mattragoza / ligan Goto Github PK
View Code? Open in Web Editor NEWDeep generative models of 3D grids for structure-based drug discovery
License: GNU General Public License v2.0
ligan's People
Contributors
Stargazers
Watchers
Forkers
eriksondale aspirincode xinyangubc plin1112 dkoes bbyun28 wa2003 rmeli sailfish009 layeqa computational-chemistry-research shotaro-0131 yhori991 dunni3 takshan rnaimehaom danny305 jssweller shikhar2333 aliang-cn shiyx409 bwingert handanyu handandiana lsjerry joonseonyoon waseem-abbas05 jeah-z menggf caiyingchun bwang-ecnu xzhiot silver-zhou753 bowen-gao wangdang511 mgyigit somous-jhzhao masterwhook fishundergraduate markussorensen gregoryschwing dharmogata sjwdblligan's Issues
AttributeError when using generate.py
Excuse me, when I use the command python3 generate.py config/generate.config. It appears a problem as follows:
Traceback (most recent call last):
File "generate.py", line 48, in
main(sys.argv[1:])
File "generate.py", line 41, in main
debug=args.debug,
File "/da1/home/changhaoyu/liGAN/liGAN/generating.py", line 98, in init
**output_kws,
File "/da1/home/changhaoyu/liGAN/liGAN/generating.py", line 671, in init
self.metrics = pd.DataFrame(columns=columns).set_index(columns)
File "/home/changhaoyu/anaconda3/envs/py37/lib/python3.7/site-packages/pandas/core/frame.py", line 392, in init
mgr = init_dict(data, index, columns, dtype=dtype)
File "/home/changhaoyu/anaconda3/envs/py37/lib/python3.7/site-packages/pandas/core/internals/construction.py", line 196, in init_dict
nan_dtype)
File "/home/changhaoyu/anaconda3/envs/py37/lib/python3.7/site-packages/pandas/core/dtypes/cast.py", line 1175, in construct_1d_arraylike_from_scalar
dtype = dtype.dtype
AttributeError: type object 'object' has no attribute 'dtype'
How can I solve it?
how I can export embeddings
Is that possible I can export embeddings for a given docked sdf, like .latent file? Thanks
How to evaluate the model?
Segmentation Fault when running tests
=================================================================================== test session starts ====================================================================================
platform linux -- Python 3.7.5, pytest-7.1.2, pluggy-1.0.0
rootdir: /home/jenkins/zhuyuxiao/LiGAN_Project/LiGAN
plugins: timeout-1.4.2, xdist-1.33.0, forked-1.2.0
collected 938 items
tests/test_atom_fitting.py ......................................................................................................................................................... [ 16%]
........................................ [ 20%]
tests/test_atom_grids.py ........ [ 21%]
tests/test_atom_structs.py . [ 21%]
tests/test_atom_types.py ......................................................................FFFFFFFatal Python error: Segmentation fault
Thread 0x00007f82ab7fe700 (most recent call first):
Thread 0x00007f82abfff700 (most recent call first):
Thread 0x00007f82e8f8b700 (most recent call first):
Thread 0x00007f82e878a700 (most recent call first):
Thread 0x00007f8308a88700 (most recent call first):
Thread 0x00007f830bfff700 (most recent call first):
Thread 0x00007f8309289700 (most recent call first):
Thread 0x00007f830a9a7700 (most recent call first):
Current thread 0x00007f8595cc4740 (most recent call first):
File "/home/jenkins/zhuyuxiao/LiGAN/tests/test_atom_types.py", line 124 in test_typer_coord_set
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/python.py", line 192 in pytest_pyfunc_call
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_callers.py", line 39 in _multicall
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_manager.py", line 80 in _hookexec
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_hooks.py", line 265 in call
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/python.py", line 1761 in runtest
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/runner.py", line 166 in pytest_runtest_call
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_callers.py", line 39 in _multicall
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_manager.py", line 80 in _hookexec
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_hooks.py", line 265 in call
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/runner.py", line 259 in
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/runner.py", line 338 in from_call
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/runner.py", line 259 in call_runtest_hook
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/runner.py", line 219 in call_and_report
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/runner.py", line 130 in runtestprotocol
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/runner.py", line 111 in pytest_runtest_protocol
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_callers.py", line 39 in _multicall
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_manager.py", line 80 in _hookexec
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_hooks.py", line 265 in call
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/main.py", line 347 in pytest_runtestloop
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_callers.py", line 39 in _multicall
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_manager.py", line 80 in _hookexec
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_hooks.py", line 265 in call
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/main.py", line 322 in _main
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/main.py", line 268 in wrap_session
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/main.py", line 315 in pytest_cmdline_main
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_callers.py", line 39 in _multicall
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_manager.py", line 80 in _hookexec
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/pluggy/_hooks.py", line 265 in call
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/config/init.py", line 165 in main
File "/home/miniconda3/envs/zyx/lib/python3.7/site-packages/_pytest/config/init.py", line 187 in console_main
File "/home/miniconda3/envs/zyx/bin/pytest", line 8 in
Segmentation fault
Errors when run pytest tests
Hi, @mattragoza I installed LiGAN successfully. But when I run pytest tests, there is a lot of errors occurred:
.............
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <torch.nn.utils.spectral_norm.SpectralNorm object at 0x7f2c7c6d6070>
module = Conv3d(18, 8, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))
do_power_iteration = True
def compute_weight(self, module: Module, do_power_iteration: bool) -> torch.Tensor:
