-
## 🐛 Bug
I tried to just read QM7 dataset - no featurizing, just download. I get a huge list of RDKit errors, which do not break processing, but are definitely worrying. This should be dealt with, …
-
### Model description
We propose adding a new model, MassFormer, to predict tandem mass spectra accurately. MassFormer uses a graph transformer architecture to model long-distance relationships betwe…
-
I would like to use the QM9 dataset to predict the dipole moment of molecules. I was able to create a model for the dataset. Its hard for me to tell apart all the different values of the output vector…
-
Hi guys,
Not sure if I am doing this incorrectly, but when I load the tox21 datasets and check for duplicates and consistent labels, I find a ton of problems.
Please see this simple example of h…
-
## Version
2.0.0
## Steps to reproduce
- Using https://github.com/vuejs-templates/webpack
- Testing single file component using Jest which uses the v-icon component like:
```
```
- Ru…
ghost updated
10 months ago
-
Dear @jkwang93 ,
I'm trying to reproduce the DRD2 case using exactly your input. However, I met with an error when training the RNN model using the Transformer generated smiles.
1. First bug:
`…
-
Dear authors,
I tried to train the model with default parameters on moses3.csv dataset, then generate with the trained model. However, the validity that I achieved is 0.868, which I think is much s…
-
Hi,
thanks for the code. How can I generate only peptides (smaller proteins) using transfer learning, can I finetune (valid_data) on peptides or is there some tweak etc? thanks!
-
We need to convert keras.io examples to work with Keras 3.
This involves two stages:
## Stage 1: tf.keras backwards compatibility check
Keras 3 is intended as a drop-in replacement for tf.ker…
-
Hello, I am trying to use Graphormer on other commonly used datasets from MoleculeNet (https://moleculenet.org/datasets-1) to check the performance, such as BACE, BBBP, etc. I have used the default hp…