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
|
# File download/unzip written 2012 by Lenna X. Peterson (arklenna@gmail.com)
# Dictionary extraction written 2011 by Hongbo Zhu
#
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
"""Download PDB Chemical Component Dictionary and generate dict.
Download and parse PDB Chemical Component Dictionary,
then write out dict for to_one_letter_code.
"""
import gzip
import inspect
import os
import warnings
from urllib.request import urlopen
url = "ftp://ftp.wwpdb.org/pub/pdb/data/monomers/components.cif.gz"
# extract name of gzip file
gzname = os.path.basename(url)
# extract name of cif file (split by sep, remove last, rejoin)
cifname = os.extsep.join(gzname.split(os.extsep)[:-1])
url_handle = urlopen(url)
with open(gzname, "wb") as gzh:
print("Downloading file... (approx. 29 MB)")
while True:
data = url_handle.read(1024)
if len(data) == 0:
break
gzh.write(data)
# size as of 13 April 2012
if os.path.getsize(gzname) < 29944258:
warnings.warn("ERROR: Downloaded file is too small", RuntimeWarning)
fh = gzip.open(gzname, "rb")
# write extracted file to disk (not necessary)
# with open(cifname, 'wb') as cifh:
# print("Extracting file...")
# cifh.write(fh.read())
# The following code written by Hongbo Zhu
# generate three_to_one_dict
# two records in PDB Chemical Component Dictionary are parsed to
# generate the dictionary:
# _chem_comp.one_letter_code
# _chem_comp.three_letter_code
three_to_one_buf = [] # all three-letter codes
three_to_one_buf_noq = [] # only those with non-'?' one-letter codes
current_line = "to_one_letter_code = {"
current_line_noq = "to_one_letter_code = {"
found_one = False # found one-letter code
found_three = False # found three-letter code
counter = 0
counter_noq = 0
line = fh.readline()
while line:
if line.startswith("_chem_comp.one_letter_code"):
one = line.strip().split()[-1]
found_one = True
if line.startswith("_chem_comp.three_letter_code"):
three = "%-3s" % (line.strip().split()[-1],) # make it three-letter
found_three = True
if found_one and found_three:
if counter % 5 == 0:
three_to_one_buf.append(f"{current_line}\n")
current_line = " "
current_line = f"{current_line}'{three}':'{one}',"
counter += 1
if one != "?":
if counter_noq % 5 == 0:
three_to_one_buf_noq.append(f"{current_line_noq}\n")
current_line_noq = " "
current_line_noq = f"{current_line_noq}'{three}':'{one}',"
counter_noq += 1
found_one = False
found_three = False
line = fh.readline()
if len(current_line) < 5:
three_to_one_buf[-1] = three_to_one_buf[:-1] # remove the last comma
three_to_one_buf.append("}")
else:
three_to_one_buf.append("%s }" % (current_line[:-1]))
if len(current_line_noq) < 5:
three_to_one_buf_noq[-1] = three_to_one_buf_noq[:-1]
three_to_one_buf_noq.append("}")
else:
three_to_one_buf_noq.append("%s }" % (current_line_noq[:-1]))
# Find path of current script
_scriptPath = os.path.abspath(os.path.split(inspect.getfile(inspect.currentframe()))[0])
# Path to SCOP module
_rafPath = os.path.normpath(os.path.join(_scriptPath, "..", "..", "Bio", "SCOP"))
_threeAllPath = os.path.join(_rafPath, "three_to_one_all.py")
_threePath = os.path.join(_rafPath, "three_to_one_dict.py")
# with open(_threeAllPath, 'w') as fh:
# fh.writelines(three_to_one_buf)
with open(_threePath, "w") as fh:
fh.writelines(three_to_one_buf_noq)
|
