MASSA-Algorithm 2.2.0__py3-none-any.whl → 2.2.2__py3-none-any.whl

MASSA_Algorithm/MASSAextraction.py

@@ -27,8 +27,8 @@ def name_extraction(file):
             else:
                 duplicates[name] = [[idx, mol]]
 
-        final_names = []
         final_names_dict = {}
+        idx_names = {}
         for k, v in duplicates.items():
             name = k
             replicates = v
@@ -39,7 +39,7 @@ def name_extraction(file):
                     final_key = f"{name}_idx-_{index}"
                     molecule.SetProp("_Name", final_key)
                     final_names_dict[final_key] = molecule
-                    final_names.append(final_key)
+                    idx_names[index] = final_key
             else:
                 for r in replicates:
                     index = r[0]
@@ -47,8 +47,15 @@ def name_extraction(file):
                     final_key = name
                     molecule.SetProp("_Name", final_key)
                     final_names_dict[final_key] = molecule
-                    final_names.append(final_key)
-        dataframe = pd.DataFrame({'molecules': pd.Series(final_names_dict)})
+                    idx_names[index] = final_key
+        f_names = [None] * (max(idx_names) + 1)
+        for i_idx, i_name in idx_names.items():
+            f_names[i_idx] = i_name
+        final_names = f_names
+        dataframe = pd.DataFrame(
+            {'molecules': [final_names_dict[name] for name in final_names]},
+            index=final_names
+            )
     return final_names, dataframe
 
 

MASSA_Algorithm/MASSAlogos.py

@@ -20,7 +20,7 @@ def initial_print():
        ██░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░█
      ██░░░░▓▓▓▓▓▓░░░░░▓▓▓▓▓▓░░░░░▓▓▓▓▓▓░░░░█                                 MASSA Algorithm:
    ████░░░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░░█████          Molecular data set sampling  —  Training-Test Separation
-  █▓▓▓███░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░███▓▓▓█                            Version: v. 2.2.0
+  █▓▓▓███░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░███▓▓▓█                            Version: v. 2.2.2
  █▒▓▓▒▒▒████░░░░░░░░░░░░░░░░░░░░░░░░░░░░████▒▒▓▓▒█
  ██▓▒▒▒▓▓▓▓██████████████████████████████▓▓▓▒▒▒▒▓█                Developed by: Gabriel Corrêa Veríssimo
  ██▒▒▒▓▓▒▒▒▒▓▓▒▒▒▒▓▓▒▒▒▒▒▒▒▒▒▒▒▒▓▓▒▒▒▒▓▓▒▒▒▓▓▒▒██                           LICENSE: AGPL-3.0

MASSA_Algorithm/MASSAopen_files.py

@@ -143,6 +143,30 @@ def read_CSV_smiles(file, write_log, drop_errors):
     return mols_sanitized
 
 
+def read_SMI_smiles(file, write_log, drop_errors):
+    # Not designed for MASSA execution. 
+    # It will not read the "Activity" column if the .smi file doesn't have headers.
+    first_row = pd.read_csv(file, sep="\t", nrows=1, header=None)
+    first_value = str(first_row.iloc[0, 0])
+    has_header = AllChem.MolFromSmiles(first_value) is None
+
+    if has_header:
+        df = pd.read_csv(file, sep="\t", header=0)
+    else:
+        df = pd.read_csv(file, sep="\t", header=None)
+        df = df.iloc[:, :2] # Keep only the first two columns
+        df.columns = ["SMILES", "Name"]
+
+    mols_sanitized = read_df_smiles(df, write_log, drop_errors)
+    return mols_sanitized
+
+def read_SMI_smiles(file, write_log, drop_errors):
+    df_supplier = pd.read_csv(file, sep="\t", header=None)
+    df_supplier.columns = ["SMILES", "Name"]
+    mols_sanitized = read_df_smiles(df_supplier, write_log, drop_errors)
+    return mols_sanitized
+
+
 def read_SDF(file, write_log, drop_errors):
     """Reads an SDF file and returns a sanitized molecule supplier.
 
@@ -283,6 +307,8 @@ def read_molecules(file, write_log, drop_errors):
         molecules = read_EXCEL_smiles(file, write_log, drop_errors)
     elif file.endswith(".csv"):
         molecules = read_CSV_smiles(file, write_log, drop_errors)
+    elif file.endswith(".smi"):
+        molecules = read_SMI_smiles(file, write_log, drop_errors)
     return molecules