Tanimoto coefficient rdkit

from rdkit import Chem
from rdkit import DataStructs
from rdkit.Chem.Fingerprints import FingerprintMols
import pandas as pd

# read and Conconate the csv's
df_1 = pd.read_csv('first.csv')
df_2 = pd.read_csv('second.csv')
df_3 = pd.concat([df_1, df_2])

# proof and make a list of SMILES
df_smiles = df_3['smiles']
c_smiles = []
for ds in df_smiles:
    try:
        cs = Chem.CanonSmiles(ds)
        c_smiles.append(cs)
    except:
        print('Invalid SMILES:', ds)
print()

# make a list of mols
ms = [Chem.MolFromSmiles(x) for x in c_smiles]

# make a list of fingerprints (fp)
fps = [FingerprintMols.FingerprintMol(x) for x in ms]

# the list for the dataframe
qu, ta, sim = [], [], []

# compare all fp pairwise without duplicates
for n in range(len(fps)-1): # -1 so the last fp will not be used
    s = DataStructs.BulkTanimotoSimilarity(fps[n], fps[n+1:]) # +1 compare with the next to the last fp
    print(c_smiles[n], c_smiles[n+1:]) # witch mol is compared with what group
    # collect the SMILES and values
    for m in range(len(s)):
        qu.append(c_smiles[n])
        ta.append(c_smiles[n+1:][m])
        sim.append(s[m])
print()

# build the dataframe and sort it
d = {'query':qu, 'target':ta, 'Similarity':sim}
df_final = pd.DataFrame(data=d)
df_final = df_final.sort_values('Similarity', ascending=False)
print(df_final)

# save as csv
df_final.to_csv('third.csv', index=False, sep=',')

Source: stackoverflow.com

Similar codes

2 votes307 views1 answer
Flask if statement
Python
1 vote320 views1 answer
How to construct simple timedelta in python
Python
0 vote319 views6 answers
Python3 vowels and consonants filter
Python
0 vote339 views1 answer
Add sign to y axis values python
Python
1 vote338 views2 answers
N factorial
Python
0 vote338 views1 answer
How to access value from <class 'pandas.core.indexes.numeric.Int64Index'>?q=int64.index
Python
0 vote323 views1 answer
Python concatenate tuple to string
Python
-1 vote299 views1 answer
Python numpy euler
Python
0 vote318 views1 answer
Ver todas linhas dataframe pandas
Python
18 votes317 views5 answers
Python continue
Python