# NB: If `do_power_iteration` is set, the `u` and `v` vectors are
# updated in power iteration **in-place**. This is very important
# because in `DataParallel` forward, the vectors (being buffers) are
# broadcast from the parallelized module to each module replica,
# which is a new module object created on the fly. And each replica
# runs its own spectral norm power iteration. So simply assigning
# the updated vectors to the module this function runs on will cause
# the update to be lost forever. And the next time the parallelized
# module is replicated, the same randomly initialized vectors are
# broadcast and used!
#
# Therefore, to make the change propagate back, we rely on two
# important behaviors (also enforced via tests):
# 1. `DataParallel` doesn't clone storage if the broadcast tensor
# is already on correct device; and it makes sure that the
# parallelized module is already on `device[0]`.
# 2. If the out tensor in `out=` kwarg has correct shape, it will
# just fill in the values.
# Therefore, since the same power iteration is performed on all
# devices, simply updating the tensors in-place will make sure that
# the module replica on `device[0]` will update the _u vector on the
# parallized module (by shared storage).
#
# However, after we update `u` and `v` in-place, we need to **clone**
# them before using them to normalize the weight. This is to support
# backproping through two forward passes, e.g., the common pattern in
# GAN training: loss = D(real) - D(fake). Otherwise, engine will
# complain that variables needed to do backward for the first forward
# (i.e., the `u` and `v` vectors) are changed in the second forward.
weight = getattr(module, self.name + '_orig')
u = getattr(module, self.name + '_u')
v = getattr(module, self.name + '_v')
weight_mat = self.reshape_weight_to_matrix(weight)
if do_power_iteration:
with torch.no_grad():
for _ in range(self.n_power_iterations):
# Spectral norm of weight equals to `u^T W v`, where `u` and `v`
# are the first left and right singular vectors.
# This power iteration produces approximations of `u` and `v`.
> v = normalize(torch.mv(weight_mat.t(), u), dim=0, eps=self.eps, out=v)
E RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling `cublasSgemv(handle, op, m, n, &alpha, a, lda, x, incx, &beta, y, incy)`
../../../miniconda3/envs/LiGAN/lib/python3.9/site-packages/torch/nn/utils/spectral_norm.py:84: RuntimeError
----------------------------- Captured stdout setup ------------------------------
Loading data
Initializing generative model and optimizer
Initializing prior model and optimizer
Initializing atom fitter and bond adder
------------------------------ Captured stdout call ------------------------------
Saving generative model state to tests/output/TEST_VAE2_iter_0.gen_model_state
Saving generative solver state to tests/output/TEST_VAE2_iter_0.gen_solver_state
Saving prior model state to tests/output/TEST_VAE2_iter_0.prior_model_state
Saving prior solver state to tests/output/TEST_VAE2_iter_0.prior_solver_state
Writing training metrics to tests/output/TEST_VAE2.train_metrics
Saving generative model state to tests/output/TEST_VAE2_iter_0.gen_model_state
Saving generative solver state to tests/output/TEST_VAE2_iter_0.gen_solver_state
Saving prior model state to tests/output/TEST_VAE2_iter_0.prior_model_state
Saving prior solver state to tests/output/TEST_VAE2_iter_0.prior_solver_state
------------------------------ Captured stderr call ------------------------------
==============================
*** Open Babel Warning in PerceiveBondOrders
Failed to kekulize aromatic bonds in OBMol::PerceiveBondOrders (title is data/crossdock2020/1A02_HUMAN_25_199_pep_0/1eez_A_rec.pdb)
_____________ TestGenerativeSolver.test_solver_train_and_test[CVAE2] _____________
self = <test_training.TestGenerativeSolver object at 0x7f2d6bd5b970>
solver = CVAE2Solver(
(gen_model): CVAE2(
(input_encoder): GridEncoder(
(level0): Conv3DBlock(
(0): Conv3DR...tures=96, out_features=128, bias=True)
(3): LeakyReLU(negative_slope=0.1)
)
)
(loss_fn): LossFunction()
)
train_params = {'fit_interval': 0, 'max_iter': 10, 'n_test_batches': 1, 'norm_interval': 10, ...}
def test_solver_train_and_test(self, solver, train_params):
max_iter = train_params['max_iter']
test_interval = train_params['test_interval']
n_test_batches = train_params['n_test_batches']
t0 = time.time()
> solver.train_and_test(**train_params)
tests/test_training.py:534:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
ligan/training.py:37: in wrapper
return method(self, *args, **kwargs)
ligan/training.py:1163: in train_and_test
self.test_models(n_batches=n_test_batches, fit_atoms=fit_atoms)
ligan/training.py:1056: in test_models
self.test_model(
ligan/training.py:1023: in test_model
loss, metrics = self.gen_forward(
ligan/training.py:625: in gen_forward
self.gen_model(
../../../miniconda3/envs/LiGAN/lib/python3.9/site-packages/torch/nn/modules/module.py:1130: in _call_impl
return forward_call(*input, **kwargs)
ligan/models.py:1130: in forward
(means, log_stds), _ = self.input_encoder(inputs)
../../../miniconda3/envs/LiGAN/lib/python3.9/site-packages/torch/nn/modules/module.py:1130: in _call_impl
return forward_call(*input, **kwargs)
ligan/models.py:682: in forward
outputs = f(inputs)
../../../miniconda3/envs/LiGAN/lib/python3.9/site-packages/torch/nn/modules/module.py:1130: in _call_impl
return forward_call(*input, **kwargs)
ligan/models.py:364: in forward
outputs = f(inputs)
../../../miniconda3/envs/LiGAN/lib/python3.9/site-packages/torch/nn/modules/module.py:1130: in _call_impl
return forward_call(*input, **kwargs)
../../../miniconda3/envs/LiGAN/lib/python3.9/site-packages/torch/nn/modules/container.py:139: in forward
input = module(input)
../../../miniconda3/envs/LiGAN/lib/python3.9/site-packages/torch/nn/modules/module.py:1137: in _call_impl
result = hook(self, input)
../../../miniconda3/envs/LiGAN/lib/python3.9/site-packages/torch/nn/utils/spectral_norm.py:105: in __call__
setattr(module, self.name, self.compute_weight(module, do_power_iteration=module.training))
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <torch.nn.utils.spectral_norm.SpectralNorm object at 0x7f2c7c958760>
module = Conv3d(36, 8, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))
do_power_iteration = True
def compute_weight(self, module: Module, do_power_iteration: bool) -> torch.Tensor:
