Our AI and data science methods integrate data from genomics, imaging, and clinical records to uncover disease mechanisms, enhance diagnostics, and inform personalized therapies.
This work is driven by interdisciplinary teams of researchers from academia, industry and university hospitals to ensure that new methods and insights are robust and widely applicable.
Our goal is to make these models both biologically meaningful and clinically useful. Achieving this requires close collaboration between computational and experimental teams, supported by shared technology platforms and interdisciplinary expertise. The result: insights that drive new diagnostics, therapies and precision medicine.
We develop machine learning models to infer gene regulatory networks and understand how regulatory information is encoded in the epigenome and non-coding genome.
Leveraging high-resolution single-cell multi-omics, we aim to interpret patient genomes in diverse contexts – including cancer cohorts, patient-derived organoids, and in-vitro systems that model disease-specific molecular phenotypes.
We integrate genomic, proteomic, and phenotypic data into mechanistic, multiscale models to uncover disease mechanisms across molecular, cellular, and organ levels.
A key strength lies in linking heterogeneous data types to biological function through mathematically grounded approaches.
We develop algorithms for processing, visualizing, and analyzing large-scale imaging data – enabling integrative, data-driven classification to improve diagnostics and personalized therapies.
Our disease-modeling platforms range from in vivo and live imaging to whole-organism and single-molecule resolution.
We integrate large-scale clinical and epidemiological datasets – including cohort studies and health records – to connect phenotypic variation with disease mechanisms.
By harmonizing data across patients and study centers, we enable bidirectional translation between healthy populations and disease cohorts, and facilitate the analysis of treatment responses.
Data Science Platforms at the Max Delbrück Center provide cutting-edge technologies, instrumentation, and methodologies – supporting both established workflows and emerging applications.
Our platforms help drive collaborative research and enable us to develop new computational and experimental approaches.
Our open-source and in-house software tools power data processing, analyses, and visualization across diverse biomedical applications.
Access our tools in the research software directory of Helmholtz
We train the next generation of data scientists through active participation in interdisciplinary PhD programs – leading HEIBRiDS, iNAMES, and Regulatory Genome, and partnering in CompCancer and other research schools.
Our Data Science group leaders are active in the Max Delbrück Center Graduate Program, which hosts PhD recruitment rounds twice a year.
/phd
Max Delbrück Center faculty contribute to MSc programs offered by our partner universities.
In the bi-weekly HEIBRiDS Lecture Series, data science experts from the academia and industry are invited to present their work.
January 28, 2022
