/A Hybrid Modeling Framework for Biochemical Reaction Kinetics Using AI and Data-Driven Approaches

A Hybrid Modeling Framework for Biochemical Reaction Kinetics Using AI and Data-Driven Approaches

Antwerpen | More than two weeks ago

A Versatile AI-Driven Framework for Predicting Reaction Dynamics in Biochemical Processes

Biochemical reactions are fundamental to numerous biological processes and applications, from metabolic pathways to drug interactions and gene regulation. However, accurately modeling these reactions remains a challenge due to their complexity, nonlinearity, and stochastic nature. This research project aims to create a baseline hybrid modeling framework that integrates traditional reaction kinetics with advanced AI and data-driven approaches to provide a flexible and robust tool for understanding and predicting biochemical dynamics.

 

The proposed framework will combine classical kinetic models with machine learning techniques, allowing for the incorporation of diverse data sources, such as experimental measurements and simulations. By developing a set of hybrid base models, we will establish a foundation that captures the core principles of reaction kinetics while remaining adaptable to different biochemical contexts.  These base models will be designed to be extensible and modular, providing a flexible platform that can be tailored to various specific applications in biomanufacturing.

 

The development of this hybrid approach will provide a versatile tool for researchers and practitioners in fields like biopharmaceutical development and systems biology. It will enable them to model, predict, and manipulate biochemical reactions with greater precision and flexibility. Ultimately, this research aims to create a general-purpose modeling platform that can accelerate innovation across the life sciences by bridging traditional reaction kinetics with cutting-edge AI techniques.



Required background: Master’s degree in Computer Science, Informatics, Physics, (biochemical) Engineering or Electronics, with knowledge about artificial intelligence and machine learning

Type of work: 70% modeling/simulation, 20% experimental, 10% literature

Supervisor: Siegfried Mercelis

Co-supervisor: Catherine Middag

Daily advisor: Furkan Elmaz

The reference code for this position is 2025-119. Mention this reference code on your application form.

Who we are
Accept marketing-cookies to view this content.
Cookie settings
imec inside out
Accept marketing-cookies to view this content.
Cookie settings

Send this job to your email