Imagine trying to brew a rare plant scent in a lab, but the biological 'machinery' needed is too complex to build. This project uses AI as a master blueprint to teach microbes how to build these complex plant molecules. It's like giving a bacteria a digital instruction manual to perfectly recreate nature's most valuable chemicals.
High-value oxygenated plant metabolites are currently difficult to produce because the necessary enzymes are hard to engineer in microbes. This makes these compounds expensive and inaccessible for wide industrial use.
A standardized AI/ML pipeline for the Design-Build-Test-Learn cycle and smart databases to optimize the production of flavonoids and terpenoids.
If you are a scent manufacturer dealing with the high cost of extracting rare plant oils — this project developed an AI/ML pipeline that enables the microbial production of terpenoids. This allows for a more stable and sustainable supply of fragrance molecules.
If you are a supplement producer dealing with inconsistent raw material quality from crops — this project developed a way to produce flavonoids using microbes. This ensures a pure, scalable, and consistent source of health-promoting plant metabolites.
If you are a biotech firm dealing with the difficulty of engineering cytochrome P450 enzymes — this project developed a standardized AI/ML platform for the Design-Build-Test-Learn cycle. This reduces the trial-and-error time when creating oxygenated plant metabolites.
Based on available project data, specific pricing or cost figures are not provided; however, the project aims to make production more cost-effective than traditional chemical synthesis.
The project aims to move from TRL 2-3 to TRL 5, focusing on scalable and competitive production of oxygenated plant metabolites to support economic valorization.
Based on available project data, specific licensing terms are not mentioned, but the project involves 11 partners including 3 SMEs and 4 industry entities.
The project actively involves regulators to reflect on the societal and ethical implications of combining AI and synthetic biology.
The project period is from 2023-09-01 to 2027-08-31.
It integrates into the biotech value chain via a modular AI/ML pipeline that covers every step of the Design-Build-Test-Learn cycle.
The consortium is well-balanced for commercialization, featuring 11 partners across 7 countries. With a 36% industry ratio, including 3 SMEs and 4 industrial partners, there is a strong bridge between the 2 universities and 4 research organizations to ensure the AI/ML tools are practically applicable to the biotech value chain.
Contact Universiteit Gent
Contact us to connect with the deCYPher consortium for AI-driven bioproduction licensing.
