K. Laukens

Semi-Supervised Learning to Boost Cardiotoxicity Prediction by Mining a Large Unlabeled Small Molecule Dataset

This study uses semi-supervised learning on a large unlabeled dataset to improve cardiotoxicity prediction for three ion channels, identifying potential cardiac-active compounds.

Benchmarking of Small Molecule Feature Representations for hERG, Nav1.5, and Cav1.2 Cardiotoxicity Prediction

This paper benchmarks small molecule feature representations for predicting cardiotoxicity against hERG, Nav1.5, and Cav1.2 channels using a new dataset and tool.

Modeling Antigen-Specific T Cell Dynamics Following Hepatitis B Vaccination indicates differences between conventional and regulatory T cell dynamics

This study models T cell dynamics post-Hepatitis B vaccination, revealing differences between conventional and regulatory T cells and their relationship to antibody responses and seropositivity.

Predicting MmpR-based bedaquiline resistance using sequence- and structure-based features

This paper develops a machine learning model to predict bedaquiline resistance using sequence and structural features of Rv0678 variants, achieving moderate performance but not sufficient for clinical use.

Selective whole-genome sequencing of Plasmodium parasites directly from blood samples by Nanopore adaptive sampling

This study demonstrates that adaptive Nanopore sequencing can effectively enrich for Plasmodium DNA in blood samples, achieving sufficient coverage for drug resistance variant detection.

Investigating the Role of Chromatin Remodeler FOXA1 in Ferroptotic Cell Death

This study investigates the role of FOXA1 in ferroptotic cell death in multiple myeloma cells, finding that FOXA1 is upregulated and binds to pericentromeric regions during ferroptosis.

Predicted epitope binding core motifs and common amino acid polymorphisms distinguish protective- from susceptibility-associated HLA alleles in leishmaniasis

Preexisting memory CD4 T cells in nÏave individuals confer robust immunity upon hepatitis B vaccination

The paper shows preexisting memory CD4 T cells in unvaccinated individuals correlate with stronger hepatitis B vaccine responses and predicts immune outcomes using TCR sequencing and machine learning.

On the feasibility of mining CD8+ T-cell receptor patterns underlying immunogenic peptide recognition.

The paper develops a random forest classifier to predict T-cell receptor recognition of peptides and identifies structural CDR3 features associated with immunogenicity.