Andreas Leha

The paper evaluates the stability of feature selection using GCNN+LRP and GCNN+SHAP for gene expression data, comparing them to classical ML methods.

The paper introduces GLRP, a method to explain Graph-CNN decisions in breast cancer metastasis prediction, identifying patient-specific molecular subnetworks that align with clinical knowledge.

The paper characterizes proteome variation across 202 human iPSC lines, identifies 700 pQTLs, and links pQTLs to disease-associated GWAS variants.

The paper examines articulation patterns in adults who stutter (AWS) and adults who do not stutter (ANS) during fluent-sounding utterances, finding no major differences in movement patterns between groups.

The paper uses single-cell RNA-seq of differentiating iPS cells from 125 donors to identify expression quantitative trait loci influencing gene expression during endoderm differentiation.

The paper identifies EGFR signaling in the RIS neuron and its indirect activation via the ALA neuron as mechanisms for sleep induction following cellular stress in C. elegans.

The paper integrates genetic and cell biological data from human iPSC lines to identify intrinsic and extrinsic factors driving inter-individual variability in cell behavior.

This study analyzes 522 human iPSCs to identify genetic sources of phenotypic variation, finding 5-25% of variation in traits like differentiation capacity is due to individual differences.