1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
|
#!/usr/bin/python
#
# * This library is free software; you can redistribute it and/or
# * modify it under the terms of the GNU Lesser General Public
# * License as published by the Free Software Foundation; either
# * version 2.1 of the License, or (at your option) any later version.
# *
# * This library is distributed in the hope that it will be useful,
# * but WITHOUT ANY WARRANTY; without even the implied warranty of
# * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# * Lesser General Public License for more details.
#
#propka3.0, revision 182 2011-08-09
#-------------------------------------------------------------------------------------------------------
#-- --
#-- PROPKA: A PROTEIN PKA PREDICTOR --
#-- --
#-- VERSION 3.0, 01/01/2011, COPENHAGEN --
#-- BY MATS H.M. OLSSON AND CHRESTEN R. SONDERGARD --
#-- --
#-------------------------------------------------------------------------------------------------------
#
#
#-------------------------------------------------------------------------------------------------------
# References:
#
# Very Fast Empirical Prediction and Rationalization of Protein pKa Values
# Hui Li, Andrew D. Robertson and Jan H. Jensen
# PROTEINS: Structure, Function, and Bioinformatics 61:704-721 (2005)
#
# Very Fast Prediction and Rationalization of pKa Values for Protein-Ligand Complexes
# Delphine C. Bas, David M. Rogers and Jan H. Jensen
# PROTEINS: Structure, Function, and Bioinformatics 73:765-783 (2008)
#
# PROPKA3: Consistent Treatment of Internal and Surface Residues in Empirical pKa predictions
# Mats H.M. Olsson, Chresten R. Sondergard, Michal Rostkowski, and Jan H. Jensen
# Journal of Chemical Theory and Computation, 7, 525-537 (2011)
#-------------------------------------------------------------------------------------------------------
import sys
from .lib import residueList, atomList, pka_print
# NOTE:
# The sole purpose of this module it to set up a 'corresponding-atoms-dictionary',
# which is used for the overlap procedure. The first loop sets up all back-bone
# atoms for all residue types and 'CB' for all residue-type pairs not involving GLY.
# The second loop sets all atoms for self-residue overlap, i.e. ASP-ASP, VAL-VAL.
# The final section sets up the remaining residue-pair specific corresponding atoms
# for the side-chain. The resulting dictionary might not be complete, or agree with
# what you expect for the moment; feel free to change it accordingly.
def makeCorrespondingAtomNames():
"""
setting up a dictionary to define 'corresponding atoms' between two residues for 'overlap'
"""
# getting list of all atoms
resNames = residueList("standard")
names = {}
# ----- back-bone & 'CB' section -----
# simplifying the setup by including back-bone and 'CB' with this loop
for resName1 in resNames:
names[resName1] = {}
for resName2 in resNames:
names[resName1][resName2] = [['N', 'N'],
['CA', 'CA'],
['C', 'C'],
['O', 'O']]
if resName1 != "GLY" and resName2 != "GLY":
names[resName1][resName2].append(['CB', 'CB'])
# ----- self-overlap section -----
# setting up all atoms for self-comparison
for resName in resNames:
atmNames = atomList(resName)
for atmName in atmNames:
if atmName not in ['N', 'CA', 'CB', 'C', 'O']:
names[resName][resName].append([atmName, atmName])
# ----- side-chain section -----
# side-chains left to consider (sorted alphabetically):
# ['ARG', 'ASN', 'ASP', 'CYS', 'GLN', 'GLU', 'HIS', 'ILE', 'LEU', 'LYS', 'MET', 'PHE', 'PRO', 'SER', 'THR', 'TRP', 'TYR', 'VAL']
# ARG
# None
# ASN
str1 = "ASN CG"
str2 = "ARG CG"
extendCorrespondingAtomsDictionary(names, str1, str2)
# ASP
str1 = "ASP CG"
str2 = "ARG CG"
extendCorrespondingAtomsDictionary(names, str1, str2)
str1 = "ASP OD1 OD2"
str2 = "ASN OD1 ND2"
extendCorrespondingAtomsDictionary(names, str1, str2)
# CYS
# None
# GLN
str1 = "GLN CG CD"
str2 = "ARG CG CD"
extendCorrespondingAtomsDictionary(names, str1, str2)
str1 = "GLN CG"
str2 = "ASN CG"
extendCorrespondingAtomsDictionary(names, str1, str2)
str1 = "GLN CG"
str2 = "ASP CG"
extendCorrespondingAtomsDictionary(names, str1, str2)
# GLU
# HIS
# ILE
# LEU
# LYS
# MET
# PHE
# PRO
# SER
# THR
# TRP
# TYR
str1 = "TYR CG"
str2 = "LYS CG"
extendCorrespondingAtomsDictionary(names, str1, str2)
# VAL
return names
def extendCorrespondingAtomsDictionary(names, str1, str2):
"""
extends the pairs based on list1 & list2
"""
list1 = str1.split()
list2 = str2.split()
for i in range(1, len(list1)):
names[list1[0]][list2[0]].append([list1[i], list2[i]])
names[list2[0]][list1[0]].append([list2[i], list1[i]])
return None
def main():
"""
Simple check on the corresponding atoms-dictionary
"""
corresponding_atoms = makeCorrespondingAtomNames()
resNames = residueList("standard")
for resName1 in resNames:
for resName2 in resNames:
str = "%s %s \n" % (resName1, resName2)
for i in range(len(corresponding_atoms[resName1][resName2])):
name1, name2 = corresponding_atoms[resName1][resName2][i]
str += " %-3s %-3s" % (name1, name2)
name1, name2 = corresponding_atoms[resName2][resName1][i]
str += "%-5s %-3s %-3s\n" % (" ", name1, name2)
pka_print(str)
if resName1 == resName2:
break
if __name__ == '__main__': main()
|
