AI-Guided CRISPR-Cas9 and CAR-T Cell Engineering for Precision Therapeutics

The workshop aims to provide participants with a practical understanding of AI-assisted genome editing and engineered immune-cell therapies. It focuses on how computational tools, biological data, and machine learning can support safer, more specific, and personalized CRISPR and CAR-T therapeutic strategies.

The workshop is designed to:

• Explain the principles and therapeutic applications of CRISPR-Cas9.
• Introduce AI-assisted guide RNA scoring and off-target assessment.
• Explain CAR-T cell structure, generations, target selection, and engineering strategies.
• Demonstrate how CRISPR can support next-generation CAR-T development.
• Introduce machine learning workflows for antigen prioritization and therapy-response prediction.
• Discuss safety, ethical, regulatory, and translational challenges in precision therapeutics.

📅 Day 1: AI-Guided CRISPR-Cas9 Design for Precision Genome Editing

• Focus: Understanding CRISPR-Cas9 genome editing, guide RNA design, AI-assisted scoring, and safety considerations for precision therapeutics.
• Introduction to precision therapeutics, genome editing, and the fundamentals of the CRISPR-Cas9 system.
• Understanding the role of guide RNA, Cas9 nuclease, PAM sequence, and target recognition in genome editing.
• Applications of CRISPR in cancer, rare diseases, immune disorders, and cell therapy.
• Use of AI and machine learning for CRISPR guide RNA design, on-target efficiency prediction, and off-target risk assessment.
• Importance of safety, specificity, validation, ethical considerations, and translational readiness in therapeutic genome editing.
• Overview of base editing, prime editing, and next-generation genome editing platforms.

🛠️ Hands-on:

• Perform an educational CRISPR guide RNA scoring simulation using Google Colab and a sample/synthetic DNA sequence.
• Load a sample DNA sequence, identify possible guide RNA regions, check basic PAM sequence logic, and calculate simple GC content.
• Rank guide RNA candidates using basic scoring criteria and visualize guide RNA scores.
• Discuss off-target risk conceptually for safe computational learning.
• This hands-on is for educational and computational learning only, not for wet-lab or clinical guide RNA design.

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

📅 Day 2: CAR-T Cell Engineering and Immune-Cell Therapeutic Design

• Focus: Exploring CAR-T cell engineering, immune-cell therapeutic design, tumor target selection, and CRISPR-supported immune-cell modification.
• Introduction to adoptive cell therapy, immune-cell engineering, T-cell biology, and tumor immune recognition.
• Understanding the structure of CAR-T cells, including antigen-binding domain, hinge region, transmembrane domain, and signaling domains.
• Overview of CAR-T therapy generations and major tumor-associated targets such as CD19, BCMA, HER2, EGFR, and MSLN.
• Applications of CAR-T therapy in hematological malignancies and emerging solid tumor research.
• Challenges in CAR-T therapy including antigen escape, tumor microenvironment, exhaustion, cytokine release syndrome, and neurotoxicity.
• Role of CRISPR in CAR-T engineering, including gene knockout strategies for PD-1, TCR, HLA, and immune checkpoint-related targets.
• Introduction to universal and off-the-shelf CAR-T concepts for next-generation engineered cell therapies.

🛠️ Hands-on:

• Perform CAR-T target prioritization using a sample dataset of tumor antigen expression and safety indicators.
• Load a sample antigen-expression dataset and compare tumor versus normal tissue expression.
• Identify potential CAR-T target candidates and create a simple antigen-prioritization score.
• Visualize target expression using bar plots and heatmaps.
• Interpret safety considerations such as on-target/off-tumor risk.

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

📅 Day 3: AI-Integrated CRISPR and CAR-T Workflows for Precision Therapeutics

• Focus: Integrating CRISPR, CAR-T, AI, and multi-omics workflows for next-generation precision therapeutics and engineered immune-cell therapy.
• Integration of CRISPR, CAR-T, and AI for advanced therapeutic discovery and immune-cell engineering.
• AI-based target discovery, antigen ranking, therapy response prediction, and toxicity risk assessment for immune-cell therapies.
• CRISPR screening approaches for identifying resistance genes, sensitivity genes, and therapeutic vulnerabilities.
• Engineering CAR-T cells for improved persistence, specificity, tumor penetration, and functional durability.
• Use of multi-omics data, single-cell data, gene expression, and tumor microenvironment profiling in precision immunotherapy.
• Regulatory, safety, and translational challenges in engineered cell therapy.
• Future trends including logic-gated CAR-T, armored CAR-T, universal CAR-T, synthetic biology circuits, and personalized immune-cell therapeutics.

🛠️ Hands-on:

• Build a simple AI-based therapy response prediction model using sample immune-cell therapy response data.
• Load a sample therapeutic response dataset and identify important features such as antigen expression, immune markers, and checkpoint genes.
• Prepare data for machine learning and train a basic classification model.
• Predict responder versus non-responder groups and evaluate model performance using accuracy and confusion matrix.
• Interpret results for precision therapeutic decision-making.

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

• Researchers and academicians
• PhD scholars and postgraduate students
• Biotechnology professionals
• Immunology and cancer biology researchers
• Biomedical scientists
• Bioinformatics learners
• Pharmaceutical professionals
• Industry professionals working in life sciences and healthcare
• Individuals interested in genome editing, cancer immunotherapy, immune-cell engineering, synthetic biology, and AI-assisted biomedical research

After completing the workshop, participants will be able to:

• Understand the fundamentals of CRISPR-Cas9 and CAR-T cell therapy.
• Explain how AI can improve guide RNA design and editing-efficiency prediction.
• Evaluate basic on-target and off-target considerations.
• Identify and prioritize potential CAR-T therapeutic targets.
• Analyze sample biological datasets using Python and Google Colab.
• Build a basic machine learning model for therapy-response prediction.
• Interpret model performance and explainable AI results.
• Understand safety concerns related to genome editing and engineered cell therapies.
• Explore emerging approaches such as universal CAR-T, armored CAR-T, logic-gated therapies, base editing, and prime editing.