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. Each mRNA sequence required extensive experimentation to optimise 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 synthesised and tested, creating a bottleneck that limited the number of therapeutic programmes Moderna could pursue simultaneously.
Moderna's mRNA platform generates an immense design space: the number of possible nucleotide sequences encoding a target protein is astronomically large, and each sequence's translation efficiency, immunogenicity, and stability profile must be predicted before costly wet-lab synthesis. 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 analysed. Researchers relied on intuition and small-scale pattern recognition rather than data-driven insights across the company's entire experimental history — a gap that AWS infrastructure would later help address.
Moderna implemented an AI-driven mRNA design platform — the Drug Design Studio, built on AWS — that uses machine learning to predict which mRNA sequences will exhibit desired properties based on historical experimental data. The platform ingests data from thousands of prior synthesis and testing cycles, learning patterns that correlate sequence features with stability, expression efficiency, and safety profiles. Deep-learning sequence-optimisation models jointly predict mRNA translation efficiency, structural stability, and immunogenicity, enabling in-silico screening of billions of candidate sequences before selecting those most likely to succeed in preclinical testing.
The company also deployed ChatGPT Enterprise across the organisation, creating over 750 custom GPTs within two months — spanning legal, research, manufacturing, and commercial functions. One key application, Dose ID GPT, helps clinical teams evaluate optimal vaccine doses by applying standard dose-selection criteria and generating analytical charts. Moderna's legal team achieved 100% adoption of ChatGPT Enterprise, and average employee usage reached 120 conversations per week.
On the manufacturing side, Moderna automated significant portions of production using AI-controlled systems that monitor quality in real time, adjust parameters to maintain specifications, and predict potential failures before they occur. This automation — combined with robotic high-throughput synthesis — scaled the company from 30 mRNA candidates per month to over 1,000, with turnaround times of just a few weeks per lot.
This is an industry case study based on publicly available information. Moderna is not a Pertama Partners client.
We help enterprises across Southeast Asia design and deliver AI transformation programs. Let’s talk about what’s possible for your team.
