Challenges in developing cell culture media using machine learning.

Area of Science:

• Biotechnology and Biomedical Engineering
• Cell Biology and Tissue Engineering

Background:

• Cell culture media are crucial for microbial and mammalian cell applications in food, pharmaceutical, and medical sectors.
• Optimizing culture media is essential for enhancing cell culture performance and advancing cell culture engineering.
• Established methods like one-factor-at-a-time (OFAT) and response surface methodology (RSM) exist for media optimization.

Purpose of the Study:

• To introduce machine learning (ML) as an emerging technology in cell culture engineering for developing efficient culture media.
• To summarize commonly used ML algorithms and their successful applications in medium optimization.
• To highlight the advantages of ML-assisted medium development and guide method selection.

Main Methods:

• Review of emerging machine learning (ML) technologies in conjunction with high-throughput experimental techniques.
• Summarization of commonly employed ML algorithms relevant to biological and chemical optimization problems.
• Analysis of successful case studies demonstrating ML application in cell culture medium development.

Main Results:

• Machine learning integration with high-throughput experimentation offers a powerful approach for developing highly effective cell culture media.
• Various ML algorithms have demonstrated success in optimizing complex media formulations, leading to improved cell growth and productivity.
• ML-assisted development provides a more efficient and data-driven alternative to traditional optimization methods.

Conclusions:

• Machine learning represents a significant advancement in cell culture engineering, particularly for medium optimization.
• The adoption of ML can lead to substantial improvements in cell culture performance across various industries.
• This review provides insights for selecting appropriate ML-based optimization strategies tailored to specific cell culture objectives.