AAV Vector Design Agent

The AAV Vector Design Agent provides AI-driven design of adeno-associated virus vectors for gene therapy applications. It covers capsid selection and engineering, promoter/enhancer design, transgene optimization, and manufacturing considerations.

When to Use This Skill

• When selecting optimal AAV serotype for tissue-specific targeting.
• To design novel capsid variants with enhanced properties.
• For optimizing transgene expression cassettes.
• When predicting immunogenicity and neutralizing antibody escape.
• To design liver-detargeted or CNS-tropic vectors.

Core Capabilities

1. Capsid Selection: Match AAV serotype to target tissue based on tropism profiles.

1. Capsid Engineering: Design modified capsids for enhanced transduction or immune evasion.

1. Promoter Design: Select and optimize tissue-specific or ubiquitous promoters.

1. Transgene Optimization: Codon optimization and regulatory element design.

1. Immunogenicity Prediction: Predict NAb binding and T-cell epitopes.

1. Manufacturing Assessment: Evaluate producibility and purification considerations.

AAV Serotype Tropism

Workflow

1. Input: Target tissue, therapeutic gene, patient population characteristics.

1. Capsid Selection: Rank serotypes by tropism profile match.

1. Capsid Engineering: Design modifications if needed (peptide insertion, point mutations).

1. Cassette Design: Optimize ITR-to-ITR expression cassette.

1. Immunogenicity Analysis: Predict NAb prevalence and T-cell epitopes.

1. Manufacturing Review: Assess production feasibility.

1. Output: Complete vector design with rationale.

Example Usage

User: "Design an AAV vector for liver-directed gene therapy in hemophilia B with low immunogenicity."

Agent Action:

python3 Skills/Gene_Therapy/AAV_Vector_Design_Agent/aav_designer.py \
    --target_tissue liver \
    --therapeutic_gene F9 \
    --indication hemophilia_b \
    --minimize_immunogenicity true \
    --nab_escape true \
    --promoter liver_specific \
    --output aav_design/

Expression Cassette Components

5' ITR - [Promoter] - [5' UTR] - [Transgene] - [WPRE] - [PolyA] - 3' ITR

Packaging limit: ~4.7 kb between ITRs

Promoter Options:

Capsid Engineering Strategies

Directed Evolution:

• Error-prone PCR libraries
• DNA shuffling
• Selection in target tissue

Rational Design:

• Peptide display (insertion in variable loops)
• Point mutations for receptor targeting
• Tyrosine-to-phenylalanine for stability

Machine Learning:

• Sequence-function models
• Generative models for novel capsids
• Tropism prediction

Immunogenicity Considerations

Pre-existing NAbs:

Mitigation Strategies:

• Serotype selection based on patient screening
• Engineered NAb-evading capsids
• Immunosuppression protocols
• Plasmapheresis

AI/ML Components

Tropism Prediction:

• CNN on capsid sequence
• Cell-type specific transduction
• Cross-species translation

Immunogenicity Modeling:

• MHC binding prediction
• T-cell epitope mapping
• NAb epitope prediction

Expression Optimization:

• Codon optimization algorithms
• RNA structure prediction
• miRNA target site avoidance

Manufacturing Considerations

Prerequisites

• Python 3.10+
• Sequence analysis tools
• Immunoinformatics packages
• Structural biology tools

Related Skills

• CRISPR_Design_Agent - For gene editing payloads
• Protein_Engineering - For capsid design
• RNA_Therapeutics - For alternative modalities

Regulatory Considerations

1. Biodistribution: Required for IND
2. Shedding: Vector in bodily fluids
3. Germline transmission: Gonadal presence
4. Integration risk: Random vs site-specific
5. Immunogenicity: Pre-existing and induced

Author

AI Group - Biomedical AI Platform