The AI4B.io Lab centers its research on developing a deep understanding of how novel AI technology can strengthen the effectiveness and efficiency of research and business processes in the biotech industry.
To drive these advancements, the lab leverages key technical AI components, focusing primarily on:
With a commitment to multidisciplinary research, specifically prioritizing explainable AI.
The AI4B.io Lab is dedicated to bridging the gap between advanced artificial intelligence research and industrial biotechnology applications.
The lab’s mission and vision are to build the fundamental knowledge base, scientific theories, and AI tools necessary to develop biobased products and optimize large-scale biobased production technologies.
The impact of the lab lies in accelerating a comprehensive digital transformation across the biotech industry, achieved by validating AI breakthroughs directly in complex industrial settings alongside industry partners, fostering young scientific entrepreneurship, and embedding explainable AI frameworks to build trust across the bioscience ecosystem.
Digital twin and smart plant scheduling – Developing an AI-based framework/advisory tool for optimal batch scheduling to maximize plant output of an enzyme production line, and balance product performance and quality against operational costs.
Digital twin for large-scale fermentation – Evaluating how AI methods can be applied to develop an accurate real-time simulation of fermentation performance indicators in response to dynamic process inputs for industrial scale fed-batch operated fermentation units of 50-500 m3.
Digital twin of lab automation processes and self-learning platforms – Developing autonomous systems that evaluate and develop ‘self-learning’ experimental design algorithms, combine data-driven approaches with mechanistic modelling and other things.
Machine learning for genome-phenotype engineering – Evaluating and implementing so-called ‘representation learning’ methods on multi-omics data from strain development projects.
Machine learning for iterative metabolic engineering – Determining how AI/ML methods can support efficient exploration of a large solution space for (iterative) strain improvement.
Hi-OSCAR: Hierarchical Open-set Classifier for Human Activity Recognition Journal Article
In: 2025.
Jaxkineticmodel: Neural ordinary differential equations inspired parameterization of kinetic models Journal Article
In: PLOS Computational Biology, vol. 21, no. 7, pp. e1012733, 2025.
Learning From Scenarios for Stochastic Repairable Scheduling Proceedings Article
In: International Conference on Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR), Springer, 2024.
Simulated Design–Build–Test–Learn Cycles for Consistent Comparison of Machine Learning Methods in Metabolic Engineering Journal Article
In: ACS Synthetic Biology, vol. 12, no. 9, pp. 2622–2633, 2023.
Rolling Horizon Simulation Optimization For A Multi-Objective Biomanufacturing Scheduling Journal Article
In: 2023.
Unveiling microbial biomarkers of ruminant methane emission through machine learning Journal Article
In: Frontiers in Microbiology, vol. 14, pp. 1308363, 2023.
ERnet: a tool for the semantic segmentation and quantitative analysis of endoplasmic reticulum topology Journal Article
In: Nature Methods, vol. 20, no. 4, pp. 572–579, 2023.
An analysis of organism lifelines in an industrial bioreactor using Lattice-Boltzmann CFD Journal Article
In: Chemical Engineering Science, vol. 259, pp. 117793, 2022.
Analysis of Measure-Valued Derivatives in a Reinforcement Learning Actor-Critic Framework Proceedings Article
In: Association for Computing Machinery, 2022.
Dynamic Scenario Reduction for Simulation Based Optimization Under Uncertainty Journal Article
In: 2022.
Autonomous experimentation systems for materials development: A community perspective Journal Article
In: Matter, vol. 4, no. 8, pp. 2702–2726, 2021.
Next-Generation Experimentation with Self-Driving Laboratories Journal Article
In: Trends in Chemistry, vol. 1, no. 3, pp. 282–295, 2019.
From industrial fermentor to CFD-guided downscaling: what have we learned? Journal Article
In: Biochemical Engineering Journal, 2018.
In: Chemical Engineering Science, vol. 175, pp. 358–368, 2018.
Delft University of Technology (TU Delft) is the largest public technical university in the Netherlands, providing academic research expertise, faculty supervision, and educational resources across computer science and biotechnology.
DSM-firmenich is a global science-based company specializing in health, nutrition, and biosciences that provides industrial use cases, co-supervision, and real-world evaluation settings for the lab’s AI solutions.
