MASSA-Algorithm 0.9.4__py3-none-any.whl → 0.9.6__py3-none-any.whl

MASSA_Algorithm/MASSAlogos.py

@@ -20,7 +20,7 @@ def initial_print():
        ██░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░█
      ██░░░░▓▓▓▓▓▓░░░░░▓▓▓▓▓▓░░░░░▓▓▓▓▓▓░░░░█                                 MASSA Algorithm:
    ████░░░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░░░░▓▓▓▓░░░░░█████          Molecular data set sampling  —  Training-Test Separation
-  █▓▓▓███░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░███▓▓▓█                            Version: v. 0.9.4
+  █▓▓▓███░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░███▓▓▓█                            Version: v. 0.9.6
  █▒▓▓▒▒▒████░░░░░░░░░░░░░░░░░░░░░░░░░░░░████▒▒▓▓▒█
  ██▓▒▒▒▓▓▓▓██████████████████████████████▓▓▓▒▒▒▒▓█                Developed by: Gabriel Corrêa Veríssimo
  ██▒▒▒▓▓▒▒▒▒▓▓▒▒▒▒▓▓▒▒▒▒▒▒▒▒▒▒▒▒▓▓▒▒▒▒▓▓▒▒▒▓▓▒▒██                           LICENSE: AGPL-3.0

MASSA_Algorithm/MASSAopen_files.py

@@ -1,45 +1,294 @@
+import pandas as pd
 from rdkit.Chem import AllChem
 
+
+def find_smiles_column(columns):
+    """
+    Find the name of the "SMILES" column.
+
+    Args:
+        columns (list): receives a list with the name of pandas columns.
+
+    Raises:
+        ValueError: if there is no column named "SMILES" raises an error.
+
+    Returns:
+        column_name (str): returns the name of the "SMILES" column.
+    """
+    smiles_columns = []
+    smile_column = ""
+
+    for column in columns:
+        if "smiles" == column.lower():
+            smiles_columns.append(column)
+    if len(smiles_columns) > 1:
+        """
+        Warning: If there are more than one "SMILES" (case insensitive) column
+        the first one will be chosen.
+        """
+
+        print("Warning: There is more than one"
+              " column named 'smiles' (case insensitive)."
+              " The first one was chosen.")
+        smile_column = smiles_columns[0]
+        return smile_column
+    elif len(smiles_columns) == 1:
+        smile_column = smiles_columns[0]
+        return smile_column
+    else:
+        error = "Error: There is no column named 'SMILES'"
+        raise ValueError(error)
+
+
+def find_name_column(columns):
+    """
+    Find the name of the molecule name column.
+
+    Args:
+        columns (list): receives a list with the name of pandas columns.
+
+    Returns:
+        column_name (str): returns the name of the molecule name column.
+    """
+
+    for column in columns:
+        if "molecule name" == column.lower():
+            print((f"Found '{column}' column."
+                   " Using it to name the molecules."))
+            name_column = column
+            return name_column
+        elif "name" == column.lower():
+            print((f"Found '{column}' column."
+                   " Using it to name the molecules."))
+            name_column = column
+            return name_column
+        elif "molecule chembl id" == column.lower():
+            print((f"Found '{column}' column."
+                   " Using it to name the molecules."))
+            name_column = column
+            return name_column
+        elif "id" == column.lower():
+            print((f"Found '{column}' column."
+                   " Using it to name the molecules."))
+            name_column = column
+            return name_column
+        else:
+            print(("Unable to find a column with molecule names."
+                   " Using the index to name the molecules."))
+            name_column = "index"
+            return name_column
+
+
+def read_df_smiles(df, WriteLog):
+    """Reads an dataframe and returns a sanitized molecule supplier.
+
+    Args:
+        df_supplier (pd.DataFrame): pd.DataFrame object with SMILES.
+        WriteLog (file object): Log file object to write error messages.
+
+    Returns:
+        AllChem.SDMolSupplier like: Sanitized molecule supplier.
