Kevin Wu

Drug-like antibody design against challenging targets with atomic precision

This paper introduces a computational antibody design platform that generates drug-like antibodies with high developability and atomic accuracy, demonstrating its utility for challenging therapeutic targets.

Zero-shot antibody design in a 24-well plate

This paper introduces Chai-2, a model that designs antibodies with a 16% hit rate, achieving success in 50% of targets without prior binders, and enables rapid validation in under two weeks.

Chai-1: Decoding the molecular interactions of life

Chai-1 matches AlphaFold3 on PoseBusters ligand poses (77% vs 76%), beats AlphaFold-Multimer 2.3 on low-homology interfaces, and stays competitive without MSAs on multimers and antibodies.

ProteinCLIP: enhancing protein language models with natural language

ProteinCLIP refines pre-trained protein language model embeddings using contrastive learning between amino acid sequences and functional text, achieving state-of-the-art results in protein tasks.

TCR-BERT: learning the grammar of T-cell receptors for flexible antigen-binding analyses

TCR-BERT uses self-supervised transfer learning on unlabeled T-cell receptor sequences to learn representations that improve antigen-binding prediction, specificity clustering, and computational TCR sequence design.

BABEL enables cross-modality translation between multi-omic profiles at single-cell resolution

BABEL translates between scRNA-seq and scATAC-seq at single-cell resolution, enabling synthesis of paired multi-omic data when only one modality is available.

RNA-GPS Predicts SARS-CoV-2 RNA Localization to Host Mitochondria and Nucleolus

The paper predicts SARS-CoV-2 RNA localization to host mitochondria and nucleolus using machine learning, identifying key regions in viral RNA that drive this localization.