def zinc_molecule_filter(mol):
"""
Flags molecules based on problematic functional groups as
provided set of ZINC rules from
http://blaster.docking.org/filtering/rules_default.txt.
:param mol: rdkit mol object
:return: Returns True if molecule is okay (ie does not match any of
therules), False if otherwise
"""
params = FilterCatalogParams()
params.AddCatalog(FilterCatalogParams.FilterCatalogs.ZINC)
catalog = FilterCatalog(params)
return not catalog.HasMatch(mol)
def init():
global catalog
params = FilterCatalogParams()
params.AddCatalog(FilterCatalogParams.FilterCatalogs.PAINS_A)
params.AddCatalog(FilterCatalogParams.FilterCatalogs.PAINS_B)
params.AddCatalog(FilterCatalogParams.FilterCatalogs.PAINS_C)
catalog = FilterCatalog(params)
# https://www.rdkit.org/docs/source/rdkit.Chem.rdfiltercatalog.html
import pandas as pd
from rdkit import Chem
from rdkit.Chem.FilterCatalog import FilterCatalog, FilterCatalogParams
from rdkit.Chem import Draw
# from rdkit.Chem.Draw import IPythonConsole
# Read list with SMARTS for PAINS
pains_list = pd.read_csv("../pains/wehi_pains.csv", header=None)
pains_list.columns = ["SMARTS", "ID"]
# initialize filter
params = FilterCatalogParams()
params.AddCatalog(FilterCatalogParams.FilterCatalogs.PAINS)
catalog = FilterCatalog(params)
def pass_pains(smiles):
# Returns True if mol has no PAINS substructures
mol = Chem.MolFromSmiles(smiles)
entry = catalog.GetFirstMatch(mol) # Get first matching PAINS
# entry.GetDescription().capitalize()
if entry:
return False
return True
def pains_highlight(smiles):
# Returns image of molecule with PAINS highlighted
# Note: maybe some SMARTS strings will throw errors: https://github.com/rdkit/rdkit/issues/3912