RNADiscrepancy 0.0.2__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- RNADiscrepancy/.test.py.swp +0 -0
- RNADiscrepancy/__init__.py +0 -0
- RNADiscrepancy/measures.py +171 -0
- RNADiscrepancy/references.py +66 -0
- RNADiscrepancy/rna.py +57 -0
- RNADiscrepancy/test.py +61 -0
- RNADiscrepancy/utilities.py +7 -0
- rnadiscrepancy-0.0.2.dist-info/METADATA +63 -0
- rnadiscrepancy-0.0.2.dist-info/RECORD +11 -0
- rnadiscrepancy-0.0.2.dist-info/WHEEL +4 -0
- rnadiscrepancy-0.0.2.dist-info/licenses/LICENSE +17 -0
|
Binary file
|
|
File without changes
|
|
@@ -0,0 +1,171 @@
|
|
|
1
|
+
import math
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
import numpy as np
|
|
5
|
+
from scipy.spatial.transform import Rotation
|
|
6
|
+
|
|
7
|
+
from RNADiscrepancy import references
|
|
8
|
+
from RNADiscrepancy.rna import Atom, Nucleotide
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
def c1prime_distance_difference(pair1, pair2):
|
|
12
|
+
"""Returns the difference in distance between the C1' atoms (connecting sugar to residue) in the two pairs
|
|
13
|
+
always positive
|
|
14
|
+
"""
|
|
15
|
+
|
|
16
|
+
|
|
17
|
+
(nt1_left, nt1_right), (nt2_left, nt2_right) = pair1, pair2
|
|
18
|
+
dist_c1 = abs(nt1_left["C1'"].distance(nt1_right["C1'"]) - nt2_left["C1'"].distance(nt2_right["C2'"]))
|
|
19
|
+
|
|
20
|
+
return dist_c1
|
|
21
|
+
|
|
22
|
+
|
|
23
|
+
def c1prime_translation(pair1, pair2):
|
|
24
|
+
"""
|
|
25
|
+
Here we have to do things in regards to the _left and _right side symmetricaly
|
|
26
|
+
|
|
27
|
+
1'. Use N1/N9 of their reference as (0, 0)
|
|
28
|
+
2'. Rotate to align the first base to the reference (and apply rotation to the pair)
|
|
29
|
+
"""
|
|
30
|
+
|
|
31
|
+
(nt1_left, nt1_right), (nt2_left, nt2_right) = pair1, pair2
|
|
32
|
+
|
|
33
|
+
ref_nt1_left = references.nucleotide[nt1_left.name]
|
|
34
|
+
ref_nt1_right = references.nucleotide[nt1_right.name]
|
|
35
|
+
ref_nt2_left = references.nucleotide[nt2_left.name]
|
|
36
|
+
ref_nt2_right = references.nucleotide[nt2_right.name]
|
|
37
|
+
|
|
38
|
+
#Retrieve position of nucleotide + ref for alignment
|
|
39
|
+
nt1_left_pos = []
|
|
40
|
+
nt1_left_pos_ref = []
|
|
41
|
+
for atom_name, atom in nt1_left.items():
|
|
42
|
+
try:
|
|
43
|
+
nt1_left_pos_ref.append(ref_nt1_left[atom_name].position)
|
|
44
|
+
nt1_left_pos.append(atom.position)
|
|
45
|
+
except KeyError:
|
|
46
|
+
continue
|
|
47
|
+
|
|
48
|
+
nt1_right_pos = []
|
|
49
|
+
nt1_right_pos_ref = []
|
|
50
|
+
for atom_name, atom in nt1_right.items():
|
|
51
|
+
try:
|
|
52
|
+
nt1_right_pos_ref.append(ref_nt1_right[atom_name].position)
|
|
53
|
+
nt1_right_pos.append(atom.position)
|
|
54
|
+
except KeyError:
|
|
55
|
+
continue
|
|
56
|
+
|
|
57
|
+
|
|
58
|
+
nt2_left_pos = []
|
|
59
|
+
nt2_left_pos_ref = []
|
|
60
|
+
for atom_name, atom in nt2_left.items():
|
|
61
|
+
try:
|
|
62
|
+
nt2_left_pos_ref.append(ref_nt2_left[atom_name].position)
|
|
63
|
+
nt2_left_pos.append(atom.position)
|
|
64
|
+
except KeyError:
|
|
65
|
+
continue
|
|
66
|
+
|
|
67
|
+
nt2_right_pos = []
|
|
68
|
+
nt2_right_pos_ref = []
|
|
69
|
+
for atom_name, atom in nt2_right.items():
|
|
70
|
+
try:
|
|
71
|
+
nt2_right_pos_ref.append(ref_nt2_right[atom_name].position)
|
|
72
|
+
nt2_right_pos.append(atom.position)
|
|
73
|
+
except KeyError:
|
|
74
|
+
continue
|
|
75
|
+
|
|
76
|
+
|
|
77
|
+
|
|
78
|
+
nt1_left_rotation = best_rotation(nt1_left_pos_ref, np.array(ref_nt1_left.ribose_fulcrum.position),
|
|
79
|
+
nt1_left_pos, np.array(nt1_left.ribose_fulcrum.position))[0]
|
|
80
|
+
nt1_right_rotation = best_rotation(nt1_right_pos_ref, np.array(ref_nt1_right.ribose_fulcrum.position),
|
|
81
|
+
nt1_right_pos, np.array(nt1_right.ribose_fulcrum.position))[0]
|
|
82
|
+
nt2_left_rotation = best_rotation(nt2_left_pos_ref, np.array(ref_nt2_left.ribose_fulcrum.position),
|
|
83
|
+
nt2_left_pos, np.array(nt2_left.ribose_fulcrum.position))[0]
|
|
84
|
+
nt2_right_rotation = best_rotation(nt2_right_pos_ref, np.array(ref_nt2_right.ribose_fulcrum.position),
|
|
85
|
+
nt2_right_pos, np.array(nt2_right.ribose_fulcrum.position))[0]
|
|
86
|
+
|
|
87
|
+
|
|
88
|
+
c1p_1right = nt1_right["C1'"].position
|
|
89
|
+
c1p_1right = (c1p_1right - np.array(nt1_left.ribose_fulcrum.position)) @ nt1_left_rotation
