got the arguments working

.gitignore

@@ -5,3 +5,7 @@ __pycache__/
 *.pyc
 *.pyo
 *.pyd
+
+
+#output folder of results
+output

bin/create-pathways.py

@@ -22,24 +22,24 @@ def main():
 
     taxon_id = "9606"
 
-    if args.input_file:
+    if args.pathway_list:
         # Read pathways from the input file
         try:
-            pathways_df = pd.read_csv(args.input_file, sep='\t')
+            pathways_df = pd.read_csv(args.pathway_list, sep='\t')
             pathways = dict(zip(pathways_df['ID'], pathways_df['PathwayName']))
         except Exception as e:
-            logger.error(f"Error reading input file: {e}")
+            logger.error(f"Error reading pathway list file: {e}")
             return
     else:
-        logger.error("Input file (--input_file) is required.")
+        logger.error("Pathway file (--pathway-list) is required.")
         return
 
     # create a .tsv file for pathways list
     pathways_list_df = pd.DataFrame(list(pathways.items()), columns=['ID', 'PathwayName'])
-    pathways_list_df.to_csv(args.output, sep='\t', index=False)
+    pathways_list_df.to_csv(args.output_dir, sep='\t', index=False)
 
     for pathway_id, pathway_name in pathways.items():
-        generate_pathway_file(pathway_id, taxon_id, pathway_name, decompose=args.decompose)
+        generate_pathway_file(pathway_id, taxon_id, pathway_name)
 
 
 if __name__ == "__main__":

pyproject.toml

@@ -11,6 +11,7 @@ python = "^3.9"
 py2neo = "^2021.2.4"
 pandas = "^2.2.0"
 numpy = "^1.26.3"
+pyarrow = "^15.0.0"
 
 
 [tool.poetry.group.dev.dependencies]

src/argument_parser.py

@@ -6,7 +6,8 @@ def parse_args():
     parser = argparse.ArgumentParser(description='pathway_creation')
     parser.add_argument('--debug', action='store_true', help='Enable debugging')
     parser.add_argument('--verbose', action='store_true', help='Enable verbose logging')
-    parser.add_argument('--input_file', type=str, help='Input file containing pathway information')
+    parser.add_argument('--pathway-list', type=str, help='Input file containing pathway information')
+    parser.add_argument('--output-dir', type=str, default='output', help='Output folder (default: output)')
 
     return parser.parse_args()
 

src/reaction_generator.py

@@ -71,7 +71,7 @@ def break_apart_entity(entity_id):
         logger.debug(f"Debugging: break_apart_entity - labels: {labels}")
         logger.debug(f"Debugging: break_apart_entity - broken_apart_members: {broken_apart_members}")
 
-        if set(broken_apart_members) == set(member_ids):
+        if set(tuple(broken_apart_members)) == set(tuple(member_ids)):
             return [[entity_id]]
         else:
             uid = str(uuid.uuid4())
@@ -270,10 +270,12 @@ def get_reactions_df(pathway_id):
     reaction_ids = pd.unique(reaction_connections_df[['parent_reaction_id', 'child_reaction_id']].values.ravel('K'))
     reaction_ids = reaction_ids[~pd.isna(reaction_ids)]  # removing NA value from list
 
-    reaction_inputs_and_outputs_filename = 'reaction_inputs_and_outputs_df_' + pathway_id + '.tsv'
+    reaction_inputs_and_outputs_df = None
+
+    reaction_inputs_and_outputs_filename = 'reaction_inputs_and_outputs_df_' + str(pathway_id) + '.tsv'
     if os.path.isfile(reaction_inputs_and_outputs_filename):
         reaction_inputs_and_outputs_df = pd.read_table(reaction_inputs_and_outputs_filename, delimiter="\t")
-
+    else:
         reaction_inputs_and_outputs_df = get_reaction_inputs_and_outputs(reaction_ids)
         reaction_inputs_and_outputs_df.to_csv(reaction_inputs_and_outputs_filename, sep="\t")