-
Notifications
You must be signed in to change notification settings - Fork 0
/
main_H.py
496 lines (417 loc) · 19.1 KB
/
main_H.py
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
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
import numpy as np
import sys
import os
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
from rdkit.Chem import AllChem
from rdkit import Chem
from rdkit.Chem import rdDetermineBonds
print("########################################################")
print(" Transition State Guess Generation ")
print(" C-H Bonds in Polyaromatic Hydrocarbons ")
print("########################################################")
#
# Helper Functions
#
def detect_aldehyde(mol,cidx,hidx):
carbon = mol.GetAtomWithIdx(cidx)
if carbon.GetSymbol()!='C':
return False
vicinals = carbon.GetNeighbors()
hydrogens = 0
CO_double_bond = False
for vicinal in vicinals:
if vicinal.GetSymbol() == 'H':
hydrogens += 1
elif vicinal.GetSymbol() == 'O':
bond = mol.GetBondBetweenAtoms(cidx,vicinal.GetIdx())
if bond.GetBondType() == Chem.rdchem.BondType.DOUBLE:
CO_double_bond = True
return hydrogens == 1 and CO_double_bond
def get_vector_length(vector):
length = np.linalg.norm(vector)
return length
def xyz_to_mol(coord_path):
raw_mol = AllChem.MolFromXYZFile(coord_path)
return raw_mol
def replace_h(path, idx, new_line, output):
with open(path, 'r') as file:
lines = file.readlines()
lines[idx] = f'{new_line}\n'
with open(output, 'w') as file:
num_atoms = int(lines[0].strip())
num_atoms += 1
lines[0] = f'{num_atoms}\n'
file.writelines(lines)
def delete_h(path, idx, output):
with open(path, 'r') as file:
lines = file.readlines()
del lines[idx]
with open(output,'w') as file:
num_atoms = int(lines[0].strip())
num_atoms -= 1
lines[0] = f'{num_atoms}\n'
file.writelines(lines)
print(f'Product for H idx {idx-1} saved as XYZ File in {output}.')
def teta_v(vector1, vector2):
vector1_norm = vector1 / np.linalg.norm(vector1)
vector2_norm = vector2 / np.linalg.norm(vector2)
angle = np.arccos(np.dot(vector1_norm, vector2_norm))
return angle
def mol_with_atom_index(mol):
for atom in mol.GetAtoms():
atom.SetAtomMapNum(atom.GetIdx())
atom.SetAtomMapNum(atom.GetIdx()+1)
return mol
def scale_ch(vector, ch_ts_length):
if get_vector_length(vector) == 0:
raise ValueError("Vector has a length l = 0, cannot be scaled!")
scale = float(ch_ts_length) / float(get_vector_length(vector))
new_vector = scale * vector
return new_vector
def add_hydrogen(vector, h_distance):
if get_vector_length(vector) == 0:
raise ValueError("Vector has a length l = 0, cannot be scaled!")
scale = float(h_distance) / float(get_vector_length(vector))
new_vector = scale * vector
return new_vector
def rotate_vector(vector, angle, axis):
axis = np.array(axis)
axis = axis / np.linalg.norm(axis)
rotated_vector = (np.cos(angle) * vector + np.sin(angle) * np.cross(axis, vector) + (1-np.cos(angle)) * np.dot(axis,vector) * axis)
return rotated_vector
def add_hydrogen_to_oxygen(vector, h_distance):
if get_vector_length(vector) == 0:
raise ValueError("Vector length = 0, cannot be scaled!")
