Auto3D 2.2.7__tar.gz → 2.2.8__tar.gz

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.
Files changed (51) hide show
  1. {Auto3D-2.2.7/src/Auto3D.egg-info → Auto3D-2.2.8}/PKG-INFO +4 -1
  2. {Auto3D-2.2.7 → Auto3D-2.2.8}/README.md +3 -0
  3. {Auto3D-2.2.7 → Auto3D-2.2.8}/setup.cfg +1 -1
  4. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/__pycache__/auto3D.cpython-39.pyc +0 -0
  5. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/auto3D.py +3 -2
  6. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/batch_opt/__pycache__/batchopt.cpython-39.pyc +0 -0
  7. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/batch_opt/batchopt.py +81 -55
  8. {Auto3D-2.2.7 → Auto3D-2.2.8/src/Auto3D.egg-info}/PKG-INFO +4 -1
  9. {Auto3D-2.2.7 → Auto3D-2.2.8}/LICENSE +0 -0
  10. {Auto3D-2.2.7 → Auto3D-2.2.8}/MANIFEST.in +0 -0
  11. {Auto3D-2.2.7 → Auto3D-2.2.8}/pyproject.toml +0 -0
  12. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/.gitignore +0 -0
  13. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/ASE/__init__.py +0 -0
  14. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/ASE/__pycache__/__init__.cpython-39.pyc +0 -0
  15. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/ASE/__pycache__/geometry.cpython-39.pyc +0 -0
  16. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/ASE/__pycache__/thermo.cpython-39.pyc +0 -0
  17. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/ASE/geometry.py +0 -0
  18. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/ASE/thermo.py +0 -0
  19. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/SPE.py +0 -0
  20. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/__init__.py +0 -0
  21. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/__pycache__/SPE.cpython-39.pyc +0 -0
  22. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/__pycache__/__init__.cpython-39.pyc +0 -0
  23. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/__pycache__/isomer_engine.cpython-39.pyc +0 -0
  24. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/__pycache__/ranking.cpython-39.pyc +0 -0
  25. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/__pycache__/tautomer.cpython-39.pyc +0 -0
  26. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/__pycache__/utils.cpython-39.pyc +0 -0
  27. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/__pycache__/utils_file.cpython-39.pyc +0 -0
  28. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/batch_opt/ANI2xt_no_rep.py +0 -0
  29. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/batch_opt/ANI2xt_rep.py +0 -0
  30. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/batch_opt/__init__.py +0 -0
  31. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/batch_opt/__pycache__/ANI2xt_no_rep.cpython-39.pyc +0 -0
  32. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/batch_opt/__pycache__/__init__.cpython-39.pyc +0 -0
  33. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/isomer_engine.py +0 -0
  34. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/models/__init__.py +0 -0
  35. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/models/aimnet2_wb97m-d3_0.jpt +0 -0
  36. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/models/aimnet2_wb97m_ens_f.jpt +0 -0
  37. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/models/ani2xt_no_repulsion.pt +0 -0
  38. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/ranking.py +0 -0
  39. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/tautomer.py +0 -0
  40. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/utils.py +0 -0
  41. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D/utils_file.py +0 -0
  42. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D.egg-info/SOURCES.txt +0 -0
  43. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D.egg-info/dependency_links.txt +0 -0
  44. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D.egg-info/requires.txt +0 -0
  45. {Auto3D-2.2.7 → Auto3D-2.2.8}/src/Auto3D.egg-info/top_level.txt +0 -0
  46. {Auto3D-2.2.7 → Auto3D-2.2.8}/tests/test_SPE.py +0 -0
  47. {Auto3D-2.2.7 → Auto3D-2.2.8}/tests/test_auto3D.py +0 -0
  48. {Auto3D-2.2.7 → Auto3D-2.2.8}/tests/test_isomer_engine.py +0 -0
  49. {Auto3D-2.2.7 → Auto3D-2.2.8}/tests/test_tauto.py +0 -0
  50. {Auto3D-2.2.7 → Auto3D-2.2.8}/tests/test_thermo.py +0 -0
  51. {Auto3D-2.2.7 → Auto3D-2.2.8}/tests/test_utils.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: Auto3D
3
- Version: 2.2.7
3
+ Version: 2.2.8
4
4
  Summary: Generating Low-energy 3D Conformers from SMILES/SDF
5
5
  Home-page: https://github.com/isayevlab/Auto3D_pkg
6
6
  Author: 'Zhen Liu, Tetiana Zubatiuk, Adrian Roitberg, Olexandr Isayev'
@@ -32,6 +32,9 @@ Requires-Dist: pyyaml
32
32
 
