Shenzhen Bay Laboratory

RNA language model transfer-trained from ESM-2 via a pseudo-protein alphabet mapping, outperforming 12 RNA language models in zero-shot evaluation.

RNA-protein contact prediction from sequence, built on ERNIE-RNA and ESM-2 embeddings. Reaches 0.77 auROC where AlphaFold 3 reaches 0.61.

Structure-based 3D molecule generation that denoises a ligand at atom level and motif level at once, conditioned on the target protein's pocket.

Peptide language model that generates antimicrobial, anticancer, and target-binding sequences, adapted per task by Mixture-of-Experts plugins.