##############################################################################
#                                                                            #
#                   Open Babel file: phmodel.txt                             #
#                                                                            #
#  Copyright (c) 1998-2001 by OpenEye Scientific Software, Inc.              #
#  Some portions Copyright (c) 2001-2003 by Geoffrey R. Hutchison            #
#  Part of the Open Babel package, under the GNU General Public License (GPL)#
#                                                                            #
#  pH model data (used by phmodel.cpp:OBPhModel)                             #
#                                                                            #
# TRANSFORM: chemical transforms can be used to modify formal charges, bond  #
#            orders, and to delete atoms (i.e hydrogens). Changes are applied#
#        to vector bound atoms (use the [:#] SMARTS notation) and bonds      #
#            between vector bound atoms.                                     #
# SEEDCHARGE: used to seed partial charges.  Seed partial charges            #
#             are used as initial values in Gasteiger charge calculation     #
#                                                                            #
##############################################################################

#carboxylic acid							# pKa
#TRANSFORM O=CO[#1:1] >> O=CO						4.0 # pKa from acid (AH)
TRANSFORM O=C[OD1-0:1] >> O=C[O-:1]					4.0 # pKa from acid (AH)

#uncomment for vinylogous carboxylic acids (e.g. ascorbic acid)
TRANSFORM [O:1]=[C:2][C:3]=[C:4][O:5] >> [O-:1][C:2]=[C:3][C:4]=[O:5]	4.0 # pKa from acid (AH)

#charged amine
TRANSFORM [N^3;!$(N~[!#6;!#1]):1] >> [N+:1]				10.0 # pKa from conjugated acid (BH+)

#imidazole: note pKa=7.0
#if you uncomment this, also uncomment the seedcharge statement below
TRANSFORM [nD2:1]1c[nH]cc1 >> [n+:1]1c[nH]cc1				7.0

#imine
TRANSFORM [ND3+0:1]=[#6] >> [ND3+:1]=[#6]				4.0 # pKa from conjugated acid (BH+)

#tetrazole
TRANSFORM [nD2:1]([#1:2])1[nD2-0][nD2-0][nD2-0]c1 >> [n-:1]1nnnc1	4.89 #pKa from acid (AH)
TRANSFORM [nD2-0]1[nD2:1]([#1:2])[nD2-0][nD2-0]c1 >> n1[n-:1]nnc1	4.89 #pKa from acid (AH)
TRANSFORM [nD2-0:1]1[nD2-0][nD2-0][nD2-0]c1 >> [n-:1]1nnnc1		4.89 #pKa from acid (AH)

#azide
TRANSFORM [ND1:1]=[ND2:2]=A >> [N-:1]=[N+:2]=A				1E+10 # always apply transformation
TRANSFORM [ND2:1]=[ND2:2]=A >> N=[N+:2]=A				1E+10 # always apply this transformation

#hydroxamic acid
#TRANSFORM O=CN[OD1-0:1][#1:2] >> O=CN[O-:1]				8.0
TRANSFORM O=CN[OD1-0:1]     >> O=CN[O-:1]				8.0

#sulfinic acid
TRANSFORM [SD3](=O)[OD1:1]   >> [SD3](=O)[O-:1]				2.0
TRANSFORM [SD3](=O)[O:1][#1:2] >> [SD3](=O)[O-:1]			2.0

#sulfonic acid
TRANSFORM [SD4]([!D1])(=O)(=O)[OD1:1] >> [SD4]([!D1])(=O)(=O)[O-:1]	-2.6
TRANSFORM [SD4]([!D1])(=O)(=O)[O:1][#1:2] >> [SD4]([!D1])(=O)(=O)[O-:1]	-2.6
#sulfuric acid (same as sulfonic acid...)
#TRANSFORM [SD4]([!D1])(=O)(=O)[OD1:1] >> [SD4]([!D1])(=O)(=O)[O-:1]
#TRANSFORM [SD4]([!D1])(=O)(=O)[O:1][#1:2] >> [SD4]([!D1])(=O)(=O)[O-:1]

#guanidine or amidine
TRANSFORM [#6^2+0:1](~[N^2])(~[N^2])* >> [#6+:1](~N)(~N)*		12.5

#phosphate ester
TRANSFORM [PD4](=O)([OD2])([OD2])[OD1:1] >> [PD4](=O)([OD2])([OD2])[O-:1]	2.0
#TRANSFORM [PD4](=O)([OD2])([OD2])[OD1:1][#1:2] >> [PD4](=O)([OD2])([OD2])[O-:1]	2.0

#phosphoric acid
#TRANSFORM O=P([!D1])([O:1][#1:2])[O:3][#1:4] >> O=P([*D2,*D3])([O:1])[O:3]	2.12
TRANSFORM O=P([!D1])([O:1][#1:2])[OD1]       >> O=P([!D1])([O:1])O		2.12
TRANSFORM O=P([*D2,*D3])([OD1:1])[OD1:2] >> O=P([*D2,*D3])([O-:1])[O-:2]	2.12
#phosphate

#
#	Amino acids
#									pKa sidechain
# aspartic acid
#TRANSFORM O=CC(N)CC(=O)O[#1:1] >> O=CC(N)CC(=O)O			3.8
TRANSFORM O=C(O)C(N)CC(=O)[OD1:1] >> O=C(O)C(N)CC(=O)[O-:1]		3.8 
TRANSFORM O=C(NCC=O)C(N)CC(=O)[OD1:1] >> O=C(NCC=O)C(N)CC(=O)[O-:1]     3.8 

