Python Descriptors.MolWt方法代码示例

# 需要导入模块: from rdkit.Chem import Descriptors [as 别名]
# 或者: from rdkit.Chem.Descriptors import MolWt [as 别名]
def filter_smiles(sml):
    try:
        m = Chem.MolFromSmiles(sml)
        logp = Descriptors.MolLogP(m)
        mol_weight = Descriptors.MolWt(m)
        num_heavy_atoms = Descriptors.HeavyAtomCount(m)
        atom_num_list = [atom.GetAtomicNum() for atom in m.GetAtoms()]
        is_organic = set(atom_num_list) <= ORGANIC_ATOM_SET
        if ((logp > -5) & (logp < 7) & 
            (mol_weight > 12) & (mol_weight < 600) &
            (num_heavy_atoms > 3) & (num_heavy_atoms < 50) &
            is_organic ):
            return Chem.MolToSmiles(m)
        else:
            return float('nan')
    except:
        return float('nan') 

# 需要导入模块: from rdkit.Chem import Descriptors [as 别名]
# 或者: from rdkit.Chem.Descriptors import MolWt [as 别名]
def evaluate(self, lst_in):
        """
        Evaluate structure alerts on a list of SMILES
        :param lst_in: input list of [SMILES, Name]
        :return: list of alerts matched or "OK"
        """
        smiles, name = lst_in
        mol = Chem.MolFromSmiles(smiles)
        if mol is None:
            return [smiles, name, 'INVALID', -999, -999, -999, -999, -999]
        desc_list = [MolWt(mol), MolLogP(mol), NumHDonors(mol), NumHAcceptors(mol), TPSA(mol),
                     CalcNumRotatableBonds(mol)]
        for row in self.rule_list:
            patt, max_val, desc = row
            if len(mol.GetSubstructMatches(patt)) > max_val:
                return [smiles, name] + [desc + " > %d" % (max_val)] + desc_list
        return [smiles, name] + ["OK"] + desc_list 

# 需要导入模块: from rdkit.Chem import Descriptors [as 别名]
# 或者: from rdkit.Chem.Descriptors import MolWt [as 别名]
def preprocessMolecule(inp):
	def checkC(mm):
		mwt = Descriptors.MolWt(mm)
		for atom in mm.GetAtoms():
			if atom.GetAtomicNum() == 6 and 100 <= mwt <= 1000: return True
		return False
	def checkHm(mm):
		for atom in mm.GetAtoms():
			if atom.GetAtomicNum() in [2,10,13,18]: return False
			if 21 <= atom.GetAtomicNum() <= 32: return False
			if 36 <= atom.GetAtomicNum() <= 52: return False
			if atom.GetAtomicNum() >= 54: return False
		return True
	try: std_mol = standardise.run(inp)
	except standardise.StandardiseException: return None
	if not std_mol or checkHm(std_mol) == False or checkC(std_mol) == False: return None
	else: return std_mol

#preprocess exception to catch 

# 需要导入模块: from rdkit.Chem import Descriptors [as 别名]
# 或者: from rdkit.Chem.Descriptors import MolWt [as 别名]
def weight(mol):
    """
    Computes molecular weight for given molecule.
    Returns float,
    """
    return Descriptors.MolWt(mol) 

# 需要导入模块: from rdkit.Chem import Descriptors [as 别名]
# 或者: from rdkit.Chem.Descriptors import MolWt [as 别名]
def molwt(self):
        return Descriptors.MolWt(self.Mol) 

# 需要导入模块: from rdkit.Chem import Descriptors [as 别名]
# 或者: from rdkit.Chem.Descriptors import MolWt [as 别名]
def mol_weight(mol: Mol) -> float:
    return Descriptors.MolWt(mol) 

# 需要导入模块: from rdkit.Chem import Descriptors [as 别名]
# 或者: from rdkit.Chem.Descriptors import MolWt [as 别名]
def properties(mol):
    """
    Calculates the properties that are required to calculate the QED descriptor.
    """
    matches = []
    if mol is None:
        raise WrongArgument("properties(mol)", "mol argument is \'None\'")
    x = [0] * 9
    # MW
    x[0] = Descriptors.MolWt(mol)
    # ALOGP
    x[1] = Descriptors.MolLogP(mol)
    for hba in Acceptors:                                                        # HBA
        if mol.HasSubstructMatch(hba):
            matches = mol.GetSubstructMatches(hba)
            x[2] += len(matches)
    x[3] = Descriptors.NumHDonors(
        mol)                                            # HBD
    # PSA
    x[4] = Descriptors.TPSA(mol)
    x[5] = Descriptors.NumRotatableBonds(
        mol)                                    # ROTB
    x[6] = Chem.GetSSSR(Chem.DeleteSubstructs(
        deepcopy(mol), AliphaticRings))    # AROM
    for alert in StructuralAlerts:                                                # ALERTS
        if (mol.HasSubstructMatch(alert)):
            x[7] += 1
    ro5_failed = 0
    if x[3] > 5:
        ro5_failed += 1  # HBD
    if x[2] > 10:
        ro5_failed += 1  # HBA
    if x[0] >= 500:
        ro5_failed += 1
    if x[1] > 5:
        ro5_failed += 1
    x[8] = ro5_failed
    return x 

