SYBA added

README.md

@@ -1,6 +1,6 @@
 ---
 title: Molgenevalmetric
-emoji: 😻
+emoji: 
 colorFrom: pink
 colorTo: indigo
 sdk: gradio

app.py

@@ -1,16 +1,22 @@
 import pandas as pd
 df = pd.read_csv('/Users/saicharan/chembl_10000.csv')
+from molgenevalmetric import SYBAscore
 
 import evaluate
-molgenevalmetric = evaluate.load("saicharan2804/molgenevalmetric")
+met = evaluate.load("saicharan2804/molgenevalmetric")
 
 ls= df['SMILES'].tolist()
-ls_gen = ls[0:5000]
-ls_train = ls[5000:10000]
+ls_gen = ls[0:500]
+ls_train = ls[500:1000]
 
 print('computing')
+print(SYBAscore(gen=ls_gen))
+# print(met.compute(gensmi = ls_gen, trainsmi = ls_train))
+# print(qed_metric(gen=ls_gen))
+# print(logP_metric(gen=ls_gen))
+# print(average_sascore(gen=ls_gen))
 
-print(molgenevalmetric.compute(gensmi = ls_gen, trainsmi = ls_train))
+# print(oracles(gen=ls_gen, train=ls_train))
 
 # import evaluate
 # from evaluate.utils import launch_gradio_widget

molgenevalmetric.py

@@ -1,12 +1,9 @@
 
 import evaluate
 import datasets
-# import moses
-# from moses import metrics
 import pandas as pd
 from tdc import Evaluator
 from tdc import Oracle
-# from metrics import novelty, fraction_valid, fraction_unique, SAscore, internal_diversity,fcd_metric, SYBAscore, oracles
 from rdkit.Chem.QED import qed
 from rdkit.Chem.Crippen import MolLogP
 import os
@@ -30,16 +27,11 @@ import pandas as pd
 from rdkit import rdBase
 from rdkit.Contrib.SA_Score import sascorer
 import sys
-
 from rdkit.Chem import RDConfig
 import os
-# sys.path.append(os.path.join(RDConfig.RDContribDir, 'SA_Score'))
-# import sascorer
 import pandas as pd
 from fcd_torch import FCD
-# from syba.syba import SybaClassifier
-
-# from SCScore import SCScorer
+from syba.syba import SybaClassifier
 
 from myscscore.SCScore import SCScorer
 import warnings
@@ -401,32 +393,32 @@ def fcd_metric(gen, train, n_jobs = 1, device = None):
     fcd = FCD(device=device, n_jobs= n_jobs)
     return fcd(gen, train)
 
-# def SYBAscore(gen):
-#     """
-#     Compute the average SYBA score for a list of SMILES strings.
-
-#     Parameters:
-#     - smiles_list (list of str): A list of SMILES strings representing molecules.
-
-#     Returns:
-#     - float: The average SYBA score for the list of molecules.
-#     """
-#     syba = SybaClassifier()
-#     syba.fitDefaultScore()
-#     scores = []
-
-#     for smiles in gen:
-#         try:
-#             score = syba.predict(smi=smiles)
-#             scores.append(score)
-#         except Exception as e:
-#             print(f"Error processing SMILES '{smiles}': {e}")
-#             continue
-
-#     if scores:
-#         return sum(scores) / len(scores)
-#     else:
-#         return None  # Or handle empty list or all failed predictions as needed
+def SYBAscore(gen):
+    """
+    Compute the average SYBA score for a list of SMILES strings.
+
+    Parameters:
+    - smiles_list (list of str): A list of SMILES strings representing molecules.
+
+    Returns:
+    - float: The average SYBA score for the list of molecules.
+    """
+    syba = SybaClassifier()
+    syba.fitDefaultScore()
+    scores = []
+
+    for smiles in gen:
+        try:
+            score = syba.predict(smi=smiles)
+            scores.append(score)
+        except Exception as e:
+            print(f"Error processing SMILES '{smiles}': {e}")
+            continue
+
+    if scores:
+        return sum(scores) / len(scores)
+    else:
+        return None  # Or handle empty list or all failed predictions as needed
 
 def qed_metric(gen):
     """
@@ -604,11 +596,9 @@ class molgenevalmetric(evaluate.Metric):
         metrics['Oracles'] = oracles(gen = gensmi, train = trainsmi)
         metrics['QED'] = qed_metric(gen=gensmi)
         metrics['LogP'] = logP_metric(gen=gensmi)
-
-        # print('computing')
-
         metrics['SA'] = average_sascore(gen=gensmi)
         metrics['SCS'] = synthetic_complexity_score(gen=gensmi)
+        metrics['SYBA'] = SYBAscore(gen=gensmi)
 
         return metrics
 

requirements.txt

@@ -1,9 +1,11 @@
 git+https://github.com/huggingface/evaluate@main
 git+https://github.com/saicharan2804/myscscore
+git+https://github.com/saicharan2804/mysybascore
 numpy
 pandas
 scipy
 torch
 rdkit
 pyarrow
-fcd-torch
+fcd-torch
+PyTDC