AI-Powered CRISPR/Cas9 Nanoparticle Delivery: Non-Viral Gene Editing

Aim

Workshop Objectives

Workshop Structure

📅 Day 1: CRISPR/Cas9 Target Design, Guide RNA Selection & Off-Target Analysis

• CRISPR/Cas9 mechanism, sgRNA design, PAM recognition, and gene-editing applications
• Principles of guide-RNA selection and on-target efficiency
• GC content, specificity, and guide-quality metrics
• Off-target prediction and genome-editing safety
• Comparative use of CRISPOR and CHOPCHOP
• Selection of high-quality guides for therapeutic delivery

🛠️ Hands-on:

• Select a target gene
• Design guide RNAs using CRISPOR
• Compare guide candidates using CHOPCHOP
• Evaluate on-target and off-target scores
• Rank guide RNAs for nanoparticle delivery

🧰 Tools Covered:

CRISPOR, CHOPCHOP, genomic sequence resources, and guide-ranking templates

📅 Day 2: Nanoparticle Design for Non-Viral CRISPR Delivery

• Viral versus non-viral CRISPR delivery
• Delivery of DNA, mRNA, sgRNA, and Cas9 RNPs
• Lipid, polymeric, hybrid, and inorganic nanoparticle systems
• Particle size, surface charge, composition, stability, and cargo loading
• Cellular uptake, endosomal escape, and targeted delivery
• Cytotoxicity, immune response, and biocompatibility
• Structure–property relationships for CRISPR nanocarriers
• Preparation of formulation data for AI modelling

🛠️ Hands-on:

• Retrieve nanoparticle-related molecular data from PubChem
• Generate descriptors and fingerprints using RDKit
• Combine molecular and formulation properties
• Visualise structure–property relationships
• Prepare an AI-ready nanoparticle formulation dataset

🧰 Tools Covered:

PubChem, RDKit, Google Colab, Python, pandas, NumPy, Matplotlib, and formulation datasets

📅 Day 3: AI Prediction, Explainable Optimization & CRISPR Delivery Prioritization

• Machine learning for nanoparticle formulation screening
• Delivery-efficiency and safety prediction
• Feature engineering for molecular and formulation parameters
• Random Forest and XGBoost modelling
• Model validation and performance evaluation
• Explainable AI using SHAP
• Identification of key drivers of delivery efficiency and toxicity
• Multi-parameter formulation prioritization
• Translational considerations in non-viral CRISPR delivery

🛠️ Hands-on:

• Train an XGBoost model for delivery-performance prediction
• Evaluate predictive accuracy
• Interpret important features using SHAP
• Compare nanoparticle candidates by predicted efficiency and safety
• Integrate guide-RNA quality with formulation performance
• Rank CRISPR delivery candidates for further validation

🧰 Tools Covered:

Google Colab, Python, RDKit, XGBoost, SHAP, pandas, scikit-learn, Matplotlib, and formulation-ranking templates

Who Should Enrol?

Important Dates

Workshop Outcomes

Meet Your Mentor(s)

Prof. Kumud Malhotra

Professor and Dean

Biotechnology

more

Fee Structure