-
Hi,
Thanks for the really nice and well explained paper.
I had a question regarding how the prediction output is invariant to the order of the atoms in the molecule. One can randomly permute th…
-
# ❓ Questions & Help
## Details
I recently uploaded the model weights for RoBERTa trained on a chemical benchmark dataset called ZINC15K for masked-language modelling of individual atoms in …
-
## Description of the issue
Within the class fuels a subclass ~~`ElectricFuel`~~ `SyntheticFuel` is missing. This class should also have the subclasses `Hydrogen`, `SyntheticMethane` and `Synthetic…
-
Hi all,
I am training a transformer model to predict chemical reactions from chemical molecules in string representation.
Does your project support plug-n-chug for models not trained on languag…
-
I get a segfault in COSMA for CP2K RPA on a system of 256 water molecules. The backtrace is:
```
Program received signal SIGSEGV: Segmentation fault - invalid memory reference.
Backtrace for th…
-
**Description:**
- DeepChem Version: master
- Platform: linux
The following examples currently throw exceptions on master.
Checklist is for fixing them one at a time.
- [ …
-
pip install kg_emerging_viruses gives the following error
`
ERROR: Could not find a version that satisfies the requirement kg_emerging_viruses (from versions: none)
ERROR: No matching distribution …
-
I have an unexpected error when extracting protein features. My code is as follows:
```
import deepchem as dc
pdbbind_tasks, pdbbind_datasets, transformers = dc.molnet.load_pdbbind(featurizer="grid…
-
I applied the example of 'test_graph_conv_atom_features' to add atom properties for ```ConvMolFeaturizer``` and managed to add atom(or molecule) properties through my data. But if I change the mode o…
-
I tried using WeaveTensorGraph to create models and train them, but I got the wrong information in the source code.
This is my code:
```
tox21_tasks, tox21_datasets, transformers = dc.molnet.load…