torchdrug
torchdrug copied to clipboard
DeepGraphLearning
A powerful and flexible machine learning platform for drug discovery
```python from torchdrug import datasets, data reaction_dataset = datasets.USPTO50k("~/molecule-datasets/", lazy=True, node_feature="center_identification", kekulize=True, ) synthon_dataset = datasets.USPTO50k("~/molecule-datasets/", as_synthon=True, node_feature="synthon_completion", lazy=True, kekulize=True) ``` will give below error ``` TypeError Traceback (most recent...
In the [retrosynthesis tutorial](https://torchdrug.ai/docs/tutorials/retrosynthesis.html#) this code of [synthon completion](https://torchdrug.ai/docs/tutorials/retrosynthesis.html#synthon-completion) ```python synthon_optimizer = torch.optim.Adam(synthon_task.parameters(), lr=1e-3) synthon_solver = core.Engine(synthon_task, synthon_train, synthon_valid, synthon_test, synthon_optimizer, gpus=[0], batch_size=128) synthon_solver.train(num_epoch=1) synthon_solver.evaluate("valid") synthon_solver.save("g2gs_synthon_model.pth") ``` gives below error...
Trying to build a customized dataset as follows for the molecular generation task. ```python @R.register("datasets.Smol") @doc.copy_args(data.MoleculeDataset.load_csv, ignore=("smiles_field", "target_fields")) class Smol(data.MoleculeDataset): smiles_file = "/content/drive/MyDrive/molecule_design/resources/smiles_train.csv" target_fields = ["SPLIT"] def __init__(self, smiles_file, verbose=1,...
Hi, I would like to know (if it is possible) how to get the graph from a list of smiles and then feed it into a GNN ( GIN for...
When we train a model for molecule property prediction it gives different results every time when we train the model. It varies a lot in terms of performance. That makes...
Thanks for releasing `torchdrug` 0.1.3! I updated to the new version and see improved behavior in many places. However, unfortunately some functionalities that were stable in `0.1.2` are failing now....
In the [retrosynthesis tutorial](https://torchdrug.ai/docs/tutorials/retrosynthesis.html#) ```python from torchdrug.utils import plot for i in range(2): sample = reaction_dataset[i] reactant, product = sample["graph"] reactants = reactant.connected_components()[0] products = product.connected_components()[0] plot.reaction(reactants, products) ``` gives...
For property prediction when we replace model to `SchNet` in the [tutorial ](https://torchdrug.ai/docs/tutorials/property_prediction.html) and keeping other parameters as it is, we recieves below error. Note: I used colab version of...
Currently, there's a limitation on the versions of Python on which `torchdrug` can be installed https://github.com/DeepGraphLearning/torchdrug/blob/278bcc8cba914d562bd84d749833f2d67a6c11c1/setup.py#L43 I'm not sure why this is here - most of its dependencies are version...
Metadata
Owner
Metadata
A powerful and flexible machine learning platform for drug discovery