|
|
90
|
+
c1p_2right = nt2_right["C1'"].position
|
|
91
|
+
c1p_2right = (c1p_2right - np.array(nt2_left.ribose_fulcrum.position)) @ nt2_left_rotation
|
|
92
|
+
c1p_t1 = math.sqrt((c1p_1right[0] - c1p_2right[0])**2 + (c1p_1right[1] - c1p_2right[1])**2)
|
|
93
|
+
|
|
94
|
+
|
|
95
|
+
c1p_1left = nt1_left["C1'"].position
|
|
96
|
+
c1p_1left = (c1p_1left - np.array(nt1_right.ribose_fulcrum.position)) @ nt1_right_rotation
|
|
97
|
+
c1p_2left = nt2_left["C1'"].position
|
|
98
|
+
c1p_2left = (c1p_2left - np.array(nt2_right.ribose_fulcrum.position)) @ nt2_right_rotation
|
|
99
|
+
c1p_t2 = math.sqrt((c1p_1left[0] - c1p_2left[0])**2 + (c1p_1left[1] - c1p_2left[1])**2)
|
|
100
|
+
|
|
101
|
+
|
|
102
|
+
bond_1right = [nt1_right["C1'"].position, nt1_right.ribose_fulcrum.position]
|
|
103
|
+
bond_1right = (bond_1right - np.array(nt1_left.ribose_fulcrum.position)) @ nt1_left_rotation
|
|
104
|
+
bond_2right = [nt2_right["C1'"].position, nt2_left.ribose_fulcrum.position]
|
|
105
|
+
bond_2right = (bond_2right - np.array(nt2_left.ribose_fulcrum.position)) @ nt2_left_rotation
|
|
106
|
+
bond_1right[:, 2:] = 0
|
|
107
|
+
bond_2right[:, 2:] = 0
|
|
108
|
+
output = best_rotation(bond_1right[:2, :], 0, bond_2right[:2, :], 0)
|
|
109
|
+
theta1 = math.acos(output[0][0][0])
|
|
110
|
+
|
|
111
|
+
bond_1left = [nt1_left["C1'"].position, nt1_left.ribose_fulcrum.position]
|
|
112
|
+
bond_1left = (bond_1left - np.array(nt1_right.ribose_fulcrum.position)) @ nt1_right_rotation
|
|
113
|
+
bond_2left = [nt2_left["C1'"].position, nt2_left.ribose_fulcrum.position]
|
|
114
|
+
bond_2left = (bond_2left - np.array(nt2_right.ribose_fulcrum.position)) @ nt2_right_rotation
|
|
115
|
+
bond_1left[:, 2:] = 0
|
|
116
|
+
bond_2left[:, 2:] = 0
|
|
117
|
+
output = best_rotation(bond_1left, 0, bond_2left, 0)
|
|
118
|
+
theta2 = math.acos(output[0][0][0])
|
|
119
|
+
|
|
120
|
+
|
|
121
|
+
return c1p_t1, c1p_t2, theta1, theta2
|
|
122
|
+
|
|
123
|
+
|
|
124
|
+
|
|
125
|
+
|
|
126
|
+
def isodiscrepancy(pair1, pair2):
|
|
127
|
+
"""
|
|
128
|
+
Return IDI between pairs (nt1_left, nt1_right) and (nt2_left, nt2_right)
|
|
129
|
+
it assumes the orientation is to align nt1_left with nt2_left / nt1_right with nt2_right
|
|
130
|
+
|
|
131
|
+
we follow https://doi.org/10.1093/nar/gkp011
|
|
132
|
+
|
|
133
|
+
1) delta c1' distances
|
|
134
|
+
2) align on one N1/N9 and see other C1' translation distance
|
|
135
|
+
3) rotation in plane to orient same second base in relation to first
|
|
136
|
+
"""
|
|
137
|
+
|
|
138
|
+
c1prime_dist_delta = c1prime_distance_difference(pair1, pair2)
|
|
139
|
+
c1prime_t1, c1prime_t2, theta1, theta2 = c1prime_translation(pair1, pair2)
|
|
140
|
+
|
|
141
|
+
return math.sqrt(c1prime_dist_delta**2
|
|
142
|
+
+ (c1prime_t1**2 + c1prime_t2**2)/2
|
|
143
|
+
+ ((2 * theta1)**2 + (2 * theta2)**2)/2
|
|
144
|
+
)
|
|
145
|
+
|
|
146
|
+
def best_rotation(A, center_A, B, center_B):
|
|
147
|
+
A_centered = A - center_A
|
|
148
|
+
B_centered = B - center_B
|
|
149
|
+
rotation, _ = Rotation.align_vectors(A_centered, B_centered)
|
|
150
|
+
rotation = rotation.as_matrix()
|
|
151
|
+
B2A = B_centered @ rotation + center_A
|
|
152
|
+
difference = A_centered - B2A + center_A
|
|
153
|
+
sum_square_error = float(np.sum(difference ** 2))
|
|
154
|
+
RMSD = float(np.sqrt(sum_square_error / len(A)))
|
|
155
|
+
return rotation, B2A, center_A, center_B, sum_square_error, RMSD
|
|
156
|
+
|
|
157
|
+
|
|
158
|
+
def best_mean_centered_rotation(A, B):
|
|
159
|
+
"""Least-squares rigid-body fit transform of two numpy array
|
|
160
|
+
The center of mass of the nucleotide is at (0, 0, 0)
|
|
161
|
+
returns
|
|
162
|
+
rotation : matrix
|
|
163
|
+
B2A : B moved to over A
|
|
164
|
+
mean_A,
|
|
165
|
+
mean_B,
|
|
166
|
+
sum_square_error,
|
|
167
|
+
RMSD
|
|
168
|
+
"""
|
|
169
|
+
mean_A = A.mean(axis=0)
|
|
170
|
+
mean_B = B.mean(axis=0)
|
|
171
|
+
return best_rotation(A, mean_A, B, mean_B)
|
|
@@ -0,0 +1,66 @@
|
|
|
1
|
+
from RNADiscrepancy import rna
|
|
2
|
+
|
|
3
|
+
"""
|
|
4
|
+
Position of idealized nucleotides heavy atoms with center at (0,0,0)
|
|
5
|
+
It follows FR3D standard orientation with the Watson-Crick edge in
|
|
6
|
+
the positive x and y quadrant.
