In essence, we probed the model's ability to ricapitulate family statistics, bootstrap protein structure prediction, and assess mutation effect, demonstrating excellent performance across all tasks, especially using test-time-scaling via prompt conditioning.
You can use the model right now to freely generate families for single sequence inputs (i.e., diversification conditioned by intrinsic representations of evolution), or to engineer proteins based on family promts (diversification by conditioning on particular evoluationary trajectories).
Dec 22, 2025 14:57