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)
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 get_filters(self):
"""
This loads in the filters which will be used.
Returns:
:returns: rdkit.Chem.rdfiltercatalog.FilterCatalog filters: A set of
RDKit Filters
"""
# Make a list of the NIH filter.
params = FilterCatalogParams()
params.AddCatalog(FilterCatalogParams.FilterCatalogs.NIH)
# This is our set of all the NIH filters
filters = FilterCatalog.FilterCatalog(params)
return filters
def get_filters_list(self):
"""
This loads in the filters which will be used.
Returns:
:returns: rdkit.Chem.rdfiltercatalog.FilterCatalog filters: A set of
RDKit Filters
"""
# Make a list of all the different PAINS Filters. PAINS should include
# PAINS_A,PAINS_B, and PAINS_C, but because RDKit documentation
# doesn't specify this explicitly we have included all 4 of the PAINS
# FilterCatalogs for precaution.
params_PAINS_A = FilterCatalogParams()
params_PAINS_A.AddCatalog(FilterCatalogParams.FilterCatalogs.PAINS_A)
params_PAINS_B = FilterCatalogParams()
params_PAINS_B.AddCatalog(FilterCatalogParams.FilterCatalogs.PAINS_B)
params_PAINS_C = FilterCatalogParams()
params_PAINS_C.AddCatalog(FilterCatalogParams.FilterCatalogs.PAINS_C)
params_PAINS = FilterCatalogParams()
params_PAINS.AddCatalog(FilterCatalogParams.FilterCatalogs.PAINS)
params_list = [
params_PAINS_A, params_PAINS_B, params_PAINS_C, params_PAINS
]
filters_list = []
for param in params_list:
filter = FilterCatalog.FilterCatalog(param)
filters_list.append(filter)
return filters_list
# PAINS filter - RDKit
# https://projects.volkamerlab.org/teachopencadd/talktorials/T003_compound_unwanted_substructures.html
# 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):