# NB: If `do_power_iteration` is set, the `u` and `v` vectors are
# updated in power iteration **in-place**. This is very important
# because in `DataParallel` forward, the vectors (being buffers) are
# broadcast from the parallelized module to each module replica,
# which is a new module object created on the fly. And each replica
# runs its own spectral norm power iteration. So simply assigning
# the updated vectors to the module this function runs on will cause
# the update to be lost forever. And the next time the parallelized
# module is replicated, the same randomly initialized vectors are
# broadcast and used!
#
# Therefore, to make the change propagate back, we rely on two
# important behaviors (also enforced via tests):
# 1. `DataParallel` doesn't clone storage if the broadcast tensor
# is already on correct device; and it makes sure that the
# parallelized module is already on `device[0]`.
# 2. If the out tensor in `out=` kwarg has correct shape, it will
# just fill in the values.
# Therefore, since the same power iteration is performed on all
# devices, simply updating the tensors in-place will make sure that
# the module replica on `device[0]` will update the _u vector on the
# parallized module (by shared storage).
#
# However, after we update `u` and `v` in-place, we need to **clone**
# them before using them to normalize the weight. This is to support
# backproping through two forward passes, e.g., the common pattern in
# GAN training: loss = D(real) - D(fake). Otherwise, engine will
# complain that variables needed to do backward for the first forward
# (i.e., the `u` and `v` vectors) are changed in the second forward.
weight = getattr(module, self.name + '_orig')
u = getattr(module, self.name + '_u')
v = getattr(module, self.name + '_v')
weight_mat = self.reshape_weight_to_matrix(weight)
if do_power_iteration:
with torch.no_grad():
for _ in range(self.n_power_iterations):
# Spectral norm of weight equals to `u^T W v`, where `u` and `v`
# are the first left and right singular vectors.
# This power iteration produces approximations of `u` and `v`.
> v = normalize(torch.mv(weight_mat.t(), u), dim=0, eps=self.eps, out=v)
E RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling `cublasSgemv(handle, op, m, n, &alpha, a, lda, x, incx, &beta, y, incy)`
../../../miniconda3/envs/LiGAN/lib/python3.9/site-packages/torch/nn/utils/spectral_norm.py:84: RuntimeError
----------------------------- Captured stdout setup ------------------------------
Loading data
Initializing generative model and optimizer
Initializing prior model and optimizer
Initializing atom fitter and bond adder
------------------------------ Captured stdout call ------------------------------
Saving generative model state to tests/output/TEST_CVAE2_iter_0.gen_model_state
Saving generative solver state to tests/output/TEST_CVAE2_iter_0.gen_solver_state
Saving prior model state to tests/output/TEST_CVAE2_iter_0.prior_model_state
Saving prior solver state to tests/output/TEST_CVAE2_iter_0.prior_solver_state
Writing training metrics to tests/output/TEST_CVAE2.train_metrics
Saving generative model state to tests/output/TEST_CVAE2_iter_0.gen_model_state
Saving generative solver state to tests/output/TEST_CVAE2_iter_0.gen_solver_state
Saving prior model state to tests/output/TEST_CVAE2_iter_0.prior_model_state
Saving prior solver state to tests/output/TEST_CVAE2_iter_0.prior_solver_state
------------------------------ Captured stderr call ------------------------------
==============================
*** Open Babel Warning in PerceiveBondOrders
Failed to kekulize aromatic bonds in OBMol::PerceiveBondOrders (title is data/crossdock2020/1A02_HUMAN_25_199_pep_0/1eez_A_rec.pdb)
================================ warnings summary ================================
tests/test_atom_fitting.py: 21 warnings
tests/test_training.py: 112 warnings
/NAS/lh/software/miniconda3/envs/LiGAN/lib/python3.9/site-packages/torch/cuda/memory.py:278: FutureWarning: torch.cuda.reset_max_memory_allocated now calls torch.cuda.reset_peak_memory_stats, which resets /all/ peak memory stats.
warnings.warn(
tests/test_atom_grids.py::TestAtomGrid::test_get_coords
/NAS/lh/software/liGAN/new/LiGAN/./ligan/atom_grids.py:163: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
idx = idx // dim
tests/test_models.py::test_interpolate
/NAS/lh/software/liGAN/new/LiGAN/tests/test_models.py:50: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
start_idx = (interp_step + batch_idxs) // n_samples
-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
============================ short test summary info =============================
FAILED tests/test_bond_adding.py::TestBondAdding::test_make_ob_mol[oadc-tests/input/benzene.sdf]
FAILED tests/test_bond_adding.py::TestBondAdding::test_make_ob_mol[oadc-tests/input/neopentane.sdf]
FAILED tests/test_bond_adding.py::TestBondAdding::test_make_ob_mol[oadc-tests/input/ATP.sdf]
FAILED tests/test_bond_adding.py::TestBondAdding::test_make_ob_mol[oadc-tests/input/4fic_C_0UL.sdf]
FAILED tests/test_data.py::TestMolDataset::test_benchmark[False] - ValueError: ...
FAILED tests/test_data.py::TestMolDataset::test_benchmark[True] - AssertionErro...
FAILED tests/test_models.py::TestConv3DReLU::test_forward_cuda[Conv3DReLU] - Ru...
FAILED tests/test_models.py::TestConv3DReLU::test_forward_cuda[TConv3DReLU] - R...
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[Conv3DBlock-c-1]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[Conv3DBlock-c-2]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[Conv3DBlock-c-4]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[Conv3DBlock-r-1]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[Conv3DBlock-r-2]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[Conv3DBlock-r-4]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[Conv3DBlock-d-1]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[Conv3DBlock-d-2]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[Conv3DBlock-d-4]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[TConv3DBlock-c-1]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[TConv3DBlock-c-2]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[TConv3DBlock-c-4]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[TConv3DBlock-r-1]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[TConv3DBlock-r-2]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[TConv3DBlock-r-4]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[TConv3DBlock-d-1]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[TConv3DBlock-d-2]
FAILED tests/test_models.py::TestConv3DBlock::test_forward_cuda[TConv3DBlock-d-4]
FAILED tests/test_models.py::TestGridEncoder::test_enc1_forward - RuntimeError:...
FAILED tests/test_models.py::TestGridEncoder::test_enc1_backward0 - RuntimeErro...
FAILED tests/test_models.py::TestGridEncoder::test_enc1_backward1 - RuntimeErro...
FAILED tests/test_models.py::TestGridEncoder::test_enc2_forward - RuntimeError:...
FAILED tests/test_models.py::TestGridEncoder::test_enc2_backward0 - RuntimeErro...
FAILED tests/test_models.py::TestGridEncoder::test_enc2_backward1 - RuntimeErro...
FAILED tests/test_models.py::TestGridDecoder::test_forward - RuntimeError: CUDA...
FAILED tests/test_models.py::TestGridDecoder::test_backward0 - RuntimeError: CU...
FAILED tests/test_models.py::TestGridDecoder::test_backward1 - RuntimeError: CU...
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[AE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[AE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[CE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[CE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[VAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[VAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[CVAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[CVAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[GAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[GAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[CGAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[CGAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[VAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[VAE2-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[CVAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_poster[CVAE2-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[AE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[AE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[CE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[CE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[VAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[VAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[CVAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[CVAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[GAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[GAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[CGAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[CGAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[VAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[VAE2-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[CVAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_forward_prior[CVAE2-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[AE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[AE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[CE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[CE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[VAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[VAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[CVAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[CVAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[GAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[GAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[CGAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[CGAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[VAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[VAE2-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[CVAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster0[CVAE2-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[AE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[AE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[CE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[CE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[VAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[VAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[CVAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[CVAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[GAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[GAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[CGAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[CGAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[VAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[VAE2-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[CVAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_poster1[CVAE2-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[AE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[AE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[CE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[CE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[VAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[VAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[CVAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[CVAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[GAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[GAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[CGAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[CGAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[VAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[VAE2-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[CVAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior0[CVAE2-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[AE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[AE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[CE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[CE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[VAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[VAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[CVAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[CVAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[GAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[GAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[CGAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[CGAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[VAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[VAE2-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[CVAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_backward_prior1[CVAE2-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[AE-0-c-0] - ...
