Le Li

The paper introduces PIONEER2, a method that improves protein-protein interface prediction by integrating structural homology and deep learning, outperforming AlphaFold3 in certain scenarios.

This paper introduces NetFlow3D, a framework that integrates protein structure and interaction networks to identify significant mutation clusters and modules in cancer, revealing biological processes not found by traditional methods.

The paper introduces COMSV, a method for identifying structural variations in cancer samples, showing high sensitivity and specificity and detecting hundreds of novel SVs per sample.

DeepERA uses deep learning to predict drug-target interactions by integrating heterogeneous data, identifying 45,603 novel interactions including those related to SARS-CoV-2.

This study evaluates the impact of 5-hydroxymethylcytosine (5hmC) and PDR on gene expression inference using WGBS and oxWGBS data from normal and tumor tissues.

OMSV identifies large structural variations from optical maps with high accuracy, outperforming existing methods and detecting many missed by sequencing.