33
33
  Please check out the information at [**documentation**](https://auto3d.readthedocs.io/en/latest/index.html), including [installation](https://auto3d.readthedocs.io/en/latest/installation.html), [usage](https://auto3d.readthedocs.io/en/latest/usage.html), [API](https://auto3d.readthedocs.io/en/latest/api.html) and [citation](https://auto3d.readthedocs.io/en/latest/citation.html).
34
34
 
35
+ - **Jupyter notebook examples** can be found [here](https://github.com/isayevlab/Auto3D_pkg/tree/main/example)
36
+ - To-do list for **improvement and new features** can be found [here](https://github.com/isayevlab/Auto3D_pkg/discussions). You are welcomed to share your thoughts.
37
+ - Bugs go to the [issues](https://github.com/isayevlab/Auto3D_pkg/issues)
35
38
 
36
39
  ## Minimum Dependencies Installatioin
37
40
  1. Python >= 3.7
@@ -13,6 +13,9 @@
13
13
 
14
14
  Please check out the information at [**documentation**](https://auto3d.readthedocs.io/en/latest/index.html), including [installation](https://auto3d.readthedocs.io/en/latest/installation.html), [usage](https://auto3d.readthedocs.io/en/latest/usage.html), [API](https://auto3d.readthedocs.io/en/latest/api.html) and [citation](https://auto3d.readthedocs.io/en/latest/citation.html).
15
15
 
16
+ - **Jupyter notebook examples** can be found [here](https://github.com/isayevlab/Auto3D_pkg/tree/main/example)
17
+ - To-do list for **improvement and new features** can be found [here](https://github.com/isayevlab/Auto3D_pkg/discussions). You are welcomed to share your thoughts.
18
+ - Bugs go to the [issues](https://github.com/isayevlab/Auto3D_pkg/issues)
16
19
 
17
20
  ## Minimum Dependencies Installatioin
18
21
  1. Python >= 3.7
@@ -1,6 +1,6 @@
1
1
  [metadata]
2
2
  name = Auto3D
3
- version = 2.2.7
3
+ version = 2.2.8
4
4
  author = 'Zhen Liu, Tetiana Zubatiuk, Adrian Roitberg, Olexandr Isayev'
5
5
  author_email = liu5@andrew.cmu.edu, tetiana@zubatyuk.com, roitberg@ufl.edu, olexandr@olexandrisayev.com
6
6
  description = Generating Low-energy 3D Conformers from SMILES/SDF
@@ -267,9 +267,9 @@ def main(args:dict):
267
267
  start = time.time()
268
268
  # job_name = datetime.now().strftime("%Y%m%d-%H%M%S-%f") #adds microsecond in the end
269
269
 
270
- path0, mapping = encode_ids(args.path)
271
- if path0 is None:
270
+ if args.path is None:
272
271
  sys.exit("Please specify the input file path.")
272
+ path0, mapping = encode_ids(args.path)
273
273
  input_format = os.path.splitext(path0)[1][1:]
274
274
  if (input_format != "smi") and (input_format != "sdf"):
275
275
  sys.exit("Input file type is not supported. Only .smi and .sdf are supported. But the input file is " + input_format + ".")
@@ -441,6 +441,7 @@ def main(args:dict):
441
441
  logger.info(f'Program running time: {running_time_h} hour(s) and {remaining_minutes} minute(s)')
442
442
  reorder_sdf(path_combined, path0)
443
443
  path_combined = decode_ids(path_combined, mapping)
444
+ os.remove(path0)
444
445
  print(f"Output path: {path_combined}", flush=True)
445
446
  logger.info(f"Output path: {path_combined}")
446
447
  logging_queue.put(None)
@@ -1,9 +1,9 @@
1
1
  # Original source: /labspace/models/aimnet/batch_opt_script/
2
- import torch
3
- import logging
4
- import warnings
5
2
  import os
3
+
6
4
  import numpy as np
5
+ import torch
6
+
7
7
  try:
8
8
  import torchani
9
9
  except:
@@ -11,6 +11,7 @@ except:
11
11
  from collections import defaultdict
12
12
  from rdkit import Chem
13
13
  from rdkit.Chem import rdmolops
14
+
14
15
  try:
15
16
  from .ANI2xt_no_rep import ANI2xt
16
17
  except:
@@ -20,10 +21,13 @@ from Auto3D.utils import hartree2ev
20
21
 
