AI Technology: Generative Language Modeling
This project leverages cutting-edge generative AI models to design synthetic enzymes optimized for industrial applications in biofuels, agriculture, and pharmaceuticals.
By fine-tuning advanced protein language models, such as ProGen2 and ESM3, with extensive enzyme datasets, we aim to overcome the limitations of natural enzyme discovery methods.
The AI-driven approach focuses on enhancing key enzyme properties, including reaction rates, stability under extreme conditions, and adaptability to industrial workflows.
The project will classify enzymes into rare, medium, and prevalent categories, enabling tailored optimization strategies for each group. Rigorous in silico quality control, including 3D structural validation, ensures the reliability of synthetic enzymes before experimental verification.
Expected outcomes include a library of highly efficient synthetic enzymes, reducing environmental impact and contributing to the EU’s sustainability goals.
The combination of AI and bioinformatics fosters innovation across sectors, enabling rapid development of cost-effective, high-performance enzymes.
This initiative positions itself as a transformative model for future data-driven discoveries in industrial biotechnology, directly supporting Europe’s transition toward a sustainable and circular economy.