Tie‐Yan Liu

DeepVirus identifies and classifies viral dark matter in metagenomic data using a hierarchical transformer framework, revealing novel viral lineages and expanding known RNA virus diversity.

The paper introduces {micro}Protein, a framework combining deep learning and reinforcement learning to predict and discover high-gain protein mutants using single mutation data.

AI2BMD efficiently simulates large biomolecules with ab initio accuracy, outperforming DFT in speed while maintaining chemical accuracy for dynamics and free energy calculations.

This paper develops a pre-trained antibody language model to improve CDR sequence and structure generation, outperforming previous methods in antigen-specific antibody design.

CopulaNet directly learns residue co-evolution from multiple sequence alignments to improve protein structure prediction accuracy and efficiency.