In [1]:
conda install -c rdkit rdkit
In [2]:
conda install -c jirinovo pubchempy
In [2]:
from rdkit import Chem
from rdkit.Chem import AllChem
from rdkit import RDConfig
from rdkit.Chem.Draw import IPythonConsole
from rdkit.Chem import Draw
import numpy as np
from IPython.display import display,Image
In [3]:
ibu=Chem.MolFromSmiles('CC(C)CC1=CC=C(C=C1)C(C)C(=O)O')
AllChem.Compute2DCoords(ibu)
display(ibu)
In [4]:
ibu=Chem.MolFromSmiles('CC(C)CC1=CC=C(C=C1)C(C)C(=O)[O-]')
import rdkit.Chem.Lipinski as Lipinksy
print(Lipinksy.NumHDonors(ibu))
print(Lipinksy.NumHAcceptors(ibu))
print(Lipinksy.rdMolDescriptors.CalcExactMolWt(ibu))
print(Lipinksy.rdMolDescriptors.CalcCrippenDescriptors(ibu)[0])
In [5]:
import pubchempy
In [5]:
compounds = []
per_page = 10**5
for smiles in ["N=N=N", "NN#N",]:
for i in range(200):
try:
a = pcp.get_properties(
properties="CanonicalSMILES",
identifier=smiles, namespace="smiles",
searchtype="substructure",
RingsNotEmbedded=True,
listkey_count=per_page, listkey_start=i*per_page
)
except:
print("Page {} returns 500, which is "
"our signal to stop.".format(i+1))
break
print("Retrieved page {} of {} search".format(i+1, smiles))
compounds.extend(a)
In [6]:
strings=np.genfromtxt('1931431637611612961.txt',dtype=np.str)
smiles=[]
for line in strings:
if len(line[1]) < 30 and not '.' in line[1]:
smiles.append(line[1])
In [7]:
ibu_azid = 'N(N=N1)C=C1-C1=CC=C(C=C1)C(C)C(=O)O'
ibu_azid_show=Chem.MolFromSmiles("N(N=N1)C=C1-C1=CC=C(C=C1)C(C)C(=O)O")
AllChem.Compute2DCoords(ibu_azid_show)
display(ibu_azid_show)
In [12]:
azid = 'N=[N+]=[N-]'
good_mol=[]
for smi in smiles[:1500]:
if azid in smi:
newsmi=smi.replace(azid ,ibu_azid)
print(newsmi)
else:
continue
try:
newmol=Chem.MolFromSmiles(newsmi)
display(newmol)
if (Lipinksy.NumHDonors(newmol)<=5) and (Lipinksy.NumHAcceptors(newmol)<=10) and (Lipinksy.rdMolDescriptors.CalcExactMolWt(newmol)<500) and (Lipinksy.rdMolDescriptors.CalcCrippenDescriptors(newmol)[0]<=5):
AllChem.Compute2DCoords(newmol)
good_mol.append(newmol)
except:
pass
In [10]:
Chem.Draw.MolsToGridImage(good_mol, maxMols = 20, molsPerRow = 4, subImgSize = (500, 300))
In [ ]:
m3d=Chem.AddHs(good_mol[4])
Chem.AllChem.EmbedMolecule(m3d)
AllChem.MMFFOptimizeMolecule(m3d,maxIters=500,nonBondedThresh=200 )
m3d