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[AE-1-c-0] - ...
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[CE-0-c-0] - ...
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[CE-1-c-0] - ...
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[VAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[VAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[CVAE-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[CVAE-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[GAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[GAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[CGAN-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[CGAN-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[VAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[VAE2-1-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[CVAE2-0-c-0]
FAILED tests/test_models.py::TestGridGenerator::test_gen_benchmark[CVAE2-1-c-0]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_poster[AE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_poster[CE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_poster[VAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_poster[CVAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_poster[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_poster[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_poster[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_poster[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_prior[VAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_prior[CVAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_prior[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_prior[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_prior[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_prior[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_prior[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_prior[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_poster2[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_poster2[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_prior2[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_forward_prior2[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_forward_real[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_forward_real[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_forward_real[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_forward_real[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_forward_poster[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_forward_poster[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_forward_prior[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_forward_prior[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_forward_prior[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_forward_prior[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_poster[AE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_poster[CE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_poster[VAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_poster[CVAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_poster[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_poster[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_poster[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_poster[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_prior[CVAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_prior[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_prior[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_prior[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_prior[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_prior[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_poster2[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_poster2[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_backward_prior2[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_backward_real[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_backward_real[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_backward_real[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_backward_real[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_backward_poster[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_backward_poster[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_backward_prior[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_backward_prior[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_backward_prior[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_backward_prior[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_poster[AE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_poster[CE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_poster[VAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_poster[CVAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_poster[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_poster[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_poster[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_poster[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_prior[CVAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_prior[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_prior[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_prior[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_prior[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_gen_step_prior[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_step_real[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_step_real[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_step_real[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_step_real[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_step_poster[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_step_poster[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_step_prior[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_step_prior[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_step_prior[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_disc_step_prior[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_state[AE] - Ru...
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_state[CE] - Ru...
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_state[VAE] - R...
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_state[CVAE] - ...
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_state[GAN] - R...
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_state[CGAN] - ...
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_state[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_state[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_state[VAE2] - ...
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_state[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_disc[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_disc[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_disc[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_disc[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen[AE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen[CE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen[VAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen[CVAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen_fit[AE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen_fit[CE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen_fit[VAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen_fit[CVAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen_fit[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen_fit[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen_fit[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen_fit[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen_fit[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_gen_fit[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_models[AE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_models[CE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_models[VAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_models[CVAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_models[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_models[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_models[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_models[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_models[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_test_models[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_gen[AE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_gen[CE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_gen[VAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_gen[CVAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_gen[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_gen[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_gen[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_gen[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_gen[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_gen[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_disc[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_disc[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_disc[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_disc[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models[AE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models[CE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models[VAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models[CVAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models_noup[AE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models_noup[CE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models_noup[VAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models_noup[CVAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models_noup[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models_noup[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models_noup[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models_noup[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models_noup[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_models_noup[CVAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_and_test[AE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_and_test[CE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_and_test[VAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_and_test[CVAE]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_and_test[GAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_and_test[CGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_and_test[VAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_and_test[CVAEGAN]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_and_test[VAE2]
FAILED tests/test_training.py::TestGenerativeSolver::test_solver_train_and_test[CVAE2]
ERROR tests/test_data.py::TestAtomGridData::test_data_init[data/test_pockets/AROK_MYCTU_1_176_0/fixed_input_1zyu_A_rec_mutants.types]
ERROR tests/test_data.py::TestAtomGridData::test_data_init[data/test_pockets/AROK_MYCTU_1_176_0/fixed_cond_1zyu_A_rec_mutants.types]
ERROR tests/test_data.py::TestAtomGridData::test_data_find_real_mol[data/test_pockets/AROK_MYCTU_1_176_0/fixed_input_1zyu_A_rec_mutants.types]
ERROR tests/test_data.py::TestAtomGridData::test_data_find_real_mol[data/test_pockets/AROK_MYCTU_1_176_0/fixed_cond_1zyu_A_rec_mutants.types]
ERROR tests/test_data.py::TestAtomGridData::test_data_forward[data/test_pockets/AROK_MYCTU_1_176_0/fixed_input_1zyu_A_rec_mutants.types]
ERROR tests/test_data.py::TestAtomGridData::test_data_forward[data/test_pockets/AROK_MYCTU_1_176_0/fixed_cond_1zyu_A_rec_mutants.types]
ERROR tests/test_data.py::TestAtomGridData::test_data_split[data/test_pockets/AROK_MYCTU_1_176_0/fixed_input_1zyu_A_rec_mutants.types]
ERROR tests/test_data.py::TestAtomGridData::test_data_split[data/test_pockets/AROK_MYCTU_1_176_0/fixed_cond_1zyu_A_rec_mutants.types]
ERROR tests/test_data.py::TestAtomGridData::test_data_no_transform - ValueError...
ERROR tests/test_data.py::TestAtomGridData::test_data_rand_rotate - ValueError:...
ERROR tests/test_data.py::TestAtomGridData::test_data_rand_translate - ValueErr...
ERROR tests/test_data.py::TestAtomGridData::test_data_diff_cond_transform - Val...
ERROR tests/test_data.py::TestAtomGridData::test_data_consecutive - ValueError:...
