Article Complete
AIM
Capgemini’s AI Breakthrough to Accelerate Bioeconomy
Capgemini’s AI Breakthrough to Accelerate Bioeconomy
Protein Power Play

Capgemini’s AI Breakthrough to Accelerate Bioeconomy

This new approach, powered by a specialised protein large language model, predicts the most effective protein variants while using 99% less data than traditional methods.

Published Updated

Key takeaways

  • Capgemini introduces a generative AI method that reduces protein engineering data requirements by 99%.
  • This breakthrough accelerates bioinnovation in healthcare, agriculture, and environmental science.
  • The new methodology addresses data bottlenecks, enabling discoveries with smaller datasets.
  • Enhanced enzyme capabilities could significantly reduce plastic waste management costs.
  • AI predictions streamline research, cutting experiment numbers from thousands to just 43.
5 min

Capgemini, on Tuesday, introduced a generative AI-driven method for protein engineering that significantly reduces data requirements, making scientific breakthroughs faster and more accessible. 

This new approach, powered by a specialised protein large language model (pLLM), predicts the most effective protein variants while using 99% less data than traditional methods. With a patent pending, this breakthrough is expected to drive innovation across industries such as healthcare, agriculture, and environmental science.

Capgemini’s methodology tackles one of the biggest challenges in biotechnology research—the data bottleneck—by enabling discoveries with smaller datasets. 

This means organisations can develop new bio-solutions even in resource-limited environments. By reducing research costs and time, this approach allows businesses to explore solutions that were previously too expensive or impractical.

Roshan Gya, CEO of Capgemini Invent, emphasised the impact of this development: “Our new methodology is faster, more cost-effective and opens the door to new opportunities for clients to develop innovative bio-based solutions.”

Plastic Waste and Medical Research

The approach enhanced a cutinase enzyme that breaks down PET plastic by 60%, making it easier and more cost-effective to degrade plastic waste. This could help reduce environmental pollution and lower waste management costs.

AI-driven predictions reduced the number of experiments needed to improve the Green Fluorescent Protein (a widely used research marker) from thousands to just 43 while increasing its brightness by seven times. 

This efficiency can speed up drug discovery, diagnostics, and bioengineering applications.

The breakthrough has drawn praise from experts in the field. 

Stephen Wallace, professor of chemical biotechnology at the University of Edinburgh, highlighted its significance: “Capgemini’s generative AI-driven approach represents a significant leap in protein engineering. By drastically reducing data requirements, Capgemini has fundamentally transformed the innovation timeline in bioengineering.” 

He further mentioned that this breakthrough reflects a clear vision for the future of engineering biology, leveraging the design and engineering of new biocatalysts to enable more sustainable and scalable industrial processes. 

With its expertise and adaptability, Capgemini is well-positioned to drive technological advances in this exciting and rapidly evolving interdisciplinary field.

This breakthrough was developed in Capgemini’s AI-driven biotechnology lab at Cambridge Consultants in the UK. For over ten years, Cambridge Consultants has been pioneering engineering biology and AI development. 

The lab brings together experts in biology, chemistry, AI, digital twins, electronics, and sustainability to push the boundaries of scientific discovery.

Membership

Stay ahead with AI insights.

Unlimited access to premium articles, exclusive analysis, and the stories shaping India's AI economy.

Subscribe now

AIM Americas

1190 Miraloma Way Suite P, Sunnyvale, CA 94085

AIM India

1st Floor, Sakti Statesman, Bellandur, Bengaluru – 560103

© 2026 AIM. All rights reserved.