Computational Health

We develop novel computational tools powered by AI to accelerate discovery and translation. We apply cutting-edge computational methods to promote personalised health. Collaboratively, we develop predictive algorithms as well as mechanistic models to analyse molecular, imaging, and clinical data of human health and disease. We thus help to create innovative diagnostics and novel treatments for environmentally triggered diseases.

Colorful abstract image with organic shape

genetic engineering and dna modification icon

We develop robust methods for analyzing big data to address key biomedical challenges and consolidate analytical approaches using innovative digital methods. In addition, we develop novel statistical methods for trans- ethnic meta-analysis, testing for pleiotropy, rare variant burden, testing, and polygenic risk score construction.

abstract background technology concept. Artificial intelligence technology. illustration vector design

We develop and translate AI technologies for biomedical problems by constructing deep-learning methods and combining them with more mechanistic modeling approaches. In addition, we steer the computational aspects of developing single-cell atlases in healthy and disease state to build AI-driven analytics platforms for multimodal data, in particular from genomics and diverse imaging modalities.

We develop novel computational methods for multiomic data integration of epigenomic, transcriptomic, proteomic and genetic data and advanced phenotypic/in vivo observations. In addition, we design novel approaches for efficient data combination across omics levels, maximizing the information yield across the multidimensional space of datar from genomics and diverse imaging modalities.

A Journey into the Secrets of Human Cells

What the Human Cell Atlas (HCA) will tell us about ourselves and how scientists at Helmholtz Munich are facilitating this revolutionizing global endeavor.

See more details

Illustration des menschlichen Körpers, Energie betont. Generative künstliche Intelligenz. AI.

Using AI in Medicine to Combat Diseases

Artificial Intelligence (AI) is becoming increasingly crucial in medical research, and Helmholtz Munich is one of the world's leading institutions in this field. It can detect tumors as effectively as severe eye diseases.

Show more details

Shot of corridor in working data center filled with rack servers and supercomputers AI background

Big Data at Your Bedside

Analysis of genes can help in detecting diseases at an early stage as well as in determining new drug targets for therapy. Thanks to extremely powerful data processing, the field holds great promise for advancement. Helmholtz Munich is particularly at the cutting edge in the use of these new methods.

Show more details

In the future, blood samples from patients can be evaluated not only by specialists, but also by artificial intelligence. A team from Helmholtz Munich is laying the foundations for this.

Show more details

Leukemia cells in peripheral blood smear, Wright stain

How AI is Revolutionizing Medicine

Computer systems can already independently analyze health data, learn from it and even derive therapy recommendations. Which opportunities this means for patients and what research needs to apply artificial intelligence in practice.

Doctor using ultrasound equipment screening of pregnant woman.

A new interdisciplinary team at Helmholtz Munich aims to bridge one of healthcare AI's longstanding challenges: translating promising algorithms into tools that perform reliably in clinical practice. The M1 Clinical AI Consultants, based at the…

Dr. Steffen Schneider of Helmholtz Munich and KI macht Schule gGmbH has been admitted as a new member of the Young Academy. Working at the interface of artificial intelligence, neuroscience, and statistical modelling, Schneider joins the Academy's…

Researchers at Helmholtz Munich, together with international partners, have developed an ultrathin sensor patch capable of non-invasively monitoring key health parameters in preterm infants. The silk-based patch measures temperature, pH, sodium, and…

Prof. Fabian Theis has been awarded the Akademiepreis of the Berlin-Brandenburg Academy of Sciences and Humanities. The Academy honors his pioneering work in computational biomedicine and the development of novel methods for biomedical data analysis.…

Helmholtz Munich and Vector Institute Strengthen International AI Research Collaboration

Helmholtz Munich and the Vector Institute have signed a Memorandum of Understanding (MOU) to strengthen international collaboration in artificial intelligence (AI) and machine learning. The agreement establishes a formal framework for joint research,…

HAICON 2026: Workshops & Tutorials Day at Helmholtz Munich

From 8 to 11 June 2026, HAICON 2026 will bring together researchers, developers and practitioners from academia and industry in Munich to discuss the latest developments and applications of artificial intelligence. Organized by Helmholtz AI, the…

22.09.2026

Host: Iva Pritisanac
Title: TBD
Time: TBD
Location: Hybrid

22.10.2026

Host: Iva Pritisanac
Title: TBD
Time: 16.00 (CEST)
Location: Hybrid

A visualization of a machine learning model deployment with predictions being made on new data. The environment, Generative AI

Follow the link to find the latest contributions from Computational Health Center researchers at international AI conferences:

Postdoctoral Health AI Fellows Program

The newly established Postdoctoral Health AI Fellows (HAIF) Program is dedicated to fostering independent, high-impact research in computational biomedicine and health-related AI. Our mission is to empower early-career postdoctoral scientists from computational, mathematical, engineering, and physical science disciplines by granting them early scientific independence to boldly address key challenges in computational biomedicine.

Recent advances in computation have transformed our understanding of molecular processes and their effects on health and disease. Breakthroughs in modeling, AI, and large-scale data analysis have reshaped biomedicine, enabling researchers to extract meaningful insights from increasingly complex biological datasets. As high-throughput technologies generate vast volumes of data, new challenges emerge in scale, management, analysis, and interpretation. Yet, these same developments open unprecedented opportunities to uncover complex biological mechanisms, predict system behavior, and understand pathophysiological processes.

