Amazon Web Services

Discrete diffusion model for conditional antibody sequence design with germline-absorbing noising that focuses learning on somatic variation.

Antibody developability predictor pairing text and protein language models, using in-context learning to fit new assays without retraining.

Open-source Apache-2.0 reproduction of AlphaFold3 that predicts all-atom structures of proteins, RNA, DNA, small molecules, and their complexes.

Protein surface tokenizer that turns surface-exposed residues into codebook tokens, lifting SKEMPI binding affinity change prediction to r = 0.600.

Protein structure tokenizer that encodes 3D backbones as discrete VQ-VAE tokens, fixing the codebook under-utilization that caps their vocabulary.

Antibody affinity maturation framework that steers flow-matching structure generation with a binding predictor, then mutates CDRs by inverse folding.

Multimodal medical imaging foundation model for zero-shot clinical diagnosis and report generation from chest X-ray and CT in English and Chinese.

Long-context protein language model on a bidirectional Mamba backbone, outperforming ESM-2 by up to 30% at matched training token budgets.