京都大学 大学院医学研究科
人間健康科学系専攻 ビッグデータ医科学分野
← Back to Projects
HELM-BERT: Peptide Language Model
Overview
HELM-BERT is a transformer-based language model designed specifically for medium-sized peptides represented in HELM (Hierarchical Editing Language for Macromolecules) notation.
Key Features
- Pre-trained on large-scale peptide databases
- Fine-tunable for various property prediction tasks
- Supports non-natural amino acids and modifications
Results
The model achieves state-of-the-art performance on peptide property prediction benchmarks.