Dongsu Han

This paper introduces K-Fold, a method that improves prediction of conformational changes in protein complexes by modeling structural transitions from unbound to bound states.

This paper introduces RUN-DVC, a semi-supervised training method for deep variant callers that improves generalization across sequencing methods with varying error profiles.

BWA-MEME improves short-read alignment efficiency by using a machine learning approach to reduce computational overhead while maintaining accuracy.