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
|
# 输入残基列表,返回原子实例
def getAtoms(residue_list, atom_name="CA"):
'''
:param residue_list: list;残基列表
:param atom_name: string;获取的原子名,如CA,CB,O
:return: list;原子实例
'''
residuedatas = []
# 剔除异质残基
for residue in residue_list:
residue_id = residue.get_id()
# ('H_ CD', 801, ' ')
hetfield = residue_id[0]
# 确认其是否是异质残基
if hetfield[0] != "H" and hetfield[0] != "W":
if residue.has_id(atom_name):
# 获取残基编号
residuedatas.append(residue[atom_name])
return residuedatas
# 输入原子对,返回距离数组
def getDistance(atom_pairs):
'''
获得距离的数组
:param atom_pairs:list;原子对
:return: list;距离数组
'''
import itertools
atom_pairs = list(itertools.combinations(atom_pairs, 2))
distances = []
for i in atom_pairs:
distances.append(i[0] - i[1])
return distances
# 统计距离
def sumCutoffDistance(distances, distance):
'''
获取距离对
:param distances:list;距离数组
:param distance:float;阈值距离
:return:int;返回数目
'''
import numpy as np
j = np.array(distances)
return sum(j < distance)
def frequency(pdb):
from Bio.PDB.PDBParser import PDBParser
from Bio.PDB.Selection import unfold_entities
parser = PDBParser(PERMISSIVE=1)
structure_id = pdb
filename = "pdb/" + pdb + ".pdb"
structure = parser.get_structure(structure_id, filename)
model = structure[0]
chain = model["A"]
residue_list = unfold_entities(chain, "R")
atom_pairs = getAtoms(residue_list, "CA")
distances = getDistance(atom_pairs)
return sumCutoffDistance(distances, 50) / len(distances)
def frequences(pdb, distance_min, distance_max, distance_step):
'''
获取频率
:param pdb:PDB_id
:param distance_min:最小值(埃)
:param distance_max: 最大值(埃)
:param distance_step: 步长(埃)
:return:频率数组
'''
from Bio.PDB.PDBParser import PDBParser
from Bio.PDB.Selection import unfold_entities
import numpy as np
parser = PDBParser(PERMISSIVE=1)
structure_id = pdb
filename = "pdb/" + pdb + ".pdb"
structure = parser.get_structure(structure_id, filename)
model = structure[0]
chain = model["A"]
residue_list = unfold_entities(chain, "R")
atom_pairs = getAtoms(residue_list, "CA")
distances = getDistance(atom_pairs)
totals = len(distances)
frequences = []
for i in np.arange(distance_min, distance_max + distance_step, distance_step):
frequences.append(sumCutoffDistance(distances, i) / totals)
return frequences
|