We’re excited to introduce Chai-2, a major breakthrough in molecular design. Chai-2 enables zero-shot antibody discovery in a 24-well plate, exceeding previous SOTA by >100x. Thread👇

We prompt Chai-2 with 50 targets, test the designs in the lab, and observe a >15% hit rate. In just 2 weeks, we generate molecules, and synthesize + characterize them in the lab, without any iterative optimization or high-throughput lab screening.

At the core of Chai-2’s success is its multimodal generative architecture, integrating all-atom structure prediction and generative modeling. This enables Chai-2 to create novel and epitope-specific binders. 🔬Whitepaper with more details:

We believe that these results mark a transition from empirical discovery to deterministic molecular engineering. ✨Reach out at if you’d like access to Chai-2.

We’re grateful to many partners for making this possible: @OracleCloud for the massive compute that was required; @NVIDIAHealth for new GPU kernels and accelerating our sequence search; and @Sino_Biological and @AdaptyvBio for conducting many wet-lab experiments in the paper.

@joshim5 @_jackdent revolutionary work — excited to see this accelerate the industry

Wow, this is really cool. Are the model and weights open source?

This is unbelievable. This makes me so excited for the future!

yo this @aaryuniktwt

woah

Wow, so excited about this!!