Created
November 1, 2022 21:22
-
-
Save whitead/df6e53cff3102b2dbec6a2e793816a57 to your computer and use it in GitHub Desktop.
Automated naming of compounds
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import rdkit | |
from rdkit import Chem | |
from rdkit.Chem import AllChem | |
import exmol | |
import skunk | |
import math | |
import matplotlib.pyplot as plt | |
import textwrap | |
import matplotlib.pyplot as plt | |
import matplotlib.font_manager as font_manager | |
import urllib.request | |
urllib.request.urlretrieve('https://github.com/google/fonts/raw/main/ofl/ibmplexmono/IBMPlexMono-Regular.ttf', 'IBMPlexMono-Regular.ttf') | |
fe = font_manager.FontEntry( | |
fname='IBMPlexMono-Regular.ttf', | |
name='plexmono') | |
font_manager.fontManager.ttflist.append(fe) | |
plt.rcParams.update({'axes.facecolor':'#f5f4e9', | |
'grid.color' : '#AAAAAA', | |
'axes.edgecolor':'#333333', | |
'figure.facecolor':'#FFFFFF', | |
'axes.grid': False, | |
'axes.prop_cycle': plt.cycler('color', plt.cm.Dark2.colors), | |
'font.family': fe.name, | |
'figure.figsize': (3.5,3.5 / 1.2), | |
'ytick.left': True, | |
'xtick.bottom': True | |
}) | |
def ax_grid(count): | |
'''make square grid with matplotlib subplots''' | |
n = int(math.ceil(math.sqrt(count))) | |
fig, ax = plt.subplots(n, n, figsize=(n * 2, n * 2) ) | |
ax = ax.flatten() | |
print(n**2, count) | |
for a in ax[count:n**2]: | |
a.axis('off') | |
return fig, ax | |
def draw_morgan_bit(mol, bitInfo, key): | |
svg = Chem.Draw.DrawMorganBit( | |
mol, | |
key, | |
bitInfo, | |
molSize=(300, 200), | |
centerColor=None, | |
aromaticColor=None, | |
ringColor=None, | |
extraColor=(0.8, 0.8, 0.8), | |
useSVG=True, | |
) | |
try: | |
svgdata = svg.data | |
except AttributeError: | |
svgdata = svg | |
return svgdata | |
def draw_mol(m): | |
size = (300, 200) | |
dos = rdkit.Chem.Draw.MolDrawOptions() | |
dos.drawMolsSameScale = False | |
#dos.useBWAtomPalette() | |
dos.minFontSize = 16 | |
d = rdkit.Chem.Draw.rdMolDraw2D.MolDraw2DSVG(*size) | |
d.SetDrawOptions(dos) | |
d.DrawMolecule(m) | |
d.FinishDrawing() | |
return d.GetDrawingText() | |
def plot(smi): | |
mol = Chem.MolFromSmiles(smi) | |
bitInfo = {} | |
svg_dict = {} | |
AllChem.GetMorganFingerprint(mol, 3, bitInfo=bitInfo) | |
names = [] | |
used_names = set() | |
for r in range(4): | |
for b in bitInfo: | |
_, ri = bitInfo[b][0] | |
if ri != r: | |
continue | |
name = exmol.exmol._name_morgan_bit(mol, bitInfo, b) | |
if name is None or len(name) < 2 or name in used_names: | |
continue | |
names.append(name) | |
s = draw_morgan_bit(mol, bitInfo, b) | |
svg_dict[str(b)] = s | |
# ok now ban all names we've seen so far | |
used_names |= set(names) | |
print(names) | |
# set-up plot | |
fig, axs = ax_grid(len(svg_dict) + 1) | |
mol_svg = draw_mol(mol) | |
axs[0].axis('off') | |
svg_dict['mol'] = mol_svg | |
skunk.connect(axs[0], 'mol') | |
for ax, k, n in zip(axs[1:], svg_dict.keys(), names): | |
ax.axis('off') | |
ax.set_title(textwrap.fill(n, 20)) | |
skunk.connect(ax, str(k)) | |
fig.tight_layout(pad=1.0) | |
svg = skunk.insert(svg_dict) | |
plt.close() | |
skunk.display(svg) | |
plot('O=C(NCC1CCCCC1N)C2=CC=CC=C2C3=CC=C(F)C=C3C(=O)NC4CCCCC4') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment