AI-Assisted CRISPR and CAR-T Cell Engineering for Precision Medicine

Aim

Workshop Objectives

Workshop Structure

📅 Day 1: AI-Guided CRISPR Design for Precision Genome Editing

• CRISPR-Cas9 mechanism, DNA repair, and genome-editing strategies
• Target-gene, transcript, exon, and variant selection
• Guide RNA, PAM, and editing-window principles
• AI/ML-assisted guide-RNA scoring and prioritisation
• Base editing and prime editing overview
• Off-target prediction, specificity, safety, and ethics

🛠️ Hands-on: Target selection, guide-RNA design, computational scoring, and off-target assessment using sample datasets.

🧰 Tools: NCBI Gene, Ensembl, UCSC Genome Browser, UniProt, PubMed, Google Colab, Python, BioPython

📅 Day 2: CRISPR-Supported CAR-T Cell Engineering

• CAR-T architecture, generations, and therapeutic applications
• Tumour-antigen selection and target prioritisation
• Major targets: CD19, BCMA, HER2, EGFR, and MSLN
• CRISPR-based immune-cell engineering and gene knockout strategies
• Universal and next-generation CAR-T concepts
• Antigen escape, T-cell exhaustion, tumour microenvironment, and safety

🛠️ Hands-on: Analyse tumour-antigen expression data, prioritise CAR-T targets, and assess on-target/off-tumour risks.

🧰 Tools: Google Colab, Python, Pandas, NumPy, Matplotlib, Scikit-learn

📅 Day 3: AI-Integrated CRISPR–CAR-T Precision Therapeutics

• AI-assisted therapeutic target discovery and prioritisation
• CRISPR screening for resistance genes and therapeutic vulnerabilities
• Multi-omics and single-cell approaches in precision immunotherapy
• AI-based therapeutic response and toxicity prediction
• Next-generation CAR-T: logic-gated, armoured, and universal platforms
• Translational, regulatory, ethical, and biosafety considerations

🛠️ Hands-on: Build an AI/ML workflow for therapeutic response prediction and interpret key predictive features.

🧰 Tools: Google Colab, Python, Pandas, NumPy, Scikit-learn, Matplotlib, SHAP

Who Should Enrol?

Important Dates

Workshop Outcomes