Karl Kumbier

The paper introduces epiTree, a pipeline using tree-based models to detect higher-order epistatic interactions in genomic data, validated on UK Biobank data for red hair and MS prediction.

The paper investigates how GTPase and kinase domain mutations in LRRK2 affect endosomal localization and Rab phosphorylation, finding that GTPase-inactivating mutants lead to more LRRK2+ endosomes and higher Rab phosphorylation.

The paper develops a scalable platform combining microscopy and machine learning to subtype ALS patient fibroblasts, identifying a FUS-ALS phenotypic score that correlates with age and treatment response.

This paper introduces signed iRF (s-iRF), a method to refine interaction search in biological systems, identifying stable and predictive feature interactions for enhancer activity and spatial gene expression.

The paper introduces iRF, an algorithm for detecting stable high-order genomic interactions, and demonstrates its application in enhancer activity and alternative splicing.