Update app.py

app.py

@@ -250,6 +250,42 @@ def get_data_from_smile(smile, eluent_list):
 
     return X_test
 
+def get_data_from_xlsx(file_name):
+    file = pd.read_excel(file_name)
+    smiles = file['SMILES'].values
+    PEs = file['PE'].values
+    EAs = file['EA'].values
+    DCMs = file['DCM'].values
+    MeOHs = file['MeOH'].values
+    Et2Os = file['Et2O'].values
+    X_test = np.zeros([len(smiles), 179])
+    for i in range(len(smiles)):
+        smile=smiles[i]
+        eluent_sum = PEs[i] + EAs[i] + DCMs[i] + MeOHs[i] + Et2Os[i]
+        if eluent_sum != 0:
+            eluent_list = [PEs[i] / eluent_sum, EAs[i] / eluent_sum, DCMs[i] / eluent_sum, MeOHs[i] / eluent_sum, Et2Os[i] / eluent_sum]
+        else:
+            eluent_list = [0, 0, 0, 0, 0]
+        compound_mol = Chem.MolFromSmiles(smile)
+        Finger = MACCSkeys.GenMACCSKeys(Chem.MolFromSmiles(smile))
+        fingerprint = np.array([x for x in Finger])
+        compound_finger = fingerprint
+        compound_MolWt = Descriptors.ExactMolWt(compound_mol)
+        compound_TPSA = Chem.rdMolDescriptors.CalcTPSA(compound_mol)
+        compound_nRotB = Descriptors.NumRotatableBonds(compound_mol)  # Number of rotable bonds
+        compound_HBD = Descriptors.NumHDonors(compound_mol)  # Number of H bond donors
+        compound_HBA = Descriptors.NumHAcceptors(compound_mol)  # Number of H bond acceptors
+        compound_LogP = Descriptors.MolLogP(compound_mol)  # LogP
+
+        X_test[i, 0:167] = compound_finger
+        X_test[i, 167:173] = 0
+        X_test[i, 173:179] = [compound_MolWt, compound_TPSA, compound_nRotB, compound_HBD, compound_HBA, compound_LogP]
+
+        eluent_array = get_eluent_descriptor(eluent_list)
+        eluent_array = np.array(eluent_array)
+        X_test[i, 167:173] = eluent_array
+    return X_test
+    
 def predict_single(smile,PE,EA,DCM,MeOH,Et20):
     config = parse_args()
     config.add_dipole = False
@@ -264,7 +300,14 @@ def predict_single(smile,PE,EA,DCM,MeOH,Et20):
     return Rf[0]
 
 def predict_xlsx(file):
-    return file
+    file_name=file.name
+    config = parse_args()
+    config.add_dipole = False
+    X_test = get_data_from_xlsx(file_name)
+    Model = Model_ML(config, X_test)
+    Rf = Model.get_Rf()
+    return Rf
+
 if __name__=='__main__':