Projects
A Computational Framework for Prioritization of Disease-causing Mutations KU Leuven
Computational neuropsychology 2.0: A deep learning account of the pattern of deficits in visual recognition after brain damage KU Leuven
Localized brain damage can result in relatively specific problems inmental faculties, including problems with visual recognition. It is still amatter of debate why certain deficits and combinations of deficitsoccur. Recent evolutions in human neuroscience, including our ownwork, have revealed the complexity of the system that supportsvisual recognition, and models such as deep neural networks (DNNs)have offered us a computational ...
Computational models for big data algorithms. University of Antwerp
Computational structural characterisation on the nanoscale Ghent University
In this project, we aim to computationally characterize the structural and thermodynamic properties of new materials on the nanoscale. Therefore, new (semi-)analytical models will be developed for the thermodynamic potential of empty as well as guest-loaded nanoporous materials under realistic conditions as function of the thermodynamic state variables in various ensembles. These models will be parameterized using the output from advanced ...
Bootstrapping operations in language acquisition: a computational psycholinguistic approach. University of Antwerp
Biomolecular crystallography of the volatile ester synthesizing enzymes of S. cerevisiae combined with computational protein redesign of its substrate specificity KU Leuven
During the fermentation process yeast produces a huge variety of volatile esters that contribute to the aroma of food products such as beer and wine. These variety of esters are produced by only 6 different enzymes which exhibit substrate promiscuity. Currently no crystal structures are available of any of these enzymes to analyze the molecular recognition between the enzyme substrates and the binding site. Therefore the first goal will be to ...
Computational investigations of the catalytic mechanism of Staphylococcus aureus transglycosylase: design and chemical synthesis of novel mechanism-based inhibitors. University of Antwerp
Computational Studies of Small Boron Based Clusters KU Leuven
From geometrical features of the global minima, a growth mechanism for each series of the BnX clusters was established. The fundamental featuressuch as chemical bonding, electronic distribution, aromaticity, were probed using the analyses of canonical molecular orbital (CMO) in combination with other indices obtained from the electron localization function(ELF), nuclear independent chemical shift (NICS) etc
Quantitatively, ...
A computational framework for combinatorial design of molecules, genes and cells Ghent University
Recent advances in biotechnology allow to generate and screen an increasing number of variants in proteins, genetic constructs and cells. However, to maximally learn from these experiments, specialized computational methods are required. This PhD project aims to develop a general-purpose toolbox to optimize biotechnological experiments based on state-of-the-art machine learning techniques.