scale = float(h_distance) / float(get_vector_length(vector))
new_vector = scale * vector
return new_vector
def get_atomic_numbers(mol):
for atom in mol.GetAtoms():
Num = atom.GetAtomicNum()
AtmNum.append(Num)
#
# Start of the Program
#
if len(sys.argv) <= 1:
print ("usage: python3 main.py <xyz> | e.g. python3 main.py coord.xyz ")
sys.exit("Molecular coordinates are missing")
else:
file_path = sys.argv[1] # Molecular Coordinates in xyz format (Angstrom)
# Generates Products Directory for saving xyz files of products
results= 'Products'
try:
os.makedirs(results)
except FileExistsError:
pass
print("Products will be saved in Directory: Products")
#
# Define Lists
#
# Aromatic C-H Bonds
H_vectors = [] # Contains Vectors of hydrogen atoms (existing in the initial molecule)
C_vectors = [] # Contains Vectors of carbon atoms (existing in the initial molecule)
Hydrogen_Positions = []
new_coords = [] # Contains Vectors (c to h) of the elongated C-H bond
add_hydrogen_positions = []
C_H_Vector = []
ch_bonds = [] # Contains C-H bonds detected by rdkit
new_H = [] # Contains Coordinates(Angstrom) of the existing hydrogen atom but elongated to the ts length
add_H = [] # Contains Coordinates(Angstrom) of the newly added oxygen atom
third_H = []
add_HtoO_r = [] # Contains Coordinates(Angstrom) of the newly added hydrogen atom of the OH bond
AtmNum = [] # Contains atomic numbers of the molecule
# Aldehyde C-H Bonds
aldehyde_bonds = []
H_vectors_aldehyde = []
C_vectors_aldehyde = []
Hydrogen_Position_aldehyde = []
new_coords_aldehyde = []
add_hydrogen_positions_aldehyde = []
new_H_aldehyde = []
add_H_aldehyde = []
third_H_aldehyde = []
add_HtoO_r_aldehyde = []
# Aldehyde O-H Bonds
oh_bonds = []
H_vectors_oh = []
C_vectors_oh = []
Hydrogen_Position_oh = []
new_coords_oh = []
add_hydrogen_positions_oh = []
new_H_oh = []
add_H_oh = []
third_H_oh = []
add_HtoO_r_oh = []
# Aldehyde N-H Bonds
nh_bonds = []
H_vectors_nh = []
C_vectors_nh = []
Hydrogen_Position_nh = []
new_coords_nh = []
add_hydrogen_positions_nh = []
new_H_nh = []
add_H_nh = []
third_H_nh = []
add_HtoO_r_nh = []
#
# Generate Mol Object
#
raw_mol = AllChem.MolFromXYZFile(file_path)
mol= AllChem.Mol(raw_mol)
rdDetermineBonds.DetermineBonds(mol,charge=0) # TODO: Adjust charge accordingly
get_atomic_numbers(mol)
#
# TS Bond Distances
#
# if else statement allows to modify TS Bond Distances for different atom compositions
# e.g. if molecule contains nitrogen, adjust values accordingly
if 7 in AtmNum:
print("Using Nitrogen-Updated Parameters for Hydrocarbons")
ts_value = 1.52 # Elongated C-H Distance (Angstrom)
ts_value_aldehyde = 1.23 # Elongated C-H Distance for Aldehyde (Angstrom))
h_distance = ts_value+0.85 # Additional H Atom Distance to C Atom (Angstrom)
h_distance_aldehyde = ts_value_aldehyde + 1.16
ts_value_oh = 1.230
ts_value_nh = 0.310
h_distance_oh = ts_value_oh + 0.85
h_distance_nh = ts_value_nh + 0.91
else:
print("Using Default Parameters for Hydrocarbons")
ts_value = 1.52
ts_value_aldehyde = 1.23
h_distance = ts_value+0.85
h_distance_aldehyde = ts_value_aldehyde + 1.16
ts_value_oh = 1.230
ts_value_nh = 0.310
h_distance_oh = ts_value_oh + 0.85
h_distance_nh = ts_value_nh + 0.91
#################################################################################################
#
# Main Routine
#
#################################################################################################
for bond in mol.GetBonds():
atom1_idx = bond.GetBeginAtomIdx()
atom2_idx = bond.GetEndAtomIdx()
# Check for CH Bonds in different functional groups
if mol.GetAtomWithIdx(atom1_idx).GetSymbol() == 'C' and mol.GetAtomWithIdx(atom2_idx).GetSymbol() == 'H':
if detect_aldehyde(mol, atom1_idx,atom2_idx):
