-
We've gotten some good responses on our survey (https://github.com/deepchem/deepchem/issues/1722) about the future of DeepChem, and are starting to think about synthesizing the responses together. As …
-
Hi all,
Thank you very much for your hard work; this is a beautiful thing. I have two questions that I'm trying to address simultaneously.
1) I am trying to design a small binder (8-20 resi) int…
-
Hello! I am trying to add the molecule featurizers as documented in the latest chemprop documentations. However, whenever i try to run training, the following traceback error pops up. Keep in mind I f…
-
Hey Graphium community,
I'm training a bunch of models with different featurizers and I came into understanding that there seems to be no support of global molecular features (properties) within th…
-
**Describe the bug**
Simplely, I have a multipout regression task, which I use R2 score. Naturally, I used the `nn.metrics.R2Score(multioutput="raw_values")` by passing `multioutput="raw_values"`, I …
-
Our example notebooks use `trainer.test(mpnn, test_loader)`. We may want to show users how to test on their best model. They would do this by making a checkpointing callback and passing that to the tr…
-
When I execute the parse_multiple_chains.py, it runs without error messages and creates a file in the output location that I expect but the file is empty.
I'm running it on my windows laptop, here …
-
**Describe the bug**
[These lines](https://github.com/chemprop/chemprop/blob/b7d33e72bd44523117cc4672682356434a0865cf/chemprop/cli/predict.py#L257-L259) will not work for a `preds` of shape $n \times…
-
I am trying to run "Dynamic LSTM-GNN" as mentioned in the training using the follwing command "python3 -m train_dynamic --bilstm --random_g --ts_mask --add_flat --class_weights --gnn_name mpnn --read_…
-
GNN Intro Review
_The following peer review was solicited as part of the Distill review process._
_**The reviewer chose to waive anonymity.** Distill offers reviewers a choice between anon…