v4.4.3

Author: fsalbeez

README.md

@@ -2,7 +2,7 @@
 CARMEN is a diagnostic tool designed for surveillance purposes. Below are the instructions to complete your CARMEN analysis. 
 
 ## Software Version
-When cloning this repository, you will be using software version 4.4.2.
+When cloning this repository, you will be using software version 4.4.3.
 
 ## Overview
 At this point, you have ran the $Standard\ BioTools\ Dynamic\ Array^{TM}$ IFC (integrated fluidic circuit) on the $Standard\ BioTools\ Biomark^{TM}$ instrument and have completed the experimental portion of CARMEN. In running this code, you will be able to complete the data analysis portion of CARMEN and generate both binary positive/negative and quantitative signal output of your diagnostic assay. 

analyze_run.py

@@ -49,7 +49,7 @@
 
 ######################################################################################################################################################
 # assign software version
-software_version = '4.4.2'
+software_version = '4.4.3'
 
 ######################################################################################################################################################
 # data loading
@@ -843,6 +843,9 @@
 fl_rounded_ntc_thresholds_output = flagged_files[3] # NTC_thresholds
 fl_t13_hit_binary_output = flagged_files[4] # 't13__{barcode_assignment}_hit_binary
 
+# any last formatting changes to dataframes
+fl_t13_hit_binary_output.columns = fl_t13_hit_binary_output.columns.str.upper()
+
 # SAVE all the files to their respective output folders
 sheet_names = [
     "CARMEN_Hit_Results",

binary_results.py

@@ -13,6 +13,13 @@ def __init__(self):
 
     # positive = 1, negative = 0
     def hit_numeric_conv(self, binary_t13_hit_df):
-        binary_t13_hit_df = binary_t13_hit_df.replace(['POSITIVE', 'NEGATIVE'], [1,0])   
+        #deprecated approaches
+        #binary_t13_hit_df = binary_t13_hit_df.replace(['POSITIVE', 'NEGATIVE'], [1,0]) 
+        #binary_t13_hit_df = binary_t13_hit_df.applymap(lambda x: {'POSITIVE': 1, 'NEGATIVE': 0}.get(x, x))
+        
+        binary_t13_hit_df = binary_t13_hit_df.assign(
+                **{col: binary_t13_hit_df[col].map({'POSITIVE': 1, 'NEGATIVE': 0}) for col in binary_t13_hit_df.columns}
+            )
+        
         return binary_t13_hit_df
 

flags.py

@@ -15,9 +15,10 @@ def assign_flags(self, fail_nocrRNA_check_df, high_raw_ntc_signal_df, rnasep_df,
         files = [t13_hit, t13_quant_norm, pos_samples_df, ntc_thresh, t13_hit_binary] # 0, 1, 2, 3, 4
         flagged_files = [] # store modified files after applying flags
 
-        ### CPC flags 
-        ## need to be added to t13_hit_output, rounded_t13_quant_norm, summary_samples_df, ntc_thresholds_output, t13_hit_binary_output
         for i, file in enumerate(files): 
+
+            ### CPC flags 
+            ## need to be added to t13_hit_output, rounded_t13_quant_norm, summary_samples_df, ntc_thresholds_output, t13_hit_binary_output
             flagged_file = file.copy() # work on a copy of the orig file
             invalid_assays = []  #  track which assays are invalid based on QC3 test results
             for row in QC_score_per_assay_df.itertuples():
@@ -78,9 +79,11 @@ def assign_flags(self, fail_nocrRNA_check_df, high_raw_ntc_signal_df, rnasep_df,
                                             processed_samples.add((cont_ntc_sample, cont_ntc_assay))
                                             # check if the value is NA (NaN)
                                             if pd.isna(sample_row[assay_col]):
-                                                flagged_file.at[idx, assay_col] = '†'  # only dagger if value is NA
+                                                flagged_file.loc[idx, assay_col] = '†'  # only dagger if value is NA
                                             else:
-                                                flagged_file.at[idx, assay_col] = f"{sample_row[assay_col]}†"  # add dagger to the value
+                                                flagged_file[assay_col] = flagged_file[assay_col].astype(str)
+                                                #flagged_file.at[idx, assay_col] = str(flagged_file.at[idx, assay_col])
+                                                flagged_file.loc[idx, assay_col] = f"{sample_row[assay_col]}†"  # add dagger to the value
 
                 for _, row in high_raw_ntc_signal_df.iterrows(): 
                     for col in high_raw_ntc_signal_df.columns: 

median_frame.py

@@ -15,12 +15,22 @@ def create_median(self, signal_norm):
          # create a list containing t1 thru t13
         t_names = [col for col in signal_norm.columns if col.startswith('t')]
 
+        # initialize a dictionary
         med_frames = {}
-        for name in t_names:
+        # for each timepoint
+        for name in t_names: 
+            # groups signal_norm by assay and sample
+            # in groupby, pandas automatically sorts the assay col in alpha order
+            # selects the column for the specific timepoint
+            # calculate the median value for each unique group (assay and sample) for that specific timepoint
+            # finally .unstack() unstacks the sample (outer layer of grouping), so the samples are columns and assays are rows
             time_med = signal_norm.groupby(['assay', 'sample'])[name].median().unstack()
+            # clean up the names of index and columns
             time_med.index.names=['']
             time_med.columns.names=['']
+            # transpose time_med so the rows are samples and the columns are assays
             time_med_transposed = time_med.transpose()
+            # store transposed df for each timepoint into dictionary med_frames with timepoint as the key
             med_frames[name] = time_med_transposed
 
         return med_frames

t13_plotting.py

@@ -241,7 +241,7 @@ def t13_plt_heatmap(self, tgap, barcode_number, df, sample_list, assay_list, tp,
                                 ha='left', fontsize=12, style='italic')
 
                 # plot *** on x-axis that contains Invalid Samples
-                if invalid_samples:
+                if invalid_samples.size>0:
                     invalid_samples = [sample.upper() for sample in invalid_samples]
                     """
                     asterisk3_labels = [label + '***' if label in invalid_samples else label for label in frame2.columns]