aldehyde_bonds.append((atom1_idx, atom2_idx))
else:
ch_bonds.append((atom1_idx, atom2_idx))
elif mol.GetAtomWithIdx(atom1_idx).GetSymbol() == 'H' and mol.GetAtomWithIdx(atom2_idx).GetSymbol() == 'C':
if detect_aldehyde(mol,atom2_idx,atom1_idx):
aldehyde_bonds.append((atom2_idx, atom1_idx))
else:
ch_bonds.append((atom2_idx, atom1_idx))
# Check for N-H and O-H Bonds
if mol.GetAtomWithIdx(atom1_idx).GetSymbol() == 'N' and mol.GetAtomWithIdx(atom2_idx).GetSymbol() == 'H':
nh_bonds.append((atom1_idx,atom2_idx))
elif mol.GetAtomWithIdx(atom1_idx).GetSymbol() == 'H' and mol.GetAtomWithIdx(atom2_idx).GetSymbol() == 'N':
nh_bonds.append((atom1_idx,atom2_idx))
if mol.GetAtomWithIdx(atom1_idx).GetSymbol() == 'O' and mol.GetAtomWithIdx(atom2_idx).GetSymbol() == 'H':
oh_bonds.append((atom1_idx, atom2_idx))
elif mol.GetAtomWithIdx(atom1_idx).GetSymbol() == 'H' and mol.GetAtomWithIdx(atom2_idx).GetSymbol() == 'O':
oh_bonds.append((atom1_idx, atom2_idx))
configuration = mol.GetConformer()
#
# Generating X-H Bond Vectors
#
# Dealing with Aromatic C-H Bonds
for index in ch_bonds:
atom_position_C = configuration.GetAtomPosition(index[0])
atom_position_H = configuration.GetAtomPosition(index[1])
vector_Hydrogen = atom_position_H.x, atom_position_H.y, atom_position_H.z
vector_Carbon = atom_position_C.x, atom_position_C.y, atom_position_C.z
H_vectors.append(vector_Hydrogen)
C_vectors.append(vector_Carbon)
# Dealing with Aldehyde C-H Bonds
for index in aldehyde_bonds:
atom_position_C_aldehyde = configuration.GetAtomPosition(index[0])
atom_position_H_aldehyde = configuration.GetAtomPosition(index[1])
vector_Hydrogen = atom_position_H_aldehyde.x, atom_position_H_aldehyde.y, atom_position_H_aldehyde.z
vector_Carbon = atom_position_C_aldehyde.x, atom_position_C_aldehyde.y, atom_position_C_aldehyde.z
H_vectors_aldehyde.append(vector_Hydrogen)
C_vectors_aldehyde.append(vector_Carbon)
# Dealing with N-H Bonds
for index in nh_bonds:
atom_position_C_nh = configuration.GetAtomPosition(index[0])
atom_position_H_nh = configuration.GetAtomPosition(index[1])
vector_Hydrogen = atom_position_H_nh.x, atom_position_H_nh.y, atom_position_H_nh.z
vector_Carbon = atom_position_C_nh.x, atom_position_C_nh.y, atom_position_C_nh.z
H_vectors_nh.append(vector_Hydrogen)
C_vectors_nh.append(vector_Carbon)
# Dealing with O-H Bonds
for index in oh_bonds:
atom_position_C_oh = configuration.GetAtomPosition(index[0])
atom_position_H_oh = configuration.GetAtomPosition(index[1])
vector_Hydrogen = atom_position_H_oh.x, atom_position_H_oh.y, atom_position_H_oh.z
vector_Carbon = atom_position_C_oh.x, atom_position_C_oh.y, atom_position_C_oh.z
H_vectors_oh.append(vector_Hydrogen)
C_vectors_oh.append(vector_Carbon)
# ...
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
def main():
# Aromatic C-H Bonds
for c, h in zip(C_vectors, H_vectors): # c, h as tuples
v_c = np.array(c)
v_h = np.array(h)
C_H_Vector = v_h - v_c
Hydrogen_Positions.append(C_H_Vector)
ax.quiver(c[0], c[1], c[2], C_H_Vector[0], C_H_Vector[1], C_H_Vector[2], arrow_length_ratio=0.8, color='r')
new_coord = scale_ch(C_H_Vector, ts_value)
new_coords.append(new_coord)
ax.quiver(c[0], c[1], c[2], new_coord[0], new_coord[1], new_coord[2], arrow_length_ratio=0.55, color='g')
add_hydrogen_position = add_hydrogen(C_H_Vector, h_distance)
add_hydrogen_positions.append(add_hydrogen_position)
ax.quiver(c[0], c[1], c[2], add_hydrogen_position[0], add_hydrogen_position[1], add_hydrogen_position[2], arrow_length_ratio=0.1, color='b')
new_H.append((c[0] + new_coord[0], c[1] + new_coord[1], c[2] + new_coord[2]))
add_H.append((c[0] + add_hydrogen_position[0], c[1] + add_hydrogen_position[1], c[2] + add_hydrogen_position[2]))
