[FBMN] Normalize table option that propogates to all values

feature-based-molecular-networking/Makefile

@@ -3,5 +3,5 @@ include ../Makefile.deploytemplate
 
 WORKFLOW_NAME=feature-based-molecular-networking
 TOOL_FOLDER_NAME=feature-based-molecular-networking
-WORKFLOW_VERSION=release_26
+WORKFLOW_VERSION=release_27
 WORKFLOW_DESCRIPTION='Feature-Based Molecular Networking (FBMN) is a computational method that bridges popular mass spectrometry data processing tools for LC-MS/MS and molecular networking analysis on GNPS. The supported tools are: MZmine, OpenMS, MS-DIAL, MetaboScape, XCMS, Progenesis QI, and the mzTab-M format. FBMN facilitates the detection of isomers that are separated by chromatographic or ion mobility separation, and provides accurate ion abundances for statistical analysis. Note that FBMN requires processing the mass spectrometry data with a feature detection and alignment tool. For rapid/qualitative analysis, we recommend using classical molecular networking that accepts unprocessed mass spectrometry files. See the FBMN documentation at https://ccms-ucsd.github.io/GNPSDocumentation/featurebasedmolecularnetworking and refer to the "Method and Citation for Manuscripts" on the results page for citations.'

feature-based-molecular-networking/feature-based-molecular-networking/tool.xml

@@ -115,6 +115,7 @@
             <arg valueRef="inputSpectra"/>
             <arg valueRef="spectra_reformatted"/>
             <arg valueRef="workflowParameters"/>
+            <arg option="-QUANT_FILE_NORM" valueRef="@QUANT_FILE_NORM"/>
         </execution>
     </tool>
 

feature-based-molecular-networking/tools/feature-based-molecular-networking/scripts/reformat_quantification.py

@@ -26,6 +26,8 @@ def main():
     parser.add_argument('input_spectra_folder', help='input_spectra_folder')
     parser.add_argument('output_mgf', help='output_mgf')
     parser.add_argument('workflowParameters', help='workflowParameters')
+    parser.add_argument('--QUANT_FILE_NORM', default="None", help='QUANT_FILE_NORM')
+
     args = parser.parse_args()
 
     input_filenames = glob.glob(os.path.join(args.input_spectra_folder, "*"))
@@ -113,5 +115,20 @@ def main():
         compound_filename_mapping = mztabm_formatter.convert_to_feature_csv(args.quantification_table, args.quantification_table_reformatted)
         mztabm_formatter.create_mgf(input_filenames, args.output_mgf, compound_filename_mapping, name_mangle_mapping=name_mangle_mapping)
 
+    # Finally, we can renormlize the output
+    try:
+        if args.QUANT_FILE_NORM == "RowSum":
+            import pandas as pd
+            quant_df = pd.read_csv(args.quantification_table_reformatted, sep=",")
+            quant_df = quant_df.loc[:, ~quant_df.columns.str.contains('^Unnamed')]
+
+            for column in quant_df:
+                if "Peak area" in column:
+                    quant_df[column] = quant_df[column] / sum(quant_df[column]) * 1000000
+
+            quant_df.to_csv(args.quantification_table_reformatted, sep=",", index=False)
+    except:
+        pass
+
 if __name__ == "__main__":
     main()