# Machine learning in bioprocess development: From promise to practice

**Authors:** Laura Marie Helleckes, Johannes Hemmerich, Wolfgang Wiechert, Eric von Lieres, Alexander Grünberger  
**arXiv:** [2210.02200](https://arxiv.org/abs/2210.02200)  
**Date:** 2022-10-04  
**Summary page:** https://www.summarizepaper.com/en/paper/2210.02200v1/

## Key points

- Bioprocess development has been revolutionized by novel analytical techniques, digitalization, and automation.
- These advancements generate vast amounts of heterogeneous experimental data containing valuable process information.
- Data-driven methods like machine learning (ML) approaches have emerged as a promising tool to make sense of this data and exploit experimental facilities most efficiently.
- ML methods have been applied in various aspects of bioprocess development such as strain engineering and selection, bioprocess optimization, scale-up, monitoring and control.
- The review article provides successful application cases for each topic while also highlighting current challenges.
- ML is poised to play an increasingly important role in bioprocess development due to its ability to handle complex datasets and identify patterns that may not be immediately apparent to human analysts.
- The authors point out domains that can potentially benefit from technology transfer and further progress in the field of ML.
- Researchers continue to refine these techniques and explore new applications for them within this field.

## Summary

The field of bioprocess development has been revolutionized by the advent of novel analytical techniques, digitalization, and automation. These advancements have enabled the generation of vast amounts of heterogeneous experimental data that contain valuable process information. To make sense of this data and exploit experimental facilities most efficiently, data-driven methods like machine learning (ML) approaches have emerged as a promising tool. In their review article titled "Machine learning in bioprocess development: From promise to practice," Laura Marie Helleckes, Johannes Hemmerich, Wolfgang Wiechert, Eric von Lieres, and Alexander Grünberger highlight the potential of ML methods in exploring large design spaces rationally. The authors demonstrate how ML methods have been applied so far in various aspects of bioprocess development such as strain engineering and selection, bioprocess optimization, scale-up, monitoring and control. The review article provides successful application cases for each topic while also highlighting current challenges. The authors point out domains that can potentially benefit from technology transfer and further progress in the field of ML. With its ability to handle complex datasets and identify patterns that may not be immediately apparent to human analysts, ML is poised to play an increasingly important role in bioprocess development. Overall, this comprehensive review highlights the immense potential of ML methods in modern bioprocess development while also acknowledging the challenges that need to be addressed for these tools to reach their full potential. As researchers continue to refine these techniques and explore new applications for them within this field, we can expect even more exciting developments on the horizon.