|
|
7
|
+
"""
|
|
8
|
+
nucleotide = {}
|
|
9
|
+
|
|
10
|
+
ref_heavy_atoms_positions = {
|
|
11
|
+
'A' : {
|
|
12
|
+
'N9' : ([-1.110515, -1.823319, 0.0] ),
|
|
13
|
+
'C4' : ([0.007975, -1.020192, 0.0] ),
|
|
14
|
+
'N3' : ([1.298514, -1.383716, 0.0] ),
|
|
15
|
+
'N1' : ([1.754329, 1.001072, 0.0] ),
|
|
16
|
+
'C6' : ([0.453129, 1.320188, 0.0] ),
|
|
17
|
+
'N6' : ([0.092589, 2.623715, 0.0] ),
|
|
18
|
+
'C8' : ([-2.200426, -0.989732, 0.0] ),
|
|
19
|
+
'C5' : ([-0.504186, 0.282479, 0.0] ),
|
|
20
|
+
'C2' : ([2.092069, -0.307357, 0.0] ),
|
|
21
|
+
'N7' : ([-1.883477, 0.296861, 0.0] ),
|
|
22
|
+
"C1'" :([ -1.110515, (-1.823319 - 1.48), 0.000000])
|
|
23
|
+
},
|
|
24
|
+
'C' : {
|
|
25
|
+
'N1' : ([-0.380579, -1.484583, 0.0] ),
|
|
26
|
+
'C2' : ([0.908756, -0.88533, 0.0] ),
|
|
27
|
+
'O2' : ([1.888871, -1.605366, 0.0] ),
|
|
28
|
+
'N3' : ([0.931558, 0.493192, 0.0] ),
|
|
29
|
+
'C4' : ([-0.197209, 1.170043, 0.0] ),
|
|
30
|
+
'N4' : ([-0.099223, 2.524619, 0.0] ),
|
|
31
|
+
'C6' : ([-1.542632, -0.786228, 0.0] ),
|
|
32
|
+
'C5' : ([-1.509542, 0.573654, 0.0] ),
|
|
33
|
+
"C1'" : ( [ -0.380579, (-1.484583-1.48), 0.000000] )
|
|
34
|
+
},
|
|
35
|
+
'G' : {
|
|
36
|
+
'N9' : ([-1.45668, -1.711888, 0.0] ),
|
|
37
|
+
'C4' : ([-0.339093, -0.921183, 0.0] ),
|
|
38
|
+
'N3' : ([0.947138, -1.370892, 0.0] ),
|
|
39
|
+
'N1' : ([1.440727, 0.946157, 0.0] ),
|
|
40
|
+
'C6' : ([0.110442, 1.47918, 0.0] ),
|
|
41
|
+
'O6' : ([-0.059694, 2.682325, 0.0] ),
|
|
42
|
+
'C8' : ([-2.54532, -0.870005, 0.0] ),
|
|
43
|
+
'C5' : ([-0.831466, 0.385014, 0.0] ),
|
|
44
|
+
'C2' : ([1.802732, -0.378447, 0.0] ),
|
|
45
|
+
'N7' : ([-2.208072, 0.408244, 0.0] ),
|
|
46
|
+
'N2' : ([3.139287, -0.648506, 0.0] ),
|
|
47
|
+
"C1'" : ( [ -1.456680, (-1.711888-1.48), 0.000000])
|
|
48
|
+
},
|
|
49
|
+
'U' : {
|
|
50
|
+
'N1' : ([-0.32642, -1.514422, 0.0] ),
|
|
51
|
+
'C2' : ([0.933866, -0.925171, 0.0] ),
|
|
52
|
+
'O2' : ([1.96607, -1.562816, 0.0] ),
|
|
53
|
+
'N3' : ([0.868896, 0.45947, 0.0] ),
|
|
54
|
+
'C4' : ([-0.266417, 1.293935, 0.0] ),
|
|
55
|
+
'O4' : ([-0.149264, 2.505638, 0.0] ),
|
|
56
|
+
'C6' : ([-1.504181, -0.804727, 0.0] ),
|
|
57
|
+
'C5' : ([-1.52255, 0.548093, 0.0] ),
|
|
58
|
+
"C1'" : ([ -0.326420, (-1.514422-1.48), 0.000000])
|
|
59
|
+
}
|
|
60
|
+
}
|
|
61
|
+
|
|
62
|
+
for nt_name, v in ref_heavy_atoms_positions.items():
|
|
63
|
+
atoms = []
|
|
64
|
+
for atom_name, pos in v.items():
|
|
65
|
+
atoms.append(rna.Atom(atom_name, atom_name[0], *pos) )
|
|
66
|
+
nucleotide[nt_name] = rna.Nucleotide(nt_name, atoms)
|
RNADiscrepancy/rna.py
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
1
|
+
import math
|
|
2
|
+
|
|
3
|
+
class Atom:
|
|
4
|
+
def __init__(self, name, element, x, y, z):
|
|
5
|
+
self.name = name
|
|
6
|
+
self.element = element
|
|
7
|
+
self.x = x
|
|
8
|
+
self.y = y
|
|
9
|
+
self.z = z
|
|
10
|
+
|
|
11
|
+
@property
|
|
12
|
+
def position(self):
|
|
13
|
+
return self.x, self.y, self.z
|
|
14
|
+
|
|
15
|
+
def distance(self, other):
|
|
16
|
+
x, y, z = self.position
|
|
17
|
+
x2, y2, z2 = other.position
|
|
18
|
+
return math.sqrt((x - x2)**2 + (y - y2)**2 + (z - z2)**2)
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
def __eq__(self, other):
|
|
22
|
+
if isinstance(other, self.__class__):
|
|
23
|
+
return self.name == other.name
|
|
24
|
+
else:
|
|
25
|
+
return False
|
|
26
|
+
|
|
27
|
+
def __neq__(self, other):
|
|
28
|
+
return not self.__eq__(other)
|
|
29
|
+
|
|
30
|
+
def __str__(self):
|
|
31
|
+
return f"Atom class: {self.name}, {self.element}, {self.x}, {self.y}, {self.z}"
|
|
32
|
+
|
|
33
|
+
def __repr__(self):
|
|
34
|
+
return f"Atom class: {self.name}, {self.element}, {self.x}, {self.y}, {self.z}"
|
|
35
|
+
|
|
36
|
+
|
|
37
|
+
|
|
38
|
+
class Nucleotide(dict):
|
|
39
|
+
def __init__(self, name, atoms):
|
|
40
|
+
self.name = name
|
|
41
|
+
for atom in atoms:
|
|
42
|
+
self[atom.name] = atom
|
|
43
|
+
|
|
44
|
+