ERROR tests/test_data.py::TestAtomGridData::test_data_benchmark[data/test_pockets/AROK_MYCTU_1_176_0/fixed_input_1zyu_A_rec_mutants.types]
ERROR tests/test_data.py::TestAtomGridData::test_data_benchmark[data/test_pockets/AROK_MYCTU_1_176_0/fixed_cond_1zyu_A_rec_mutants.types]
ERROR tests/test_generating.py::TestGenerator::test_generator_init[data/test_pockets/AROK_MYCTU_1_176_0/fixed_input_1zyu_A_rec_mutants.types]
ERROR tests/test_generating.py::TestGenerator::test_generator_init[data/test_pockets/AROK_MYCTU_1_176_0/fixed_cond_1zyu_A_rec_mutants.types]
ERROR tests/test_generating.py::TestGenerator::test_gen_forward[data/test_pockets/AROK_MYCTU_1_176_0/fixed_input_1zyu_A_rec_mutants.types]
ERROR tests/test_generating.py::TestGenerator::test_gen_forward[data/test_pockets/AROK_MYCTU_1_176_0/fixed_cond_1zyu_A_rec_mutants.types]
ERROR tests/test_generating.py::TestGenerator::test_gen_forward2[data/test_pockets/AROK_MYCTU_1_176_0/fixed_input_1zyu_A_rec_mutants.types]
ERROR tests/test_generating.py::TestGenerator::test_gen_forward2[data/test_pockets/AROK_MYCTU_1_176_0/fixed_cond_1zyu_A_rec_mutants.types]
ERROR tests/test_generating.py::TestGenerator::test_generate[data/test_pockets/AROK_MYCTU_1_176_0/fixed_input_1zyu_A_rec_mutants.types]
ERROR tests/test_generating.py::TestGenerator::test_generate[data/test_pockets/AROK_MYCTU_1_176_0/fixed_cond_1zyu_A_rec_mutants.types]
====== 316 failed, 599 passed, 135 warnings, 23 errors in 210.03s (0:03:30) ======
I don't know if it's a cuda issue. Thanks!
License
Hello! Are there plans to add an OSI-approved license?
model cannot be trained
rd_mol_to_ob_mol conversion loses aromaticity information
When using molecules.rd_mol_to_ob_mol to convert an RDKit molecule to a OpenBabel molecule, aromaticity information seem to be lost, which results in erroneous atom types when gridding.
from molecules import rd_mol_to_ob_mol
from rdkit import Chem
from rdkit.Chem import AllChem
from openbabel import pybel
rdmol = Chem.MolFromSmiles("c1ccccc1")
AllChem.EmbedMolecule(rdmol)
w = Chem.SDWriter('rdmol.sdf')
w.write(rdmol)
w.close()
obmol = rd_mol_to_ob_mol(rdmol)
pybel.Molecule(obmol).write("sdf", "obmol.sdf", overwrite=True)How did you install rdkit?
Hi,
I have successfully installed gnina caffe, but I can not install rdkit. I want to ask how did you install rdkit (I guess you might not use conda right?)?
Here are my dependencies:
- ubuntu 18.04
- python (3.6.9 using system python)
- all other dependencies are no problem.
- rdkit built from source and shows the following errors:
CMakeFiles/testCoordGen.dir/test.cpp.o: In functionunsigned int RDKit::CoordGen::addCoords<RDKit::ROMol>(RDKit::ROMol&, RDKit::CoordGen::CoordGenParams const*)': test.cpp:(.text._ZN5RDKit8CoordGen9addCoordsINS_5ROMolEEEjRT_PKNS0_14CoordGenParamsE[_ZN5RDKit8CoordGen9addCoordsINS_5ROMolEEEjRT_PKNS0_14CoordGenParamsE]+0xff9): undefined reference toCoordgenFragmenter::splitIntoFragments(sketcherMinimizerMolecule*)'
CMakeFiles/testCoordGen.dir/test.cpp.o: In functionunsigned int RDKit::CoordGen::addCoords<RDKit::RWMol>(RDKit::RWMol&, RDKit::CoordGen::CoordGenParams const*)': test.cpp:(.text._ZN5RDKit8CoordGen9addCoordsINS_5RWMolEEEjRT_PKNS0_14CoordGenParamsE[_ZN5RDKit8CoordGen9addCoordsINS_5RWMolEEEjRT_PKNS0_14CoordGenParamsE]+0xff9): undefined reference toCoordgenFragmenter::splitIntoFragments(sketcherMinimizerMolecule*)'
collect2: error: ld returned 1 exit status
External/CoordGen/CMakeFiles/testCoordGen.dir/build.make:133: recipe for target 'External/CoordGen/testCoordGen' failed
make[2]: *** [External/CoordGen/testCoordGen] Error 1
CMakeFiles/Makefile2:3742: recipe for target 'External/CoordGen/CMakeFiles/testCoordGen.dir/all' failed
make[1]: *** [External/CoordGen/CMakeFiles/testCoordGen.dir/all] Error 2
Makefile:182: recipe for target 'all' failed
make: *** [all] Error 2
Looking forward to your reply.
Compounds with biaryl or fused ring
When the seed molecule contains biaryl or fused rings, atom fitting algorithm generates incorrect number of atoms.
For example, when I tried with 5qax, all generated rings were 5-membered rings.
I guessed that the grid density of these compounds are well overlapped and make it difficult to generate correct number of atoms.
To overcome this problem, I've changed radious_scale of gmaker in train.py and generate.py from 1.0 to 0.8. But it did't work well, because the grid value were very small to put atoms.
Do you have any ideas for this problems?
Another test set are 5d7x and 2x7t.
Segmentation fault (core dumped)
Hi,
I downloaded the code and try to run generate.py. But got a core dumped error, while importing liGAN.
Any idea of where the problem should be?
AttributeError: type object 'object' has no attribute 'dtype'
Excuse me, when I use the command python3 generate.py config/generate.config. It appears a problem as follows:
Traceback (most recent call last):
File "generate.py", line 48, in
main(sys.argv[1:])
File "generate.py", line 41, in main
debug=args.debug,
File "/da1/home/changhaoyu/liGAN/liGAN/generating.py", line 98, in init
**output_kws,
File "/da1/home/changhaoyu/liGAN/liGAN/generating.py", line 671, in init
self.metrics = pd.DataFrame(columns=columns).set_index(columns)
File "/home/changhaoyu/anaconda3/envs/py37/lib/python3.7/site-packages/pandas/core/frame.py", line 392, in init
mgr = init_dict(data, index, columns, dtype=dtype)
File "/home/changhaoyu/anaconda3/envs/py37/lib/python3.7/site-packages/pandas/core/internals/construction.py", line 196, in init_dict
nan_dtype)
File "/home/changhaoyu/anaconda3/envs/py37/lib/python3.7/site-packages/pandas/core/dtypes/cast.py", line 1175, in construct_1d_arraylike_from_scalar
dtype = dtype.dtype
AttributeError: type object 'object' has no attribute 'dtype'
How can I solve it?
Originally posted by @Matheo-Chang in #36 (comment)
colab crashed when loading data
when I run %run generate.py config/generate.config
colab crashed,and I tried restart,but the result was still the same
could u please tell me why?
how to fit a grid density to atoms and molecules?
Hi,
I am trying to fit a density to atoms, then adding bonds to these atoms and obtain the molecules.
