import requests

import pandas as pd

from rdkit.Chem.Draw import IPythonConsole
from rdkit.Chem import PandasTools
from rdkit.Chem import AllChem as Chem
from rdkit.Chem import DataStructs

from scipy.spatial.distance import *
import numpy as np
from sklearn import manifold

from ggplot import *

TRGT = 'CHEMBL5024'

re = requests.get('https://www.ebi.ac.uk/chemblws/targets/{0}/bioactivities.json'.format(TRGT))

data = pd.DataFrame(re.json()['bioactivities'])

data.head()

data = data.drop_duplicates(['parent_cmpd_chemblid'])

data.shape

assays = data[['assay_chemblid','target_chemblid']]

assays = assays.groupby('assay_chemblid').count()

goodassays = list(assays.ix[assays.assay_chemblid >= 4].index)

data = data.ix[data.assay_chemblid.isin(goodassays)]

data.shape

def fetch_SMILES(chemblid):
    return str(requests.get('https://www.ebi.ac.uk/chemblws/compounds/{}.json'.format(chemblid)).json()['compound']['smiles'])

data['SMILES'] = data['parent_cmpd_chemblid'].map(fetch_SMILES)

PandasTools.AddMoleculeColumnToFrame(data, smilesCol = 'SMILES')

mols = data[['parent_cmpd_chemblid','name_in_reference','SMILES', 'ROMol', 'assay_chemblid']]

mols.shape

mols.head()

fps = [Chem.GetMorganFingerprintAsBitVect(m,2,nBits=2048) for m in mols['ROMol']]

dist_mat = squareform(pdist(fps,'jaccard'))

pd.DataFrame(dist_mat, columns = mols['parent_cmpd_chemblid'], index=mols['parent_cmpd_chemblid']).head()

mds = manifold.MDS(n_components=2, dissimilarity="precomputed", random_state=3, n_jobs = 2)

results = mds.fit(dist_mat)

coords = results.embedding_

mols['X'] = [c[0] for c in coords]

mols['Y'] = [c[1] for c in coords]

mols.head()

rcParams['figure.figsize'] = 12,12

scatter(mols['X'], mols['Y'])

ggplot(aes(x='X', y='Y', colour='assay_chemblid'), data=mols) + geom_point() 

#TODO: D3 interactive visualisation