if name not in ('A', 'C', 'G', 'U'):
|
|
45
|
+
raise Exception(f"WTF this should be ACGU not {name}")
|
|
46
|
+
|
|
47
|
+
#Set fulcrum
|
|
48
|
+
if name in ('C', 'U'):
|
|
49
|
+
try:
|
|
50
|
+
self.ribose_fulcrum = self['N1']
|
|
51
|
+
except KeyError:
|
|
52
|
+
self.ribose_fulcrum = None
|
|
53
|
+
elif name in ('A', 'G'):
|
|
54
|
+
try:
|
|
55
|
+
self.ribose_fulcrum = self['N9']
|
|
56
|
+
except KeyError:
|
|
57
|
+
self.ribose_fulcrum = None
|
RNADiscrepancy/test.py
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
1
|
+
from collections import defaultdict
|
|
2
|
+
import pickle
|
|
3
|
+
|
|
4
|
+
|
|
5
|
+
import measures
|
|
6
|
+
import rna
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
def read_samples(path):
|
|
10
|
+
with open(path, 'rb') as f:
|
|
11
|
+
data = pickle.load(f)
|
|
12
|
+
loaded_data = defaultdict(list)
|
|
13
|
+
|
|
14
|
+
for (lw, nt1, nt2), values in data.items():
|
|
15
|
+
if not (nt1 in ('A', 'C', 'G', 'U') and nt2 in ('A', 'C', 'G', 'U')):
|
|
16
|
+
continue
|
|
17
|
+
for instance in values:
|
|
18
|
+
atoms = []
|
|
19
|
+
for name, element, x, y, z in zip(*(instance[0][k] for k in ('atoms_name', 'atoms_element', 'atoms_x', 'atoms_y', 'atoms_z'))):
|
|
20
|
+
atoms.append(rna.Atom(name, element, x, y, z))
|
|
21
|
+
nt1_nuc = rna.Nucleotide(nt1, atoms)
|
|
22
|
+
|
|
23
|
+
atoms = []
|
|
24
|
+
for name, element, x, y, z in zip(*(instance[1][k] for k in ('atoms_name', 'atoms_element', 'atoms_x', 'atoms_y', 'atoms_z'))):
|
|
25
|
+
atoms.append(rna.Atom(name, element, x, y, z))
|
|
26
|
+
nt2_nuc = rna.Nucleotide(nt2, atoms)
|
|
27
|
+
|
|
28
|
+
if nt1_nuc.ribose_fulcrum is None or nt2_nuc.ribose_fulcrum is None:
|
|
29
|
+
continue
|
|
30
|
+
|
|
31
|
+
loaded_data[lw, nt1, nt2].append((nt1_nuc, nt2_nuc))
|
|
32
|
+
|
|
33
|
+
return loaded_data
|
|
34
|
+
|
|
35
|
+
|
|
36
|
+
def compute_isodiscrepancy(pair1, pair2):
|
|
37
|
+
return measures.isodiscrepancy(pair1, pair2)
|
|
38
|
+
|
|
39
|
+
def main():
|
|
40
|
+
|
|
41
|
+
path_samples = '../../test/10samples.pickle'
|
|
42
|
+
data = read_samples(path_samples)
|
|
43
|
+
|
|
44
|
+
print(data['CWW', 'U', 'A'][0][0].name, data['CWW', 'C', 'G'][0][1].name)
|
|
45
|
+
print(compute_isodiscrepancy(data['CWW', 'U', 'A'][0], data['CWW', 'C', 'G'][0]))
|
|
46
|
+
print("\n")
|
|
47
|
+
print(compute_isodiscrepancy(data['CWW', 'A', 'U'][0], data['TWW', 'G', 'G'][0]))
|
|
48
|
+
|
|
49
|
+
U, C = data['TWW', 'U', 'C'][0]
|
|
50
|
+
for atom in C:
|
|
51
|
+
print(f'"{C[atom].name}"', end=",")
|
|
52
|
+
print()
|
|
53
|
+
for atom in C:
|
|
54
|
+
print(f'"{C[atom].element}"', end=",")
|
|
55
|
+
print()
|
|
56
|
+
for atom in C:
|
|
57
|
+
print(f"{C[atom].position}", end=",")
|
|
58
|
+
|
|
59
|
+
|
|
60
|
+
if __name__ == '__main__':
|
|
61
|
+
main()
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
from RNADiscrepancy import rna
|
|
2
|
+
|
|
3
|
+
def rawdata_format_nucleotide(nucleotide_name, list_atoms_names, list_atoms_elements, list_positions):
|
|
4
|
+
atoms = []
|
|
5
|
+
for name, element, pos in zip(list_atoms_names, list_atoms_elements, list_positions):
|
|
6
|
+
atoms.append(rna.Atom(name, element, *pos))
|
|
7
|
+
return rna.Nucleotide(nucleotide_name, atoms)
|
|
@@ -0,0 +1,63 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: RNADiscrepancy
|
|
3
|
+
Version: 0.0.2
|
|
4
|
+
Summary: Compute discrepancy between 3D RNA (sub)structures
|
|
5
|
+
Project-URL: Homepage, https://codeberg.org/vreinharz/RNADiscrepancy
|
|
6
|
+
Project-URL: Issues, https://codeberg.org/vreinharz/RNADiscrepancy/issues
|
|
7
|
+
Author-email: Vladimir Reinharz <reinharz.vladimir@uqam.ca>
|
|
8
|
+
License-Expression: GPL-3.0
|
|
9
|
+
License-File: LICENSE
|
|
10
|
+
Classifier: Operating System :: OS Independent
|
|
11
|
+
Classifier: Programming Language :: Python :: 3
|
|
12
|
+
Requires-Python: >=3.9
|
|
13
|
+
Description-Content-Type: text/markdown
|
|
14
|
+
|
|
15
|
+
