Cell and Gene Therapy AI
Cell and gene therapy is a real gap between molecular design, synthetic biology, clinical trials, and biomanufacturing. AI can help with receptor design, guide selection, vector engineering, cell-state characterization, potency assays, manufacturing analytics, and patient stratification. None of those pieces remove the core translational constraints: safety, persistence, potency, manufacturability, and clinical evidence.
- Map cell and gene therapy AI claims to product design, assay, manufacturing, or clinical evidence
- Distinguish edited-cell products, vector-delivered therapies, and engineered immune-cell therapies
- Identify where single-cell, genome, protein, and biomanufacturing chapters connect
- Recognize potency and comparability as central evidence problems
- Evaluate AI claims against regulatory and translational context
Introduction
Cell and gene therapy products sit at the most complex edge of therapeutic translation. The FDA’s cellular and gene therapy page describes CBER oversight of cellular therapy products, human gene therapy products, and related devices, with gene therapy defined around modifying or manipulating gene expression or altering biological properties of living cells for therapeutic use (FDA, 2026). That definition matters for AI because the model may affect design, characterization, manufacturing, or evidence generation.
The right evidence question is not “did AI design it?” The right question is what decision the AI output changed: target choice, receptor sequence, guide selection, vector tropism, cell-state release criterion, potency assay, patient eligibility, or manufacturing control.
Demonstrated
Demonstrated capability includes AI-assisted design and triage for bounded components: guide RNAs, protein binders, vector elements, cell-state classifiers, and release-test analytics. These outputs are useful when tied to measured editing efficiency, specificity, expression, potency, or manufacturing performance.
Demonstrated capability also includes single-cell and imaging models for characterizing engineered-cell states. These systems support product understanding, but they do not substitute for clinical safety or efficacy evidence.
Theoretical
Theoretical capability includes integrated design systems that optimize receptor design, editing strategy, cell phenotype, persistence, toxicity risk, and manufacturing control in one workflow. Current programs have partial components, not a general product-design engine.
Theoretical capability also includes AI-guided potency assays that forecast clinical effect. Potency is context-specific, and the assay must be linked to mechanism and clinical outcome.
Beyond current capabilities
Beyond current capabilities includes fully in-silico approval-grade prediction of safety and efficacy for a cell or gene therapy product. Living products change over manufacturing, delivery, engraftment, persistence, and host context.
Beyond current capabilities also includes assuming that a successful molecular design result transfers directly to a cellular therapy product. Cell source, differentiation state, exhaustion, immunogenicity, dose, persistence, and manufacturing variation decide whether the design works.
Practice Notes
- Name the product class: edited cell, viral-vector therapy, non-viral delivery, immune-cell therapy, or tissue-engineered product.
- Link the AI output to a specific decision and assay.
- Treat potency, comparability, and release testing as first-order evidence.
- Keep CMC and manufacturing variation in the model-review checklist.
- Use regulatory terminology carefully; this chapter is not regulatory advice.