A look back at the ‘Digital tools to accelerate bioproduction’ day

This focus addresses two major challenges:

• Inventorying, standardising and making experimental resources accessible in order to facilitate the exchange of software and data and reduce development costs.
• Exploiting experimental data through machine learning to build accurate predictive models — an essential lever for understanding the reactivity and transformation of biomass and optimising processes.

The day highlighted the progress made in this work, with:

• Spectral data processing and analysis
• Machine learning-based potentials to optimise atomistic simulations for calculating reaction rates
• Prediction models for biomass enzymatic hydrolysis reactivity
• Mechanistic models and hybrid machine learning/mechanistic models
• Development of tools for standardising experimental protocols for data FAIRisation
• Tools for engineering microbial strains for bioproduction
• Reverse engineering of molecular representation
• Bioreactor modelling

A big thank you to all the speakers and participants for the quality of the discussions and the collective dynamic!

For more information on this area of research: click here.