Jürgen Dönitz

FusionPath predicts gene fusion pathogenicity using protein structural data and contextual embeddings, outperforming existing methods with AUC scores of 0.95 and 0.87.

AstraKit provides a unified KNIME workflow suite for precision medicine analytics, integrating variant interpretation, multi-omics analysis, and drug response modeling.

PanCNV-Explorer integrates and normalizes copy number variation data across 33 cancer types to provide a unified resource for analyzing CNV frequency and functional impact.

AdaGenes processes and filters sequence variant data from WES/WGS efficiently, enabling scalable and interactive analysis for genomics applications.

The paper uses graph convolutional neural networks with layer-wise relevance propagation to analyze gene expression data and identify genes and pathways associated with BRCAness, outperforming traditional methods.

The paper identifies superior target genes and pathways for RNAi-based pest control in the red flour beetle using genome-wide analysis and validates effective targets for oral application in other pests.

The paper uses machine learning to predict essential genes across eukaryotes, achieving high accuracy and validating predictions in Tribolium castaneum.

The paper expands an RNAi screen in Tribolium castaneum to assess gene function diversity between beetles and flies, finding that 50% of functions are shared while others are specific to one species.