Merge pull request #134 from Proteobench/moduleddalog2

Moduleddalog2 adresses issues #40 and closes #133 #113

proteobench/modules/dda_quant/datapoint.py

@@ -42,26 +42,8 @@ def calculate_missing_quan_prec(self, df, nr_missing_0):
         return nr_quan_prec_missing
 
     def calculate_plot_data(self, df):
-        species = ["YEAST", "HUMAN", "ECOLI"]
-        prop_ratios = []
-        sum_ratios = 0
-        nr_missing_0 = 0
-        for spec in species:
-            f = len(df[df[spec] == True])
-            sum_s = np.nan_to_num(
-                df[df[spec] == True]["1|2_expected_ratio_diff"],
-                nan=0,
-                neginf=-1000,
-                posinf=1000,
-            ).sum()
-            ratio = sum_s / f
-            prop_ratio = (f / len(df)) * ratio
-            prop_ratios.append(prop_ratio)
-            sum_ratios += prop_ratio
-            nr_missing_0 += f
-
-        # TODO rename/document code
-        self.weighted_sum = round(sum_ratios, ndigits=3)
+        # compute mean of epsilon column in df
+        self.weighted_sum = round(df["epsilon"].mean(), ndigits=3)
         self.nr_prec = len(df)
 
     def generate_id(self):

proteobench/modules/dda_quant/io_parse_settings/module_settings.toml

@@ -1,12 +1,12 @@
 [species_expected_ratio]
 [species_expected_ratio.YEAST]
-"1|2" = 2.0
+"A_vs_B" = 2.0
 
 [species_expected_ratio.ECOLI]
-"1|2" = 0.25
+"A_vs_B" = 0.25
 
 [species_expected_ratio.HUMAN]
-"1|2" = 1.0
+"A_vs_B" = 1.0
 
 [general]
 min_count_multispec = 1

proteobench/modules/dda_quant/io_parse_settings/parse_settings_alphapept.toml

@@ -8,12 +8,12 @@ decoy = "Reverse"
 ms1_int_sum_apex_dn = "Intensity"
 
 [replicate_mapper]
-LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_01 = 1
-LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_02 = 1
-LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_03 = 1
-LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_01 = 2
-LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_02 = 2
-LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_03 = 2
+LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_01 = "A"
+LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_02 = "A"
+LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_03 = "A"
+LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_01 = "B"
+LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_02 = "B"
+LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_03 = "B"
 
 [run_mapper]
 LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_01 = "Condition_A_Sample_Alpha_01"

proteobench/modules/dda_quant/io_parse_settings/parse_settings_custom.toml

@@ -5,12 +5,12 @@ Charge = "Charge"
 
 
 [replicate_mapper]
-LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_01 = 1
-LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_02 = 1
-LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_03 = 1
-LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_01 = 2
-LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_02 = 2
-LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_03 = 2
+LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_01 = "A"
+LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_02 = "A"
+LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_03 = "A"
+LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_01 = "B"
+LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_02 = "B"
+LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_03 = "B"
 
 [run_mapper]
 LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_01 = "Condition_A_Sample_Alpha_01"

proteobench/modules/dda_quant/io_parse_settings/parse_settings_maxquant.toml

@@ -6,12 +6,12 @@ Proteins = "Proteins"
 Charge = "Charge"
 
 [replicate_mapper]
-LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_01 = 1
-LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_02 = 1
-LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_03 = 1
-LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_01 = 2
-LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_02 = 2
-LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_03 = 2
+LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_01 = "A"
+LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_02 = "A"
+LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_03 = "A"
+LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_01 = "B"
+LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_02 = "B"
+LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_03 = "B"
 
 [run_mapper]
 "LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_01" = "Condition_A_Sample_Alpha_01"

proteobench/modules/dda_quant/io_parse_settings/parse_settings_msfragger.toml

@@ -5,12 +5,12 @@ Protein = "Proteins"
 Charge = "Charge"
 
 [replicate_mapper]
-"A_1 Intensity" = 1
-"A_2 Intensity" = 1
-"A_3 Intensity" = 1
-"B_1 Intensity" = 2
-"B_2 Intensity" = 2
-"B_3 Intensity" = 2
+"A_1 Intensity" = "A"
+"A_2 Intensity" = "A"
+"A_3 Intensity" = "A"
+"B_1 Intensity" = "B"
+"B_2 Intensity" = "B"
+"B_3 Intensity" = "B"
 
 [run_mapper]
 "A_1 Intensity" = "Condition_A_Sample_Alpha_01"

proteobench/modules/dda_quant/io_parse_settings/parse_settings_proline.toml

@@ -6,12 +6,12 @@ sequence = "Sequence"
 
 
 [replicate_mapper]
-abundance_DDA_Condition_A_Sample_Alpha_01 = 1
-abundance_DDA_Condition_A_Sample_Alpha_02 = 1
-abundance_DDA_Condition_A_Sample_Alpha_03 = 1
-abundance_DDA_Condition_B_Sample_Alpha_01 = 2
-abundance_DDA_Condition_B_Sample_Alpha_02 = 2
-abundance_DDA_Condition_B_Sample_Alpha_03 = 2
+abundance_DDA_Condition_A_Sample_Alpha_01 = "A"
+abundance_DDA_Condition_A_Sample_Alpha_02 = "A"
+abundance_DDA_Condition_A_Sample_Alpha_03 = "A"
+abundance_DDA_Condition_B_Sample_Alpha_01 = "B"
+abundance_DDA_Condition_B_Sample_Alpha_02 = "B"
+abundance_DDA_Condition_B_Sample_Alpha_03 = "B"
 
 [run_mapper]
 "abundance_DDA_Condition_A_Sample_Alpha_01" = "Condition_A_Sample_Alpha_01"

proteobench/modules/dda_quant/io_parse_settings/parse_settings_sage.toml

@@ -4,12 +4,12 @@
 "charge" = "Charge"
 
 [replicate_mapper]
-"LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_01.mzML.gz" = 1
-"LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_02.mzML.gz" = 1
-"LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_03.mzML.gz" = 1
-"LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_01.mzML.gz" = 2
-"LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_02.mzML.gz" = 2
-"LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_03.mzML.gz" = 2
+"LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_01.mzML.gz" = "A"
+"LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_02.mzML.gz" = "A"
+"LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_03.mzML.gz" = "A"
+"LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_01.mzML.gz" = "B"
+"LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_02.mzML.gz" = "B"
+"LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_03.mzML.gz" = "B"
 
 [run_mapper]
 "LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_01.mzML" = "Condition_A_Sample_Alpha_01"

proteobench/modules/dda_quant/io_parse_settings/parse_settings_wombat.toml

@@ -3,12 +3,12 @@ protein_group = "Proteins"
 "modified_peptide" = "Modified sequence"
 
 [replicate_mapper]
-abundance_A_1 = 1
-abundance_A_2 = 1
-abundance_A_3 = 1
-abundance_B_1 = 2
-abundance_B_2 = 2
-abundance_B_3 = 2
+abundance_A_1 = "A"
+abundance_A_2 = "A"
+abundance_A_3 = "A"
+abundance_B_1 = "B"
+abundance_B_2 = "B"
+abundance_B_3 = "B"
 
 [run_mapper]
 abundance_A_1 = "Condition_A_Sample_Alpha_01"