Epistra, Hitachi, and Fermenta Achieve World-Leading Yield and Up to 73% Reduction in Lab Experiments for Pharmaceutical Intermediate (S)-Reticuline Production Using AI
Pilot-scale production validation planned during fiscal year 2025, targeting suppression of yield decline during scale-up
Epistra Inc., Hitachi, Ltd., and Fermenta Inc. announced the completion of lab-scale validation in October for the microbial fermentation process development of the pharmaceutical intermediate “(S)-reticuline.”
In this validation, Epistra’s experimental condition optimization was combined with Hitachi’s culture simulation technology to consistently optimize the production process from lab to pilot scale.
In the lab-scale validation, fermentation experiments were conducted using smart cells developed by Fermenta. Epistra and Hitachi used Epistra’s proprietary condition optimization AI “Epistra Accelerate” to identify optimal conditions in just 60 experiments from an enormous space of approximately 4.3 quadrillion possible combinations across 11 variables including temperature, pH, aeration rate, and medium composition.
As a result, the yield of (S)-reticuline improved from 3.2 g/L to 6.0 g/L, and it was confirmed that the number of lab experiments could be reduced by up to 73% compared to conventional approaches.
This initiative represents a new production development approach that integrates “AI x Simulation x Smart Cells,” achieving world-leading yield levels for bio-production using microorganisms.
These results are expected to contribute to improved productivity of intermediates used in pharmaceuticals and other products, as well as the establishment of a stable and efficient supply system.
The three companies plan to conduct pilot-scale production validation during fiscal year 2025 and will proceed with verification aimed at suppressing yield decline, a key challenge during scale-up.
Related Articles
Won Grand Prix in the 7th IP BASE AWARD Startup Category Hosted by the Japan Patent Office
On March 3, 2026, Epistra Inc. won the Grand Prix in the startup category at the '7th IP BASE AWARD' ceremony hosted by the Japan Patent Office.
Jikkenigaku Special Issue 'AI and Data-Driven Drug Discovery Research' Published — CTO Tsuzuki Authors Chapter on AI-Driven Drug Target Discovery
In 'Jikkenigaku Special Issue: AI and Data-Driven Drug Discovery Research' published by Yodosha, our CTO Taku Tsuzuki authored a chapter on AI-driven knowledge mining for drug target discovery.
Speaking Engagement: Delivered Keynote at the 10th Cell Manufacturing Kotozukuri Symposium
On March 4, 2026, CEO Yosuke Ozawa delivered a keynote speech on optimizing cell manufacturing processes using AI and robotics at the '10th Cell Manufacturing Kotozukuri Symposium' hosted by Osaka University.