def GetMHFP6(mol, nBits=2048, radius=3):
"""
MHFP6: radius=3
"""
encoder = MHFPEncoder(n_permutations=nBits)
hash_values = encoder.encode_mol(mol,
radius=radius,
rings=True,
kekulize=True,
min_radius=1)
arr = encoder.fold(hash_values, nBits)
return arr.astype(bool)
def convert(subset):
target = '/cluster/chembl/chembl.' + str(subset) + '.smi'
actives = pd.read_csv(target, sep=' ', usecols=[0], header=None)
mh = MHFPEncoder()
with open('/cluster/chembl/chembl.' + str(subset) + '.mhfp6', 'w+') as f:
for _, row in actives.iterrows():
mol = AllChem.MolFromSmiles(row[0])
if mol:
fp_vals = ','.join(map(str, mh.encode_mol(mol)))
f.write(fp_vals + '\n')
with open('/cluster/chembl/chembl.' + str(subset) + '.mhecfp4', 'w+') as f:
for _, row in actives.iterrows():
mol = AllChem.MolFromSmiles(row[0])
if mol:
fp_vals = ','.join(
map(
str,
mh.from_sparse_array([
*AllChem.GetMorganFingerprint(
mol, 2).GetNonzeroElements()
])))
f.write(fp_vals + '\n')
with open('/cluster/chembl/chembl.' + str(subset) + '.ecfp4', 'w+') as f:
for _, row in actives.iterrows():
mol = AllChem.MolFromSmiles(row[0])
if mol:
fp_vals = ','.join(
map(
str,
AllChem.GetMorganFingerprintAsBitVect(mol,
2,
nBits=2048)))
f.write(fp_vals + '\n')
from rdkit.Chem import AllChem
from mhfp.encoder import MHFPEncoder
from mhfp.lsh_forest import LSHForestHelper
# Keeping tests barebone and simple
mhfp_encoder = MHFPEncoder()
lfh = LSHForestHelper()
drugbank = []
with open('test/drugbank.smi') as f:
for line in f.readlines():
mol = AllChem.MolFromSmiles(line.strip().split()[0])
if mol:
drugbank.append(mhfp_encoder.encode_mol(mol))
for i, fp in enumerate(drugbank):
lfh.add(i, fp)
lfh.index()
def test_setup():
assert len(drugbank) == 226
def test_add():
assert len(lfh.lsh_forest.keys) == 226
def main():
""" The main function """
df = pd.read_csv("drugbank.csv").dropna(subset=["SMILES"]).reset_index(
drop=True)
enc = MHFPEncoder()
lf = tm.LSHForest(2048, 128)
fps = []
labels = []
groups = []
tpsa = []
logp = []
mw = []
h_acceptors = []
h_donors = []
ring_count = []
is_lipinski = []
has_coc = []
has_sa = []
has_tz = []
substruct_coc = AllChem.MolFromSmiles("COC")
substruct_sa = AllChem.MolFromSmiles("NS(=O)=O")
substruct_tz = AllChem.MolFromSmiles("N1N=NN=C1")
total = len(df)
for i, row in df.iterrows():
if i % 1000 == 0 and i > 0:
print(f"{round(100 * (i / total))}% done ...")
smiles = row[6]
mol = AllChem.MolFromSmiles(smiles)
if mol and mol.GetNumAtoms() > 5 and smiles.count(".") < 2:
fps.append(tm.VectorUint(enc.encode_mol(mol, min_radius=0)))
labels.append(
f'{smiles}__<a href="https://www.drugbank.ca/drugs/{row[0]}" target="_blank">{row[0]}</a>__{row[1]}'
.replace("'", ""))
groups.append(row[3].split(";")[0])
tpsa.append(Descriptors.TPSA(mol))
logp.append(Descriptors.MolLogP(mol))
mw.append(Descriptors.MolWt(mol))
h_acceptors.append(Descriptors.NumHAcceptors(mol))
h_donors.append(Descriptors.NumHDonors(mol))
ring_count.append(Descriptors.RingCount(mol))
is_lipinski.append(lipinski_pass(mol))
has_coc.append(mol.HasSubstructMatch(substruct_coc))
has_sa.append(mol.HasSubstructMatch(substruct_sa))
has_tz.append(mol.HasSubstructMatch(substruct_tz))
# Create the labels and the integer encoded array for the groups,
# as they're categorical
labels_groups, groups = Faerun.create_categories(groups)
tpsa_ranked = ss.rankdata(np.array(tpsa) / max(tpsa)) / len(tpsa)
logp_ranked = ss.rankdata(np.array(logp) / max(logp)) / len(logp)
mw_ranked = ss.rankdata(np.array(mw) / max(mw)) / len(mw)
h_acceptors_ranked = ss.rankdata(
np.array(h_acceptors) / max(h_acceptors)) / len(h_acceptors)
h_donors_ranked = ss.rankdata(