# Aldehyde C-H Bonds
for c, h in zip(C_vectors_aldehyde, H_vectors_aldehyde):
v_c_aldehyde = np.array(c)
v_h_aldehyde = np.array(h)
C_H_Vector_aldehyde = v_h_aldehyde - v_c_aldehyde
Hydrogen_Position_aldehyde.append(C_H_Vector_aldehyde)
ax.quiver(c[0], c[1], c[2], C_H_Vector_aldehyde[0], C_H_Vector_aldehyde[1], C_H_Vector_aldehyde[2], arrow_length_ratio=0.8, color='r')
new_coord_aldehyde = scale_ch(C_H_Vector_aldehyde,ts_value_aldehyde)
new_coords_aldehyde.append(new_coord_aldehyde)
ax.quiver(c[0], c[1], c[2], new_coord_aldehyde[0], new_coord_aldehyde[1], new_coord_aldehyde[2], arrow_length_ratio=0.55, color='g')
add_hydrogen_position_aldehyde = add_hydrogen(C_H_Vector_aldehyde, h_distance_aldehyde)
add_hydrogen_positions_aldehyde.append(add_hydrogen_position_aldehyde)
ax.quiver(c[0], c[1], c[2], add_hydrogen_position_aldehyde[0], add_hydrogen_position_aldehyde[1], add_hydrogen_position_aldehyde[2], arrow_length_ratio=0.1, color='b')
new_H_aldehyde.append((c[0] + new_coord_aldehyde[0], c[1] + new_coord_aldehyde[1], c[2] + new_coord_aldehyde[2]))
add_H_aldehyde.append((c[0] + add_hydrogen_position_aldehyde[0], c[1] + add_hydrogen_position_aldehyde[1], c[2] + add_hydrogen_position_aldehyde[2]))
for n, h in zip(C_vectors_nh, H_vectors_nh):
v_n = np.array(n)
v_h = np.array(h)
N_H_Vector = v_n - v_h
Hydrogen_Position_nh.append(N_H_Vector)
ax.quiver(n[0],n[1],n[2], N_H_Vector[0],N_H_Vector[1],N_H_Vector[2],arrow_length_ratio=0.8, color = 'r')
new_coord_nh = scale_ch(N_H_Vector, ts_value_nh)
new_coords_nh.append(new_coord_nh)
ax.quiver(n[0],n[1],n[2],new_coord_nh[0],new_coord_nh[1],new_coord_nh[2], arrow_length_ratio=0.55, color = 'g')
add_hydrogen_nh = add_hydrogen(N_H_Vector,h_distance_nh)
add_hydrogen_positions_nh.append(add_hydrogen_nh)
ax.quiver(n[0],n[1],n[2],add_hydrogen_nh[0],add_hydrogen_nh[1],add_hydrogen_nh[2], arrow_length_ratio = 0.1, color = 'b')
new_H_nh.append((n[0] + new_coord_nh[0], n[1] + new_coord_nh[1], n[2] + new_coord_nh[2]))
add_H_nh.append((n[0] + add_hydrogen_nh[0], n[1] + add_hydrogen_nh[1], n[2] + add_hydrogen_nh[2]))
for o, h in zip(C_vectors_oh, H_vectors_oh):
v_o = np.array(o)
v_h = np.array(h)
O_H_Vector = v_o - v_h
Hydrogen_Position_oh.append(O_H_Vector)
ax.quiver(o[0],o[1],o[2], O_H_Vector[0],O_H_Vector[1],O_H_Vector[2],arrow_length_ratio=0.8, color = 'r')
new_coord_oh = scale_ch(O_H_Vector, ts_value_oh)
new_coords_oh.append(new_coord_oh)
ax.quiver(o[0],o[1],o[2],new_coord_oh[0],new_coord_oh[1],new_coord_oh[2], arrow_length_ratio=0.55, color = 'g')
add_hydrogen_oh = add_hydrogen(O_H_Vector,h_distance_oh)
add_hydrogen_positions_oh.append(add_hydrogen_oh)
ax.quiver(o[0],o[1],o[2],add_hydrogen_oh[0],add_hydrogen_oh[1],add_hydrogen_oh[2], arrow_length_ratio = 0.1, color = 'b')
new_H_oh.append((o[0] + new_coord_oh[0], o[1] + new_coord_oh[1], o[2] + new_coord_oh[2]))
add_H_oh.append((o[0] + add_hydrogen_oh[0], o[1] + add_hydrogen_oh[1], o[2] + add_hydrogen_oh[2]))
if __name__ == "__main__":
main()
#################################################################################################
#
# Generating Coordinate Files
#
#################################################################################################
#
# Saving Changed XYZ Files
#
for ch_bond,hydrogen,added_hydrogen in zip(ch_bonds, new_H, add_H):
idx = ch_bond[1]+2
new_line = f"H {hydrogen[0]} {hydrogen[1]} {hydrogen[2]}"
second_h = f"H {added_hydrogen[0]} {added_hydrogen[1]} {added_hydrogen[2]}"
path = file_path
output = f'coord_hidx_{idx-1}.xyz'
replace_h(path, idx, new_line, output)
with open(f'coord_hidx_{idx-1}.xyz','a') as file:
file.write(second_h + '\n')
print(f'Finished with H Radical Positioning on Former H with Idx {idx-1}. Saved as XYZ File in {output}.')
