ChemBERTa-2
A collection of BERT-like transformer models pre-trained on chemical SMILES data for drug design and property prediction.
What is ChemBERTa-2?
ChemBERTa is a collection of BERT-like transformer models specifically pre-trained on chemical SMILES data for applications in chemistry and drug discovery. It applies masked language modeling techniques to molecular representations, enabling transfer learning for various chemical prediction tasks. The project provides pre-trained models that can be fine-tuned for specific applications like property prediction and chemical modeling.
Researchers, developers, and students working at the intersection of machine learning and chemistry, particularly those interested in applying transformer models to chemical data for drug design and molecular property prediction.
ChemBERTa offers specialized transformer models pre-trained on chemical data, providing a foundation for chemistry-specific machine learning tasks without requiring extensive computational resources for pre-training. The models are easily accessible through HuggingFace and integrate with existing deep learning workflows.
Overview
bert-loves-chemistry: a repository of HuggingFace models applied on chemical SMILES data for drug design, chemical modelling, etc.
Use Cases
Best For
- Transfer learning for chemical property prediction tasks
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
