-
The molnet loader functions are currently divided into two groups with inconsistent APIs for specifying featurizers and splitters.
Most of them have arguments `featurizer` and `split` to specify th…
-
Hi @anupriyatripathi
This is to initiate a discussion to resolve the current issue users are having running Qemistree.
Context:
- SIRIUS v.4.4 introduced new parameters, new tools (like CANOPU…
-
**Description:**
Hello everyone, I'm new to deepchem.
And I had run the exampl in this website: https://deepchem.io/docs/notebooks/graph_convolutional_networks_for_tox21.html
I run the whole exampl…
-
### Summary
All Ersilia models have associated metadata which users often find useful to view quickly while working with these models. At present this can be achieved in a couple of different ways,…
-
- stateful load models once and then generate again
- use torch compile?
-
There are a number of important molecular and scientific models that I would love to see implementations for in DeepChem. Implementations of any of these models would be a great contribution to DeepCh…
-
Tentatively labeling this a bug, but it may be an inherent limitation.
This query
```
{
"message": {
"query_graph": {
"edges": {
"e01": {
…
-
Great work！
Could you give me a sample file input for get_ranked_topk.py? I can't reproduce the data augmentation results of your work.
And why not just calculate the top when the data augmentation …
-
Right now the TorchMD_Net module is tied to the idea that only one thing (and maybe its derivative) is returned:
https://github.com/torchmd/torchmd-net/blob/a11684710d6ba22b29acbf709bfbc05b93f3402d/t…
-
xref: https://github.com/datamol-io/polaris/pull/3#discussion_r1226841168
It appears likely that for any benchmark we will come up with, we require a specific class, e.g. `MoleculeScoringSingleTask…