BindGRPO: Training Protein Binder Generators to Bind

Generative models of protein binders are typically trained by maximizing likelihood on natural complexes. Binding is considered primarily at inference: many candidates are sampled, scored by a structure predictor, and the highest-confidence ones are retained. Binding is therefore not part of the generator's training objective. We introduce BindGRPO to close this gap by post-training a target-conditioned binder generator using predicted binding as the reward. We formulate the denoising sampler as a Markov decision process and define Gaussian policy transitions between consecutive denoiser inputs with tractable likelihoods. The reward is AlphaFold3's interface confidence for the co-designed sequence. Training therefore does not require an experimentally determined target–binder complex. On the Cao benchmark, BindGRPO increases the in-silico success rate from $24.4\%$ to $36.7\%$, a $1.51\times$ gain over the same generator before RL fine-tuning. The improvement persists under an independent AlphaFold2 evaluator and across most evaluation thresholds, suggesting that the gain is not specific to AlphaFold3. All code and data will be released.