- which code is used for this function? (simple_fit.py)
- do we always need a reference grid in order to fitting grid density to atoms?
looking forward to your reply. Thank you.
training error.
Hi,
when I run your train.py file. I got this error: [libprotobuf ERROR google/protobuf/message_lite.cc:244] Error computing ByteSize (possible overflow?).
F1210 06:03:40.463183 1051 io.cpp:69] Check failed: proto.SerializeToOstream(&output)
*** Check failure stack trace: ***
Aborted (core dumped)
Do you know how to solve it? Thank you.
Aborted (core dumped) when generate molecules
Hello, when I use generate.py config/generate.config. It appears a problem as follows, and i couldn't locate the problem. Do you have some advices?
Setting random seed to 0
Loading data
Initializing generative model
Loading generative model state
Initializing atom fitter
Initializing bond adder
Initializing output writer
Empty DataFrame
Columns: []
Index: []
Starting to generate grids
0 0 0 0
Calling generator forward
prior = 0
stage2 = False
Getting next batch of data
Aborted (core dumped)
change configuration file for prior (no lig) sampling
I found that the default generate.config file provided is for posterior sampling (with ligand) https://github.com/mattragoza/LiGAN/blob/master/config/generate.config
What parameter(s) I need to change for prior (no lig) sampling as input file I need to provide has ligand information? "prior"? "post_factor"? anything else? Thanks,
a sample prior generate.config file is appreciated
How I can use pre-trained model to generate new chemistry with my pdb file (protein+ligand)
Thanks,
Sulfonyl group
I've noticed that when the seed molecule contains a sulfonyl group, the generated molecule (with variability factor 1.0) often contain a sulfur atoms bound to two oxygen atoms with a single bond instead of a double bond and they end up being negatively charged. This causes the molecule to break during optimization with UFF (there is not compensating +2 charge on sulfur).
I haven't been able to track down this problem so far, but I think it could be beneficial to add additional sanitization steps to generated molecules (standardization and of functional groups and neutralization of the whole molecule)?
tests ValueError: File does not exist: data/test_pockets/xxx
ERROR tests/test_generating.py::TestGenerator::test_generator_init[data/test_pockets/AROK_MYCTU_1_176_0/fixed_input_1zyu_A_rec_mutants.types] - ValueError: Could not open ...
ERROR tests/test_generating.py::TestGenerator::test_generator_init[data/test_pockets/AROK_MYCTU_1_176_0/fixed_cond_1zyu_A_rec_mutants.types] - ValueError: Could not open f...
ERROR tests/test_generating.py::TestGenerator::test_gen_forward[data/test_pockets/AROK_MYCTU_1_176_0/fixed_input_1zyu_A_rec_mutants.types] - ValueError: Could not open fil...
ERROR tests/test_generating.py::TestGenerator::test_gen_forward[data/test_pockets/AROK_MYCTU_1_176_0/fixed_cond_1zyu_A_rec_mutants.types] - ValueError: Could not open file...
ERROR tests/test_generating.py::TestGenerator::test_gen_forward2[data/test_pockets/AROK_MYCTU_1_176_0/fixed_input_1zyu_A_rec_mutants.types] - ValueError: Could not open fi...
ERROR tests/test_generating.py::TestGenerator::test_gen_forward2[data/test_pockets/AROK_MYCTU_1_176_0/fixed_cond_1zyu_A_rec_mutants.types] - ValueError: Could not open fil...
ERROR tests/test_generating.py::TestGenerator::test_generate[data/test_pockets/AROK_MYCTU_1_176_0/fixed_input_1zyu_A_rec_mutants.types] - ValueError: Could not open file d...
ERROR tests/test_generating.py::TestGenerator::test_generate[data/test_pockets/AROK_MYCTU_1_176_0/fixed_cond_1zyu_A_rec_mutants.types] - ValueError: Could not open file da...
How to train model on multiple GPUs?
In my environment, The speed of training model on single GPU is slow. Coud the model be trained on multiple GPUs? Thank you very much!
I want to train a model with the data I have.
I'm trying to learn, but there is no problem with the ligand part, but the receptor part is a problem.
Looking at the receptor structure you used, I am not using the entire pdb file, but cutting and inputting only the necessary parts from the entire pdb file.
You only need to solve this part to learn new, so I ask you a question.
And if you want to learn for the purpose of generation, please let me know a few days ago.
"{class_label:d} {affinity:f} {RMSD:f} {receptor_path} {ligand_path}" I want to know if affinity and RMSD are required for learning to proceed.
exist liGAN.model file?
I want to use your liGAN model. However, it is difficult because various problems occur in the environment setting.
Could you please configure it as a colab example?
model cannot be trained
When I attempted to train the code with train.py and the provided simple example it2_tt_0_lowrmsd_valid_mols_test0_1000.types and crossdock folder, the model froze in the dataloader next_batch part.
Looking forward to your help!
.types format for sdf file only
thank for you a great paper published. I am trying to load sdf (ligand) only to libmolgrid to generate 3d ligands. could you tell me the format of .types for only ligand (no pdb included)?
I tried only sdf, but this error happens:
e.populate('test.types')
ValueError: Example has no label at position 0. There are only 0 labels
.......................................................
the information i used in test.types file
"" cat test.types"
1.sdf
2.sdf
...
cannot run example, hung at GetBestRMS in rdkit
Thank you for this great job on liGAN. I installed liGAN to run the examples, 'python3 generate.py config/generate.config', it hung at the 27th(28th?) example, i.e.
1 0 1.36521 PA2GA_HUMAN_21_144_0/5g3n_A_rec.pdb PA2GA_HUMAN_21_144_0/5g3n_A_rec_1poe_gel_lig_tt_docked_0.sdf.gz #-6.74282
I had to specify the maxMatches in GetBestRMS to avoid hanging up. I installed the latest rdkit('2022.03.2'), not sure if it matters.