# glutamic acid
#TRANSFORM O=CC(N)CCC(=O)O[#1:1] >> O=CC(N)CCC(=O)O		        4.3
TRANSFORM O=C(O)C(N)CCC(=O)[OD1:1] >> O=C(O)C(N)CCC(=O)[O-:1]		5.0
TRANSFORM O=C(NCC=O)C(N)CCC(=O)[OD1:1] >> O=C(NCC=O)C(N)CCC(=O)[O-:1]	5.0

# arginine
TRANSFORM O=C(O)C(N)CCCNC(N)=[N:1] >> O=C(O)C(N)CCCNC(N)=[N+:1] 	12.0
TRANSFORM O=C(NCC=O)C(N)CCCNC(N)=[N:1] >> O=C(NCC=O)C(N)CCCNC(N)=[N+:1] 12.0

# lysine
TRANSFORM O=C(O)C(N)CCCC[N:1] >> O=C(O)C(N)CCCC[N+:1] 			10.5
TRANSFORM O=C(NCC=O)C(N)CCCC[N:1] >> O=C(NCC=O)C(N)CCCC[N+:1] 	        10.5

# histidine
TRANSFORM O=C(O)C(N)Cc1nc[n:1]c1  >> O=C(O)C(N)Cc1nc[n+:1]c1            6.08
TRANSFORM O=C(NCC=O)C(N)Cc1nc[n:1]c1  >> O=C(NCC=O)C(N)Cc1nc[n+:1]c1    6.08

# cysteine
TRANSFORM O=C(O)C(N)C[S:1]  >> O=C(O)C(N)C[S-:1]			 8.28
TRANSFORM O=C(NCC=O)C(N)C[S:1]  >> O=C(NCC=O)C(N)C[S-:1]		 8.28

# tyrosine
TRANSFORM O=C(O)C(N)Cc1ccc([O:1])cc1  >> O=C(O)C(N)Cc1ccc([O-:1])cc1	        10.1
TRANSFORM O=C(NCC=O)C(N)Cc1ccc([O:1])cc1  >> O=C(NCC=O)C(N)Cc1ccc([O-:1])cc1    10.1

# old:
# histidine
#TRANSFORM [nD2:1]1c[nD2]cc1 >> [n+:1]1c[nD2]cc1
# uncomment for tryptophan
# TRANSFORM [nD2:1]1cccc1 >> [n+:1]1cccc1
#, histidine pKa=6.0


#
#	Seeding partial charges for gasteiger calculation
#
#default charges
SEEDCHARGE [#6+]	1.0
SEEDCHARGE [#6-]	-1.0
SEEDCHARGE [#7+]	1.0
SEEDCHARGE [#7-]	-1.0
SEEDCHARGE [#8+]	1.0
SEEDCHARGE [#8-]	-1.0
SEEDCHARGE [#15+]	1.0
SEEDCHARGE [#15-]	-1.0
SEEDCHARGE [#16+]	1.0
SEEDCHARGE [#16-]	-1.0

#charges spread over multiple atoms
#carboxylic acid
SEEDCHARGE	C(=O)[O-]		0.0	-0.5	-0.5

#amines
SEEDCHARGE	[N+]		1.0
#tetrazole
SEEDCHARGE	[nD2]1[nD2][nD2][nD2]c1	-0.2	-0.2	-0.2   -0.2    -0.2

#sulfinic
SEEDCHARGE	[SD3](=O)[O-]		0.0	-0.5	-0.5
#sulfuric acid
SEEDCHARGE	[SD4](=O)(=O)([O-])[OH1]	0.0	-0.33	-0.33	-0.33	0.0
#sulfonic acid
SEEDCHARGE	[SD4]([D2])(~[OD1])(~[OD1])~[OD1]	0.0	0.0	-0.33	-0.33	-0.33

#guanidine
SEEDCHARGE	[#7^2]~[C^2](~[N^2])~[N^2]	0.33	0.0	0.33	0.33

#amidine
SEEDCHARGE	[#6]~[C^2](~[N^2])~[N^2]	0.0	0.0	0.5	0.5

#phosphoate ester
SEEDCHARGE	[PD4](=O)([OD2])([OD2])[OD1]	0.0	-0.5	0.0	0.0	-0.5
#phosphoric acid
SEEDCHARGE	O=P([!D1])([O-])[O-]	-0.66	0.0	0.0	-0.66	-0.66


#phosphuric acid
SEEDCHARGE	P(=O)(=O)([O-])[O-]	0.0	0.0	0.0     -0.5	-0.5
#phosphonic acid
SEEDCHARGE	[#6]P(~[OD1])(~[OD1])~[OD1]	0.0	0.0	-0.33  -0.33 -0.33

#hydroxamic acid
SEEDCHARGE	O=C[N;!$(N(C=O)C=O)][OD1]	-0.5	0.0	0.0	-0.5
SEEDCHARGE	O=CN([OD1])NC=O		-0.33	0.0	0.0	-0.33	0.0 0.0	-0.33

#imidazole: note pKa=7.0, histidine pKa=6.0
#if you uncomment this, also uncomment the transform statement above
SEEDCHARGE	[n+H]1c[nH]cc1		0.5	0.0	0.5	0.0	0.0