Update app.py

app.py

@@ -316,11 +316,11 @@ def heavy_atom(mol):
 
 
 def rotatable_bond(mol):
-    return CalcNumRotatableBonds((mol))
+    return CalcNumRotatableBonds(mol)
 
 
 def tpsa(mol):
-    return CalcTPSA((mol))
+    return CalcTPSA(mol)
 
 
 def lipinski(mol):
@@ -579,7 +579,7 @@ def ts_to_str(ts, timezone_str):
     dt = datetime.fromtimestamp(ts)
     dt = dt.replace(tzinfo=pytz.utc)  # Set the datetime object to UTC
     localized_dt = dt.astimezone(local_tz)  # Convert the datetime object to the desired timezone
-    return localized_dt.strftime('%Y-%m-%d %H:%M:%S (%Z%z)')
+    return localized_dt.strftime('%Y-%m-%d %H:%M:%S (%Z)')
 
 
 def lookup_job(job_id):
@@ -1263,7 +1263,7 @@ with gr.Blocks(theme=theme, title='DeepSEQreen', css=CSS, delete_cache=(3600, 48
                 target_gene = gr.Textbox(
                     show_label=False, visible=False,
                     interactive=True, scale=4,
-                    info='Enter a gene symbol and query. The first record is used by default.')
+                    info='Enter a gene symbol and query. The first record will be used.')
                 target_organism = gr.Textbox(
                     info='Organism scientific name (default: Homo sapiens).',
                     placeholder='Homo sapiens', show_label=False,
@@ -1715,13 +1715,23 @@ with gr.Blocks(theme=theme, title='DeepSEQreen', css=CSS, delete_cache=(3600, 48
             aligner = PairwiseAligner(scoring='blastp', mode='local')
             alignment_df = pd.read_csv('data/target_libraries/ChEMBL33_all_spe_single_prot_info.csv')
 
+            processed_fasta = process_target_fasta(fasta)
+
+            # Check for an exact match first
+            exact_match = alignment_df[alignment_df['X2'] == processed_fasta]
+            if not exact_match.empty:
+                row = exact_match.iloc[0]
+                return gr.Dropdown(value=row['protein_family'],
+                                   info=f"Reason: Exact match found with {row['ID2']} from family {row['protein_family']}")
+
+            # If no exact match, then calculate alignment score
             def align_score(query):
-                return aligner.align(process_target_fasta(fasta), query).score
+                return aligner.align(processed_fasta, query).score
 
             alignment_df['score'] = alignment_df['X2'].swifter.progress_bar(
                 desc="Detecting protein family of the target...").apply(align_score)
             row = alignment_df.loc[alignment_df['score'].idxmax()]
-            return gr.Dropdown(value=row['protein_family'].capitalize(),
+            return gr.Dropdown(value=row['protein_family'],
                                info=f"Reason: Best BLASTP score ({row['score']}) "
                                     f"with {row['ID2']} from family {row['protein_family']}")
         except Exception as e: