Moderna pioneered messenger RNA (mRNA) therapeutics, but the complexity of designing, testing, and manufacturing mRNA molecules at scale presented challenges that traditional pharmaceutical R&D processes could not address efficiently. Each mRNA sequence required extensive experimentation to optimize for stability, expression levels, and immunogenicity — a process that consumed months of laboratory work and generated limited reusable knowledge.
The company's early production capacity allowed for approximately 30 mRNA candidates per month to be synthesized and tested, creating a bottleneck that limited the number of therapeutic programs Moderna could pursue simultaneously. This capacity constraint was particularly acute during the COVID-19 vaccine development, when the urgency of the pandemic required accelerated timelines that traditional workflows could not support.
Moderna also faced a data utilization challenge. The company generated vast amounts of experimental data from mRNA synthesis, in vitro testing, and preclinical studies, but much of this data sat in disconnected systems and was not systematically analyzed to inform future designs. Researchers relied heavily on intuition and small-scale pattern recognition rather than data-driven insights across the company's entire experimental history.
Moderna implemented an AI-driven mRNA design platform that used machine learning to predict which mRNA sequences would exhibit desired properties based on historical experimental data. The platform ingested data from thousands of prior synthesis and testing cycles, learning patterns that correlated sequence features with stability, expression efficiency, and safety profiles.
The company deployed over 750 AI models across its R&D and manufacturing processes — from predicting optimal mRNA modifications to forecasting production yields and quality metrics. These models were integrated directly into Moderna's laboratory information management systems, providing real-time guidance to scientists designing new therapeutic candidates. Rather than relying on trial-and-error experimentation, researchers could use AI predictions to focus on the most promising designs, dramatically accelerating iteration cycles.
Moderna also automated significant portions of its manufacturing process using AI-controlled systems that monitored production in real time, adjusted parameters to maintain quality, and predicted potential failures before they occurred. This automation increased throughput while maintaining stringent quality standards, enabling the company to scale from boutique research production to commercial manufacturing.
“AI has fundamentally changed how we do drug discovery and development. We can now explore therapeutic possibilities at a scale and speed that was unimaginable a decade ago.”— Stéphane Bancel, CEO, Moderna
This case study is based on publicly available information about Moderna.
Learn more about ModernaEvery transformation starts with a conversation. Let's discuss your challenges and opportunities.
Discuss Your Challenge