SA score added

molgenevalmetric.py

@@ -27,6 +27,7 @@ from collections import UserList, defaultdict
 import numpy as np
 import pandas as pd
 from rdkit import rdBase
+from rdkit.Contrib.SA_Score import sascorer
 import sys
 
 from rdkit.Chem import RDConfig
@@ -213,6 +214,45 @@ def synthetic_complexity_score(gen):
     return average_score
 
 
+def calculate_sa_score(smiles):
+    """
+    Calculates the SA score for a single SMILES string.
+    
+    Parameters:
+    - smiles (str): SMILES string of the molecule.
+    
+    Returns:
+    - float: SA score of the molecule, or None if the molecule couldn't be created.
+    """
+    mol = Chem.MolFromSmiles(smiles)
+    if mol:
+        return sascorer.calculateScore(mol)
+    else:
+        return None
+
+def average_sascore(gen, n_jobs=1):
+    """
+    Computes the average synthetic accessibility score for a list of molecules
+    using parallel or sequential execution based on the n_jobs parameter.
+
+    Parameters:
+    - molecules (List[str]): List of generated SMILES strings.
+    - n_jobs (int): Number of parallel jobs to use for computation.
+
+    Returns:
+    - float: Average SA score, or None if no scores could be computed.
+    """
+
+    scores = mapper(n_jobs)(calculate_sa_score, molecules)
+    
+    # Filter out None values which indicate failed molecule creation
+    valid_scores = [score for score in scores if score is not None]
+    
+    if valid_scores:
+        return sum(valid_scores) / len(valid_scores)
+    else:
+        return None
+
 def average_agg_tanimoto(stock_vecs, gen_vecs,
                          batch_size=5000, agg='max',
                          device='cpu', p=1):
@@ -522,12 +562,12 @@ class molgenevalmetric(evaluate.Metric):
         metrics['valid'] = fraction_valid(gen=gensmi)
         metrics['unique'] = fraction_unique(gen=gensmi)
         metrics['IntDiv'] = internal_diversity(gen=gensmi)
-        metrics['FCD'] = fcd_metric(gen = gensmi, train = trainsmi)
+        # metrics['FCD'] = fcd_metric(gen = gensmi, train = trainsmi)
         # metrics['Oracles'] = oracles(gen = gensmi, train = trainsmi)
 
         print('computing')
 
-        # metrics['SA'] = SAscore(gen=gensmi)
+        metrics['SA'] = average_sascore(gen=gensmi)
         metrics['SCS'] = synthetic_complexity_score(gen=gensmi)
 
         return metrics