21
22
  torch.backends.cuda.matmul.allow_tf32 = False
22
23
  torch.backends.cudnn.allow_tf32 = False
24
+
25
+
23
26
  # hartree2eV = 27.211385
24
27
  @torch.jit.script
25
28
  class FIRE():
26
29
  """a general optimization program """
30
+
27
31
  # For a list of documentation for different optimization programs: https://wiki.fysik.dtu.dk/ase/ase/optimize.html
28
32
  def __init__(self, coord):
29
33
  ## default parameters
@@ -55,13 +59,17 @@ class FIRE():
55
59
  a = self.a.unsqueeze(-1).unsqueeze(-1)
56
60
  v = self.v
57
61
  f = forces
58
- self.v = (1.0 - a) * v + a * v.flatten(-2, -1).norm(p=2, dim=-1).unsqueeze(-1).unsqueeze(-1) * f / f.flatten(-2, -1).norm(p=2, dim=-1).unsqueeze(-1).unsqueeze(-1)
62
+ self.v = (1.0 - a) * v + a * v.flatten(-2, -1).norm(p=2, dim=-1).unsqueeze(
63
+ -1).unsqueeze(-1) * f / f.flatten(-2, -1).norm(p=2, dim=-1).unsqueeze(-1).unsqueeze(
64
+ -1)
59
65
  self.Nsteps += 1
60
66
  elif w_vf.any():
61
67
  a = self.a[w_vf].unsqueeze(-1).unsqueeze(-1)
62
68
  v = self.v[w_vf]
63
69
  f = forces[w_vf]
64
- self.v[w_vf] = (1.0 - a) * v + a * v.flatten(-2, -1).norm(p=2, dim=-1).unsqueeze(-1).unsqueeze(-1) * f / f.flatten(-2, -1).norm(p=2, dim=-1).unsqueeze(-1).unsqueeze(-1)
70
+ self.v[w_vf] = (1.0 - a) * v + a * v.flatten(-2, -1).norm(p=2, dim=-1).unsqueeze(
71
+ -1).unsqueeze(-1) * f / f.flatten(-2, -1).norm(p=2, dim=-1).unsqueeze(-1).unsqueeze(
72
+ -1)
65
73
 
66
74
  w_N = self.Nsteps > self.Nmin
67
75
  w_vfN = w_vf & w_N
@@ -109,7 +117,8 @@ class EnForce_ANI(torch.nn.Module):
109
117
  Returns:
110
118
  the energies and forces for the input molecules. One time calculation.
111
119
  """
112
- def __init__(self, ani, name, batchsize_atoms=1024*16):
120
+
121
+ def __init__(self, ani, name, batchsize_atoms=1024 * 16):
113
122
  super().__init__()
114
123
  self.add_module('ani', ani)
115
124
  self.name = name
@@ -134,7 +143,8 @@ class EnForce_ANI(torch.nn.Module):
134
143
  if self.name == "AIMNET":
135
144
  # torch.set_grad_enabled(True)
136
145
  # torch._C._set_grad_enabled(True)
137
- d = self.ani(dict(coord=coord, numbers=numbers, charge=charges)) #Output from the model
146
+ d = self.ani(
147
+ dict(coord=coord, numbers=numbers, charge=charges)) # Output from the model
138
148
  # e = (d['energy'] + d['disp_energy']).to(torch.double)
139
149
  e = d['energy'].to(torch.double)
140
150
  # g = torch.autograd.grad([e.sum()], [coord])[0] # size(100, 23, 3)
@@ -147,13 +157,13 @@ class EnForce_ANI(torch.nn.Module):
147
157
  f = -g
148
158
  elif self.name == "ANI2x":
149
159
  e = self.ani((numbers, coord)).energies
150
- e = e * hartree2ev #ANI2x (torch.models.ANI2x()) output energy unit is Hatree;
151
- #ANI ASE interface unit is eV
160
+ e = e * hartree2ev # ANI2x (torch.models.ANI2x()) output energy unit is Hatree;
161
+ # ANI ASE interface unit is eV
152
162
  g = torch.autograd.grad([e.sum()], [coord])[0]
153
163
  f = -g
154
164
  return e, f
155
165
 
