Taking the Mask Off: What Protein Binder RL Is Actually Learning

This post builds on ideas from Nick Boyd’s essay on RL and PDB-derived reward signals, particularly his analysis of structural diversity and reward bias.The models have been getting better at generating first-pass binders. Brian Naughton’s guide walks you through designing a VHH from scratch: pick a target, run your generative model of choice, filter by your in-silico structure metric of choice, and send it away to the lab for in vitro testing.As Nick Boyd(founder of Escalante) mentions, there are currently two main approaches to computational protein binder design: optimization (exemplified by BindCraft) and generative models (like BoltzGen). At the risk of repeating something already mentioned, BoltzGen is faster, but the per-binder design quality is much lower than that of something like BindCraft, which has the opposite properties. So the net computational cost is roughly the same. In his essay, Boyd shows how you can improve upon BoltzGen by borrowing the LLM posttraining…