+    """
+    columns = list(df.columns)
+
+    smi_name_column = find_smiles_column(columns)
+    name_name_column = find_name_column(columns)
+
+    # name_name_column = "index"
+    columns.remove(smi_name_column)
+    columns.remove(name_name_column)
+
+    mols = []
+    for index, row in df.iterrows():
+        try:
+            mol = AllChem.MolFromSmiles(row[smi_name_column])
+            AllChem.rdmolops.SanitizeMol(mol)
+            if name_name_column == "index":
+                mol.SetProp("_Name", str(index))
+            else:
+                mol.SetProp("_Name", str(row[name_name_column]))
+            for c in columns:
+                mol.SetProp(c, str(row[c]))
+            mols.append(mol)
+        except Exception as e:
+            mols.append(None)
+            mol_of_error = str(mol.GetProp('_Name'))
+            error = str(e)
+            precomposed = (f"[Error while reading molecule: {error}. "
+                           f"Molecule name: {mol_of_error}].")
+            composed = precomposed+'\n'
+            print(precomposed)
+            WriteLog.write(composed)
+    if None in mols:
+        print("ERROR: Error while reading molecules. "
+              "Check the log.txt file for more information."
+              "\nERROR: Closing...")
+        exit()
+    return mols
+
+
+def read_EXCEL_smiles(file, WriteLog):
+    df_supplier = pd.read_excel(file)
+    mols_sanitized = read_df_smiles(df_supplier, WriteLog)
+    return mols_sanitized
+
+
+def read_CSV_smiles(file, WriteLog):
+    df_supplier = pd.read_csv(file, sep=",")
+    mols_sanitized = read_df_smiles(df_supplier, WriteLog)
+    return mols_sanitized
+
+
+def read_SDF(file, WriteLog):
+    """Reads an SDF file and returns a sanitized molecule supplier.
+
+    Args:
+        file (str): Path to the SDF file.
+        WriteLog (file object): Log file object to write error messages.
+
+    Returns:
+        AllChem.SDMolSupplier: Sanitized molecule supplier.
+    """
+    # Open the input file.
+    mols_supplier = AllChem.SDMolSupplier(file, sanitize=False)
+    mols = []
+    for mol in mols_supplier:
+        try:
+            mols.append(AllChem.rdmolops.SanitizeMol(mol))
+        except Exception as e:
+            mols.append(None)
+            mol_of_error = str(mol.GetProp('_Name'))
+            error = str(e)
+            precomposed = (f"[Error while reading molecule: {error}. "
+                           f"Molecule name: {mol_of_error}].")
+            composed = precomposed+'\n'
+            print(precomposed)
+            WriteLog.write(composed)
+    if None in mols:
+        print("ERROR: Error while reading molecules. "
+              "Check the log.txt file for more information."
+              "\nERROR: Closing...")
+        exit()
+    mols_sanitized = AllChem.SDMolSupplier(file, sanitize=True)
+    return mols_sanitized
+
+
+def remove_comment_line(data):
+    # Remove lines starting with '#'
+    return '\n'.join(
+        line for line in data.splitlines() if not line.strip().startswith('#')
+        )
+
+
+def mol2_properties(data):
+    data_split = data.split("@")
+    properties = {}
+    for d in data_split:
+        if "MOL_PROPERTY" in d:
+            list_values = d.split("\n")
+            p_name = list_values[1]
+            p_value = list_values[3]
+            properties[p_name] = p_value
+    return properties
+
+
+def read_MOL2(file, WriteLog):
+    """Reads an MOL2 file from Discovery Studio
+       and returns a sanitized molecule supplier.
+
+    Args:
+        file (str): Path to the MOL2 file.
+        WriteLog (file object): Log file object to write error messages.
+
+    Returns:
+        AllChem.SDMolSupplier like: Sanitized molecule supplier.
+    """
+    with open(file, 'r') as f:
+        mol_data = f.read()
+    # Split the file contents on the delimiter
+    # Remove comment lines
+    mol_data = remove_comment_line(mol_data)
+
+    # Alert of MOL2 limitations.
+    print("""
+ATTENTION: .mol2 file detected.
+MOL2 files have limited support for storing molecular properties.
+Therefore, the biological properties in this file may not be \
+detected or even stored.
+We do not recommend using a .mol2 file.
+However, we provide support for .mol2 files generated by \
+Discovery Studio Visualizer.
+The biological properties in these files follow the format below:
+
+@<SCITEGIC>MOL_PROPERTY
+Name_of_property (e.g., pIC50 value)
+Type_of_property (e.g., SciTegic.value.DoubleValue)
+Value_of_the_property (e.g., 8.100000)
+          """)
+
+    # Split the file contents based on a delimiter for each molecule.
