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
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright 2018 João Pedro Rodrigues
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
Deletes all atoms matching the given element in the PDB file.
Elements are read from the element column.
Usage:
python pdb_delelem.py -<option> <pdb file>
Example:
python pdb_delelem.py -H 1CTF.pdb # deletes all protons
python pdb_delelem.py -N 1CTF.pdb # deletes all nitrogens
python pdb_delelem.py -H,N 1CTF.pdb # deletes all protons and nitrogens
This program is part of the `pdb-tools` suite of utilities and should not be
distributed isolatedly. The `pdb-tools` were created to quickly manipulate PDB
files using the terminal, and can be used sequentially, with one tool streaming
data to another. They are based on old FORTRAN77 code that was taking too much
effort to maintain and compile. RIP.
"""
import os
import sys
__author__ = ["Joao Rodrigues", "Joao M.C. Teixeira"]
__email__ = ["j.p.g.l.m.rodrigues@gmail.com", "joaomcteixeira@gmail.com"]
def check_input(args):
"""Checks whether to read from stdin/file and validates user input/options.
"""
# Defaults
option = ''
fh = sys.stdin # file handle
if not len(args):
# Reading from pipe with default option
if sys.stdin.isatty():
sys.stderr.write(__doc__)
sys.exit(1)
elif len(args) == 1:
# One of two options: option & Pipe OR file & default option
if args[0].startswith('-'):
option = args[0][1:]
if sys.stdin.isatty(): # ensure the PDB data is streamed in
emsg = 'ERROR!! No data to process!\n'
sys.stderr.write(emsg)
sys.stderr.write(__doc__)
sys.exit(1)
else:
if not os.path.isfile(args[0]):
emsg = 'ERROR!! File not found or not readable: \'{}\'\n'
sys.stderr.write(emsg.format(args[0]))
sys.stderr.write(__doc__)
sys.exit(1)
fh = open(args[0], 'r')
elif len(args) == 2:
# Two options: option & File
if not args[0].startswith('-'):
emsg = 'ERROR! First argument is not an option: \'{}\'\n'
sys.stderr.write(emsg.format(args[0]))
sys.stderr.write(__doc__)
sys.exit(1)
if not os.path.isfile(args[1]):
emsg = 'ERROR!! File not found or not readable: \'{}\'\n'
sys.stderr.write(emsg.format(args[1]))
sys.stderr.write(__doc__)
sys.exit(1)
option = args[0][1:]
fh = open(args[1], 'r')
else: # Whatever ...
sys.stderr.write(__doc__)
sys.exit(1)
# Validate option
option_set = set([o.upper().strip() for o in option.split(',') if o.strip()])
if not option_set:
sys.stderr.write('ERROR!! You must provide at least one element name\n')
sys.stderr.write(__doc__)
sys.exit(1)
else:
for elem in option_set:
if len(elem) > 2:
emsg = 'ERROR!! Element name is invalid: \'{}\'\n'
sys.stderr.write(emsg.format(elem))
sys.stderr.write(__doc__)
sys.exit(1)
return (fh, option_set)
def run(fhandle, element_set):
"""
Remove specific atoms matching the given element(s).
This function is a generator.
Parameters
----------
fhandle : a line-by-line iterator of the original PDB file.
element_set : set, list, tuple
The elements to remove.
Yields
------
str (line-by-line)
The PDB lines NOT matching the elements set.
Non-RECORDS lines are yielded as are.
"""
records = ('ATOM', 'HETATM', 'ANISOU')
for line in fhandle:
if line.startswith(records):
if line[76:78].strip() in element_set:
continue
yield line
delete_elements = run
def main():
# Check Input
pdbfh, element_set = check_input(sys.argv[1:])
# Do the job
new_pdb = run(pdbfh, element_set)
try:
_buffer = []
_buffer_size = 5000 # write N lines at a time
for lineno, line in enumerate(new_pdb):
if not (lineno % _buffer_size):
sys.stdout.write(''.join(_buffer))
_buffer = []
_buffer.append(line)
sys.stdout.write(''.join(_buffer))
sys.stdout.flush()
except IOError:
# This is here to catch Broken Pipes
# for example to use 'head' or 'tail' without
# the error message showing up
pass
# last line of the script
# We can close it even if it is sys.stdin
pdbfh.close()
sys.exit(0)
if __name__ == '__main__':
main()
|
