Cell and gene therapy (CGT) has evolved from a niche research pursuit into a central force in biopharmaceutical innovation. By engineering living cells and genetic material to repair or replace faulty biological mechanisms, these therapies can deliver outcomes that traditional drugs cannot achieve. Still, manufacturing remains fragmented and highly variable, with most processes still reliant on manual intervention and legacy systems, slowing progress toward scalability.
The growing use of advanced analytics and artificial intelligence (AI) is reshaping this landscape by enabling data-driven process control, predictive manufacturing, and greater transparency across the development lifecycle. Together, these tools are creating the foundation for scalable, reproducible, and compliant CGT manufacturing.
The expanding role of data in therapy development
Every stage of the CGT process, from cell collection to product release, generates large amounts of data. In the past, organizations stored most of that data in separate systems or tracked it manually, which made it difficult to analyze or share.
Today, advanced analytics make it possible to combine and interpret this information in real time. By bringing together data from sensors, instruments and electronic records, teams can identify which factors have the most significant effect on product quality. Machine-learning models can recognize patterns in temperature, nutrient levels, or oxygen conditions that predict how well cells will grow. When the system detects a potential problem, it can alert operators who can adjust parameters before quality is compromised.
Digital twins, which are virtual models of the manufacturing process, extend these capabilities. They use both live and historical data to simulate how changes in variables affect results, allowing scientists to test ideas without interrupting production. The insights gained can reduce failed batches, improve yields, and make better use of patient-derived material.
Improving safety and therapeutic consistency
AI-driven predictive modeling is improving consistency in both manufacturing and patient outcomes, as well as safety. For autologous therapies, where each treatment starts with an individual patient’s cells, no two samples behave the same way. Predictive algorithms can evaluate cell characteristics to anticipate how each sample will expand or differentiate. Manufacturers can then adjust culture conditions to keep potency and viability within target ranges.
In gene therapy, AI models are helping design safer and more predictable viral vectors. These tools can forecast gene expression and immune responses, allowing scientists to choose components that reduce unwanted side effects, improve clinical design, and lower the risk of late-stage failures.
Predictive control on the manufacturing floor
Manufacturing cell and gene therapies remains one of the most complex undertakings in modern biopharma. Each batch can take several weeks to complete and can cost hundreds of thousands of dollars. Traditional quality testing often happens at the end of the process, which limits the ability to fix issues that arise earlier in production.
Advanced analytics and AI now make it possible to monitor quality in real time. Predictive systems use data from multiple sources to compare current performance against established models. These systems allow operators to correct issues before they lead to failure. This approach supports the FDA’s Quality by Design principles by embedding quality control throughout the process rather than relying on end-stage testing alone.
Predictive control also improves operational efficiency. By analyzing data from multiple runs, analytics tools identify which parameters most affect yield and turnaround time. Over successive production cycles, this knowledge leads to continuous improvements in both cost and reliability.
Challenges slowing adoption
Despite its clear potential, the adoption of analytics and AI across CGT manufacturing has been gradual. The main obstacles include fragmented data systems, limited infrastructure, workforce skill gaps, and regulatory uncertainty.
Data fragmentation remains a significant barrier. Process data, quality metrics, and clinical outcomes often sit in separate databases, preventing a unified view of performance. Without common data standards, even well-designed models cannot easily compare results across facilities or products.
A lack of a standardized “language” for CGT compounds the challenge. Every manufacturer defines process steps, data elements, and parameters differently. Even basic terms, such as “viability” or “yield,” can vary depending on the test or measurement method used. Without a shared vocabulary and data model, it is nearly impossible to align or aggregate data across organizations. Developing this common language is essential to promoting interoperability and enabling meaningful data sharing. Without it, the industry cannot build datasets large enough to train AI systems effectively. Small, isolated datasets limit the accuracy and reliability of predictive models, slowing progress toward broader adoption of analytics-based decision-making.
Outdated technologies also slow progress. Many manufacturing sites still rely on instruments that lack connectivity or produce incomplete datasets. In-line measurement of key quality attributes, such as cell phenotype or vector potency, is not yet widely leveraged. Delayed or missing data reduces the effectiveness of predictive models. Modernizing equipment and upgrading digital systems requires upfront investment but is vital for long-term scalability.
Process diversity is another challenge. Each CGT product uses different materials and workflows, which limits standardization. Models trained on one platform may not apply to another. The shortage of professionals who understand both bioprocessing and data science makes it harder to develop and maintain these tools.
Regulatory uncertainty continues to influence adoption decisions, as companies weigh innovation against compliance risk. Agencies such as the FDA and EMA support innovation in advanced manufacturing but require clear evidence that AI-based systems do not compromise safety or efficacy. Changing a validated process can trigger new qualification steps or extended review timelines. As regulatory frameworks mature, companies will gain more confidence in integrating advanced analytics into production.
Building a framework for digital maturity
Overcoming these challenges will take coordination across the CGT ecosystem. Manufacturers, technology providers, and regulators can work together to define shared data standards and secure methods for information exchange. Collaborative initiatives focused on precompetitive data sharing could provide the large datasets needed to refine predictive models and improve benchmarking.
Investment in infrastructure will also accelerate progress. Cloud-based data environments, automated data collection, and integrated manufacturing execution systems make it easier to analyze and act on information. Consistent, high-quality data is the foundation for reliable analytics.
Developing the right workforce is equally important. The field needs professionals who understand both the biology of cell therapies and the computational tools that support them. Partnerships with universities and training programs can help close this gap and prepare teams for the digital era of manufacturing.
Looking ahead
Advanced analytics and AI are not replacing human expertise in CGT manufacturing. Instead, they are enhancing it. These tools allow scientists and engineers to make faster, more informed decisions and to maintain tighter control over complex processes. Predictive modeling and continuous monitoring reduce risk, improve efficiency, and help ensure that every patient receives a therapy that meets the highest standards of quality and safety.
As the industry moves from small-scale, patient-specific production to broader commercial supply, digital transformation will become essential. Early adopters of analytics gain a stronger position to maintain consistency and respond to increasing market demand. The combination of biology and data science is shaping a new standard for advanced therapeutics and moving the promise of curative medicine closer to everyday clinical reality.
Photo: Weiquan Lin, Getty Images
Dustin Kerns is Director of Marketing at Title21 Health Solutions, where he helps advance digital transformation across the life science ecosystem. He has more than a decade of marketing experience in healthcare, with the past two years focused on the biotherapies space. As the parent of a child with Type 1 Diabetes, he is personally inspired by the potential of advanced therapies to improve patient outcomes and change lives.
This post appears through the MedCity Influencers program. Anyone can publish their perspective on business and innovation in healthcare on MedCity News through MedCity Influencers. Click here to find out how.
