Author

Michaela Unger

Else Kröner Fresenius Center for Digital HealthORCID 0000-0001-5811-0200Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Bioinformatics· 2

Signature Assays, Organisms & Methods

Click to filter · or open tag

Organism:human· 2 Research Focus:benchmarking· 1 Approach:deep learning· 1 Research Focus:differential expression· 1 Approach:diffusion model· 1 Assay:imaging· 1 Approach:machine learning (classical)· 1 Research Focus:variant calling· 1

Frequent Co-Authors

Jakob Nikolas KatheriD· 2 shared Laura ŽigutytėiD· 2 shared Tim LenziD· 2 shared Zunamys Itzell CarreroiD· 2 shared Alexander T. PearsoniD· 1 shared Andreas MöckiD· 1 shared Asier Rabasco MeneghettiiD· 1 shared Carolin Victoria SchneideriD· 1 shared

Activity by Year

2025-2026 · peak 1/yr

Co-Author Collaboration Network

10 top collaborators · 37 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

2 shared papersBioinformatics

Jakob Nikolas KatherORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

BioinformaticsCancer ResearchPeer-reviewedJun 17, 2026

Counterfactual Diffusion Models for Interpretable Explanations of Artificial Intelligence Models in Pathology

Laura Žigutytė, Tim Lenz, Tianyu Han…·Jakob Nikolas Kather

MoPaDi generates counterfactual explanations for histopathology images to reveal morphological features driving classifier predictions, improving interpretability in digital pathology.

DOI 10.1158/0008-5472.can-25-5645

humanimaging

𝕏 PostBluesky

BioinformaticsbioRxivPreprintJan 6, 2025

End-to-end deep learning versus machine learning for biomarker discovery in cancer genomes

Michaela Unger, Chiara Maria Lavinia Loeffler, Julien Vibert…·Jakob Nikolas Kather

This study compares deep learning and machine learning for biomarker prediction in cancer genomes, finding DL performs better in cross-assay and data-sparse settings.

3 citations

humanwhole-exome sequencing

𝕏 PostBluesky