#!/usr/bin/env python
# coding: utf-8

# In[27]:


get_ipython().run_line_magic('matplotlib', 'inline')
import matplotlib.pyplot as plt
import os
from rdkit import Chem
from rdkit import RDConfig

import pandas as pd
import janitor
from janitor import chemistry

from rdkit.Chem import PandasTools
from rdkit.Chem.Draw import IPythonConsole

from sklearn.decomposition import PCA
plt.style.use('ggplot')


# In[28]:


path = os.path.join(RDConfig.RDDocsDir,'Book/data/cdk2.sdf')


# In[29]:


df = PandasTools.LoadSDF(path)


# In[30]:


df.head(2)


# In[31]:


fp1=chemistry.morgan_fingerprint(df, mols_col='ROMol', radius=2, nbits=512, kind='bits')


# In[32]:


type(fp1)


# In[33]:


fp1.head(2)


# In[34]:


fp1.shape


# In[35]:


fp2=chemistry.morgan_fingerprint(df, mols_col='ROMol', radius=2, nbits=512, kind='counts')
fp2.shape


# In[38]:


pca = PCA(n_components=3)


# In[45]:


pca_res = pca.fit_transform(fp2)


# In[46]:


plt.scatter(pca_res[:,0], pca_res[:,1], c=df.Cluster)


# In[36]:


df['SMILES'] = df.ROMol.apply(Chem.MolToSmiles)
df.head(2)


# In[12]:


df = chemistry.smiles2mol(df, smiles_col='SMILES', mols_col='newROMol', progressbar='notebook')


# In[13]:


df.head(2)


# In[14]:


# add_column function is not native pandas method.
# df['NumAtm'] = df.ROMol.apply(Chem.Mol.GetAtoms) 
df = df.add_column('NumAtm', [Chem.Mol.GetNumAtoms(mol) for mol in df.ROMol])


# In[ ]:


df.head(2)