fragments.txt

// Copyright (C) 2003 Rational Discovery LLC
//  This file is part of the RDKit.
//  The contents are covered by the terms of the BSD license
//  which is included in the file license.txt, found at the root
//  of the RDKit source tree.
// NOTES:
//  - larger functional groups should come before smaller ones involving
//    the same core atom
//  - the first atom in the SMARTS query is not part of the group itself
//  - it is essential that the fields in this file be separated by tabs
//    (not spaces).
//
//   Label	SMARTS	Notes
//--------------------------------------------------
-NC(=O)CH3	*-[N;D2]-[C;D3](=O)-[C;D1;H3]	methyl amide
-C(=O)O	*-C(=O)[O;D1]	carboxylic acids
-C(=O)OMe	*-C(=O)[O;D2]-[C;D1;H3]	carbonyl methyl ester
-C(=O)H	*-C(=O)-[C;D1]	terminal aldehyde
-C(=O)N	   *-C(=O)-[N;D1]	amide
-C(=O)CH3	*-C(=O)-[C;D1;H3]	carbonyl methyl
-N=C=O	   *-[N;D2]=[C;D2]=[O;D1]	isocyanate
-N=C=S	   *-[N;D2]=[C;D2]=[S;D1]	isothiocyanate
//--------------------------------------------------
// Nitrogen containing
-NO2	   *-[N;D3](=[O;D1])[O;D1]	nitro
-N=O	   *-[N;R0]=[O;D1]	nitroso
=N-O	   *=[N;R0]-[O;D1]	oximes
=NCH3	   *=[N;R0]-[C;D1;H3]	Imines
-N=CH2	   *-[N;R0]=[C;D1;H2]	Imines
-N=NCH3	   *-[N;D2]=[N;D2]-[C;D1;H3]	terminal azo
-N=N	   *-[N;D2]=[N;D1]	hydrazines
-N#N	   *-[N;D2]#[N;D1]	diazo
-C#N	   *-[C;D2]#[N;D1]	cyano
//--------------------------------------------------
// S containing
-SO2NH2	*-[S;D4](=[O;D1])(=[O;D1])-[N;D1]	primary sulfonamide
-NHSO2CH3	*-[N;D2]-[S;D4](=[O;D1])(=[O;D1])-[C;D1;H3]	methyl sulfonamide
-SO3H	*-[S;D4](=O)(=O)-[O;D1]	sulfonic acid
-SO3CH3	*-[S;D4](=O)(=O)-[O;D2]-[C;D1;H3]	methyl ester sulfonyl
-SO2CH3	*-[S;D4](=O)(=O)-[C;D1;H3]	methyl sulfonyl
-SO2Cl	*-[S;D4](=O)(=O)-[Cl]	sulfonyl chloride
-SOCH3	*-[S;D3](=O)-[C;D1]	methyl sulfinyl
-SCH3	*-[S;D2]-[C;D1;H3]	methylthio
-S	*-[S;D1]	thiols
=S	*=[S;D1]	thiocarbonyls
//--------------------------------------------------
//Miscellaneous fragments:
-X	*-[#9,#17,#35,#53]	   halogens
-tBu	*-[C;D4]([C;D1])([C;D1])-[C;D1]	t-butyl
-CF3	*-[C;D4](F)(F)F	trifluoromethyl
-C#CH	*-[C;D2]#[C;D1;H]	acetylenes
-cPropyl	*-[C;D3]1-[C;D2]-[C;D2]1	cyclopropyl
//--------------------------------------------------
//Really teeny stuff:
-OEt	*-[O;D2]-[C;D2]-[C;D1;H3]	ethoxy
-OMe	*-[O;D2]-[C;D1;H3]	methoxy
-O	*-[O;D1]	side-chain hydroxyls
=O	*=[O;D1]	side-chain aldehydes or ketones
-N	   *-[N;D1]	primary amines
=N	   *=[N;D1]	???
#N	   *#[N;D1]	nitriles

framgents.py

from rdkit import Chem
import pandas as pd
import matplotlib.pyplot as plt

# Get fragments
fragments_df = pd.read_csv("fragments.txt", sep="\t", comment="/", names=["label", "smarts", "name"])
fragments = {row["name"]: Chem.MolFromSmarts(row["smarts"]) for _,row in fragments_df.iterrows()}
def get_functional_groups(mol, fragments):
    return {label: len(mol.GetSubstructMatches(fragment)) for label, fragment in fragments.items()} 


# Get functional groups
smiles_list = ["CO",...] # Put your list of smiles here
mols = [Chem.MolFromSmiles(smi) for smi in mols]
functional_groups = [get_functional_groups(mol, fragments) for mol in mols]
functional_group_df = pd.DataFrame(functional_groups)

#Make figure
fig, ax = plt.subplots(1)
sums[:10].plot.bar(ax=ax, rot=45, )
ax.tick_params(direction="in")
ax.set_ylabel("Counts")
ax.set_xticklabels(sums[:10].index, rotation=30, ha='right')