+    mol_blocks = mol_data.split("@<TRIPOS>MOLECULE")
+
+    # List to store molecules.
+    mols = []
+
+    # Iterate over each block and reassemble the molecule data
+    for mol_block in mol_blocks:
+        if mol_block.strip():  # To avoid empty blocks
+            mol_block = "@<TRIPOS>MOLECULE" + mol_block
+            properties = mol2_properties(mol_block)
+            mol = AllChem.MolFromMol2Block(mol_block)
+            try:
+                AllChem.rdmolops.SanitizeMol(mol)
+                for p, p_value in properties.items():
+                    mol.SetProp(p, str(p_value))
+                mols.append(mol)
+            except Exception as e:
+                mols.append(None)
+                mol_of_error = str(mol.GetProp('_Name'))
+                error = str(e)
+                precomposed = (f"[Error while reading molecule: {error}. "
+                               f"Molecule name: {mol_of_error}].")
+                composed = precomposed+'\n'
+                print(precomposed)
+                WriteLog.write(composed)
+    if None in mols:
+        print("ERROR: Error while reading molecules. "
+              "Check the log.txt file for more information."
+              "\nERROR: Closing...")
+        exit()
+    return mols
+
+
 def read_molecules(file, WriteLog):
-	mols_supplier = AllChem.SDMolSupplier(file, sanitize=False) # Open the input file.
-	mols = []
-	for mol in mols_supplier:
-		try:
-			mols.append(AllChem.rdmolops.SanitizeMol(mol))
-		except Exception as e:
-			mols.append(None)
-			mol_of_error = str(mol.GetProp('_Name'))
-			error = str(e)
-			precomposed = '[Error while reading molecule: \"' + error +  '\". Molecule name: \"' +  mol_of_error + '\".]'
-			composed = precomposed+'\n'
-			print(precomposed)
-			WriteLog.write(composed)
-	if None in mols:
-		print('ERROR: Error while reading molecules. Check the log.txt file for more information. \nERROR: Closing...') # Print an error.
-		exit()
-	mols_supplier_sanitized = AllChem.SDMolSupplier(file, sanitize=True)
-	return mols_supplier_sanitized
-
-def error_check(file):
-	for i in file:
-		if i == None: # If any molecule is not able to be read: 
-			print('ERROR: Unable to read a molecule') # Print an error.
-			exit()
-		else:
-			pass
+    if file.endswith(".mol2"):
+        molecules = read_MOL2(file, WriteLog)
+    elif file.endswith(".sdf") or file.endswith(".mol"):
+        molecules = read_SDF(file, WriteLog)
+    elif file.endswith(".xlsx") or file.endswith(".xls"):
+        molecules = read_EXCEL_smiles(file, WriteLog)
+    elif file.endswith(".csv"):
+        molecules = read_CSV_smiles(file, WriteLog)
+    return molecules
+
 
 def hydrogen_add(file):
-	molsH = []
-	for i in file:
-		molsH.append(AllChem.AddHs(i, addCoords = True)) # Add hydrogens keeping 3D coordenates.
-	return molsH
-
-def get_sdf_property_names(file): # Extracting the property names from the ".sdf" input file.
-	sdf_property_names = []
-	for i in file:
-		for a in list(i.GetPropNames()):
-			sdf_property_names.append(a)
-	sdf_property_names = list(set(sdf_property_names))
-	if 'Name' in sdf_property_names: # Drop the molecule name from the property list.
-		sdf_property_names.remove('Name')
-	return sdf_property_names
+    molsH = []
+    for i in file:
+        i = AllChem.AddHs(i, addCoords=True)
+        molsH.append(i)
+        # Add hydrogens keeping 3D coordenates.
+    return molsH
+
+
+def get_sdf_property_names(file):
+    # Extracting the property names from the ".sdf" input file.
+    sdf_property_names = []
+    for i in file:
+        for a in list(i.GetPropNames()):
+            sdf_property_names.append(a)
+    sdf_property_names = list(set(sdf_property_names))
+    if 'Name' in sdf_property_names:
+        # Drop the molecule name from the property list.
