Zuobai Zhang

Latent generative search unlocks de novo design of untapped biomolecular interactions at scale

Reward-guided inference-time search over the Proteína-Complexa sequence-structure codesign model yields validated binders across 127 targets, kinases and a free carbohydrate, with codesigned sequences outperforming ProteinMPNN redesign.

Bering: joint cell segmentation and annotation for spatial transcriptomics with transferred graph embeddings

Bering improves cell segmentation and annotation in spatial transcriptomics by using graph embeddings and transfer learning, achieving better accuracy across different technologies and tissues.

Pretrainable Geometric Graph Neural Network for Antibody Affinity Maturation

This paper introduces GearBind, a geometric graph neural network for in silico antibody affinity maturation, achieving significant improvements in binding affinity.

Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic data

This paper introduces scETM, a model that learns interpretable gene and cell type embeddings from scRNA-seq data, showing cross-tissue and cross-species transferability.