for ch_bond,hydrogen,added_hydrogen in zip(aldehyde_bonds, new_H_aldehyde, add_H_aldehyde):
idx = ch_bond[1]+2
new_line = f"H {hydrogen[0]} {hydrogen[1]} {hydrogen[2]}"
second_h = f"H {added_hydrogen[0]} {added_hydrogen[1]} {added_hydrogen[2]}"
path = file_path
output = f'coord_hidx_{idx-1}.xyz'
replace_h(path, idx, new_line, output)
with open(f'coord_hidx_{idx-1}.xyz','a') as file:
file.write(second_h + '\n')
print(f'Finished with H Radical Positioning on Former H with Idx {idx-1}. Saved as XYZ File in {output}.')
for ch_bond,hydrogen,added_hydrogen in zip(nh_bonds, new_H_nh, add_H_nh):
idx = ch_bond[0]+2
new_line = f"H {hydrogen[0]} {hydrogen[1]} {hydrogen[2]}"
second_h = f"H {added_hydrogen[0]} {added_hydrogen[1]} {added_hydrogen[2]}"
path = file_path
output = f'coord_hidx_{idx-1}.xyz'
replace_h(path, idx, new_line, output)
with open(f'coord_hidx_{idx-1}.xyz','a') as file:
file.write(second_h + '\n')
print(f'Finished with H Radical Positioning on Former H with Idx {idx-1}. Saved as XYZ File in {output}.')
for ch_bond,hydrogen,added_hydrogen in zip(oh_bonds, new_H_oh, add_H_oh):
idx = ch_bond[0]+2
new_line = f"H {hydrogen[0]} {hydrogen[1]} {hydrogen[2]}"
second_h = f"H {added_hydrogen[0]} {added_hydrogen[1]} {added_hydrogen[2]}"
path = file_path
output = f'coord_hidx_{idx-1}.xyz'
replace_h(path, idx, new_line, output)
with open(f'coord_hidx_{idx-1}.xyz','a') as file:
file.write(second_h + '\n')
print(f'Finished with H Radical Positioning on Former H with Idx {idx-1}. Saved as XYZ File in {output}.')
#
# Generating Product Geometries
#
# Aromatic C-H Bonds
for ch_bond,hydrogen in zip(ch_bonds, new_H):
idx = ch_bond[1]+2
path = file_path
output = f'Products/product_idx_{idx-1}.xyz'
delete_h(path, idx, output)
# Aldehyde C-H Bonds
for ch_bond,hydrogen in zip(aldehyde_bonds, new_H_aldehyde):
idx = ch_bond[1]+2
path = file_path
output = f'Products/product_idx_{idx-1}.xyz'
delete_h(path, idx, output)
# N-H Bonds
for nh_bond,hydrogen in zip(nh_bonds, new_H_nh):
idx = nh_bond[0]+2
path = file_path
output = f'Products/product_idx_{idx-1}.xyz'
delete_h(path, idx, output)
# O-H Bonds
for oh_bond,hydrogen in zip(oh_bonds, new_H_oh):
idx = oh_bond[0]+2
path = file_path
output = f'Products/product_idx_{idx-1}.xyz'
delete_h(path, idx, output)
#
# Vector Plotting
#
print("########################################################")
print(" Vector Visualisation ")
print("########################################################")
ax.set_xlabel('X Coordinate')
ax.set_ylabel('Y Coordinate')
ax.set_zlabel('Z Coordinate')
ax.set_xlim([-5,5])
ax.set_ylim([-5,5])
ax.set_zlim([-5,5])
legend1 = mpatches.Patch(color='red', label='Initial C-H Bonds')
legend2 = mpatches.Patch(color='green', label='Elongated C-H Bonds')
legend3 = mpatches.Patch(color='blue', label='Additional Hydrogen Atoms')
visualize = input("Do you want to plot the C-H vectors? yes/no:").lower()
if visualize == "yes":
plt.legend(handles=[legend1,legend2,legend3])
plt.show()
print("########################################################")
print(" END OF THE PROGRAM ")
print("########################################################")
else:
print("########################################################")
print(" END OF THE PROGRAM ")
print("########################################################")