Thanks
SA_Score and NP_Score
I found
"from SA_Score import sascorer
from NP_Score import npscorer"
in generate.py. But I failed to find where the declaration of these functions are. Could you provide them?
how to set the input for simple_fit.py and test_dkoes_simple_fit.py
Hi,
I am trying to use simple_fit.py and test_dkoes_simple_fit.py to obtain a molecules from a grid. I tried the following setting for the input path of sdf file:
--for simple_fit.py, I used the exact same code and input a sdf file.
if name == 'main':
results = []
print('Globbing input files')
files = glob.glob('/home.local/Level_admin/yang/liGAN/1b3g_ligand.sdf')
print (files)
print('Starting to fit molecules')
for (i,fname) in enumerate(files):
print (i,fname)
try:
start = time.time()
struct, fittime, loss, fixes, rmsd = fitmol(fname,25)
mol,misses = make_mol(struct)
mol = pybel.Molecule(mol)
totaltime = time.time()-start
ligname = os.path.split(fname)[1]
mol.write('sdf','output/fit_%s'%ligname,overwrite=True)
print('{}/{}'.format(i+1, len(files)))
except Exception as e:
print("Failed",fname,e)
results = pd.DataFrame(results,columns=('lig','loss','fixes','fittime','totaltime','misses','rmsd'))
results.to_csv('cntfixes.csv')
sns.boxplot(data=results,x='misses',y='loss')
plt.savefig('loss_by_misses_box.png')
plt.hist(results.loss,bins=np.logspace(-6,1,8))
plt.gca().set_xscale('log')
plt.savefig('loss_hist.png')
print('Low loss but nonzero misses, sorted by misses:')
print(results[(results.loss < 0.1) & (results.misses > 0)].sort_values(by='misses'))
print('Overall average loss:')
print(np.mean(results.loss))
plt.hist(results.fittime)
plt.savefig('fit_time_hist.png')
print('Average fit time and total time')
print(np.mean(results.fittime))
print(np.mean(results.totaltime))
print('Undefined RMSD sorted by loss:')
print(results[np.isinf(results.rmsd)].sort_values(by='loss'))
print('All results sorted by loss:')
print(results.sort_values(by='loss'))
and got the following error: Failed /home.local/Level_admin/yang/liGAN/1b3g_ligand.sdf Invalid input dimensions in forward of Coords2Grid
what is your final KL loss value in your liGAN paper?
Hi
I obtained over 90% valid percentage of posterior sampling of liGAN, but I got 0% valid percentage from prior sampling of liGAN.
My final KL loss is around 3, which i think it is already small.
I want to ask what is your final KL loss in you liGAN paper? since this loss is not reported in your results.
Thank you!
Error when run cmake of libmogrid
Hi, when I run cmake of libmogrid, there is an error as below:
cmake .. \
-DCMAKE_INSTALL_PREFIX=$CONDA_PREFIX \
-DOPENBABEL3_INCLUDE_DIR=$CONDA_PREFIX/include/openbabel3 \
-DOPENBABEL3_LIBRARIES=$CONDA_PREFIX/lib/libopenbabel.so \
-DZLIB_LIBRARY=$CONDA_PREFIX/lib/libz.so
CMake Error at /NAS/lh/software/miniconda3/envs/LiGAN/share/cmake-3.24/Modules/CMakeDetermineCXXCompiler.cmake:48 (message):
Could not find compiler set in environment variable CXX:
/NAS/lh/software/miniconda3/bin/x86_64-conda-linux-gnu-c++.
Call Stack (most recent call first):
CMakeLists.txt:2 (project)
CMake Error: CMAKE_CXX_COMPILER not set, after EnableLanguage
CMake Error: CMAKE_CUDA_COMPILER not set, after EnableLanguage
-- Configuring incomplete, errors occurred!
See also "/NAS/lh/software/liGAN/new/libmolgrid/build/CMakeFiles/CMakeOutput.log".
I don't know how to solve it. Thanks!
Conflict between RDKIT and conda-molgrid
Hi, I try to install molgrid using conda-molgrid. When I finished installing molgrid, there was an error installing RDKit:
conda install -c conda-forge rdkit
Solving environment: failed with repodata from current_repodata.json, will retry with next repodata source.
Collecting package metadata (repodata.json): done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.
Solving environment: /
Found conflicts! Looking for incompatible packages.
This can take several minutes. Press CTRL-C to abort. | failed
I try to install rdkit from source, but there is still an error:
make[1]: *** [Code/GraphMol/CMakeFiles/graphmoltestChirality.dir/all] Error 2
[ 61%] Linking CXX static library libRDKitDescriptors_static.a
[ 61%] Built target Descriptors_static
[ 61%] Linking CXX executable graphmolMolOpsTest
/NAS/lh/software/miniconda3/envs/molgrid/bin/../lib/gcc/x86_64-conda-linux-gnu/9.4.0/../../../../x86_64-conda-linux-gnu/bin/ld: warning: libboost_iostreams-mt.so.1.53.0, needed by /usr/local/lib/libmaeparser.so, not found (try using -rpath or -rpath-link)
/NAS/lh/software/miniconda3/envs/molgrid/bin/../lib/gcc/x86_64-conda-linux-gnu/9.4.0/../../../../x86_64-conda-linux-gnu/bin/ld: warning: libboost_regex-mt.so.1.53.0, needed by /usr/local/lib/libmaeparser.so, not found (try using -rpath or -rpath-link)
/NAS/lh/software/miniconda3/envs/molgrid/bin/../lib/gcc/x86_64-conda-linux-gnu/9.4.0/../../../../x86_64-conda-linux-gnu/bin/ld: ../../lib/libRDKitFileParsers.so.1.2022.09.1pre: undefined reference to `schrodinger::mae::Block::getIndexedBlock(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)'
/NAS/lh/software/miniconda3/envs/molgrid/bin/../lib/gcc/x86_64-conda-linux-gnu/9.4.0/../../../../x86_64-conda-linux-gnu/bin/ld: ../../lib/libRDKitDepictor.so.1.2022.09.1pre: undefined reference to `sketcherMinimizer::setTemplateFileDir(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)'
/NAS/lh/software/miniconda3/envs/molgrid/bin/../lib/gcc/x86_64-conda-linux-gnu/9.4.0/../../../../x86_64-conda-linux-gnu/bin/ld: ../../lib/libRDKitFileParsers.so.1.2022.09.1pre: undefined reference to `schrodinger::mae::Reader::next(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)'
collect2: error: ld returned 1 exit status
make[2]: *** [Code/GraphMol/graphmolMolOpsTest] Error 1
make[1]: *** [Code/GraphMol/CMakeFiles/graphmolMolOpsTest.dir/all] Error 2
make: *** [all] Error 2
Is the generated molecules really conditional on the receptor?
Hi, I have questions for your paper: Generating 3D Molecular Structures Conditional on a
Receptor Binding Site with Deep Generative Models.
- You include binding pocket in both encoder and decoder of VAE, but is it possible that finally VAE learns to ignore the features of binding pocket? Since your final output is try to reconstruct from input ligand only.
- I noticed you provided some experiments to show the different perfornace of "with receptor" and "without receptor" using prior sampling only, as shown in figure 7. But did you check the different performance on posterior sampling? I mean what if input a unpaired binding pocket and ligand? does it reconstruct the input ligand no matter which binding pockets you input to vae?
