Improving Generalizability of Protein Sequence Models with Data Augmentations
Hongyu Shen, Layne C. Price, Mohammad Taha Bahadori, Franziska Seeger
The paper improves protein sequence model generalizability by applying data augmentations and contrastive learning, showing performance gains across multiple tasks.
bioRxiv · Feb 18, 2021 · PreprintBioinformatics