Unlike traditional postdoctoral positions, HAIF fellows join the Computational Health Center (CHC) at Helmholtz Munich as independent early-career researchers with greater autonomy. Each fellow has access to mentoring by two senior researchers, either two CHC Principal Investigators, or one Principal Investigator and one external expert from university, industry or a start-up. With this support structure, fellows have the freedom to develop and apply comprehensive computational strategies to tackle challenges in health research.

By leveraging experimental, computational, and statistical approaches, the HAIF Program empowers fellows to explore new scientific frontiers that integrate data-driven and experimental methodologies. Working closely with experimental partners in Munich and beyond, fellows bring fresh perspectives to significant biological and biomedical challenges—stimulating innovation and driving the development of transformative solutions.

The call for applications will open in mid-December!

Apply here

Guedes, J. ; Woldmar, N. ; Baltás, E. ; Kriston, A. ; Migh, E. ; Kovács, F. ; Oskolas, H. ; Marko-Varga, M. ; Appelqvist, R. ; Wieslander, E. ; Szasz, A.M. ; Veréb, Z. ; Gyulai, R. ; Németh, I.B. ; Malm, J. ; Horvath, P. ; Gil, J. ; Marko-Varga, G.

AI-based digital pathology and spatial proteomics enable precision oncology: A case report of recurrent melanoma in a young patient.

Kiechle, J. ; Fischer, S.M. ; Lang, D. ; Bercea, C.-I. ; Nyflot, M.J. ; Felsner, L. ; Schnabel, J.A. ; Peeken, J.C.

TomoGraphView: 3D medical image classification with omnidirectional slice representations and graph neural networks.

Li, Q. ; Nambu, R. ; Yaqiang, H. ; Shen, X. ; Argmann, C. ; Guan, R. ; Janssen, E. ; Le Voyer, T. ; Warner, N. ; Yu, D.D. ; Guo, J. ; Long, K. ; Ouahed, J. ; Field, M. ; Collen, L. ; Bibus, J. ; Illig, D. ; Rohlfs, M. ; Yu, Z. ; Yang, S. ; Li, W. ; Platt, C.D. ; Comella, P.H. ; Jordan, D. ; Suárez-Fariñas, M. ; Alosaimi, M.F. ; Peters, L.A. ; Rosain, J. ; Fieschi, C. ; Puel, A. ; Hsieh, E.W.Y. ; Naito, T. ; Zeng, Z. ; Rodríguez-Belvís, M.V. ; Palomino, L. ; Küster, P. ; Li, D. ; Klein, C. ; Snapper, S.B. ; Casanova, J.L. ; Geha, R. ; Hoffenberg, E. ; McGovern, D.P.B. ; Schadt, E. ; Kotlarz, D.M. ; Li, D. ; Muise, A.M.

BIRC3 (Encoding cIAP2) variants result in dysregulated RIPK1 signaling leading to increased epithelial cell death and are associated with monogenic crohn’s disease.

Klose, D. ; Milaneschi, Y. ; Han, L.K.M. ; van der Wee, N.J.A. ; Arnold, M. ; Brydges, C.R. ; Dehkordi, S.M. ; Kastenmüller, G. ; Daouk, R.K. ; Penninx, B.W.J.H.

Determinants of the plasma metabolome: Cross-sectional and longitudinal associations over six years in the NESDA cohort.

Moyon, L. ; Marsico, A.

Machine learning and language models for RNA structure prediction: Progress and perspectives.

Boggan, R.M. ; Michalettou, T. ; Ng, Y.S. ; Franklin, I.G. ; Cortés, L.T. ; Alston, C.L. ; Blakely, E.L. ; Büchner, B. ; Bugiardini, E. ; Colclough, K. ; Feeney, C. ; Hanna, M.G. ; Hattersley, A.T. ; Klopstock, T. ; Kornblum, C. ; Mancuso, M. ; Patel, K.A. ; Pitceathly, R.D.S. ; Pizzamiglio, C. ; Prokisch, H. ; Schäfer, J. ; Schaefer, A.M. ; Shepherd, M. ; Thaele, A. ; Thomas, R.H. ; Turnbull, D.M. ; Woodward, C.E. ; McFarland, R. ; Taylor, R.W. ; Cordell, H.J. ; Pickett, S.J.

Identification of nuclear genetic loci linked to clinical features of the m.3243A>G mitochondrial DNA variant.

Schmiegel, S. ; Marchi, H. ; Röchter, M.H. ; Rudwaleit, M. ; Fuchs, C.

Single-label and multi-label classification for disease recognition with special consideration of comorbidities.

Sens, D. ; Shilova, L. ; Dalca, A.V. ; Schnabel, J.A. ; Casale, F.P.

GEMCONT:Genetics-based Multimodal Contrastive Learning Enhances Phenotypic embeddings and Boosts Genetic Discovery.

Foundation Models in Health Research

Foundation models are advanced artificial intelligence systems designed to process vast amounts of data and to complete a range of downstream tasks. Being trained on extensive datasets these models are now revolutionizing biomedical research, accelerating discovery and translation. At the Computational Health Center we and our partners leverage these cutting-edge models to decode the complexities of human biology, aiming to pave the way for innovative treatments and a deeper understanding of health and disease.

View the page