AI-based Prediction of Protease Cleavage and Kinetics in Protein Digestion

Project Overview

This PhD project aims to develop AI models to predict protease cleavage sites and peptide release kinetics in protein digestion, combining state-of-the-art analytical chemistry techniques such as quantitative LC-MS with data-driven kinetic modelling. Understanding protein hydrolysis is crucial in nutritional science and food technology, yet remains difficult to predict.

The project will generate a comprehensive experimental dataset, determining kinetic parameters from peptide concentration time courses using quantitative UHPLC-PDA-ESI-MS. Special focus will be on the interplay of multiple digestive proteases and structural changes in dietary proteins influencing enzymatic action. Amino acid sequences surrounding cleavage sites will be analyzed to identify patterns that inform predictive models, starting from the protein's amino acid sequence.

What You Will Do

• Take ownership of the project and conduct research including state-of-the-art LC-MS analyses.
• Develop kinetic models to describe peptide release kinetics.
• Publish findings in peer-reviewed journals and present at scientific conferences.
• Supervise BSc and MSc students and contribute to educational activities.
• Complete PhD program requirements including training and supervision plans.

Expected Outcomes

A predictive tool for peptide formation and concentrations during digestion will be established. This will yield novel insights into protease specificity and digestion kinetics, facilitating the rational design of specialized protein hydrolysates tailored for infants, elderly, and athletes.

Why This Matters

Improved understanding of protein digestion mechanisms and peptide dynamics will enhance utilization of dietary proteins' nutritional properties. This has direct implications for designing foods that better meet the needs of vulnerable populations and athletes, addressing current limitations in nutritional science.