#RNADiscrepancy
|
|
16
|
+
|
|
17
|
+
isostericity
|
|
18
|
+
RMSD
|
|
19
|
+
maybe more?
|
|
20
|
+
|
|
21
|
+
|
|
22
|
+
```python
|
|
23
|
+
>>> from RNADiscrepancy.utilities import rawdata_format_nucleotide
|
|
24
|
+
>>> from RNADiscrepancy.measures import isodiscrepancy
|
|
25
|
+
>>> cwwAU_A_list_atoms = ["P","OP1","OP2","O5'","C5'","C4'","O4'","C3'","O3'","C2'","O2'","C1'","N9","C8","N7","C5","C6","N6","N1","C2","N3","C4"]
|
|
26
|
+
>>> cwwAU_A_list_atoms_elements = ["P","O","O","O","C","C","O","C","O","C","O","C","N","C","N","C","C","N","N","C","N","C"]
|
|
27
|
+
>>> cwwAU_A_list_positions = [(-46.6870002746582, -80.67400360107422, -42.457000732421875),(-45.249000549316406, -80.74099731445312, -42.09299850463867),(-47.303001403808594, -79.36100006103516, -42.77299880981445),(-46.92900085449219, -81.6449966430664, -43.694000244140625),(-47.27000045776367, -83.01000213623047, -43.49399948120117),(-47.70500183105469, -83.62999725341797, -44.79600143432617),(-49.13199996948242, -83.92400360107422, -44.75299835205078),(-47.60100173950195, -82.73999786376953, -46.02299880981445),(-46.290000915527344, -82.58599853515625, -46.52899932861328),(-48.512001037597656, -83.47599792480469, -46.97999954223633),(-47.96799850463867, -84.72100067138672, -47.375),(-49.6870002746582, -83.72000122070312, -46.04600143432617),(-50.590999603271484, -82.5719985961914, -46.012001037597656),(-50.654998779296875, -81.52100372314453, -45.125),(-51.59299850463867, -80.6449966430664, -45.40800094604492),(-52.19300079345703, -81.16400146484375, -46.55400085449219),(-53.26100158691406, -80.71800231933594, -47.35499954223633),(-53.959999084472656, -79.60900115966797, -47.10100173950195),(-53.59199905395508, -81.46099853515625, -48.4379997253418),(-52.902000427246094, -82.58399963378906, -48.68299865722656),(-51.887001037597656, -83.11399841308594, -48.000999450683594),(-51.58000183105469, -82.34600067138672, -46.9370002746582)]
|
|
28
|
+
>>> cwwAU_U_list_atoms = ["P","OP1","OP2","O5'","C5'","C4'","O4'","C3'","O3'","C2'","O2'","C1'","N1","C2","O2","N3","C4","O4","C5","C6"]
|
|
29
|
+
>>> cwwAU_U_list_atoms_elements = ["P","O","O","O","C","C","O","C","O","C","O","C","N","C","O","N","C","O","C","C"]
|
|
30
|
+
>>> cwwAU_U_list_positions = [(-62.04399871826172, -78.197998046875, -52.75299835205078),(-63.35599899291992, -78.33399963378906, -53.4370002746582),(-61.986000061035156, -77.62999725341797, -51.382999420166016),(-61.347999572753906, -79.62899780273438, -52.72700119018555),(-61.56800079345703, -80.56199645996094, -53.777000427246094),(-60.268001556396484, -81.21900177001953, -54.17399978637695),(-59.19599914550781, -80.2249984741211, -54.268001556396484),(-59.689998626708984, -82.20500183105469, -53.178001403808594),(-60.340999603271484, -83.45899963378906, -53.125),(-58.26900100708008, -82.29499816894531, -53.6879997253418),(-58.19900131225586, -82.8759994506836, -54.974998474121094),(-57.983001708984375, -80.80400085449219, -53.79199981689453),(-57.66400146484375, -80.25, -52.470001220703125),(-56.564998626708984, -80.7750015258789, -51.81100082397461),(-55.832000732421875, -81.61399841308594, -52.30500030517578),(-56.35599899291992, -80.28099822998047, -50.54899978637695),(-57.10900115966797, -79.3290023803711, -49.89699935913086),(-56.82600021362305, -79.02300262451172, -48.737998962402344),(-58.20600128173828, -78.81199645996094, -50.659000396728516),(-58.439998626708984, -79.2750015258789, -51.88999938964844)]
|
|
31
|
+
>>> twwUC_U_list_atoms = ["P","OP1","OP2","O5'","C5'","C4'","O4'","C3'","O3'","C2'","O2'","C1'","N1","C2","O2","N3","C4","O4","C5","C6"]
|
|
32
|
+
>>> twwUC_U_list_atoms_elements = ["P","O","O","O","C","C","O","C","O","C","O","C","N","C","O","N","C","O","C","C"]
|
|
33
|
+
