+    differentially_expressed_proteins_df = pd.merge(
+        protein_df,
+        outputs["differential_expressed_columns_df"],
+        on="Protein ID",
+        how="left",
     )
-    differentially_expressed_proteins_df = pd.merge(protein_df, outputs["differential_expressed_columns_df"], on="Protein ID", how="left")
     differentially_expressed_proteins_df = differentially_expressed_proteins_df.loc[
-        differentially_expressed_proteins_df["Protein ID"].isin(outputs["differential_expressed_columns_df"]["Protein ID"])
+        differentially_expressed_proteins_df["Protein ID"].isin(
+            outputs["differential_expressed_columns_df"]["Protein ID"]
+        )
     ]
-    significant_proteins_df = pd.merge(protein_df, outputs["significant_columns_df"], on="Protein ID", how="left")
+    significant_proteins_df = pd.merge(
+        protein_df, outputs["significant_columns_df"], on="Protein ID", how="left"
+    )
     significant_proteins_df = significant_proteins_df.loc[
-        significant_proteins_df["Protein ID"].isin(outputs["significant_columns_df"]["Protein ID"])
+        significant_proteins_df["Protein ID"].isin(
+            outputs["significant_columns_df"]["Protein ID"]
+        )
     ]
 
     return dict(
@@ -80,14 +94,14 @@ def mann_whitney_test_on_intensity_data(
 
 
 def mann_whitney_test_on_ptm_data(
-        ptm_df: pd.DataFrame,
-        metadata_df: pd.DataFrame,
-        grouping: str,
-        group1: str,
-        group2: str,
-        alpha=0.05,
-        multiple_testing_correction_method: str = "Benjamini-Hochberg",
-        p_value_calculation_method: str = "auto"
+    ptm_df: pd.DataFrame,
+    metadata_df: pd.DataFrame,
+    grouping: str,
+    group1: str,
+    group2: str,
+    alpha=0.05,
+    multiple_testing_correction_method: str = "Benjamini-Hochberg",
+    p_value_calculation_method: str = "auto",
 ) -> dict:
     """
     Perform Mann-Whitney U test on all PTMs in the given PTM data frame.
@@ -126,7 +140,7 @@ def mann_whitney_test_on_ptm_data(
         alpha=alpha,
         multiple_testing_correction_method=multiple_testing_correction_method,
         columns_name="PTM",
-        p_value_calculation_method=p_value_calculation_method
+        p_value_calculation_method=p_value_calculation_method,
     )
 
     return dict(
@@ -141,16 +155,16 @@ def mann_whitney_test_on_ptm_data(
 
 
 def mann_whitney_test_on_columns(
-        df: pd.DataFrame,
-        metadata_df: pd.DataFrame,
-        grouping: str,
-        group1: str,
-        group2: str,
-        log_base: str = None,
-        alpha=0.05,
-        multiple_testing_correction_method: str = "Benjamini-Hochberg",
-        columns_name: str = "Protein ID",
-        p_value_calculation_method: str = "auto"
+    df: pd.DataFrame,
+    metadata_df: pd.DataFrame,
+    grouping: str,
+    group1: str,
+    group2: str,
+    log_base: str = None,
+    alpha=0.05,
+    multiple_testing_correction_method: str = "Benjamini-Hochberg",
+    columns_name: str = "Protein ID",
+    p_value_calculation_method: str = "auto",
 ) -> dict:
     """
     Perform Mann-Whitney U test on all columns of the data frame.
@@ -197,8 +211,12 @@ def mann_whitney_test_on_columns(
     for column in data_columns:
         group1_data = df_with_groups[df_with_groups[grouping] == group1][column]
         group2_data = df_with_groups[df_with_groups[grouping] == group2][column]
-        u_statistic, p_value = (
-            stats.mannwhitneyu(group1_data, group2_data, alternative="two-sided", method=p_value_calculation_method))
+        u_statistic, p_value = stats.mannwhitneyu(
+            group1_data,
+            group2_data,
+            alternative="two-sided",
+            method=p_value_calculation_method,
+        )
 
         if not np.isnan(p_value):
             log2_fold_change = (
@@ -243,9 +261,13 @@ def mann_whitney_test_on_columns(
 
     significant_columns_df = combined_df[
         combined_df["corrected_p_value"] <= corrected_alpha
-        ]
+    ]
 
-    messages = [dict(level=logging.INFO, msg=f"Invalid columns: {invalid_columns}")] if invalid_columns else []
+    messages = (
+        [dict(level=logging.INFO, msg=f"Invalid columns: {invalid_columns}")]
+        if invalid_columns
+        else []
+    )
 
     return dict(
         differential_expressed_columns_df=combined_df,