Skip to content

Add HuggingFaceFeaturizer for molecular embeddings - #118

Open
Joao-Cheixo wants to merge 5 commits into
BioSystemsUM:masterfrom
Joao-Cheixo:master
Open

Add HuggingFaceFeaturizer for molecular embeddings#118
Joao-Cheixo wants to merge 5 commits into
BioSystemsUM:masterfrom
Joao-Cheixo:master

Conversation

@Joao-Cheixo

Copy link
Copy Markdown

Implemented a new featurizer (HuggingFaceFeaturizer) based on Hugging Face models for generating molecular embeddings from SMILES.

Integrated with DeepMol featurization pipeline.
Ensured compatibility with existing workflows.

Initial experiments performed on MoleculeNet datasets.
Further benchmarking and evaluation ongoing.

@jcapels jcapels left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM but address the comments I left

Comment thread tests/integration_tests/dataset/test_dataset_features.py Outdated
Comment thread examples/notebooks/data/bace.csv Outdated
Comment thread examples/notebooks/data/hiv.csv Outdated
Comment thread examples/test_HuggingFaceFeaturizer_standalone.py Outdated
Comment thread examples/notebooks/benchmarking1.ipynb Outdated
@Joao-Cheixo

Copy link
Copy Markdown
Author

Thank you for the review I've addressed the requested changes,
Please let me know if there's anything else I should change.

  • Removed the notebooks, datasets, and generated benchmark results.
  • Resolved the merge conflicts with the latest master.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants