Shenzhen University

Protein-ligand scoring function that conditions probabilistic geometric potentials on language model priors to rank docked poses and binding affinity.

Pan-cancer single-cell foundation model with a hybrid Transformer-Mamba architecture, released with the PanFoMaBench cancer evaluation benchmark.

Structure-free peptide binder design conditioned only on a target protein sequence, using contrastive alignment to steer a latent diffusion model.

Structure-based drug design pipeline generating 3D molecules in binding pockets, raising zero-shot CrossDocked2020 docking success from 53% to 64%.

Host-pathogen protein interaction predictor scoring bacterial effector and human protein pairs from frozen ESM-2 embeddings with a transformer.

Structure-based 3D molecule generation with one diffusion backbone for fragment growing, linker design, scaffold hopping, and side-chain decoration.

Structure-based drug design model pairing SE(3)-equivariant diffusion with retrieval of pocket-matched scaffolds to generate ligands for a target.

Whole-slide pathology assistant that states the morphological findings behind each diagnosis, trained on 180k VQA pairs from 9,850 gigapixel slides.

Ultrasound foundation model pretrained by federated learning across 16 institutions, transferring to disease diagnosis and lesion segmentation.

Vision-language model for annotation-free pathology localization, marking the finding a text prompt names in X-ray, histology and fundus images.

Cell type annotation for single-cell RNA-seq that builds a graph per signaling pathway, learning across pathway views with graph neural networks.