Sheng Chen

DiffDec generates structure-aware R-groups for molecular scaffolds using a diffusion model, achieving higher recovery rates and better binding affinity than existing methods.

AIxFuse generates dual-target drugs by learning pharmacophore fusion patterns that satisfy structural constraints from molecular docking, outperforming existing methods in success rate and binding free energy.

This paper introduces GraphEBM, an SE(3)-equivariant graph attention network for protein side chain conformation, outperforming existing methods in rotamer recovery and combinatorial optimization.

GraphBepi predicts B-cell epitopes using AlphaFold2 structures and a pretrained language model, outperforming existing methods in AUC and AUPR.

LMetalSite predicts metal ion-binding sites from protein sequences using a pretrained language model and multi-task learning, achieving higher accuracy than structure-based methods.

This paper predicts drug-protein interactions using a deep learning framework that combines 2D protein distance maps and drug molecular notation, achieving competitive performance on benchmark datasets.

This paper introduces SPROF, a method using 2D pairwise residue distance maps and image captioning to predict protein sequence profiles, achieving a 5.2% improvement over SPIN2.