+        sdf_property_names.remove('Name')
+    return sdf_property_names

{MASSA_Algorithm-0.9.4.dist-info → MASSA_Algorithm-0.9.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: MASSA-Algorithm
-Version: 0.9.4
+Version: 0.9.6
 Summary: MASSA Algorithm is a Python package to separate data sets of molecules into training and test sets, considering the diversity of structural, physicochemical and biological characteristics of these molecules.
 Home-page: https://github.com/gcverissimo/MASSA_Algorithm
 Author: Gabriel Corrêa Veríssimo
@@ -18,13 +18,13 @@ Classifier: Topic :: Scientific/Engineering :: Chemistry
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy (<2.0)
+Requires-Dist: numpy<2.0
 Requires-Dist: rdkit
 Requires-Dist: pandas
-Requires-Dist: matplotlib (>=3.2)
-Requires-Dist: scipy (>=1.6)
-Requires-Dist: scikit-learn (>0.24)
-Requires-Dist: kmodes (>=0.10)
+Requires-Dist: matplotlib>=3.2
+Requires-Dist: scipy>=1.6
+Requires-Dist: scikit-learn>0.24
+Requires-Dist: kmodes>=0.10
 
 # MASSA Algorithm
 MASSA Algorithm: A tool for separating data sets of molecules into training and test sets. Developed with the objective of preparing data sets for the generation of prediction models in cheminformatics.
@@ -60,7 +60,18 @@ Once installed, the program can be run directly from the command line:
 MASSA_Algorithm -i <input_file>.sdf -o <output_file>.sdf
 ```
 
-A list of optional arguments include:
+Required arguments:
+* **Input file**: ```-i``` or ```--input```.
+    * MASSA Algorithm accepts input files in the formats: .sdf, .mol, .mol2, .xlsx, .xls, and .csv. However, the .sdf format is preferred. Notes:
+        * .mol2 files have limitations in storing molecular properties and follow different saving patterns. Due to this, we only support .mol2 files that are generated by Discovery Studio Visualizer.
+        * For .xlsx, .xls, and .csv:
+            * MASSA will look for a column with smiles in the name and use it as the source of input molecules.
+            * MASSA will look for a column with one of the following names in the priority order: Molecule name, Name, Molecule ChEMBL ID, or ID. If none of these columns are found, it will use the molecule index.
+* **Output file**: ```-o``` or ```--output```.
+    * Enter the output file name or file path. Image files will be saved to a folder within the same directory as the output file.
+    * It is highly recommended to use an .sdf file to avoid errors.
+
+Optional arguments include:
 * **Percentage of molecules in training set**: ```-p``` or ```--percentage_of_training```.
     * Percentage of molecules in training set. Must be a number from 0 to 1.
     * Default = 0.8.
@@ -68,11 +79,11 @@ A list of optional arguments include:
     * Number of biological activities that will be used to separate the set into training and test.
     * Default = 1.
 * **Name of biological activities for separation**: ```-s``` or ```--the_biological_activities```.
-    * Enter a list with the names of biological activities separated by commas and no spaces.
+    * The biological activity(ies) or other y-property(ies) used for QSAR or machine learning modeling. The algorithm can handle one or more properties. Enter a list with the names of biological activities separated by commas and no spaces. These properties must be represented as either integers or floating-point numbers. If your dataset is represented in classes (e.g., active or inactive; soluble, partially soluble, or insoluble), you should represent them as integers (e.g., 0 or 1; 1, 2, or 3).
     * Example: ```MASSA_Algorithm -i <input_file>.sdf -o <output_file>.sdf -s pIC50,pMIC```.
     * Default = If not entered directly on the command line, it will be requested during algorithm execution.
 * **Number of principal components in PCA**: ```-n``` or ```--number_of_PCs```.
-    * Defines the number of principal components to reduce the dimensionality of variables related to biological, physicochemical and structural domains. If the value is a decimal between 0 and 1, the number of principal components is what justifies for (```<input number>```* 100)% of the variance. If the value is greater than 1, the number of PCs will be exactly the input integer, but PAY ATTENTION:
+    * Defines the number of principal components to reduce the dimensionality of variables related to biological, physicochemical and structural domains. If the value is a decimal between 0 and 1, the number of principal components is what explains for (```<input number>```* 100)% of the variance. If the value is greater than 1, the number of PCs will be exactly the input integer, but PAY ATTENTION:
 
         1) If the number of PCs is an integer and equal to or greater than the number of physicochemical properties (7), the PCA step will be bypassed for this domain.
