Jeremias Krause

The paper systematically perturbs the human genome to reveal a relational network of genomic dependencies, uncovering 'relons' that reflect functional and evolutionary constraints.

Genolator is a multimodal large language model that combines genomic and structural data with natural language to interpret protein function, outperforming existing models in accuracy.

This paper predicts the pathogenicity of missense variants using graph embeddings of protein structures generated by ESMFold and XGBoost.

The paper analyzes mutational constraint in short open reading frames (sORFs) and their genomic neighbors using the gnomAD 4.0 dataset, identifying a subset of highly constrained sORFs similar to canonical genes.

CNVizard is a lightweight Streamlit app for interactive CNV analysis, visualization, and annotation, compatible with CNVkit and AnnotSV.

This paper develops a deep learning method to predict genetic alterations from histological images across multiple cancer types.