Juyong Lee

OmniScore learns shared geometric representations of diverse biomolecular complexes and improves quality assessment and interaction prediction across molecular classes.

PREpiBind evaluates ten protein representations for pMHC-II binding prediction across multiple datasets, showing varying performance depending on the task and evaluation method.

LEN-Seek is a method for ligand binding-site similarity search using a graph VAE that encodes structural information into a latent space, achieving faster and more scalable results than existing methods.

This study designs a de novo RSV antigen using AI to reduce immunopathology while maintaining immunogenicity, showing safety and efficacy in preclinical models.

The paper identifies and validates four kynureninases using homology searches and protein language models, with the most active one showing significant tumor reduction in mouse models.

This paper introduces a multi-state modeling protocol for kinases using AlphaFold2 to improve structure-based virtual screening by overcoming structural biases and enhancing the identification of diverse inhibitors.

CRFalign improves protein sequence-structure alignment by combining HMM-HMM comparison with conditional random fields and gradient boosted trees, showing better performance on remote homologs.

A-Prot uses MSA Transformer to predict protein 3D structures, outperforming existing methods in long-range contact prediction and CASP14 target modeling.

Concatenating receptor and peptide sequences via a poly-glycine linker enables AlphaFold2 to predict bound peptide conformations within 3.0 A C-RMSD for over half of benchmarked protein-peptide complexes.