GetRDKitFPGenerator.py

# -*- coding: utf-8 -*-
"""
Created on Fri Oct 25 23:16:39 2019
 rdkit.Chem.rdFingerprintGenerator.GetRDKitFPGenerator([(int)minPath=1[, (int)maxPath=7[, (bool)useHs=True[, (bool)branchedPaths=True[, (bool)useBondOrder=True[, (bool)countSimulation=False[, (AtomPairsParameters)countBounds=None[, (int)fpSize=2048[, (int)numBitsPerFeature=2[, (AtomPairsParameters)atomInvariantsGenerator=None]]]]]]]]]]) → FingerprintGenerator64 :

    Get an RDKit fingerprint generator

        ARGUMENTS:

                minPath: the minimum path length (in bonds) to be included
                maxPath: the maximum path length (in bonds) to be included
                useHs: toggles inclusion of Hs in paths (if the molecule has explicit Hs)
                branchedPaths: toggles generation of branched subgraphs, not just linear paths
                useBondOrder: toggles inclusion of bond orders in the path hashes
                useCountSimulation: if set, use count simulation while generating the fingerprint
                countBounds: boundaries for count simulation, corresponding bit will be set if the count is higher than the number provided for that spot
                fpSize: size of the generated fingerprint, does not affect the sparse versions
                numBitsPerFeature: the number of bits set per path/subgraph found
                atomInvariantsGenerator: atom invariants to be used during fingerprint generation

        RETURNS: FingerprintGenerator



@author: goraj
"""

from scipy.sparse import dok_matrix
from rdkit import Chem
from rdkit.Chem.rdFingerprintGenerator import GetRDKitFPGenerator

molecules = [
     Chem.MolFromSmiles('C1=CC=C(C(=C1)CC(=O)O)NC2=C(C=CC=C2Cl)Cl')
     for _ in range(100)
]

def rdk(molecules):
    rdk_gen = GetRDKitFPGenerator()
    for j, molecule in enumerate(molecules):
        
        M = None
        
        fp = rdk_gen.GetSparseCountFingerprint(molecule)
        if M is None:
            M = dok_matrix((fp.GetLength(), len(molecules)))
        
        for (k, v) in fp.GetNonzeroElements().items():
            M[k, j] = v
    return M

M = rdk(molecules)