🧬 The software can help design processes for purifying advanced therapies during manufacturing.
🔬 The goal is to predict how protein products will behave when purified in a chromatography column.
📊 The AI is being trained to understand and describe the physical properties of proteins in numerical terms.
⚙️ This research builds on previous work using molecular descriptors and the latest developments in machine learning.
🌟 In the future, manufacturers may be able to improve their process development and understand protein biology using AI.
Introduction:
Researchers from the University of Natural Resources and Life Sciences in Vienna are using artificial intelligence (AI) to describe the 3D structure of therapeutic proteins. Their goal is to develop software that can assist in the design of purification processes for advanced therapies during manufacturing.
- The researchers aim to link the 3D appearance of proteins to their molecular structure through AI.
- The AI is being trained to understand and describe different shapes of proteins in numerical terms.
- The software could potentially predict how protein products will behave when purified in a chromatography column, which can aid in process development for manufacturers of cell and gene therapies.
- The team is using the latest developments in machine learning to enhance their research from previous descriptive approaches to now having a mechanistic model underlying the predictions.
- Future applications of AI in protein research may also allow for a better understanding of the biology of proteins.
Conclusion:
The Austrian researchers are using artificial intelligence to advance downstream processing by training it to describe the 3D structure of therapeutic proteins. Their work aims to provide a deeper understanding of protein behavior during purification processes, potentially benefiting manufacturers of cell and gene therapies. The use of AI in this context has the potential to significantly improve process development and optimization. Additionally, this research may lead to a better understanding of protein biology in the future.