>>> twwUC_U_list_positions = [(52.62300109863281, 163.0240020751953, 82.34400177001953),(51.7239990234375, 162.08799743652344, 81.61499786376953),(53.42900085449219, 164.01199340820312, 81.5770034790039),(51.78300094604492, 163.79200744628906, 83.45999908447266),(50.75199890136719, 163.1179962158203, 84.20899963378906),(50.0260009765625, 164.10000610351562, 85.0989990234375),(50.957000732421875, 164.63400268554688, 86.0719985961914),(49.45600128173828, 165.31300354003906, 84.38600158691406),(48.15599822998047, 165.03599548339844, 83.86499786376953),(49.45199966430664, 166.3730010986328, 85.48100280761719),(48.358001708984375, 166.2570037841797, 86.36199951171875),(50.731998443603516, 166.02000427246094, 86.24299621582031),(51.94499969482422, 166.73500061035156, 85.80999755859375),(51.97999954223633, 168.10499572753906, 85.95700073242188),(51.03900146484375, 168.75, 86.38800048828125),(53.1619987487793, 168.69700622558594, 85.58200073242188),(54.284000396728516, 168.07400512695312, 85.08399963378906),(55.29899978637695, 168.73300170898438, 84.87999725341797),(54.16299819946289, 166.66700744628906, 84.93399810791016),(53.02899932861328, 166.0590057373047, 85.28900146484375)]
|
|
34
|
+
>>> twwUC_C_list_atoms = ["P","OP1","OP2","O5'","C5'","C4'","O4'","C3'","O3'","C2'","O2'","C1'","N1","C2","O2","N3","C4","N4","C5","C6"]
|
|
35
|
+
>>> twwUC_C_list_atoms_elements = ["P","O","O","O","C","C","O","C","O","C","O","C","N","C","O","N","C","N","C","C"]
|
|
36
|
+
>>> twwUC_C_list_positions = [(51.45399856567383, 178.2270050048828, 85.64199829101562),(51.52799987792969, 179.64500427246094, 85.23200225830078),(50.196998596191406, 177.45799255371094, 85.41799926757812),(52.66400146484375, 177.4499969482422, 84.95800018310547),(54.012001037597656, 177.9250030517578, 85.10099792480469),(54.97700119018555, 176.7689971923828, 85.08399963378906),(54.652000427246094, 175.8520050048828, 86.15599822998047),(54.93899917602539, 175.89599609375, 83.8489990234375),(55.71099853515625, 176.46200561523438, 82.81400299072266),(55.54800033569336, 174.60000610351562, 84.3550033569336),(56.957000732421875, 174.67799377441406, 84.4469985961914),(54.93899917602539, 174.52000427246094, 85.75399780273438),(53.6879997253418, 173.73199462890625, 85.80500030517578),(53.76300048828125, 172.32899475097656, 85.83999633789062),(54.87699890136719, 171.78500366210938, 85.81199645996094),(52.61399841308594, 171.60699462890625, 85.89900207519531),(51.43299865722656, 172.22999572753906, 85.91899871826172),(50.332000732421875, 171.48800659179688, 85.98400115966797),(51.32899856567383, 173.6479949951172, 85.87699890136719),(52.46799850463867, 174.35299682617188, 85.82099914550781)]
|
|
37
|
+
>>> cww_AU_A = rawdata_format_nucleotide('A', cwwAU_A_list_atoms, cwwAU_A_list_atoms_elements, cwwAU_A_list_positions)
|
|
38
|
+
>>> cww_AU_U = rawdata_format_nucleotide('U', cwwAU_U_list_atoms, cwwAU_U_list_atoms_elements, cwwAU_U_list_positions)
|
|
39
|
+
>>> tww_UC_U = rawdata_format_nucleotide('U', twwUC_U_list_atoms, twwUC_U_list_atoms_elements, twwUC_U_list_positions)
|
|
40
|
+
>>> tww_UC_C = rawdata_format_nucleotide('C', twwUC_C_list_atoms, twwUC_C_list_atoms_elements, twwUC_C_list_positions)
|
|
41
|
+
>>> >>> from RNADiscrepancy.utilities import rawdata_format_nucleotide
|
|
42
|
+
>>> from RNADiscrepancy.measures import isodiscrepancy
|
|
43
|
+
>>> cwwAU_A_list_atoms = ["P","OP1","OP2","O5'","C5'","C4'","O4'","C3'","O3'","C2'","O2'","C1'","N9","C8","N7","C5","C6","N6","N1","C2","N3","C4"]
|
|
44
|
+
>>> cwwAU_A_list_atoms_elements = ["P","O","O","O","C","C","O","C","O","C","O","C","N","C","N","C","C","N","N","C","N","C"]
|
|
45
|
+
