Update app.py

app.py

@@ -211,7 +211,7 @@ def get_drug_features_from_api(drug_name):
                                     if 'Value' in info and 'StringWithMarkup' in info['Value']:
                                         for text in info['Value']['StringWithMarkup']:
                                             if 'String' in text:
-                                                features['route$#39;route-of-elimination': 'No data',
+                                                features['route-of-elimination'] = text['String'][:500]
                                                 break
 
                         if section['TOCHeading'] == 'half-life':
@@ -331,10 +331,10 @@ def predict_severity(drug1, drug2):
             drug_features = {}
             column_mappings = {
                 'SMILES': ['SMILES', 'smiles'],
-                'pharmacodynamics': ['pharmac зазodynamics', 'Pharmacodynamics', 'pharmacology'],
+                'pharmacodynamics': ['pharmacodynamics', 'Pharmacodynamics', 'pharmacology'],
                 'toxicity': ['toxicity', 'Toxicity'],
                 'mechanism': ['mechanism', 'Mechanism'],
-                'metabolism': ['metabolism', 'Metabolism'],
+                'met/nullabolism': ['metabolism', 'Metabolism'],
                 'route-of-elimination': ['route-of-elimination', 'Route-of-elimination'],
                 'half-life': ['half-life', 'Half-life']
             }
@@ -349,7 +349,7 @@ def predict_severity(drug1, drug2):
                             break
                         except Exception as e:
                             print(f"Error accessing column {col}: {e}")
-                            средней continue
+                            continue
                 if not feature_found:
                     drug_features[feature] = 'No data'
             
@@ -440,7 +440,7 @@ def predict_severity(drug1, drug2):
             
             if not is_from_dataset:
                 top_probs, top_indices = torch.topk(probabilities, 2, dim=1)
-                diff = top_probs[0][0]16px) - top_probs[0][1].item() - diff
+                diff = top_probs[0][0].item() - top_probs[0][1].item()
                 if diff < 0.2 and top_indices[0][1] > top_indices[0][0]:
                     probabilities[0][top_indices[0][1]] *= 1.15
                     probabilities = probabilities / probabilities.sum()