Anne-Christin Hauschild

Benchmarking Graph Neural Networks for Multi-Omics Cancer Subtyping using Methylation and Gene Expression Profiles

This study benchmarks graph neural networks for cancer subtyping using methylation and gene expression data, finding that ChebNet performs best and simple readout layers improve performance.

BenchXAI: Comprehensive Benchmarking of Post-hoc Explainable AI Methods on Multi-Modal Biomedical Data

BenchXAI benchmarks fifteen post-hoc XAI methods on multi-modal biomedical data, finding some methods perform well across tasks while others struggle.

Ensemble Post-hoc Explainable AI for Multilead ECG: Identifying Disease-Relevant Features in Single-Lead Interpretations

The paper evaluates XAI methods for a 1D-ResNet ECG classifier, finding some methods consistently highlight clinically relevant features while others do not.

Effect of Data Heterogeneity in Clinical MALDI-TOF Mass Spectra Profiles on Direct Antimicrobial Resistance Prediction through Machine Learning

The paper introduces a large mass spectra dataset for antimicrobial resistance prediction, evaluates its performance, and analyzes the impact of data heterogeneity on machine learning models.

On the importance of data transformation for data integration in single-cell RNA sequencing analysis

This study evaluates the impact of data transformation methods on single-cell RNA sequencing integration and shows that optimized preprocessing can reduce batch effects and noise.

CODEX: COunterfactual Deep learning for the in-silico EXploration of cancer cell line perturbations

CODEX models causal effects of perturbations on cancer cell lines using counterfactual reasoning, enabling in-silico exploration of drug combinations and genetic modifications.

Species-Agnostic Transfer Learning for Cross-species Transcriptomics Data Integration without Gene Orthology

This paper develops a species-agnostic transfer learning method for cross-species transcriptomics data integration without gene orthology, showing improved performance in predicting unseen cell types.

Ensemble-GNN: federated ensemble learning with graph neural networks for disease module discovery and classification

Ensemble-GNN enables federated, ensemble-based graph neural networks for disease module discovery using patient-specific PPI networks and omics data.

CLARUS: An Interactive Explainable AI Platform for Manual Counterfactuals in Graph Neural Networks

CLARUS is an interactive explainable AI platform for GNNs that allows clinicians to validate, modify, and retrain models using patient-specific biological networks.

Transfer Learning Compensates Limited Data, Batch-Effects, And Technical Heterogeneity In Single-Cell Sequencing

This paper demonstrates that transfer learning improves analysis of small single-cell datasets by overcoming data scarcity, batch effects, and technical heterogeneity using large-scale bulk data.