rdkit/Data/FragmentDescriptors.csv

1	# Copyright (C) 2002 Rational Discovery LLC
2	# This file is part of the RDKit.
3	# The contents are covered by the terms of the BSD license
4	# which is included in the file license.txt, found at the root
5	# of the RDKit source tree.
6	#Code	Description	SMARTS	MOE_SMARTS	Notes
7	##########
8	# Oxygens
9	##########
10	fr_C=O	Number of carbonyl O	[CX3]=[OX1]	C=O	Includes carboxylic acids, esters, amides, etc.
11	fr_C=O_noCOO	Number of carbonyl O, excluding COOH	[C!$(C-[OH])]=O	[C!$(C-[OH])]=O	Excludes COOH but not COO- (assumes no formal charge) hydroxyls. Includes esters, amides, etc.
12	fr_Al_OH	Number of aliphatic hydroxyl groups	[C!$(C=O)]-[OH]	[C!$(C=O)]-[OH]	Excludes COOH but not COO- (assumes no formal charge) hydroxyls
13	fr_Ar_OH	Number of aromatic hydroxyl groups	c[OH1]	c[OH1]
14	fr_methoxy	Number of methoxy groups -OCH3	[OX2](-[#6])-[CH3]	O(-[#6])-CH3	Aliphatic. Includes esters. Includes OMe groups on aromatic rings.
15	fr_oxime	Number of oxime groups	[CX3]=[NX2]-[OX2]	C=N-O
16	fr_ester	Number of esters	[#6][CX3](=O)[OX2H0][#6]	C(=O)O-C
17	fr_Al_COO	Number of aliphatic carboxylic acids	C-C(=O)[O;H1,-]	C-C(=O)[OH] or C-C(=O)[O-]
18	fr_Ar_COO	Number of Aromatic carboxylic acide	c-C(=O)[O;H1,-]	c-C(=O)[OH] or c-C(=O)[O-]
19	fr_COO	Number of carboxylic acids	[#6]C(=O)[O;H,-1]	[#6]C(=O)[OH] or [#6]C(=O)[O-]
20	fr_COO2	Number of carboxylic acids	[CX3](=O)[OX1H0-,OX2H1]	[#6]C(=O)[OH] or [#6]C(=O)[O-]
21	fr_ketone	Number of ketones	[#6][CX3](=O)[#6]
22	fr_ether	Number of ether oxygens (including phenoxy)	[OD2]([#6])[#6]
23	fr_phenol	Number of phenols	[OX2H]-c1ccccc1
24	fr_aldehyde	Number of aldehydes	[CX3H1](=O)[#6]
25	############
26	# Nitrogens
27	############
28	fr_quatN	Number of quarternary nitrogens	[$([NX4+]),$([NX4]=*)]	[NX4]
29	fr_NH2	Number of Primary amines	[NH2,nH2]	[NH2]	Include aromatic Ns
30	fr_NH1	Number of Secondary amines	[NH1,nH1]	[NH1] or [nH1]
31	fr_NH0	Number of Tertiary amines	[NH0,nH0]	[NH0] or [nH0]
32	fr_Ar_N	Number of aromatic nitrogens	n	n
33	fr_Ar_NH	Number of aromatic amines	[nH]
34	fr_aniline	Number of anilines	c-[NX3;!$(N=*)]
35	fr_Imine	Number of Imines	[Nv3](=C)-[#6]	[Nv3](=C)-[#6]	Aliphatic. Excludes aromatic sp2 nitrogens.
