AAVGen: Precision Engineering of Adeno-associated Viral Capsids for Renal Selective Targeting

Mohammadreza Ghaffarzadeh-Esfahani; Yousof Gheisari

q-bio.QMFeb 21, 2026

AAVGen: Precision Engineering of Adeno-associated Viral Capsids for Renal Selective Targeting

Authors: Mohammadreza Ghaffarzadeh-Esfahani, Yousof Gheisari

Organizations: Regenerative Medicine Research Center, Isfahan University of Medical Sciences, Isfahan, Iran · Department of Genetics and Molecular Biology, Isfahan University of Medical Sciences, Isfahan, Iran

Abstract

Adeno-associated viruses (AAVs) are promising vectors for gene therapy, but their native serotypes face limitations in tissue tropism, immune evasion, and production efficiency. Engineering capsids to overcome these hurdles is challenging due to the vast sequence space and the difficulty of simultaneously optimizing multiple functional properties. The complexity also adds when it comes to the kidney, which presents unique anatomical barriers and cellular targets that require precise and efficient vector engineering. Here, we present AAVGen, a generative artificial intelligence framework for de novo design of AAV capsids with enhanced multi-trait profiles. AAVGen integrates a protein language model (PLM) with supervised fine-tuning (SFT) and a reinforcement learning technique termed Group Sequence Policy Optimization (GSPO). The model is guided by a composite reward signal derived from three ESM-2-based regression predictors, each trained to predict a key property: production fitness, kidney tropism, and thermostability. Our results demonstrate that AAVGen produces a diverse library of novel VP1 protein sequences. In silico validations revealed that the majority of the generated variants have superior performance across all three employed indices, indicating successful multi-objective optimization. Furthermore, structural analysis via AlphaFold3 confirms that the generated sequences preserve the canonical capsid folding despite sequence diversification. AAVGen establishes a foundation for data-driven viral vector engineering, accelerating the development of next-generation AAV vectors with tailored functional characteristics.

Figures & tables

Figure 1: Development and assessment workflow of AAVGen. The left upper panel illustrates the dataset curation process. The right upper panel details the model training phase, which includes supervised fine-tuning (SFT), custom reward modeling, and group sequence policy optimization (GSPO). The lower panel outlines the assessment procedure, comprising generation analysis, evaluation of production fitness, kidney tropism, thermostability, and structural analysis.

Figure 2: Evaluation of regression models. (A) Training loss progression for models predicting production fitness, kidney tropism, and thermostability. (B) Correlation between experimentally determined (true) and model-predicted scores for production fitness, kidney tropism, and thermostability.

Figure 3: Reward progression in training with group sequence policy optimization (GSPO). (A) Total reward over the course of training. (B) Reward progression during training of AAVGen for reward functions that produce production fitness, kidney tropism, and thermostability. (C) Reward assignment logic for each objective, defined by the mean absolute error of model predictions on the validation set relative to the wild-type (WT) reference for production fitness, kidney tropism, and thermostability.

Figure 4: Sequence diversity and alignment metrics of the AAVGen-generated library. (A) Performance benchmarks of the generative model regarding sequence novelty. Left: Cumulative repetitiveness of generated sequences across increasing subset sizes ( $N=1{,}000$ ) for a library of 500,000 variants. Right: Distribution of sequence lengths for the training set (blue) and generated sequences (orange) relative to the wild-type (WT) AAV2 VP1 sequence (dashed line). (B) Alignment-based divergence of generated variants from the AAV2 WT reference. Left: Frequency distribution of edit distances from the WT sequence. The majority of synthetic variants contain between 10 and 15 mutations compared to the WT template. Right: Correlation between sequence similarity and identity percentages. Data points are colored by alignment score (ranging from 1425 to $>1460$ ), illustrating that the generated sequences maintain high conservation ( $>98.5\%$ identity) while exploring a diverse landscape of substitution patterns.

Figure 5: Functional property analysis of generated AAVGen sequences. (A) Qualitative classification of generated sequences into “Best”, “Good”, “Uncertain”, and “Bad” categories based on predicted production fitness, kidney tropism, and thermostability scores. (B) Pairwise correlation analyses between predicted production fitness, kidney tropism, and thermostability scores. (C) Joint three-dimensional distribution of predicted production fitness, kidney tropism, and thermostability scores, with each point colored according to the average of these three scores.

Figure 6: Structural analysis of the generated sequences. (A) Left: Distribution of Root Mean Square Deviation (RMSD) for $n=500$ sampled protein sequences from AAVGen and $n=250$ randomly generated relative to the wild-type (WT) reference. For each sequence, the median RMSD was calculated across five independent AlphaFold3 structure predictions. Right: Relationship between sequence length and median RMSD, indicating a modest increase in RMSD with longer sequences, while AAVGen sequences consistently maintain lower RMSD compared with random sequences. (B) Correlation analysis between median RMSD and predicted functional attributes. (C) Representative structural alignments of the four generated sequences exhibiting the lowest median RMSD. Structures are superimposed on the WT model. Green regions denote high spatial conservation, where C $\alpha$ atoms lie within 0.5 Å of the WT reference. Structural divergence is highlighted by red (non-conserved residues in the mutant) and blue (corresponding residues in the WT).

Explore similar work

Reinforcement-guided generative protein language models enable de novo design of highly diverse AAV capsids
Mar 19, 2026Lucas Ferraz, Ana F. Rodrigues, Pedro Giesteira Cotovio +5Protein Design Constrained Generative Modeling
LASIGE, Faculdade de Ciências da Universidade de Lisboa, Lisboa, Portugal · iBET – Instituto de Biologia Experimental e Tecnológica, Oeiras, Portugal · BioISI, Faculdade de Ciências da Universidade de Lisboa, Lisboa, Portugal
Exploring the limits of pre-trained embeddings in machine-guided protein design: a case study on predicting AAV vector viability
Feb 16, 2026Ana F. Rodrigues, Lucas Ferraz, Laura Balbi +2Protein Representation Learning Protein Language Models
LASIGE, Faculdade de Ciências da Universidade de Lisboa, Lisboa, Portugal
Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation
May 12, 2026Roman Klypa, Alberto Bietti, Sergei GrudininMolecular Generation Conditional Generation
Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK · Grenoble, France · Center for Computational Mathematics, Flatiron Institute +1

Mar 19, 2026J/K move · Enter open · S save

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

Lucas Ferraz, Ana F. Rodrigues, Pedro Giesteira Cotovio, Mafalda Ventura+4

LASIGE, Faculdade de Ciências da Universidade de Lisboa, Lisboa, Portugal · iBET – Instituto de Biologia Experimental e Tecnológica, Oeiras, Portugal · BioISI, Faculdade de Ciências da Universidade de Lisboa, Lisboa, Portugal

Protein Design Constrained Generative Modeling Protein Language Models

Open paper AskPDF 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.

Abstract

Explore similar work

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

Exploring the limits of pre-trained embeddings in machine-guided protein design: a case study on predicting AAV vector viability

Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation