Analysis of aleatoric and epistemic uncertainty in machine learning.

Deep learning for regulatory genomics

Doctoral project Gaetan De Waele

Doctoral project Jelle Hustinx

Machine learning methods for single-cell transcriptomics

Novel methods for quantifying aleatoric and epistemic uncertainty in machine learning

Optimising DNA metabarcoding and machine learning for advanced impact assessments in the North Sea: A case study on sand extraction.

A comparative study of conformal prediction methods for valid uncertainty quantification in machine learning.

Doctoral project Azimberdy Besya

Doctoral project Michiel Elewaut

Doctoral project Michiel Stock

Integration of synthetic biology, systems biology and machine learning for the production of chitooligosaccharides in <i>Escherichia coli</i>

Model reduction and parameter estimation for kinetic models of biochemical reaction networks

Identification of adaptive mechanisms leading to reduced antibiotic susceptibility in bacterial biofilms using experimental evolution and machine learning approaches

Nieuwe applicaties in informatiebevraging, beeldverwerking en bio-informatica hebben geleid tot de ontwikkeling van nieuwe machine learning methoden om meerdere targets tegelijkertijd te voorspellen. Recent werden tal van nieuwe methoden ontwikkeld in ver

Novel neural networks for single-cell sequencing technologies

Uncertainty in machine learning

Interlocking synthetic biology, systems biology and artificial intelligence to develop a more efficient metabolic engineering workflow: a highly efficient biotechnological production platform for monoclonal chitooligosaccharides.

Microbial resource management of aquaculture ecosystems to prevent pathogen invasion

New-to-nature Biological Sensors: Unlocking the full potential of biological sensors beyond nature

Past climate extremes and their impact on the terrestrial carbon cycle

Retracing the steps of enzyme evolution: an exploration of ancestral sequence space

Synthetic biology and artificial intelligence, mutual learning to advance together and jointly drive industrial biotechnology - accelerating knowledge discovery and strain engineering

Reciprocal preference relations transitivity properties and graph structures as knowledge instruments for complex learning algorithms.