deepchem / deepchem/deepchem

RdkitGridFeaturizer fails to featurize the datapoint since last two week

Open
#4,181 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
7k
Forks
2.3k
PR merge metrics
No merged PRs in 30d

Description

Hi, I currently encounter an issue about RdkitGridFeaturizer in deepchem. This featurizer cannot featurize the datapoint since last monday. Two weeks ago, I used this RdkitGridFeaturizer to featurize the datapoint and this featurizer worked well. However, last Monday I used the same code to featurize the datapoint and the RdkitGridFeaturizer failed to featurize the datapoint. I set up the environment based on the deepchem tuturioal e-book and use Colab. I attach my code here and screenshot here.

featurizer = dc.feat.RdkitGridFeaturizer(voxel_width=2.0
, feature_types=['ecfp', 'splif', 'salt_bridge', 'hbond']
, flatten=True
, sanitize=True)

tasks, datasets, transformers = dc.molnet.load_pdbbind(featurizer=featurizer, set_name="refined", reload=True,
data_dir='/content/drive/MyDrive/Conda',
save_dir='/content/drive/MyDrive/Conda')

![No Issue](https://github.com/user-attachments/assets/a6306308-333a-4578-b958-e659450fe328)
![Issue appear](https://github.com/user-attachments/assets/8e3d418d-8017-4279-97dd-c724996106f7)

Contributor guide

Open the contributing guide

Research direction

Start by reproducing the provided RdkitGridFeaturizer and load_pdbbind code in Colab, capturing the exception that is missing from the report. Compare the failing datapoint and environment with the previously working setup; done means the datapoint featurizes successfully or the incompatibility is identified and documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.