156
- # @torch.jit.script_method
166
+ # @torch.jit.script_method
157
167
  def forward_batched(self, coord, numbers, charges):
158
168
  """Calculate the energies and forces for input molecules.
159
169
 
@@ -171,26 +181,28 @@ class EnForce_ANI(torch.nn.Module):
171
181
  e = []
172
182
  f = []
173
183
  idx = torch.arange(B, device=coord.device)
174
- for batch in idx.split(self.batchsize_atoms // N): #How was the batchsize_atoms decided?
184
+ for batch in idx.split(self.batchsize_atoms // N): # How was the batchsize_atoms decided?
175
185
  _e, _f = self(coord[batch], numbers[batch], charges[batch])
176
186
  e.append(_e)
177
187
  f.append(_f)
178
188
  return torch.cat(e, dim=0), torch.cat(f, dim=0)
179
189
 
190
+
180
191
  def print_stats(state, patience):
181
192
  """Print the optimization status"""
182
193
  numbers = state['numbers']
183
194
  num_total = numbers.size()[0]
184
195
  num_converged_dropped = torch.sum(state['converged_mask']).to('cpu')
185
- oscillating_count = state['oscilating_count'].to('cpu').reshape(-1,) >= patience
196
+ oscillating_count = state['oscilating_count'].to('cpu').reshape(-1, ) >= patience
186
197
  num_dropped = torch.sum(oscillating_count)
187
198
  num_converged = num_converged_dropped - num_dropped
188
199
  num_active = num_total - num_converged_dropped
189
- print("Total 3D structures: %i Converged: %i Dropped(Oscillating): %i Active: %i" %
200
+ print("Total 3D structures: %i Converged: %i Dropped(Oscillating): %i Active: %i" %
190
201
  (num_total, num_converged, num_dropped, num_active), flush=True)
191
202
  # logging.info("Total 3D structures: %i Converged: %i Dropped(Oscillating): %i Active: %i" %
192
203
  # (num_total, num_converged, num_dropped, num_active))
193
204
 
205
+
194
206
  def n_steps(state, n, opttol, patience):
195
207
  """Doing n steps optimization for each input. Only converged structures are
196
208
  modified at each step. n_steps does not change input conformer order.
@@ -207,58 +219,65 @@ def n_steps(state, n, opttol, patience):
207
219
  optimizer = FIRE(coord)
208
220
  # the following two terms are used to detect oscillating conformers
209
221
  smallest_fmax0 = torch.tensor(np.ones((len(coord), 1)) * 999,
210
- dtype=torch.float).to(coord.device)
222
+ dtype=torch.float).to(coord.device)
211
223
  oscilating_count0 = torch.tensor(np.zeros((len(coord), 1)),
212
224
  dtype=torch.float).to(coord.device)
213
225
  state["oscilating_count"] = oscilating_count0
214
- assert(len(coord.shape) == 3)
215
- assert(len(numbers.shape) == 2)
216
- assert(len(charges.shape) == 1)
217
- assert(len(smallest_fmax0.shape) == 2)
218
- assert(len(oscilating_count0.shape) == 2)
219
- for istep in tqdm(range(1, (n+1), 1)):
220
- not_converged = ~ state['converged_mask'] #Essential tracker handle, size fixed
226
+ assert (len(coord.shape) == 3)
227
+ assert (len(numbers.shape) == 2)
228
+ assert (len(charges.shape) == 1)
229
+ assert (len(smallest_fmax0.shape) == 2)
230
+ assert (len(oscilating_count0.shape) == 2)
231
+ for istep in tqdm(range(1, (n + 1), 1)):
232
+ not_converged = ~ state['converged_mask'] # Essential tracker handle, size fixed
221
233
  # stop optimization if all structures converged.
222
234
  if not not_converged.any():
223
235
  break
224
236
 