Looking forward to your reply. Thanks.
Training data format
Hi,
Thank you for this interesting and insightful work. I would like to follow your experimental setting. I have the following questions about the data format.
(1) How many training protein-ligand pairs you have after you filter out any poses that have RMSD greater than 2A? Is it 486740, which is the number of lines in it2_tt_0_lowrmsd_mols_train0_fixed.types.
(2) Could you explain the meaning of each line in it2_tt_0_lowrmsd_mols_train0_fixed.types? For example, what do the fist three numbers mean in the following line?
1 5.119186 1.97462 1433B_HUMAN_1_240_pep_0/4gnt_A_rec.pdb 1433B_HUMAN_1_240_pep_0/4gnt_A_rec_5f74_amp_lig_tt_min_0.sdf.gz #-6.28497
Thank you in advance.
Sulfonyl double bonds not retained in OB to RDKit conversion
I think the function fitting.convert_ob_mol_to_rd_mol() suffers of the same problem described in #15 . While double bonds are now correctly assigned to the sulfonyl group by Open Babel, the conversion to RDKit seems to make them disappear again.
gnina minmize problem
hello. Thank you for sharing liGAN. I applied gnina mimize to liGAN a few months ago and used it well, but like the method you shared while setting up the new one, I cloned the most recent LiGAN git and build molgrid and liGAN normally. 1) sh download_weights.sh
2) python3 generate.py config/generate.config
Installed gnina confirmed working 2nd photo.
I ran it as before through the command. However, the generation process did not proceed because of gnina, which was used a few months ago. Please check once
why 1024-D latent space?
Hi,
Why choosing 1024-dimensional latent space? did you try other dimensions?
Thank you.
where is the output for generated molecules and matrix?
I just installed ligan, and ran python3 generate.py config/generate.config
everything is fine. I think I finished the run, now I am wondering where is the output files with generated molecules? do we have some post-analysis scripts available? like evaluation matrix and score for the generated molecules? Thanks,
How to use PDB of Alphafold2 to drug discovery?
Hi @mattragoza I want to use pdb of alphafold2 to find molecules. Do I only need to change two parameters: data_root and data_file in config/generate.config? Is the 'crossdock2020' the default reference files? for example:
data_root: data/
data_file: data/alphafold.pdb
Thanks!
Rings without carbon
From time to time it seems that compounds containing rings with no carbon are generated and the following line
https://github.com/mattragoza/liGAN/blob/618e9433dee29db3c1c1a8028ff583409a16f5ab/fitting.py#L512
fails with a ZeroDivisionError exception:
File "/ligan/fitting.py", line 557, in make_obmol
if aromatic_ccnt/carbon_cnt >= .5 and aromatic_ccnt != ring.Size():
ZeroDivisionError: division by zero
Can not access to https://bits.csb.pitt.edu/files/ to download those files
Excuse me, there are some problems happend when I was attempt to use sh download_weights.sh to download the model`s weights. The web(https://bits.csb.pitt.edu) appears to be out of service resulting in the inability to download the required files. Would you please check it out ? Thanks !
Can not run `generate.py` to generate molecules.
Hi,
I'm trying to use your models to generate some molecules, however when I run generate.py as shown in the README.md, there are errors related to
from SA_Score import sascorer
from NP_Score import npscorer
There seems no such modules, or maybe some files are missing?
I also found there is a refactor branch, are there some generate.py like scripts in this branch? Or there are only training scripts.
I would greatly appreciate it if you would provide some clues or solutions of my question.
"Aborted (core dumped)" error using tutorial for Generating molecules
I tried to follow the tutorial for generating molecules: python3 generate.py config/generate.config
I got the "Aborted (core dumped)" error after the output stopped at "Getting next batch of data" for a long while:
any thought? is this due to I donot have enough memory (I have 160GB for now)
Get killed when running generate.py
Hi,
I found that the code will be killed when running genreate.py
I debugged the code and found that the code is killed in line 330 of atom_types.py file.
Could you please help me solve this problem?
Thank you very much.
Train_file and test_file are missing
Hi,
I couldn't find the train file "it2_tt_0_lowrmsd_mols_train0_fixed.types" and test file "it2_tt_0_lowrmsd_mols_test0_fixed.types" in data/crossdock folder.
Could you please provide these two files?
Thank you!
CUDNN Error (out of memory?): CUDNN_STATUS_EXECUTION_FAILED
Hi, @mattragoza ,when I When I execute “python3 generate.py config/generate.config” this command，,Something went wrong.What should I do about it.
valence error
Hi,
In the Bond inference algorithm, you remove bad valence. However, I generated some molecules with bad valence using you trained model. Have you ever had such a problem?
Looking forward to your help! Thank you very much!
feedback about generated molecules
Hi,
thank you for publishing this fantastic work.
May I give some feedback about the generated molecules? I tested liGAN (posterior and prior model) on our protein target with reference molecule, and the test sets in the demo. When I view the SMILES of the generated molecules, it seems that a high ratio of the molecules have weird structures. Is it normal? For example, it occurs quite often that the structures have multi-fused cyclic compounds, which are not so realistic. Another example is that a super big ring (which may contain 7 or 8 atoms) shows up.
Bests
Chencheng
cuda error
Until last Friday, the generation using the pre-trained model was working well. From yesterday RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling cublasSgemv(handle, op, m, n, &alpha, a, lda, x, incx, &beta, y, incy) I wonder if this has ever happened.
libmolgrid was also built via conda-molgrid.
MemoryError at molgrid.ExampleProvider().next_batch()
Hi.
First , I get the error (Segmentation fault (core dumped)), so I manually installing libmolgrid, and I solved this problem.
After, I get the MemoryError in molgrid.ExampleProvider().next_batch(). [/liGAN/data.py(139 line)] The code just froze at next_batch under libmolgrid library. At this time, my batch_size and n_examples have been set to 1.
This is my server configuration. Mem is 377G, Swp is 7.63G and 10018MiB GPU memory(GeForce RTX 3080).
I find this grid dimensions is 48, I don't know how much memory we need to run. I don’t know if it’s the memory problem of my server or the problem of the molgrid package.
Please tell me the configuration of the server required for testing.
Looking forward to your help! Thank you very munch!
Get Stuck when runing generate.py
Hi,
Thanks for your amazing work and code!
I followed the instructions on the github page and try to run: python3 generate.py config/generate.config
However, it stuck at here for a long time
How long does it take to finish the generation procedure typically?
Thanks!
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.