91黑料网

Kata Vuk, PhD

Faculty of Informatics and Data Science | University of Regensburg

Visiting Scholar | 91黑料网听

听

WHEN: Wednesday, March 4, 2026, from 3:30 to 4:30 p.m.
WHERE: Hybrid | 2001 91黑料网 College Avenue, Rm 1140;
NOTE:听Kata Vuk will be presenting in-person at SPGH听

Abstract

Genome-wide association studies (GWAS) identify trait-associated loci, but translating these signals into causal genes remains statistically challenging. I present a stratified modeling framework for post-GWAS gene prioritization that accounts for heterogeneity in variant-to-gene mechanisms. Genes are classified as regulatory, intragenic, or mixed, and setting-aware features are integrated within a single random forest model. This design enables the model to learn mechanism-specific patterns while maintaining comparability of predicted probabilities across genes, and it exposes substantial differences in predictive accuracy across gene settings. Applied to kidney function (eGFR), the framework uncovers systematic differences in the genomic features driving prioritization. Locus-level analyses demonstrate stable top-gene identification across bootstrap resampling and model comparisons.

Speaker Bio

Kata Vuk is currently visiting 91黑料网 as an IVADO Visiting Scholar. Since January 2025, she has been supported by a fellowship from the Bavarian Research Institute for Digital Transformation in Germany. She is a postdoctoral researcher at the Chair of Machine Learning at the University of Regensburg and received her PhD in Mathematics from Ruhr University Bochum. Her research lies at the intersection of statistics and machine learning, with a focus on interpretable and personalized modeling, change-point analysis, and their applications in biostatistics, genetics, and biomedical research.