# Reinforcement-guided generative protein language models enable de novo design of highly diverse AAV capsids

arXiv: https://arxiv.org/abs/2603.19473 · HTML: https://mlsanity.com/paper/2603.19473/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 41 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 4 of 4)

- [Posterior Collapse and Latent Variable Non-identifiability](https://mlsanity.com/paper/2301.00537/) (2023)
- [Variational auto-encoding of protein sequences](https://mlsanity.com/paper/1712.03346/) (2017)
- [Exploring the Protein Sequence Space with Global Generative Models](https://mlsanity.com/paper/2305.01941/) (2023)
- [Exploring the limits of pre-trained embeddings in machine-guided protein design: a case study on predicting AAV vector viability](https://mlsanity.com/paper/2602.14828/) (2026)

## Abstract (arXiv)

Adeno-associated viral (AAV) vectors are widely used delivery platforms in gene therapy, and the design of improved capsids is key to expanding their therapeutic potential. A central challenge in AAV bioengineering, as in protein design more broadly, is the vast sequence design space relative to the scale of feasible experimental screening. Machine-guided generative approaches provide a powerful means of navigating this landscape and proposing novel protein sequences that satisfy functional constraints. Here, we develop a generative design framework based on protein language models and reinforcement learning to generate highly novel yet functionally plausible AAV capsids. A pretrained model was fine-tuned on experimentally validated capsid sequences to learn patterns associated with viability. Reinforcement learning was then used to guide sequence generation, with a reward function that jointly promoted predicted viability and sequence novelty, thereby enabling exploration beyond regions represented in the training data. Comparative analyses showed that fine-tuning alone produces sequences with high predicted viability but remains biased toward the training distribution, whereas reinforcement learining-guided generation reaches more distant regions of sequence space while maintaining high predicted viability. Finally, we propose a candidate selection strategy that integrates predicted viability, sequence novelty, and biophysical properties to prioritize variants for downstream evaluation. This work establishes a framework for the generative exploration of protein sequence space and advances the application of generative protein language models to AAV bioengineering.