36	fr_nitrile	Number of nitriles	[NX1]#[CX2]	C#N
37	fr_hdrzine	Number of hydrazine groups	[NX3]-[NX3]	[NX3]-[NX3]	Includes primary, secondary hydrazines, carbazides, cyclic hydrazines. Excludes hydrazones
38	fr_hdrzone	Number of hydrazone groups	C=N-[NX3]	C=N-[NX3]	Includes cyclic hydrazones
39	fr_nitroso	Number of nitroso groups, excluding NO2	[N!$(N-O)]=O	[N!$(N-O)]=O	Includes N-N=O
40	fr_N-O	Number of hydroxylamine groups	[N!$(N=O)](-O)-C	[N!$(N=O)](-O)-C
41	fr_nitro	Number of nitro groups	[$([NX3](=O)=O),$([NX3+](=O)[O-])][!#8]	N(=O)(O)[#6]
42	#fr_nitro	Number of nitro groups	N(=O)(O)[#6]	N(=O)(O)[#6]
43	fr_azo	Number of azo groups	[#6]-N=N-[#6]	[#6]-N=N-[#6]	Both nitrogens must be attached to a C. Excludes azides.
44	fr_diazo	Number of diazo groups	[N+]#N	[N+]#N
45	fr_azide	Number of azide groups	[$(*-[NX2-]-[NX2+]#[NX1]),$(*-[NX2]=[NX2+]=[NX1-])]	[#6]-N=[N+]=[N-]
46	fr_amide	Number of amides	C(=O)-N	C(=O)-N	Any amide
47	fr_priamide	Number of primary amides	C(=O)-[NH2]	C(=O)-[NH2]
48	fr_amidine	Number of amidine groups	C(=N)(-N)-[!#7]	C(=N)(-N)-[!#7]	Excludes guanidine
49	fr_guanido	Number of guanidine groups	C(=N)(N)N	C(=N)(N)N
50	fr_Nhpyrrole	Number of H-pyrrole nitrogens	[nH]	[nH]
51	fr_imide	Number of imide groups	N(-C(=O))-C=O	N(-C(=O))-C=O
52	fr_isocyan	Number of isocyanates	N=C=O	N=C=O
53	fr_isothiocyan	Number of isothiocyanates	N=C=S	N=C=S
54	fr_thiocyan	Number of thiocyanates	S-C#N	S-C#N
55	###########
56	# Halogens
57	###########
58	fr_halogen	Number of halogens	[#9,#17,#35,#53]	F or I or Cl or Br
59	fr_alkyl_halide	Number of alkyl halides	[CX4]-[Cl,Br,I,F]
60	##########
61	# Sulfurs
62	##########
63	fr_sulfide	Number of thioether	[SX2](-[#6])-C	[SLp2](-[#6])-C	Aliphatic. Excludes sulfones, etc. Includes SMe groups on aromatic rings.
64	fr_SH	Number of thiol groups	[SH]	[SH]
65	fr_C=S	Number of thiocarbonyl	C=[SX1]	C=S	Includes thioamides, thioureas, etc.
66	fr_sulfone	Number of sulfone groups	S(=,-[OX1;+0,-1])(=,-[OX1;+0,-1])(-[#6])-[#6]	S(=O)(=O)(-[#6])-[#6] or S(-[O-])(-[O-])(-[#6])-[#6]	Or charged form. Excludes sulfonamides, sulfonyl Cl, etc..
67	fr_sulfone	Number of sulfone groups	S(=,-[OX1;+0,-1])(=,-[OX1;+0,-1])(-[#6])-[#6]	S(=O)(=O)(-[#6])-[#6] or S(-[O-])(-[O-])(-[#6])-[#6]	Or charged form. Excludes sulfonamides, sulfonyl Cl, etc..
68	fr_sulfonamd	Number of sulfonamides	N-S(=,-[OX1;+0,-1])(=,-[OX1;+0,-1])-[#6]	N-S(=O)(=O)-[#6] or N-S(-[O-])(-[O-])-[#6]	Any sulfonamide
69	fr_prisulfonamd	Number of primary sulfonamides	[NH2]-S(=,-[OX1;+0;-1])(=,-[OX1;+0;-1])-[#6]	[NH2]-S(=O)(=O)-[#6] or [NH2]-S(-[O-])(-[O-])-[#6]
70	##################################
71	# Miscellaneous Functional Groups
72	##################################
73	fr_barbitur	Number of barbiturate groups	C1C(=O)NC(=O)NC1=O	C1C(=O)NC(=O)NC1=O
74	fr_urea	Number of urea groups	C(=O)(-N)-N	C(=O)(-N)-N	Includes cyclic ureas, hydroxyureas, barbiturates, etc.
