Generative steering to adapt proteins beyond native biological contexts
Abstract
Proteins evolved for native biological contexts often fail when deployed in new cellular environments or therapeutic settings. We present ProVADA, a test-time framework that steers a pretrained protein generator toward externally defined properties while preserving functional constraints. Its Mixture-Adaptation Directed Annealing sampler combines coordinated mutations, population selection, and annealing to navigate rugged objective landscapes. Experimentally, ProVADA converted secreted human renin into an active, drug-inhibitable cytosolic protease and extensively deimmunized two murine single-chain antibody fragments to reduce HLA visibility while retaining antigen recognition. ESCAPE-seq measurements confirmed substantial depletion of HLA-I binder peptides across alleles. Deimmunized FMC63 variants retained CAR-T-cell killing and showed fewer binders than a tested humanized comparator. Together, these results demonstrate that broad sequence redesign can adapt functional proteins to non-native biological contexts.
Related
- Challenges and progress in RNA velocity: Comparative analysis across multiple biological contexts
- Eukaryotic AUG initiation contexts consist of a broad range of nucleotide patterns associated with distinct biological functions
- RNAGEN: A Generative Adversarial Network‐Based Model to Generate Synthetic RNA Sequences to Target Proteins
- A compact generative language model learns the compositional grammar of phase-separating proteins
- Distinct proteomic and acylproteomic adaptations to succinate dehydrogenase loss in two cell contexts
BibTeX
@misc{zhang2026generative,
title = {{Generative steering to adapt proteins beyond native biological contexts}},
author = {Xiaowei Zhang and Wenhui Sophia Lu and Ben Viggiano and Kevin Reynolds and Sophia Burick and Elena Sotillo and Haoyu Dai and Geonhu Lee and Zixuan Liu and Nuoya Yang and Luis S. Mille-Fragoso and Euan Ashley and Bingfei Yu and Crystal L. Mackall and Wing Hung Wong and Xiaojing J. Gao},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.1101/2025.07.11.664238},
url = {https://doi.org/10.1101/2025.07.11.664238},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Generative steering to adapt proteins beyond native biological contexts
AU - Xiaowei Zhang
AU - Wenhui Sophia Lu
AU - Ben Viggiano
AU - Kevin Reynolds
AU - Sophia Burick
AU - Elena Sotillo
AU - Haoyu Dai
AU - Geonhu Lee
AU - Zixuan Liu
AU - Nuoya Yang
AU - Luis S. Mille-Fragoso
AU - Euan Ashley
AU - Bingfei Yu
AU - Crystal L. Mackall
AU - Wing Hung Wong
AU - Xiaojing J. Gao
PY - 2026
DA - 2026/10/18
PB - bioRxiv
DO - 10.1101/2025.07.11.664238
UR - https://doi.org/10.1101/2025.07.11.664238
AB - Proteins evolved for native biological contexts often fail when deployed in new cellular environments or therapeutic settings. We present ProVADA, a test-time framework that steers a pretrained protein generator toward externally defined properties while preserving functional constraints. Its Mixture-Adaptation Directed Annealing sampler combines coordinated mutations, population selection, and annealing to navigate rugged objective landscapes. Experimentally, ProVADA converted secreted human renin into an active, drug-inhibitable cytosolic protease and extensively deimmunized two murine single-chain antibody fragments to reduce HLA visibility while retaining antigen recognition. ESCAPE-seq measurements confirmed substantial depletion of HLA-I binder peptides across alleles. Deimmunized FMC63 variants retained CAR-T-cell killing and showed fewer binders than a tested humanized comparator. Together, these results demonstrate that broad sequence redesign can adapt functional proteins to non-native biological contexts.
SN - 2692-8205
ER -