Research on Automated Optimization of Cell Manufacturing Protocols for Regenerative Medicine Using Our AI Published in eLife
Epistra Inc., as part of a joint research group with RIKEN and Robotic Biology Institute Inc., has developed a robot-AI system that autonomously conducts trial-and-error exploration of cell culture conditions, and has successfully improved cell culture protocols used in regenerative medicine.
Research Overview
In this research, we conducted proof-of-concept experiments for automated protocol optimization by combining a robot capable of high-precision life science experimental operations with our artificial intelligence software “Epistra Accelerate.” Through three rounds of experiments (144 conditions) conducted over six months, we achieved the highest evaluation score to date (91%).
Results
The research results demonstrate that robotic and AI-driven exploration alone, without expert intervention, can identify conditions that produce results of quality equivalent to those achieved by experts, proving the feasibility of autonomous experimentation in the field of cell culture.
Related Articles
Epistra Contributes Article on "AI-Robot-Driven Drug Development" to Pharmacia, Journal of the Pharmaceutical Society of Japan
Epistra CTO Taku Tsuzuki and CEO Yosuke Ozawa contributed an article on AI-robot-driven drug development to Pharmacia, Vol. 62 No. 7, published by the Pharmaceutical Society of Japan.
Cell Culture Optimization Software 'CellTune Ver.2' Launches Globally
Epistra Inc. announces the global launch of 'CellTune Ver.2,' the updated version of the co-developed cell culture optimization software with Shimadzu Corporation, on June 29, 2026. The new version introduces cloud-based subscription delivery and overseas expansion of custom media manufacturing services.
Speaking Engagement: CEO Yosuke Ozawa Presented at the 10th Shonan iPark Regenerative Medicine Seminar
On June 3, 2026, Epistra Inc. CEO Yosuke Ozawa presented at the 10th Shonan iPark Regenerative Medicine Seminar, sharing implementation case studies and future prospects for AI and mathematical optimization in regenerative medicine process development.