# 需要导入模块: from rdkit.Chem import Descriptors [as 别名]
# 或者: from rdkit.Chem.Descriptors import MolWt [as 别名]
def logP_mw(fnames, is_active=False):
    """ logP and molecular weight calculation for logP ~ MW chemical space visualization

    Arguments:
        fnames (list): List of file paths that contains CANONICAL_SMILES (, LOGP and MWT
            if it contains the logP and molecular weight for each molecule).
        is_active (bool, optional): selecting only active ligands (True) or all of the molecules (False)
            if it is true, the molecule with PCHEMBL_VALUE >= 6.5 or SCORE > 0.5 will be selected.
            (Default: False)

    Returns:
        df (DataFrame)： The table contains three columns;
            molecular weight, logP and index of file name in the fnames
    """
    df = pd.DataFrame()
    for i, fname in enumerate(fnames):
        print(fname)
        sub = pd.read_table(fname)
        sub['LABEL'] = i
        if 'PCHEMBL_VALUE' in sub.columns:
            sub = sub[sub.PCHEMBL_VALUE >= (6.5 if is_active else 0)]
        elif 'SCORE' in sub.columns:
            sub = sub[sub.SCORE > (0.5 if is_active else 0)]
        sub = sub.drop_duplicates(subset='CANONICAL_SMILES')
        if not ('LOGP' in sub.columns and 'MWT' in sub.columns):
            # If the the table does not contain LOGP and MWT
            # it will calculate these coefficients with RDKit.
            logp, mwt = [], []
            for i, row in sub.iterrows():
                try:
                    mol = Chem.MolFromSmiles(row.CANONICAL_SMILES)
                    x, y = desc.MolWt(mol), Crippen.MolLogP(mol)
                    logp.append(y)
                    mwt.append(x)
                except:
                    sub = sub.drop(i)
                    print(row.CANONICAL_SMILES)
            sub['LOGP'], sub['MWT'] = logp, mwt
        df = df.append(sub[['MWT', 'LOGP', 'LABEL']])
    return df 

# 需要导入模块: from rdkit.Chem import Descriptors [as 别名]
# 或者: from rdkit.Chem.Descriptors import MolWt [as 别名]
def calc_esol_descriptors(self, mol):
        """
        Calcuate mw,logp,rotors and aromatic proportion (ap)
        :param mol: input molecule
        :return: named tuple with descriptor values
        """
        mw = Descriptors.MolWt(mol)
        logp = Crippen.MolLogP(mol)
        rotors = Lipinski.NumRotatableBonds(mol)
        ap = self.calc_ap(mol)
        return self.Descriptor(mw=mw, logp=logp, rotors=rotors, ap=ap) 

# 需要导入模块: from rdkit.Chem import Descriptors [as 别名]
# 或者: from rdkit.Chem.Descriptors import MolWt [as 别名]
def PhyChem(smiles):
    """ Calculating the 19D physicochemical descriptors for each molecules,
    the value has been normalized with Gaussian distribution.

    Arguments:
        smiles (list): list of SMILES strings.
    Returns:
        props (ndarray): m X 19 matrix as nomalized PhysChem descriptors.
            m is the No. of samples
    """
    props = []
    for smile in smiles:
        mol = Chem.MolFromSmiles(smile)
        try:
            MW = desc.MolWt(mol)
            LOGP = Crippen.MolLogP(mol)
            HBA = Lipinski.NumHAcceptors(mol)
            HBD = Lipinski.NumHDonors(mol)
            rotable = Lipinski.NumRotatableBonds(mol)
            amide = AllChem.CalcNumAmideBonds(mol)
            bridge = AllChem.CalcNumBridgeheadAtoms(mol)
            heteroA = Lipinski.NumHeteroatoms(mol)
            heavy = Lipinski.HeavyAtomCount(mol)
            spiro = AllChem.CalcNumSpiroAtoms(mol)
            FCSP3 = AllChem.CalcFractionCSP3(mol)
            ring = Lipinski.RingCount(mol)
            Aliphatic = AllChem.CalcNumAliphaticRings(mol)
            aromatic = AllChem.CalcNumAromaticRings(mol)
            saturated = AllChem.CalcNumSaturatedRings(mol)
            heteroR = AllChem.CalcNumHeterocycles(mol)
            TPSA = MolSurf.TPSA(mol)
            valence = desc.NumValenceElectrons(mol)
            mr = Crippen.MolMR(mol)
            # charge = AllChem.ComputeGasteigerCharges(mol)
            prop = [MW, LOGP, HBA, HBD, rotable, amide, bridge, heteroA, heavy, spiro,
                    FCSP3, ring, Aliphatic, aromatic, saturated, heteroR, TPSA, valence, mr]
        except:
            print(smile)
            prop = [0] * 19
        props.append(prop)
    props = np.array(props)
    props = Scaler().fit_transform(props)
    return props