(Product Release) AI-Driven Solutions for Lab-Automation
An Alliance between Artificial Intelligence and Lab Automation: AI-driven optimisation solution for culture media in self-driving laboratories
- Artificial Intelligence (AI) and Machine Learning (ML) have been shown to accelerate research by 2-10 times.
- We are pioneering in leveraging the power of AI and ML in lab-automated synthetic biology, such as alternative proteins and biomaterials.*
- Identifying the optimal media is a classic challenge in biology. The optimal media composition can be influenced by more than 20 variables such as the amount of vitamins, growth factors and trace materials. This is a high-dimensional problem that is best solved using high-dimensional approaches.
- However, classic DoE methods are suboptimal at tackling high-dimensional problems and are ineffective at addressing problems with more than 5 variables.
- Compared to classic DOE, AI & ML methods excel in high-dimensional problem spaces, allowing us to evaluate many more complex combinations at the same time to efficiently discover the optimal combination.
*For example, Cosenza et al. (2023) show how AI helped discover "several media [...] with 23% more growth at only 62.5% of the cost of the control".
Combined with lab automation, the AI-pipeline can accelerate discovery of optimal media by 2 to 10 times.
Matterhorn Studio is showcasing their AI-powered solution at SLAS 2024 on May 28th in Barcelona:
Plug & Play AI-Pipelines that accelerate media optimisation by 2-10 times.
Join us for hands-on demonstrations of how our AI-solutions can power your lab automation setup to identify optimal media.
About Matterhorn Studio:
Matterhorn Studio is pioneering the OptStore, the world's first marketplace for Artificial Intelligence Plug-ins for Lab Automation.
Try our tutorial today on matterhorn.studio, or visit us at SLAS on Booth 512 E to learn more about how you can integrate AI-driven optimisation in your lab today.
Get in touch
We will happily guide you through the emerging space of data-driven material discovery. We look forward to learn from your experience and problem space.
