Carsten Marr
Director Institute of AI for Health“Our interdisciplinary collaborations between computational researchers, biomedical scientists, and clinical experts drive progress and innovation in health AI.”
“Our interdisciplinary teams of computational researches and clinical experts are key for progress in health AI”
Research Focus
My lab advances the diagnosis, treatment and understanding of severe blood disorders. We do this by developing custom machine learning algorithms to classify individual cells and patients. Single cell-based big data analysis helps us to identify potential drug targets. Using our prior knowledge of haematopoiesis, the production of blood cells, we fit time-resolved data with mechanistic mathematical models. Combining the power of AI with our knowledge of biomedical systems is one of our current research challenges.
Gottschlich, Adrian, Moritz Thomas, Ruth Grünmeier, …, Carsten Marr and Sebatian Kobold. 2023 Single-Cell Transcriptomic Atlas-Guided Development of CAR-T Cells for the Treatment of Acute Myeloid Leukemia. Nature Biotechnology
Boushehri, Sayedali S., Katharina Essig, ..., Elke Glasmacher, Carsten Marr, and Fabian Schmich. 2023 Explainable machine learning for profiling the immunological synapse and functional characterization of therapeutic antibodies. Nature Communications
Hehr, Matthias, ..., Carsten Marr. 2023 Explainable AI identifies diagnostic cells of genetic AML subtypes. PLOS Digital Health
Matek, Christian, Sebastian Krappe, Christian Münzenmayer, Torsten Haferlach, and Carsten Marr. 2021 Highly Accurate Differentiation of Bone Marrow Cell Morphologies Using Deep Neural Networks on a Large Image Data Set. Blood
Matek, Christian, Simone Schwarz, Karsten Spiekermann, and Carsten Marr. 2019 Human-level recognition of blast cells in acute myeloid leukaemia with convolutional neural networks. Nature Machine Intelligence
Strasser, Michael K., Philipp S. Hoppe, Dirk Loeffler, Konstantinos D. Kokkaliaris, Timm Schroeder, Fabian J. Theis, and Carsten Marr. 2018 Lineage Marker Synchrony in Hematopoietic Genealogies Refutes the PU.1/GATA1 Toggle Switch Paradigm. Nature Communications
Buggenthin, Felix, Florian Buettner, ..., Timm Schroeder, Fabian J Theis, and Carsten Marr. 2017 Prospective identification of hematopoietic lineage choice by deep learning. Nature Methods
For the complete list of publications, see Google Scholar
Skills & Expertise
Machine learningMechanistic modelling
Single cell profilingComputational hematopathology
Professional Background
Director of the Institute of AI for Health
Deputy director at the Institute of Computational Biology
Helmholtz Munich / Modeling stem cell kinetics
Honors and Awards
2024: Eugen Münch Prize for Innovative Healthcare from the Röhn Foundation
2024: Visiting Professor at Feinberg School of Medicine - Northwestern University, USA
2023: ERC Proof of Concept Grant
2019: ERC Consolidator Grant
2017: Erwin-Schrödinger Prize
2017: CSB2 Prize in Systems Biology