75	fr_term_acetylene	Number of terminal acetylenes	C#[CH]	C#[CH]
76	fr_imidazole	Number of imidazole rings	n1cncc1	n1cncc1	Includes bicyclics
77	fr_furan	Number of furan rings	o1cccc1	o1cccc1	Includes bicyclics
78	fr_thiophene	Number of thiophene rings	s1cccc1	s1cccc1	Includes bicyclics
79	fr_thiazole	Number of thiazole rings	c1scnc1	c1scnc1	Includes bicyclics
80	fr_oxazole	Number of oxazole rings	c1ocnc1	c1ocnc1	Includes bicyclics
81	fr_pyridine	Number of pyridine rings	n1ccccc1	n1ccccc1	Includes bicyclics
82	fr_piperdine	Number of piperdine rings	N1CCCCC1	N1CCCCC1
83	fr_piperzine	Number of piperzine rings	N1CCNCC1	N1CCNCC1
84	fr_morpholine	Number of morpholine rings	O1CCNCC1	O1CCNCC1
85	fr_lactam	Number of beta lactams	N1C(=O)CC1	N1C(=O)CC1
86	fr_lactone	Number of cyclic esters (lactones)	[C&R1](=O)[O&R1][C&R1]
87	#fr_intrahbonds	Number of intramolecular H-bonds (o-OH and -C=O) + (o-NH2 and -COOH) + 8-OH/NH2 in quinolones		c1([OH])c(C(=O))aaaa1 or c1([OH])c([NH2])aaaa1 or c1([NH2])c(C(=O)[OH])aaaa1 or n1c2c([OH])cccc2ccc1 or n1c2c([NH2])cccc2ccc1	This is just a guess and may be missing other possible examples
88	fr_tetrazole	Number of tetrazole rings	c1nnnn1	c1nnnn1
89	fr_epoxide	Number of epoxide rings	O1CC1	O1CC1
90	fr_unbrch_alkane	Number of unbranched alkanes of at least 4 members (excludes halogenated alkanes)	[R0;D2][R0;D2][R0;D2][R0;D2]
91	fr_bicyclic	Bicyclic	[R2][R2]
92	fr_benzene	Number of benzene rings	c1ccccc1
93	#############
94	# Phosphates
95	#############
96	fr_phos_acid	Number of phosphoric acid groups	[$(P(=[OX1])([$([OX2H]),$([OX1-]),$([OX2]P)])([$([OX2H]),$([OX1-]),$([OX2]P)])[$([OX2H]),$([OX1-]),$([OX2]P)]),$([P+]([OX1-])([$([OX2H]),$([OX1-]),$([OX2]P)])([$([OX2H]),$([OX1-]),$([OX2]P)])[$([OX2H]),$([OX1-]),$([OX2]P)])]
97	fr_phos_ester	Number of phosphoric ester groups	[$(P(=[OX1])([OX2][#6])([$([OX2H]),$([OX1-]),$([OX2][#6])])[$([OX2H]),$([OX1-]),$([OX2][#6]),$([OX2]P)]),$([P+]([OX1-])([OX2][#6])([$([OX2H]),$([OX1-]),$([OX2][#6])])[$([OX2H]),$([OX1-]),$([OX2][#6]),$([OX2]P)])]
98	#####################
99	# Topliss Metabolism
100	#####################
101	fr_nitro_arom	Number of nitro benzene ring substituents	[$(c1(-[$([NX3](=O)=O),$([NX3+](=O)[O-])])ccccc1)]
102	#fr_nitro_arom	Number of nitro aromatic ring substituents	c-[$([NX3](=O)=O),$([NX3+](=O)[O-])]
103	fr_nitro_arom_nonortho	Number of non-ortho nitro benzene ring substituents	[$(c1(-[$([NX3](=O)=O),$([NX3+](=O)[O-])])ccccc1);!$(cc-!:*)]