>>> cwwAU_A_list_positions = [(-46.6870002746582, -80.67400360107422, -42.457000732421875),(-45.249000549316406, -80.74099731445312, -42.09299850463867),(-47.303001403808594, -79.36100006103516, -42.77299880981445),(-46.92900085449219, -81.6449966430664, -43.694000244140625),(-47.27000045776367, -83.01000213623047, -43.49399948120117),(-47.70500183105469, -83.62999725341797, -44.79600143432617),(-49.13199996948242, -83.92400360107422, -44.75299835205078),(-47.60100173950195, -82.73999786376953, -46.02299880981445),(-46.290000915527344, -82.58599853515625, -46.52899932861328),(-48.512001037597656, -83.47599792480469, -46.97999954223633),(-47.96799850463867, -84.72100067138672, -47.375),(-49.6870002746582, -83.72000122070312, -46.04600143432617),(-50.590999603271484, -82.5719985961914, -46.012001037597656),(-50.654998779296875, -81.52100372314453, -45.125),(-51.59299850463867, -80.6449966430664, -45.40800094604492),(-52.19300079345703, -81.16400146484375, -46.55400085449219),(-53.26100158691406, -80.71800231933594, -47.35499954223633),(-53.959999084472656, -79.60900115966797, -47.10100173950195),(-53.59199905395508, -81.46099853515625, -48.4379997253418),(-52.902000427246094, -82.58399963378906, -48.68299865722656),(-51.887001037597656, -83.11399841308594, -48.000999450683594),(-51.58000183105469, -82.34600067138672, -46.9370002746582)]
|
|
46
|
+
>>> cwwAU_U_list_atoms = ["P","OP1","OP2","O5'","C5'","C4'","O4'","C3'","O3'","C2'","O2'","C1'","N1","C2","O2","N3","C4","O4","C5","C6"]
|
|
47
|
+
>>> cwwAU_U_list_atoms_elements = ["P","O","O","O","C","C","O","C","O","C","O","C","N","C","O","N","C","O","C","C"]
|
|
48
|
+
>>> cwwAU_U_list_positions = [(-62.04399871826172, -78.197998046875, -52.75299835205078),(-63.35599899291992, -78.33399963378906, -53.4370002746582),(-61.986000061035156, -77.62999725341797, -51.382999420166016),(-61.347999572753906, -79.62899780273438, -52.72700119018555),(-61.56800079345703, -80.56199645996094, -53.777000427246094),(-60.268001556396484, -81.21900177001953, -54.17399978637695),(-59.19599914550781, -80.2249984741211, -54.268001556396484),(-59.689998626708984, -82.20500183105469, -53.178001403808594),(-60.340999603271484, -83.45899963378906, -53.125),(-58.26900100708008, -82.29499816894531, -53.6879997253418),(-58.19900131225586, -82.8759994506836, -54.974998474121094),(-57.983001708984375, -80.80400085449219, -53.79199981689453),(-57.66400146484375, -80.25, -52.470001220703125),(-56.564998626708984, -80.7750015258789, -51.81100082397461),(-55.832000732421875, -81.61399841308594, -52.30500030517578),(-56.35599899291992, -80.28099822998047, -50.54899978637695),(-57.10900115966797, -79.3290023803711, -49.89699935913086),(-56.82600021362305, -79.02300262451172, -48.737998962402344),(-58.20600128173828, -78.81199645996094, -50.659000396728516),(-58.439998626708984, -79.2750015258789, -51.88999938964844)]
|
|
49
|
+
>>> twwUC_U_list_atoms = ["P","OP1","OP2","O5'","C5'","C4'","O4'","C3'","O3'","C2'","O2'","C1'","N1","C2","O2","N3","C4","O4","C5","C6"]
|
|
50
|
+
>>> twwUC_U_list_atoms_elements = ["P","O","O","O","C","C","O","C","O","C","O","C","N","C","O","N","C","O","C","C"]
|
|
51
|
+
>>> twwUC_U_list_positions = [(52.62300109863281, 163.0240020751953, 82.34400177001953),(51.7239990234375, 162.08799743652344, 81.61499786376953),(53.42900085449219, 164.01199340820312, 81.5770034790039),(51.78300094604492, 163.79200744628906, 83.45999908447266),(50.75199890136719, 163.1179962158203, 84.20899963378906),(50.0260009765625, 164.10000610351562, 85.0989990234375),(50.957000732421875, 164.63400268554688, 86.0719985961914),(49.45600128173828, 165.31300354003906, 84.38600158691406),(48.15599822998047, 165.03599548339844, 83.86499786376953),(49.45199966430664, 166.3730010986328, 85.48100280761719),(48.358001708984375, 166.2570037841797, 86.36199951171875),(50.731998443603516, 166.02000427246094, 86.24299621582031),(51.94499969482422, 166.73500061035156, 85.80999755859375),(51.97999954223633, 168.10499572753906, 85.95700073242188),(51.03900146484375, 168.75, 86.38800048828125),(53.1619987487793, 168.69700622558594, 85.58200073242188),(54.284000396728516, 168.07400512695312, 85.08399963378906),(55.29899978637695, 168.73300170898438, 84.87999725341797),(54.16299819946289, 166.66700744628906, 84.93399810791016),(53.02899932861328, 166.0590057373047, 85.28900146484375)]
|
|
52
|
+
>>> twwUC_C_list_atoms = ["P","OP1","OP2","O5'","C5'","C4'","O4'","C3'","O3'","C2'","O2'","C1'","N1","C2","O2","N3","C4","N4","C5","C6"]