225
- coord = state['coord'][not_converged] #Subset coordinates, size=not_converged.
237
+ coord = state['coord'][not_converged] # Subset coordinates, size=not_converged.
226
238
  numbers = state['numbers'][not_converged]
227
239
  charges = state['charges'][not_converged]
228
240
  smallest_fmax = smallest_fmax0[not_converged]
229
241
  oscilating_count = state["oscilating_count"][not_converged]
230
242
 
231
243
  coord.requires_grad_(True)
232
- e, f = state['nn'].forward_batched(coord, numbers, charges) #Key step to calculate all energies and forces.
244
+ e, f = state['nn'].forward_batched(coord, numbers,
245
+ charges) # Key step to calculate all energies and forces.
233
246
  coord.requires_grad_(False)
234
247
 
235
248
  coord = optimizer(coord, f)
236
- fmax = f.norm(dim=-1).max(dim=-1)[0] #Tensor, Norm is the length of each vector. Here it returns the maximum force length for ecah conformer. Size (100)
237
- assert(len(fmax.shape) == 1)
249
+ fmax = f.norm(dim=-1).max(dim=-1)[
250
+ 0] # Tensor, Norm is the length of each vector. Here it returns the maximum force length for ecah conformer. Size (100)
251
+ assert (len(fmax.shape) == 1)
238
252
  not_converged_post1 = fmax > opttol
239
253
 
240
- #update smallest_fmax for each molecule
254
+ # update smallest_fmax for each molecule
241
255
  fmax_reduced = fmax.reshape(-1, 1) < smallest_fmax
242
- fmax_reduced = fmax_reduced.reshape(-1,)
256
+ fmax_reduced = fmax_reduced.reshape(-1, )
243
257
  smallest_fmax[fmax_reduced] = fmax.reshape(-1, 1)[fmax_reduced]
244
- #reduce count to 0 for reducing; raise count for non-reducing
258
+ # reduce count to 0 for reducing; raise count for non-reducing
245
259
  oscilating_count[fmax_reduced] = 0
246
260
  fmax_not_reduced = ~fmax_reduced
247
261
  oscilating_count += fmax_not_reduced.reshape(-1, 1)
248
262
  not_oscilating = oscilating_count < patience
249
- not_oscilating = not_oscilating.reshape(-1,)
263
+ not_oscilating = not_oscilating.reshape(-1, )
250
264
  not_converged_post = not_converged_post1 & not_oscilating
251
265
 
252
- optimizer.clean(not_converged_post) #Subset v, a in FIRE for next optimization
253
-
254
- state['converged_mask'][not_converged] = ~ not_converged_post #Update converged_mask, so that converged structures will not be updated in future steps.
255
- state['fmax'][not_converged] = fmax #Update fmax for conformers that are optimized in this iteration
256
- state['energy'][not_converged] = e.detach() #Update energy for conformers that are optimized in this iteration
257
- state['coord'][not_converged] = coord #Update coordinates for conformers that are optimized in this iteration
266
+ optimizer.clean(not_converged_post) # Subset v, a in FIRE for next optimization
267
+
268
+ state['converged_mask'][
269
+ not_converged] = ~ not_converged_post # Update converged_mask, so that converged structures will not be updated in future steps.
270
+ state['fmax'][
271
+ not_converged] = fmax # Update fmax for conformers that are optimized in this iteration
272
+ state['energy'][
273
+ not_converged] = e.detach() # Update energy for conformers that are optimized in this iteration
274
+ state['coord'][
275
+ not_converged] = coord # Update coordinates for conformers that are optimized in this iteration
258
276
  smallest_fmax0[not_converged] = smallest_fmax # update smalles_fmax for each conformer
259
- state["oscilating_count"][not_converged] = oscilating_count #update counts for continuous no reduction in fmax
260
-
261
- if (istep % (n//10)) == 0:
277
+ state["oscilating_count"][
278
+ not_converged] = oscilating_count # update counts for continuous no reduction in fmax
279
+
280
+ if (istep % (n // 10)) == 0:
262
281
  print_stats(state, patience)
263
282
  if istep == (n):
264
283
  print("Reaching maximum optimization step: ", end="")
@@ -286,9 +305,10 @@ def ensemble_opt(net, coord, numbers, charges, param, model, device):
286
305
  numbers = torch.tensor(numbers, dtype=torch.long, device=device)
287
306
  charges = torch.tensor(charges, dtype=torch.long, device=device)
288
307
  converged_mask = torch.zeros(coord.shape[0], dtype=torch.bool, device=device)
289
- fmax = torch.full(coord.shape[:1], 999.0, device=coord.device) # size=N, a tensored filled with 999.0, representing the current maximum forces at each conformer.
308
+ fmax = torch.full(coord.shape[:1], 999.0,
309
+ device=coord.device) # size=N, a tensored filled with 999.0, representing the current maximum forces at each conformer.
290
310
  energy = torch.full(coord.shape[:1], 999.0, dtype=torch.double, device=coord.device)
291
- ids = torch.arange(coord.shape[0], device=coord.device) #Returns a 1D tensor
311
+ ids = torch.arange(coord.shape[0], device=coord.device) # Returns a 1D tensor
292
312
  # optimizer = FIRE(coord)
293
313
 
