PROTAC Design Agent

The PROTAC Design Agent provides AI-assisted design of Proteolysis Targeting Chimeras (PROTACs) for targeted protein degradation. It integrates machine learning for ternary complex prediction, linker design, E3 ligase selection, and ADMET optimization to accelerate degrader drug discovery for oncology and other therapeutic areas.

When to Use This Skill

• When designing PROTAC degraders for a target protein.
• For optimizing linker chemistry and length.
• To predict ternary complex formation and degradation efficiency.
• When selecting optimal E3 ligase (CRBN, VHL) for the target.
• For optimizing ADMET properties of degrader molecules.

Core Capabilities

1. Warhead Selection: Identify optimal target protein ligands.

1. E3 Ligase Selection: Choose CRBN, VHL, or other E3 recruiters.

1. Linker Design: Optimize linker length, chemistry, and rigidity.

1. Ternary Complex Prediction: Model POI-PROTAC-E3 formation.

1. Degradation Efficiency Modeling: Predict DC50 and Dmax.

1. ADMET Optimization: Balance potency with drug-like properties.

PROTAC Components

E3 Ligase Options

Workflow

1. Input: Target protein structure/sequence, known ligands (optional).

1. Warhead Design: Generate/optimize POI binding moiety.

1. E3 Selection: Choose optimal E3 ligase for target/tissue.

1. Linker Library: Generate diverse linker options.

1. Ternary Complex Modeling: Predict complex formation.

1. Ranking: Score by predicted degradation and ADMET.

1. Output: Ranked PROTAC designs with synthesis routes.

Example Usage

User: "Design a PROTAC to degrade BRD4 using CRBN as the E3 ligase, optimizing for oral bioavailability."

Agent Action:

python3 Skills/Drug_Discovery/PROTAC_Design_Agent/design_protac.py \
    --target BRD4 \
    --target_structure pdb:3MXF \
    --warhead_smiles "JQ1_core_smiles" \
    --e3_ligase CRBN \
    --linker_library peg,alkyl,piperdine \
    --linker_length_range 4,12 \
    --optimize_oral true \
    --output protac_designs/

Linker Design Parameters

Output Components

Degradation Efficiency Metrics

AI/ML Components

Ternary Complex Prediction:

• AlphaFold-Multimer adaptation
• Geometric deep learning
• Molecular dynamics validation

Degradation Modeling:

• Quantitative degradation prediction
• Transfer learning from degrader databases
• Multi-task learning (DC50, Dmax, kinetics)

Linker Optimization:

• Generative models (VAE, diffusion)
• Reinforcement learning
• Multi-objective Bayesian optimization

ADMET Prediction:

• Property prediction models
• Chameleonicity assessment
• Oral bioavailability scoring

Clinical Pipeline Status (2026)

Design Considerations

Prerequisites

• Python 3.10+
• RDKit, Open Babel
• AlphaFold2/3
• Molecular dynamics (GROMACS/OpenMM)
• PyTorch for ML models

Related Skills

• Molecular_Glue_Discovery_Agent - Glue degraders
• TPD_Ternary_Complex_Agent - Complex prediction
• Molecular_Docking_Agent - Docking analysis
• ADMET_Prediction_Agent - Property prediction

ADMET Optimization Strategies

Special Considerations

1. Target Suitability: Not all proteins are degradable
2. E3 Expression: Check tissue-specific E3 levels
3. Ubiquitination Sites: Surface lysines needed
4. Resistance: Target mutations, E3 downregulation
5. Selectivity: Validate off-target degradation

Quality Control Metrics

Author

AI Group - Biomedical AI Platform