Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Updated kappa according to RDKit and removed non-functional descriptor #1

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Updated kappa according to RDKit and removed non-functional descriptor #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0a94942
Updated kappa descriptors file according to recent RDKit
NeerajPise May 12, 2020
c2d8af8
Removed a non-functional descriptor from list
NeerajPise May 12, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 17 additions & 5 deletions smdt/descriptors/kappa.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,23 @@

from rdkit import Chem
from rdkit.Chem import rdchem
from rdkit.Chem import pyPeriodicTable as PeriodicTable
periodicTable = rdchem.GetPeriodicTable()
#from rdkit.Chem import pyPeriodicTable as PeriodicTable
periodicTable = Chem.GetPeriodicTable()
import pandas as pd


hallKierAlphas = {'Br': [None, None, 0.48],
'C': [-0.22, -0.13, 0.0],
'Cl': [None, None, 0.29],
'F': [None, None, -0.07],
'H': [0.0, 0.0, 0.0],
'I': [None, None, 0.73],
'N': [-0.29, -0.2, -0.04],
'O': [None, -0.2, -0.04],
'P': [None, 0.3, 0.43],
'S': [None, 0.22, 0.35]}


def CalculateKappa1(mol):
"""
Calculation of molecular shape index for one bonded fragment
Expand Down Expand Up @@ -59,12 +71,12 @@ def _HallKierAlpha(mol):
Calculation of the Hall-Kier alpha value for a molecule
"""
alphaSum = 0.0
rC = PeriodicTable.nameTable['C'][5]
rC = periodicTable.GetRb0(6)
for atom in mol.GetAtoms():
atNum = atom.GetAtomicNum()
if not atNum: continue
symb = atom.GetSymbol()
alphaV = PeriodicTable.hallKierAlphas.get(symb, None)
alphaV = hallKierAlphas.get(symb, None)
if alphaV is not None:
hyb = atom.GetHybridization() - 2
if hyb < len(alphaV):
Expand All @@ -74,7 +86,7 @@ def _HallKierAlpha(mol):
else:
alpha = alphaV[-1]
else:
rA = PeriodicTable.nameTable[symb][5]
rA = periodicTable.GetRb0(atNum)
alpha = rA / rC - 1
alphaSum += alpha
return alphaSum
Expand Down
18 changes: 13 additions & 5 deletions smdt/molecular_descriptors.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,7 +112,7 @@
'PEOEVSA10', 'PEOEVSA11', 'PEOEVSA12', 'PEOEVSA13', 'EstateVSA0', 'EstateVSA1', 'EstateVSA2',
'EstateVSA3', 'EstateVSA4', 'EstateVSA5', 'EstateVSA6', 'EstateVSA7', 'EstateVSA8', 'EstateVSA9',
'EstateVSA10', 'VSAEstate0', 'VSAEstate1', 'VSAEstate2', 'VSAEstate3', 'VSAEstate4', 'VSAEstate5',
'VSAEstate6', 'VSAEstate7', 'VSAEstate8', 'VSAEstate9', 'VSAEstate10']
'VSAEstate6', 'VSAEstate7', 'VSAEstate8', 'VSAEstate9']

_moran = ['MATSm1', 'MATSm2', 'MATSm3', 'MATSm4', 'MATSm5', 'MATSm6', 'MATSm7', 'MATSm8', 'MATSv1',
'MATSv2', 'MATSv3', 'MATSv4', 'MATSv5', 'MATSv6', 'MATSv7', 'MATSv8', 'MATSe1', 'MATSe2',
Expand Down Expand Up @@ -162,6 +162,7 @@ def getAllDescriptorsforMol(mol):
'geary': _geary, 'kappa': _kappa, 'moe': _moe, 'moran': _moran, 'moreaubroto': _moreaubroto}



def getDescriptors(data, descriptor_type = 'topology'):
smiles, target = utils.descriptor_target_split(data)
cols = descriptor_list[descriptor_type]
Expand All @@ -180,11 +181,18 @@ def getAllDescriptors(data):
smiles, target = utils.descriptor_target_split(data)
cols = _topology + _constitutional + _bcut + _basak + _cats2d + _charge + _connectivity + _estate + _geary + _kappa + _moe + _moran + _moreaubroto
AllDescriptors = pd.DataFrame(columns=cols)
ignore = ['Ta', 'Nb', 'Os', 'Y', 'Ir', 'Re', 'Ba', 'Ac', 'Ti', 'U','V','Hf', 'La', 'Nd', 'Eu', 'Dy', 'Ce', 'Sm', 'Pd', 'Zr', 'Ru', 'W', 'Rh', 'Er', 'Th']
print('\nCalculating Molecular Descriptors...')
for i in range(len(smiles)):
print('Row %d out of %d' % (i + 1, len(smiles)), end='')
print('\r', end='')
AllDescriptors.loc[i] = getAllDescriptorsforMol(Chem.MolFromSmiles(smiles['SMILES'][i]))
for i in range(0,len(data)):
break_counter = 0;
for j in ignore:
if j in smiles['SMILES'][i]:
break_counter = 1;

if break_counter == 0:
print('Row %d out of %d' % (i + 1, len(smiles)), end='')
print('\r', end='')
AllDescriptors.loc[i] = getAllDescriptorsforMol(Chem.MolFromSmiles(smiles['SMILES'][i]))
final_df = utils.descriptor_target_join(AllDescriptors, target)
print('\nCalculating Molecular Descriptors Completed.')
return final_df