High-Yield Astaxanthin Production Process Development and Scale-up Validation from Wild-Type Phaffia rhodozyma via Parameter Optimization and LSTM Modeling

Po Chen¹Xingli Shi²Jingyan Jiang²Huanghe Cheng²Jinyan Chai²Zhenggang Xie^2,3*Mohd Helmi Sani^3*

• ¹Gastroenterology and Urology Department Ⅱ, Hunan Cancer Hospital, Changsha, China
• ²T&J Bioengineering (Shanghai) Co., Ltd., Shanghai, China
• ³Universiti Teknologi Malaysia Faculty of Science, Skudai, Malaysia

This study developed an integrated strategy that combines traditional parameter optimization with LSTM (Long Short-Term Memory) intelligent modeling to significantly enhance astaxanthin production from the wild-type Phaffia rhodozyma GDMCC 2.218. Through systematic optimization, optimal fermentation conditions were determined (temperature 20°C, pH 4.5, dissolved oxygen 20%), achieving an astaxanthin yield of 387.32 mg/L within 144 hours in a 500 mL bioreactor. Upon scaleup to 5 L, the yield was further improved to 400.62 mg/L (165 hours), demonstrating process robustness. An innovative LSTM prediction model was constructed (R² = 0.978) to predict astaxanthin concentration. The achieved yield not only far exceeded previously reported wild-type strain levels (a 10-to 20-fold improvement) but also reached or surpassed the production levels of most engineered strains. This research confirms the feasibility of achieving commercial-scale production of high-value natural astaxanthin through non-genetically modified approaches. The resulting product combines high productivity, safety, and regulatory advantages, providing an innovative solution for industrial-scale natural astaxanthin production.