update(main, tidy, utils): arg -ox output files extension tsv|csv|txt

tracegroomer/__main__.py

@@ -13,10 +13,10 @@ def prep_args() -> argparse.ArgumentParser:
                                      formatter_class=show_defaults)
 
     parser.add_argument('-cf', '--config_file', type=str,
-                        help="Configuration file given as absolute path.")
+                        help="Configuration file given as absolute path")
 
     parser.add_argument('-lm', '--labeled_metabo_file', type=str, default=None,
-                        help="Labeled metabolomics input file, absolute path.")
+                        help="Labeled metabolomics input file, absolute path")
 
     parser.add_argument('-tf', '--type_of_file', type=str, default=None,
                         help="One of the following: \
@@ -25,27 +25,27 @@ def prep_args() -> argparse.ArgumentParser:
     parser.add_argument('--amountMaterial_path', type=str, default=None,
                         help="absolute path to the file having the amount \
                            of material (number of cells, tissue weight, etc) \
-                           by sample, for the normalization.")
+                           by sample, for the normalization")
 
     parser.add_argument("--alternative_div_amount_material",
                         action=argparse.BooleanOptionalAction, default=True,
                         help="When dividing values by the amount of  \
                         material, also multiplies by 'mean(amountMaterial)' \
-                        to stay in abundance units.")
+                        to stay in abundance units")
 
     parser.add_argument("--div_isotopologues_by_amount_material",
                         action=argparse.BooleanOptionalAction,
                         default=True,
                         help="Apply normalization by the amount of material, \
                         at the level of isotopologue absolute values. \
                         After this, re-computes all derived metrics. \
-                        If False, only total abundances are normalized.")
+                        If False, only total abundances are normalized")
 
     parser.add_argument("--use_internal_standard", default=None, type=str,
                         help='Internal Standard for performing the division: \
                         total_abundances/internal_standard, \
                         example: --use_internal_standard Myristic_acid_d27. \
-                        By default is not performed.')
+                        By default is not performed')
 
     parser.add_argument("--remove_these_metabolites", default=None, type=str,
                         help="Absolute path to the file with columns:  \
@@ -59,8 +59,8 @@ def prep_args() -> argparse.ArgumentParser:
                         help="Plot isotopologue values, as given")
 
     parser.add_argument("--isosprop_min_admitted", default=-0.5, type=float,
-                        help="Metabolites whose isotopologues are less  \
-                        or equal to this cutoff, are removed.")
+                        help="Metabolites whose isotopologues proportions are\
+                        less or equal to this cutoff, are removed")
 
     parser.add_argument("--fractions_stomp_values",
                         action=argparse.BooleanOptionalAction, default=True,
@@ -72,12 +72,17 @@ def prep_args() -> argparse.ArgumentParser:
     parser.add_argument("--under_detection_limit_set_nan",
                         action=argparse.BooleanOptionalAction,
                         default=True, help="On VIB results. Any abundance \
-                           < LOD (Limit Of Detection), is set as NaN.")
+                           < LOD (Limit Of Detection), is set as NaN")
 
     parser.add_argument("--subtract_blankavg",
                         action=argparse.BooleanOptionalAction, default=True,
                         help="On VIB results. From samples' abundances,  \
-                          subtracts the average of the blanks.")
+                          subtracts the average of the blanks")
+
+    # output files extension
+    parser.add_argument("-ox", "--output_files_extension", type=str,
+                        default="csv", help="Extension for the output files, \
+                        must be one of the following: csv|tsv|txt")
 
     return parser
 

tracegroomer/tidy.py

@@ -168,8 +168,8 @@ def save_isotopologues_preview(self, args, confdict, groom_out_path):
             if not os.path.exists(output_plots_dir):
                 os.makedirs(output_plots_dir)
             ut.save_isos_preview(
-                compartmentalized_dict, self.metadata,
-                output_plots_dir, args.isotopologues_preview)
+                compartmentalized_dict, self.metadata, output_plots_dir,
+                args.isotopologues_preview, args.output_files_extension)
             logger.info(f"saved figures to {output_plots_dir}")
 
     def pull_internal_standard(self, confdict, args):
@@ -304,7 +304,7 @@ def check_confdict_completeness(confdict) -> None:
                         f" in columns_variable_description")
 
 
-def save_tables(frames_dict, groom_out_path) -> None:
+def save_tables(frames_dict, groom_out_path, output_extension) -> None:
     for k in frames_dict.keys():
         # reunify the compartments
         tmpli = list()
@@ -320,10 +320,10 @@ def save_tables(frames_dict, groom_out_path) -> None:
         final_df.index.name = "ID"
         final_df = final_df.reset_index()
         final_df = final_df.drop_duplicates()
-        final_df.to_csv(os.path.join(groom_out_path, f"{k}.csv"),
-                        sep='\t', header=True, index=False)
+        o_file_path = os.path.join(groom_out_path, f"{k}.{output_extension}")
+        final_df.to_csv(o_file_path, sep='\t', header=True, index=False)
 
-        logger.info(f"File saved to: {os.path.join(groom_out_path, k)}.csv")
+        logger.info(f"File saved to: {o_file_path}")
         # note : do not clear zero rows, as gives problem pd.merge
 
 
@@ -351,7 +351,8 @@ def wrapper_common_steps(combo_data: CompositeData,
     combo_data.drop_metabolites()
     combo_data.stomp_fraction_values(args, confdict)
     combo_data.transfer__abund_nan__to_all_tables(confdict)
-    save_tables(combo_data.frames_dict, groom_out_path)
+    save_tables(combo_data.frames_dict, groom_out_path,
+                args.output_files_extension)
 
 
 def perform_type_prep(args, confdict, metadata_used_extension: str,

tracegroomer/utils.py

@@ -362,7 +362,7 @@ def save_heatmap_sums_isos(thesums, figuretitle, outputfigure) -> None:
 
 
 def save_isos_preview(dict_isos_prop, metadata, output_plots_dir,
-                      the_boolean_arg) -> None:
+                      the_boolean_arg, output_extension) -> None:
     if the_boolean_arg:
         for k in metadata['compartment'].unique().tolist():
             df = dict_isos_prop[k]
@@ -387,7 +387,7 @@ def save_isos_preview(dict_isos_prop, metadata, output_plots_dir,
             dfmelt = pd.melt(df, id_vars=['metabolite', 'isotopologue_type'])
             dfmelt = impute_custom_levels_to_df(dfmelt)
             table_minimalbymet(dfmelt, os.path.join(output_plots_dir,
-                               f"minextremesIso_{k}.csv"))
+                               f"minextremesIso_{k}.{output_extension}"))
             outputfigure = os.path.join(output_plots_dir, f"allsampleIsos_{k}.pdf")
             figtitle = f"{k} compartment, Isotopologues (proportions) \
             across all samples"