ITN E-MUSE ESR14: Modeling the effects of ripening conditions on flavour development of semi-hard...

Updated: 2 months ago
Job Type: FullTime
Deadline: 15 Oct 2021

H2020-MSCA-ITN E-MUSE: Complex microbial Ecosystems MUltiScale modElling: mechanistic and data driven approaches integration

The E-MUSE training programme aims at developing young researchers’ skills at the interface between artificial intelligence and life sciences. The challenge is to acquire a shared language bridging life science questions and original modelling approaches. The research programme of the E-MUSE network is to develop innovative modelling methodologies to understand a complex microbial ecosystem and identify levers to control and/or predict its evolution. To deal with biological complexity, biologists, mathematicians, and computer scientists have to work together to develop innovative methodologies. An important complexity of this domain originates from scales and dynamics issues, ranging from local kinetics at the level of the cell to emerging macroscopic properties of the biological system. The development of high throughput techniques provides more and more large datasets, but knowledge is not easily inferred from this huge amount of data and multiscale dynamics are still incompletely characterised and predicted. E-MUSE’s transdisciplinary network gathers academic and industrial partners to equip (15) Early Stage Researchers (ESRs) with scientific, research and transferable skills to become leaders in academic research or industry. They will be at the cutting edge of the modelling methodologies that we apply to model structural and dynamic features of microbial communities, to identify key processes and biomarkers for specific applications.

ESR14 to be recruited by KU Leuven/BioTeC+ will set-up and execute fermentations with cheeses (plant-based or hybrid) and study the effect of various storage/ripening conditions on flavour development and microbial stability. Based on the data obtained, ESR14 will develop a mathematical model to predict condition-dependent characteristics of plant-based cheeses. Correlations between ripening conditions, cheese properties and the final flavour of the product will be investigated using linear and non-linear methods. Based on the identified relations and the data available, a regression model based on machine learning methods will be trained and validated for the prediction of the properties of cheese analogues. 

Expected result:

This project is expected to generate a mathematical in silico model that predicts the impact of ripening conditions of semi hard cheese on flavour formation which will be extended to plant based cheese analogues based on high throughput experimental data (... For more information see

View or Apply

Similar Positions