294
314
  state = dict(
@@ -297,7 +317,7 @@ def ensemble_opt(net, coord, numbers, charges, param, model, device):
297
317
  # optimizer=optimizer, nn=net, fmax=fmax, energy=energy,
298
318
  nn=net, fmax=fmax, energy=energy,
299
319
  timing=defaultdict(float), charges=charges,
300
- he=list(), close=list() #!!! he and close?
320
+ he=list(), close=list() # !!! he and close?
301
321
  )
302
322
 
303
323
  n_steps(state, param['opt_steps'], param['opttol'], param['patience'])
@@ -316,9 +336,10 @@ def ensemble_opt(net, coord, numbers, charges, param, model, device):
316
336
 
317
337
  def padding_coords(lists, pad_value=0.0):
318
338
  lengths = [len(lst) for lst in lists]
319
- pad_length = [max(lengths) - len(lst) for lst in lists]
339
+ max_length = max(lengths)
340
+ pad_length = [max_length - len(lst) for lst in lists]
320
341
  assert (len(pad_length) == len(lists))
321
-
342
+
322
343
  lists_padded = []
323
344
  for i in range(len(pad_length)):
324
345
  lst_i = lists[i]
@@ -327,11 +348,13 @@ def padding_coords(lists, pad_value=0.0):
327
348
  lists_padded.append(lst_i_padded)
328
349
  return lists_padded
329
350
 
351
+
330
352
  def padding_species(lists, pad_value=-1):
331
353
  lengths = [len(lst) for lst in lists]
332
- pad_length = [max(lengths) - len(lst) for lst in lists]
354
+ max_length = max(lengths)
355
+ pad_length = [max_length - len(lst) for lst in lists]
333
356
  assert (len(pad_length) == len(lists))
334
-
357
+
335
358
  lists_padded = []
336
359
  for i in range(len(pad_length)):
337
360
  lst_i = lists[i]
@@ -344,13 +367,13 @@ def padding_species(lists, pad_value=-1):
344
367
  def mols2lists(mols, model):
345
368
  '''mols: rdkit mol object'''
346
369
  species_order = ("H", 'C', 'N', 'O', 'S', 'F', 'Cl')
347
- ani2xt_index = {1:0, 6:1, 7:2, 8:3, 9:4, 16:5, 17:6}
370
+ ani2xt_index = {1: 0, 6: 1, 7: 2, 8: 3, 9: 4, 16: 5, 17: 6}
348
371
  # coord = [[a.coords for a in mol.atoms] for mol in mols]
349
372
  coord = [mol.GetConformer().GetPositions().tolist() for mol in mols]
350
- coord = [[tuple(xyz) for xyz in inner] for inner in coord] #to be consistent with legacy code
373
+ coord = [[tuple(xyz) for xyz in inner] for inner in coord] # to be consistent with legacy code
351
374
  # charges = [mol.charge for mol in mols]
352
375
  charges = [rdmolops.GetFormalCharge(mol) for mol in mols]
353
-
376
+
354
377
  if model == "ANI2xt":
355
378
  # numbers = [[ani2xt_index[a.atomicnum] for a in mol.atoms] for mol in mols]
356
379
  numbers = [[ani2xt_index[a.GetAtomicNum()] for a in mol.GetAtoms()] for mol in mols]
@@ -370,16 +393,18 @@ class optimizing(object):
370
393
  root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
371
394
  if model == "AIMNET":
372
395
  # self.ani = torch.jit.load(os.path.join(root, "models/aimnet2nqed_pc14iall_b97m_sae.jpt"), map_location=device) # Return a ScriptModule object
373
- self.ani = torch.jit.load(os.path.join(root, "models/aimnet2_wb97m_ens_f.jpt"), map_location=device)
396
+ self.ani = torch.jit.load(os.path.join(root, "models/aimnet2_wb97m_ens_f.jpt"),
397
+ map_location=device)
374
398
  elif model == "ANI2xt":
375
399
  self.ani = ANI2xt(device)
376
400
  elif model == "ANI2x":
377
401
  self.ani = torchani.models.ANI2x(periodic_table_index=True).to(device)
378
402
  else:
379
403
  raise ValueError("Model has to be ANI2x, ANI2xt or AIMNET.")
380
-
404
+
381
405
  def run(self):
382
- print("Preparing for parallel optimizing... (Max optimization steps: %i)" % self.config["opt_steps"])
406
+ print("Preparing for parallel optimizing... (Max optimization steps: %i)" % self.config[
407
+ "opt_steps"])
383
408
  # logging.info("Preparing for parallel optimizing... (Max optimization steps: %i)" % self.config["opt_steps"])
384
409
  mols = list(Chem.SDMolSupplier(self.in_f, removeHs=False))
385
410
  print(f"Total 3D conformers: {len(mols)}", flush=True)
@@ -392,13 +417,14 @@ class optimizing(object):
392
417
  coord_padded = padding_coords(coord, 0)
393
418
  numbers_padded = padding_species(numbers, -1)
394
419
 