104	fr_dihydropyridine	Number of dihydropyridines	[$([NX3H1]1-C=C-C-C=C1),$([Nv3]1=C-C-C=C-C1),$([Nv3]1=C-C=C-C-C1),$([NX3H1]1-C-C=C-C=C1)]
105	#fr_readily_oxidized	Number of readily oxidized moieties: thiols+dihydropyridines
106	fr_phenol_noOrthoHbond	Number of phenolic OH excluding ortho intramolecular Hbond substituents	[$(c1(-[OX2H])ccccc1);!$(cc-!:[CH2]-[OX2H]);!$(cc-!:C(=O)[O;H1,-]);!$(cc-!:C(=O)-[NH2])]
107	fr_Al_OH_noTert	Number of aliphatic hydroxyl groups excluding tert-OH	[$(C-[OX2H]);!$([CX3](-[OX2H])=[OX1]);!$([CD4]-[OX2H])]
108	fr_benzodiazepine	Number of benzodiazepines with no additional fused rings	[c&R2]12[c&R1][c&R1][c&R1][c&R1][c&R2]1[N&R1][C&R1][C&R1][N&R1]=[C&R1]2
109	fr_para_hydroxylation	Number of para-hydroxylation sites	[$([cH]1[cH]cc(c[cH]1)~[$([#8,$([#8]~[H,c,C])])]),$([cH]1[cH]cc(c[cH]1)~[$([#7X3,$([#7](~[H,c,C])~[H,c,C])])]),$([cH]1[cH]cc(c[cH]1)-!:[$([NX3H,$(NC(=O)[H,c,C])])])]	na	Includes benzofuran and benzimidazole
110	#fr_para_hydroxylation	Number of para-hydroxylation sites	[$([cH]1[cH]cc(c[cH]1)-!:[$([OX2,$(O-[H,c,C])])]),$([cH]1[cH]cc(c[cH]1)-!:[$([NX3,$(N([H,c,C])-[H,c,C])])]),$([cH]1[cH]cc(c[cH]1)-!:[$([NX3H,$(NC(=O)[H,c,C])])])]
111	fr_allylic_oxid	Number of allylic oxidation sites excluding steroid dienone	[$(C=C-C);!$(C=C-C-[N,O,S]);!$(C=C-C-C-[N,O]);!$(C12=CC(=O)CCC1C3C(C4C(CCC4)CC3)CC2)]
112	fr_aryl_methyl	Number of aryl methyl sites for hydroxylation	[$(a-[CH3]),$(a-[CH2]-[CH3]),$(a-[CH2]-[CH2]~[!N;!O]);!$(a(:a!:*):a!:*)]
113	fr_Ndealkylation1	Number of XCCNR groups	[$(N(-[CH3])-C-[$(C~O),$(C-a),$(C-N),$(C=C)]),$(N(-[CH2][CH3])-C-[$(C~O),$(C-a),$(C-N),$(C=C)])]
114	fr_Ndealkylation2	Number of tert-alicyclic amines (no heteroatoms, not quinine-like bridged N)	[$([N&R1]1(-C)CCC1),$([N&R1]1(-C)CCCC1),$([N&R1]1(-C)CCCCC1),$([N&R1]1(-C)CCCCCC1),$([N&R1]1(-C)CCCCCCC1)]
115	fr_alkyl_carbamate	Number of alkyl carbamates (subject to hydrolysis)	C[NH1]C(=O)OC
116	fr_ketone_Topliss	Number of ketones excluding diaryl, a,b-unsat. dienones, heteroatom on Calpha	[$([CX3](=[OX1])(C)([c,C]));!$([CX3](=[OX1])([CH1]=C)[c,C])]
117	fr_ArN	Number of N functional groups attached to aromatics	[$(a-[NX3H2]),$(a-[NH1][NH2]),$(a-C(=[OX1])[NH1][NH2]),$(a-C(=[NH])[NH2])]
118	fr_HOCCN	Number of C(OH)CCN-Ctert-alkyl or C(OH)CCNcyclic	[$([OX2H1][CX4][CX4H2][NX3&R1]),$([OH1][CX4][CX4H2][NX3][CX4](C)(C)C)]
119	###############
120	# Toxicophores
121	###############