# Standard Data Science Boilerplate
import numpy as np
import pandas as pd
import scipy

import chart_studio.plotly as py
import plotly.graph_objs as go
from plotly.offline import iplot, init_notebook_mode
init_notebook_mode(connected=True)

import cufflinks as cf
cf.go_offline(connected=True)
cf.set_config_file(colorscale='plotly', world_readable=True)

# Extra options
#pd.options.display.max_rows = 30
#pd.options.display.max_columns = 25

# Show all code cells outputs
from IPython.core.interactiveshell import InteractiveShell
InteractiveShell.ast_node_interactivity = 'all'

import os
from IPython.display import Image, display, HTML
import ipywidgets as widgets
from ipywidgets import interact, interact_manual

#Boilerplate RDKit
import rdkit
from rdkit import Chem
from rdkit.Chem import AllChem
import rdkit.rdBase
from rdkit.Chem.MACCSkeys import GenMACCSKeys
from rdkit import DataStructs
from rdkit.DataStructs import BitVectToText
from rdkit.Chem.Draw import IPythonConsole
from rdkit.Chem import Draw
from rdkit import DataStructs
import pandas as pd 
from rdkit.Chem import PandasTools as PandasTools
from rdkit.Chem import Descriptors as Descriptors

RDKit WARNING: [07:23:42] Enabling RDKit 2019.09.1 jupyter extensions

sdfFilePath ='FDA2019smallmols.sdf'
moldf = PandasTools.LoadSDF(sdfFilePath,molColName='SMILES')
#moldf["HBA"].fillna(0, inplace=True)
moldf["logP"]=moldf["logP"].astype({'logP': float})
moldf["logD"]=moldf["logD"].astype({'logD': float})
moldf["mass"]=moldf["mass"].astype({'mass': float})
moldf["HBA"]=moldf["HBA"].astype({'HBA': float})
moldf["HBD"]=moldf["HBD"].astype({'HBD': float})
moldf["atomCount"]=moldf["atomCount"].astype({'atomCount': float})
moldf["TPSA"]=moldf["TPSA"].astype({'TPSA': float})
moldf["RBC"]=moldf["RBC"].astype({'RBC': float})
moldf["MR"]=moldf["MR"].astype({'MR': float})
moldf["HAC"]=moldf["HAC"].astype({'HAC': float})
moldf["FractionAromatic"]=moldf["FractionAromatic"].astype({'FractionAromatic': float})

moldf.head(2)

	Name	Drug Name	Active Ingredient	Approval Date	FDA-approved use on approval date*	CSID	Done	abzn	logP	logD	...	Brenda	PDBligand	Kegg Ligand	Human Metab	Lipidmaps	rhea	swisslipids	NIH Clinical	Mcule	PharmGKB
0	atoms 43 bonds 48	Ubrelvy	ubrogepant	12/23/2019	Acute treatment of migraine with or without au...	28536135	Done	Neutral	3.07	3.07	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	atoms 31 bonds 34	Dayvigo	lemborexant	12/20/2019	Insomnia	34500836	Done	Neutral	3.34	3.34	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

2 rows × 61 columns

moldf.dtypes

Name                                  object
Drug Name                             object
Active Ingredient                     object
Approval Date                         object
FDA-approved use on approval date*    object
                                       ...  
rhea                                  object
swisslipids                           object
NIH Clinical                          object
Mcule                                 object
PharmGKB                              object
Length: 61, dtype: object

#Need to work out how to compute range appropriate for property
@interact
def show_molecules_more_than(column=list(moldf.select_dtypes('number').columns), x=(-4, 10, 1),):
    display(HTML(f'<h2>Showing molecules with {column} > {x}<h2>'))
    display(moldf.loc[moldf[column] > x, ['Active Ingredient', 'logP','logD', 'atomCount', 'mass', 'HBA', 'SMILES', 'CSID']])

@interact
def scatter(x=list(moldf.select_dtypes('number').columns), 
                 y=list(moldf.select_dtypes('number').columns)[1:]):
    moldf.iplot(kind='scatter', x=x, y=y, mode='markers', 
             xTitle=x.title(), yTitle=y.title(), title=f'{y.title()} vs {x.title()}')

@interact
def scatter_plot(x=list(moldf.select_dtypes('number').columns), 
                 y=list(moldf.select_dtypes('number').columns)[1:]):
    moldf.iplot(kind='scatter3d', x=x, y=y, z= 'abzn', mode='markers', categories='Active Ingredient',
             xTitle=x.title(), yTitle=y.title(), title=f'{y.title()} vs {x.title()}')

#possible options for structures

mol=moldf.loc[3,'SMILES']
mol

'71602803'

import requests
import IPython.display as Disp  
Mycid = moldf.loc[3, 'Pubchem']
url=('https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/%s/PNG' % Mycid)
Disp.Image(requests.get(url).content)