Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / United Kingdom

Marie Skłodowska-Curie Action · Running

AI-EvoYeast Harnessing Genomic Instability with Al-Driven Adaptive Laboratory Evolution for Accelerated Yeast Bioproduction

Coordinator
Imperial College of Science Technology and Medicine, United Kingdom
Runs
1 May 2026 to 30 April 2028
Status
Running
EU funding
€260k
Total cost
—
Partners
1 organisations in 1 countries
Type
Marie Skłodowska-Curie Action
Grant agreement
101281441

What the project is doing

In the project's own words, from its summary on CORDIS.

The production of high-volume albumins, essential proteins for therapeutics and sustainable food, faces critical bottlenecks. In medicine, the supply of human serum albumin (HSA) is constrained by a reliance on plasma, which carries pathogen risks and supply vulnerabilities. In the food sector, ovalbumin production via precision fermentation offers a sustainable alternative to animal agriculture. Still, they both require overcoming major yield and cost-effectiveness barriers to be viable at an industrial scale.

To address these challenges, AI-EvoYeast will exploit the inherent instability of polyploid yeast as an engine for accelerated evolution, integrating it with product-coupled selection to drive the evolution of albumin-hyperproducing strains. By employing an unbiased evolutionary approach, the platform enables the cell itself to explore a vast solution space of mutations, gene expression changes, and network-level adaptations, overcoming the stress of protein hyperproduction and the limits of rational design.

The AI-EvoYeast project will develop a next-generation yeast (S. cerevisiae) platform, transforming a biological challenge, genomic instability, into a powerful engineering asset. Unlike traditional Adaptive Laboratory Evolution (ALE), AI-EvoYeast integrates Artificial Intelligence (AI) and Machine Learning (ML), fuelled by multi-omics data, to decipher adaptive mechanisms and build a predictive model for optimal genomic configurations.

Insights from explainable AI (XAI) will then guide precise CRISPR interventions to reconstruct superior phenotypes in a stable industrial chassis. This project pioneers a highly generalisable AI-augmented evolutionary strategy. By creating a predictive platform technology estimated to slash R&D timelines by up to 50%, it will secure a sustainable, cost-effective European supply of vital proteins for the pharmaceutical and food industries.

This directly supports EU strategic autonomy and leadership in the global bioeconomy.

Topics

Who is involved

OrganisationCityCountryRole
Imperial College of Science Technology and MedicineLondonUnited KingdomCoordinator

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI