def generate_fingerprints_and_create_list(self):
#generate fingerprints of predicted ligands and known ligands:
gen_mo = rdFingerprintGenerator.GetMorganGenerator(fpSize=2048,
radius=2)
predicted_fps = [
gen_mo.GetFingerprint(mol) for mol in self.predicted['molecules']
]
true_fps = [
gen_mo.GetFingerprint(mol) for mol in self.true_pos['molecules']
]
similarities = list()
for count, mol in enumerate(predicted_fps):
tanimoto_values = ([
DataStructs.TanimotoSimilarity(mol, i) for i in true_fps
])
index_of_highest = np.argmax(tanimoto_values)
similarities.append(tanimoto_values[index_of_highest])
#module code is in: https://github.com/rdkit/rdkit/tree/master/Contrib/SA_Score
sa_score = [
sascorer.calculateScore(i)
for i in list(self.predicted['molecules'])
]
#create a list holding the QED drug-likeness score
#reference: https://doi.org/10.1038/nchem.1243
qeds = [qed(mol) for mol in self.predicted['molecules']]
#create a list holding logp:
logp = [Descriptors.MolLogP(m) for m in self.predicted['molecules']]
#filter catalog usage instructions are here: https://github.com/rdkit/rdkit/pull/536
params = FilterCatalogParams()
params.AddCatalog(FilterCatalogParams.FilterCatalogs.BRENK)
catalog = FilterCatalog(params)
self.brenk = np.array(
[catalog.HasMatch(m) for m in self.predicted['molecules']])
#add these lists as columns to the 'predicted' pd.DataFrame
self.predicted['similarities'] = similarities
self.predicted['sa_score'] = sa_score
self.predicted['qeds'] = qeds
self.predicted['logp'] = logp
print(self.predicted['logp'] < 6)
shortlist_mask = ((self.predicted['similarities'] < 0.2) &
(self.predicted['sa_score'] < 4) &
(self.predicted['qeds'] > 0.25) &
(self.predicted['logp'] < 6) & (~self.brenk))
params[1].AddCatalog(FilterCatalogParams.FilterCatalogs.PAINS_A)
params[2].AddCatalog(FilterCatalogParams.FilterCatalogs.PAINS_B)
params[3].AddCatalog(FilterCatalogParams.FilterCatalogs.PAINS_C)
catalog_pains = FilterCatalog(params[0])
catalog_painsA = FilterCatalog(params[1])
catalog_painsB = FilterCatalog(params[2])
catalog_painsC = FilterCatalog(params[3])
entries_pains = []
entries_painsA = []
entries_painsB = []
entries_painsC = []
entries_painsAll = []
for i in range(len(data)):
if catalog_pains.HasMatch(data[i]):
entries_pains.append(i)
if catalog_painsA.HasMatch(data[i]):
entries_painsA.append(i)
if catalog_painsB.HasMatch(data[i]):
entries_painsB.append(i)
if catalog_painsC.HasMatch(data[i]):
entries_painsC.append(i)
if catalog_pains.HasMatch(data[i]) or catalog_painsA.HasMatch(
data[i]) or catalog_painsB.HasMatch(
data[i]) or catalog_painsC.HasMatch(data[i]):
entries_painsAll.append(i)
print(len(entries_pains), len(entries_painsA), len(entries_painsB),
len(entries_painsC), len(entries_painsAll))
print(
