Katharina Baum

The paper uses a multi-omics framework to analyze PAH endothelial cells and identifies kinase-related alterations and potential drug targets.

The paper demonstrates how to select synthetic data for transfer learning in dynamical biological systems, showing performance improvements of up to 92% in mean absolute error.

This paper benchmarks uncertainty-aware models for drug response prediction in cancer cell lines, finding ensemble-based methods better detect distribution shifts while distributional models reduce prediction errors in high-confidence subsets.

The paper develops a computational model to analyze how MYCN-induced expression changes affect energy metabolism in neuroblastoma, revealing Warburg-like flux alterations and potential metabolic bistability.

CombDNF predicts disease-specific drug combinations using network-based features and clinically validated data, outperforming existing methods by 84% in AUPR across four diseases.

This paper evaluates drug response prediction models and finds that deep learning models perform similarly to simple baselines, highlighting issues in current model evaluation practices.

PEPerMINT imputes missing peptide abundance values in proteomics using graph neural networks, outperforming existing methods across multiple datasets and missingness scenarios.

DrDimont predicts differential drug response by integrating multi-omics networks and provides explainable results, outperforming methods based on differential protein expression or PageRank in breast cancer data.

LoopDetect identifies feedback loops in ODE models across MATLAB, Python, and R, supporting parameter ranges and user-defined states.