np.array(h_donors) / max(h_donors)) / len(h_donors)
ring_count_ranked = ss.rankdata(
np.array(ring_count) / max(ring_count)) / len(ring_count)
lf.batch_add(fps)
lf.index()
cfg = tm.LayoutConfiguration()
cfg.k = 100
# cfg.sl_extra_scaling_steps = 1
cfg.sl_repeats = 2
cfg.mmm_repeats = 2
cfg.node_size = 2
x, y, s, t, _ = tm.layout_from_lsh_forest(lf, config=cfg)
# Define a colormap highlighting approved vs non-approved
custom_cmap = ListedColormap(
[
"#2ecc71", "#9b59b6", "#ecf0f1", "#e74c3c", "#e67e22", "#f1c40f",
"#95a5a6"
],
name="custom",
)
bin_cmap = ListedColormap(["#e74c3c", "#2ecc71"], name="bin_cmap")
f = Faerun(
clear_color="#222222",
coords=False,
view="front",
impress=
'made with <a href="http://tmap.gdb.tools" target="_blank">tmap</a><br />and <a href="https://github.com/reymond-group/faerun-python" target="_blank">faerun</a><br /><a href="https://gist.github.com/daenuprobst/5cddd0159c0cf4758fb16b4b4acbef89">source</a>',
)
f.add_scatter(
"Drugbank",
{
"x":
x,
"y":
y,
"c": [
groups,
is_lipinski,
has_coc,
has_sa,
has_tz,
tpsa_ranked,
logp_ranked,
mw_ranked,
h_acceptors_ranked,
h_donors_ranked,
ring_count_ranked,
],
"labels":
labels,
},
shader="smoothCircle",
colormap=[
custom_cmap,
bin_cmap,
bin_cmap,
bin_cmap,
bin_cmap,
"viridis",
"viridis",
"viridis",
"viridis",
"viridis",
"viridis",
],
point_scale=2.5,
categorical=[
True, True, True, True, True, False, False, False, False, False
],
has_legend=True,
legend_labels=[
labels_groups,
[(0, "No"), (1, "Yes")],
[(0, "No"), (1, "Yes")],
[(0, "No"), (1, "Yes")],
[(0, "No"), (1, "Yes")],
],
selected_labels=["SMILES", "Drugbank ID", "Name"],
series_title=[
"Group",
"Lipinski",
"Ethers",
"Sulfonamides",
"Tetrazoles",
"TPSA",
"logP",
"Mol Weight",
"H Acceptors",
"H Donors",
"Ring Count",
],
max_legend_label=[
None,
None,
None,
None,
None,
str(round(max(tpsa))),
str(round(max(logp))),
str(round(max(mw))),
str(round(max(h_acceptors))),
str(round(max(h_donors))),
str(round(max(ring_count))),
],
min_legend_label=[
None,
None,
None,
None,
None,
str(round(min(tpsa))),
str(round(min(logp))),
str(round(min(mw))),
str(round(min(h_acceptors))),
str(round(min(h_donors))),
str(round(min(ring_count))),
],
title_index=2,
legend_title="",
)
f.add_tree("drugbanktree", {"from": s, "to": t}, point_helper="Drugbank")
f.plot("drugbank", template="smiles")
# print(x)
# print(y)
enc = MHFPEncoder(512)
fps = []
if not os.path.isfile('fps.dat'):
with open('drugbank.smi', 'r') as f:
i = 0
for line in f:
smiles = line.split()[0].strip()
mol = AllChem.MolFromSmiles(smiles)
if mol:
fps.append(enc.encode_mol(mol))
i += 1
if i > 2000: break
pickle.dump(fps, open('fps.dat', 'wb'))
else:
fps = pickle.load(open('fps.dat', 'rb'))
m = enc.encode(
"N=C(N)NCCC[C@H](NC(=O)[C@@H]1CCCN1C(=O)[C@H](N)Cc1ccccc1)C(=O)N1CCC[C@H]1C(=O)NCC(=O)NCC(=O)NCC(=O)NCC(=O)N[C@@H](CC(=O)N)C(=O)NCC(=O)N[C@@H](CC(=O)O)C(=O)N[C@@H](Cc1ccccc1)C(=O)N[C@@H](CCC(=O)O)C(=O)N[C@@H](CCC(=O)O)C(=O)N[C@@H]([C@@H](C)CC)C(=O)N1CCC[C@H]1C(=O)N[C@@H](CCC(=O)O)C(=O)N[C@@H](CCC(=O)O)C(=O)N[C@@H](Cc1ccc(O)cc1)C(=O)N[C@@H](CC(C)C)C(=O)O"
)
n = enc.encode(
"O=C(N1[C@@H](CCC1)C(=O)NNC(=O)N)[C@@H](NC(=O)[C@@H](NC(=O)[C@H](NC(=O)[C@@H](NC(=O)[C@@H](NC(=O)[C@@H](NC(=O)[C@@H](NC(=O)[C@H]1NC(=O)CC1)Cc1[nH]cnc1)Cc1c2c([nH]c1)cccc2)CO)Cc1ccc(O)cc1)COC(C)(C)C)CC(C)C)CCCN=C(N)N"
)
q = enc.encode(
"[C@@H](C(=O)NCC(=O)N[C@@H](C(=O)N[C@@H](C)C(=O)N[C@@H](C(=O)N[C@H](C(=O)N[C@@H](C(=O)N[C@H](C(=O)N[C@@H](C(=O)N[C@H](C(=O)N[C@@H](C(=O)N[C@H](C(=O)N[C@@H](C(=O)N[C@H](C(=O)NCCO)Cc1c2c(cccc2)[nH]c1)CC(C)C)Cc1c[nH]c2c1cccc2)CC(C)C)Cc1c[nH]c2c1cccc2)CC(C)C)Cc1c[nH]c2c1cccc2)C(C)C)C(C)C)C(C)C)CC(C)C)(C(C)C)NC=O"
)