         2) The same for the biological domain.

{MASSA_Algorithm-0.9.4.dist-info → MASSA_Algorithm-0.9.6.dist-info}/RECORD

@@ -3,16 +3,16 @@ MASSA_Algorithm/MASSAargs.py,sha256=MCOBlRm6sx6TUQHLwJrW-ktdSNiQltyFjyfJbS-1dVc,
 MASSA_Algorithm/MASSAcluster.py,sha256=orRK3rqEpH4j-C4LiS2rp3z4f1gM_rvsjgqiljvtlUI,11293
 MASSA_Algorithm/MASSAdescriptors.py,sha256=3wd4MXfqTJU6w-sUolEhsCKIOCS2ye1tSkXvOXwFn2c,2716
 MASSA_Algorithm/MASSAextraction.py,sha256=bADEWtpEE5P0hg9O-8piD659GrPfHUeqyyaAYCWlsAs,4976
-MASSA_Algorithm/MASSAlogos.py,sha256=gu5suAiFlp1Dfn-Zcvl80oDEq4sVsdXSjfrduXvZ_mU,3528
+MASSA_Algorithm/MASSAlogos.py,sha256=xl1EI77Y4eU-QUWjAgZlRaFTHY-ufAUSaIc9oXaYyXM,3528
 MASSA_Algorithm/MASSAmoloutput.py,sha256=LsyeCvIc9SPiFjVXTOQ3GVXDzhB9sc-MYWGGvIbOcwQ,2512
 MASSA_Algorithm/MASSAod.py,sha256=y0tizbYYtw34iJEf8c_5XPfQHHxF9RSRGjbmSZ0qRWk,487
-MASSA_Algorithm/MASSAopen_files.py,sha256=aPYCBNSmSPasL1wyuYvM7Nd1mTyGG9GMcyDdOAYQ3GE,1600
+MASSA_Algorithm/MASSAopen_files.py,sha256=U6koZg-IBVRUasl1Htl6S3CjZcOmJ-lKx-Ud-LXz4ws,9928
 MASSA_Algorithm/MASSApreparation.py,sha256=I4JpddMfBX1btYomNI5vflN1gyllJKodbQgtYf9imWY,3208
 MASSA_Algorithm/MASSAsplit.py,sha256=qsZgvXAat4UleaF0Qaa4Y-CtsMQU_NaIJvK-ypOzkbw,5330
 MASSA_Algorithm/__init__.py,sha256=yY3Tbs-t4HSl4I0Ev0RcHMnHU7SwljlWRveiRJkeCB8,10
-MASSA_Algorithm-0.9.4.dist-info/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
-MASSA_Algorithm-0.9.4.dist-info/METADATA,sha256=_bGdINXx2Z0BpgKn7uo8W49wvnWfDfwZLGQtL1huBpc,6552
-MASSA_Algorithm-0.9.4.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-MASSA_Algorithm-0.9.4.dist-info/entry_points.txt,sha256=oMtqswy07Di-w2uIYAEvenBKl0ovsr9AYm_yxn6LGtU,63
-MASSA_Algorithm-0.9.4.dist-info/top_level.txt,sha256=IZyttJ20RSD8w9nAcaTHWAvkvxHV5FGaVGB7mDrw9Cc,16
-MASSA_Algorithm-0.9.4.dist-info/RECORD,,
+MASSA_Algorithm-0.9.6.dist-info/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
+MASSA_Algorithm-0.9.6.dist-info/METADATA,sha256=pGGMRnNlvEcZg3JzCoz027iZ7PBOwqEQsKAymKsErho,7967
+MASSA_Algorithm-0.9.6.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+MASSA_Algorithm-0.9.6.dist-info/entry_points.txt,sha256=oMtqswy07Di-w2uIYAEvenBKl0ovsr9AYm_yxn6LGtU,63
+MASSA_Algorithm-0.9.6.dist-info/top_level.txt,sha256=IZyttJ20RSD8w9nAcaTHWAvkvxHV5FGaVGB7mDrw9Cc,16
+MASSA_Algorithm-0.9.6.dist-info/RECORD,,

{MASSA_Algorithm-0.9.4.dist-info → MASSA_Algorithm-0.9.6.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.38.4)
+Generator: setuptools (75.6.0)
 Root-Is-Purelib: true
 Tag: py3-none-any