VIB-KU Leuven Center for Microbiology

Bioinspired CNNs for border completion in occluded images

Abstract We exploit the mathematical modeling of the border completion problem in the visual cortex to design convolutional neural network (CNN) filters that enhance robustness to image occlusions. We evaluate our CNN architecture, BorderNet, on three occluded datasets–MNIST, Fas...

Five-country analysis of geographic and dietary drivers of gut microbiome composition and genomic variation

Abstract Human diet and lifestyle vary widely across cultures, shaping global diversity in gut microbiome composition and function. However, comparable cross-population studies have been limited by methodological heterogeneity. The Human Diets and Microbiome Initiative (THDMI) in...

Mental disorders, service use, and perceived treatment need among college students after the COVID-19 pandemic and the role of social connection: an epidemiological study

Abstract Background College students affected by mental disorders can be very impaired; yet, treatment rates remain low. The COVID-19 pandemic undoubtably posed strain on students, limiting their social life, which is an important determinant of health. However, recent estimates...

Aggregation framework for continuous digital health measures and application to walking activity data

Abstract No standardized procedures for aggregating continuous digital health measures exist. Using a modified Delphi approach, we developed a framework to standardize the selection of aggregations that provide clinically meaningful, stable values. This was applied to aggregate s...

Simultaneous Network Design With Restricted Link Usage

ABSTRACT Given a digraph with two terminal vertices and as well as a conservative cost function and several not necessarily disjoint color classes on its arc set, our goal is to find a minimum‐cost subset of the arcs such that its intersection with each color class contains an ‐...

Hints of self-medication? Pathogen exposure-dependent foraging decisions of bumblebees

Abstract Self-medication is the selective consumption of compounds that reduce infection and is a widespread form of adaptive plasticity across animals. However, relevant medicinal floral compounds remain poorly tested in bees. Here, we used robotic flowers to test the hypothesis...

Three‐Dimensional Optical and Computational Reconstruction of Colloidal Electrokinetic Flows via Multiplane Imaging and Multiscale Modeling

ABSTRACT Sorting, filtering, and controlling colloidal particles is crucial in many fields, ranging from chemistry to biology and physics. Dielectrophoresis (DEP) enables selective manipulation of colloids by non‐uniform AC electric fields, yet the associated three‐dimensional na...

High-throughput protocol for assessing antibiotic resistance using agar dilution, acoustic liquid handling, and semi-automated image analysis

Conventional minimum inhibitory concentration (MIC) assays used to determine the antibiotic susceptibility of microorganisms are inherently low-throughput and labor intensive. Here, we present a high-throughput agar dilution MIC assay to efficiently assess resistance profiles acr...

Warped Geometries of Segre–Veronese Manifolds

Abstract. Segre–Veronese manifolds are smooth submanifolds of tensors comprising the partially symmetric rank-1 tensors. We investigate a one-parameter family of warped geometries of Segre–Veronese manifolds which includes the standard Euclidean geometry. This parameter controls...

The sweet spot in protein design—Where deep learning meets first principles

This Perspective explores recent methods and prospective ideas for developing hybrid AI-physics-based pipelines for protein and antibody de novo design. We argue that the highest-confidence candidates emerge where deep learning and first-principles models agree, a "sweet spot" th...