ProVADA: Generating Subcellular Protein Variants via Ensemble-Guided Test-Time Steering

Wenhui Sophia Lu, Xiaowei Zhang, L. Santiago Mille-Fragoso, Haoyu Dai, Xiaojing J Gao, Wing Hung Wong

Keywords: protein engineering, test-time steering, population-annealing, sequential importance sampling, generative prior, protein variant design, subcellular localization

TL;DR: We introduce Protein Variant ADAptation (ProVADA), an ensemble-guided, test-time steering framework that combines implicit generative priors with fitness oracles via a composite functional objective for protein variant design.

Abstract: Engineering protein variants that retain functionality in non-native environments remains a significant challenge due to the intricate topology of sequence-fitness landscapes. Experimental strategies often require extensive labor and domain expertise. While recent advances in protein generative modeling offer a promising in silico alternative, many of these methods rely on differentiable fitness predictors, which limits their applicability. To this end, we introduce Protein Variant ADAptation (ProVADA), an ensemble-guided, test-time steering framework that integrates implicit generative priors with fitness oracles via a unified composite objective. ProVADA leverages Mixture-Adaptation Directed Annealing (MADA), a novel sampler integrating population-annealing, adaptive mixture proposals, and directed local mutations. Furthermore, ProVADA requires no gradients or explicit likelihoods, yet efficiently concentrates sampling on high‐fitness, low-divergence variants. We demonstrate its effectiveness by redesigning human renin for cytosolic functionality. Our results achieve significant gains in predicted localization fitness while preserving structural integrity.

Submission Number: 157