|
|
53
|
+
>>> twwUC_C_list_atoms_elements = ["P","O","O","O","C","C","O","C","O","C","O","C","N","C","O","N","C","N","C","C"]
|
|
54
|
+
>>> twwUC_C_list_positions = [(51.45399856567383, 178.2270050048828, 85.64199829101562),(51.52799987792969, 179.64500427246094, 85.23200225830078),(50.196998596191406, 177.45799255371094, 85.41799926757812),(52.66400146484375, 177.4499969482422, 84.95800018310547),(54.012001037597656, 177.9250030517578, 85.10099792480469),(54.97700119018555, 176.7689971923828, 85.08399963378906),(54.652000427246094, 175.8520050048828, 86.15599822998047),(54.93899917602539, 175.89599609375, 83.8489990234375),(55.71099853515625, 176.46200561523438, 82.81400299072266),(55.54800033569336, 174.60000610351562, 84.3550033569336),(56.957000732421875, 174.67799377441406, 84.4469985961914),(54.93899917602539, 174.52000427246094, 85.75399780273438),(53.6879997253418, 173.73199462890625, 85.80500030517578),(53.76300048828125, 172.32899475097656, 85.83999633789062),(54.87699890136719, 171.78500366210938, 85.81199645996094),(52.61399841308594, 171.60699462890625, 85.89900207519531),(51.43299865722656, 172.22999572753906, 85.91899871826172),(50.332000732421875, 171.48800659179688, 85.98400115966797),(51.32899856567383, 173.6479949951172, 85.87699890136719),(52.46799850463867, 174.35299682617188, 85.82099914550781)]
|
|
55
|
+
>>> cww_AU_A = rawdata_format_nucleotide('A', cwwAU_A_list_atoms, cwwAU_A_list_atoms_elements, cwwAU_A_list_positions)
|
|
56
|
+
>>> cww_AU_U = rawdata_format_nucleotide('U', cwwAU_U_list_atoms, cwwAU_U_list_atoms_elements, cwwAU_U_list_positions)
|
|
57
|
+
>>> tww_UC_U = rawdata_format_nucleotide('U', twwUC_U_list_atoms, twwUC_U_list_atoms_elements, twwUC_U_list_positions)
|
|
58
|
+
>>> tww_UC_C = rawdata_format_nucleotide('C', twwUC_C_list_atoms, twwUC_C_list_atoms_elements, twwUC_C_list_positions)
|
|
59
|
+
>>> cww_AU = (cww_AU_A, cww_AU_U)
|
|
60
|
+
>>> tww_UC = (tww_UC_U, tww_UC_C)
|
|
61
|
+
>>> isodiscrepancy(cww_AU, tww_UC)
|
|
62
|
+
15.096495858783285
|
|
63
|
+
```
|
|
@@ -0,0 +1,11 @@
|
|
|
1
|
+
RNADiscrepancy/.test.py.swp,sha256=O0hTheO5Qz2CKDgdfs9ps0rNNW2MVBlJB2h1sP8_JUw,12288
|
|
2
|
+
RNADiscrepancy/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
3
|
+
RNADiscrepancy/measures.py,sha256=7L5awwoMGEF1qaLo7aXWk9llWbQNfVza13vEVUtandQ,6569
|
|
4
|
+
RNADiscrepancy/references.py,sha256=WX8psZMoWil7Hxphpu1lmO1u2k0Yh2BHc-WxeuAn5O4,2505
|
|
5
|
+
RNADiscrepancy/rna.py,sha256=7KxwlxlE9DWsefZPLJEmk3fFLghBDcHKSyzU-iGpYys,1508
|
|
6
|
+
RNADiscrepancy/test.py,sha256=wr0Oi21za2FUrSgtBbB6T31rv3iMp8CaJp5Wp9i-vkA,1891
|
|
7
|
+
RNADiscrepancy/utilities.py,sha256=F6dzmQUGKz_725_pPD5VY8gtvv6dWh1-CX-CTHzWSYQ,342
|
|
8
|
+
rnadiscrepancy-0.0.2.dist-info/METADATA,sha256=BFpbWOWhcnlbt4_wQS5JDvNGSmo4D8DECK01a7vC8DQ,13951
|
|
9
|
+
rnadiscrepancy-0.0.2.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
|
|
10
|
+
rnadiscrepancy-0.0.2.dist-info/licenses/LICENSE,sha256=dP7Glyxd-54WGXrTuhOs_HelxCoX5jwPCluWFnvMHUE,749
|
|
11
|
+
rnadiscrepancy-0.0.2.dist-info/RECORD,,
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
RNADiscrepancy - Computing RNA discrepancy values
|
|
2
|
+
|
|
3
|
+
Copyright (C) 2026 Vladimir Reinharz
|
|
4
|
+
|
|
5
|
+
This program is free software: you can redistribute it and/or modify
|
|
6
|
+
it under the terms of the GNU General Public License as published by
|
|
7
|
+
the Free Software Foundation, either version 3 of the License, or
|
|
8
|
+
(at your option) any later version.
|
|
9
|
+
|
|
10
|
+
This program is distributed in the hope that it will be useful,
|
|
11
|
+
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
12
|
+
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
13
|
+
GNU General Public License for more details.
|
|
14
|
+
|
|
15
|
+
You should have received a copy of the GNU General Public License
|
|
16
|
+
along with this program. If not, see <https://www.gnu.org/licenses/>.
|
|
17
|
+
|