395
- for p in self.ani.parameters():
420
+ for p in self.ani.parameters():
396
421
  p.requires_grad_(False)
397
- ani = EnForce_ANI(self.ani, self.model, self.config["batchsize_atoms"]) # Interesting, EnForce_ANI inherites nn.module, bu can still accept a ScriptModule object as the input
422
+ ani = EnForce_ANI(self.ani, self.model, self.config[
423
+ "batchsize_atoms"]) # Interesting, EnForce_ANI inherites nn.module, bu can still accept a ScriptModule object as the input
398
424
 
399
425
  with torch.jit.optimized_execution(False):
400
426
  optdict = ensemble_opt(ani, coord_padded, numbers_padded, charges,
401
- self.config, self.model, self.device) #Magic step
427
+ self.config, self.model, self.device) # Magic step
402
428
 
403
429
  energies = optdict['energy']
404
430
  fmax = optdict['fmax']
@@ -416,4 +442,4 @@ class optimizing(object):
416
442
  coord = optdict['coord'][i]
417
443
  for i, atom in enumerate(mol.GetAtoms()):
418
444
  mol.GetConformer().SetAtomPosition(atom.GetIdx(), coord[i])
419
- f.write(mol)
445
+ f.write(mol)
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: Auto3D
3
- Version: 2.2.7
3
+ Version: 2.2.8
4
4
  Summary: Generating Low-energy 3D Conformers from SMILES/SDF
5
5
  Home-page: https://github.com/isayevlab/Auto3D_pkg
6
6
  Author: 'Zhen Liu, Tetiana Zubatiuk, Adrian Roitberg, Olexandr Isayev'
@@ -32,6 +32,9 @@ Requires-Dist: pyyaml
32
32
 
33
33
  Please check out the information at [**documentation**](https://auto3d.readthedocs.io/en/latest/index.html), including [installation](https://auto3d.readthedocs.io/en/latest/installation.html), [usage](https://auto3d.readthedocs.io/en/latest/usage.html), [API](https://auto3d.readthedocs.io/en/latest/api.html) and [citation](https://auto3d.readthedocs.io/en/latest/citation.html).
34
34
 
35
+ - **Jupyter notebook examples** can be found [here](https://github.com/isayevlab/Auto3D_pkg/tree/main/example)
36
+ - To-do list for **improvement and new features** can be found [here](https://github.com/isayevlab/Auto3D_pkg/discussions). You are welcomed to share your thoughts.
37
+ - Bugs go to the [issues](https://github.com/isayevlab/Auto3D_pkg/issues)
35
38
 
36
39
  ## Minimum Dependencies Installatioin
37
40
  1. Python >= 3.7
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes