Yanjing Li

This paper introduces a generative AI framework for designing transmembrane β-barrel nanopores with customizable properties for ion sensing, DNA translocation, and transport.

This paper introduces RigidSSL, a geometric pretraining framework for protein design and conformational modeling, improving designability and capturing realistic dynamics.

An all-atom diffusion model using a 14-atom residue representation and sparse U-Net architecture accelerates biomolecular design 10-fold, enabling experimentally validated DNA-binding proteins and multi-turnover cysteine hydrolases.

AtomWorks, a modular atom-level data framework, trains structure prediction and design models; the resulting RF3 improves chirality handling and performs between AF3 and Boltz.