Medical Data Science

With its high-throughput laboratories, Fraunhofer ITMP has expertise in the 4D-data and FAIR handling of research data. Its goal to design the hardware and software technical basis for open research platforms and test environments for research and industry, in which the concepts of digitalized health research and its commercial offers can be researched and tested in practice.

A special focus lies on the investigation of immune-mediated diseases gained during close co-operation with clinicians, which Fraunhofer ITMP can offer for a spectrum of disease models, formulation of therapeutic pathways and bioanalytics. Clinical questions and tests are developed in cooperation with a broad network of industrial partners and are performed according to the standard "Quality by Design".



  • Handling "human" data appropriately
  • Data management and ontologies
  • Static and dynamic analyses, especially of longitudinal data sets
  • Biostatistical support of clinical and preclinical studies
  • Application-oriented algorithms (AI and machine learning)
  • Digital biomarkers and fingerprints

Planning, implementation and test operation of data sovereign infrastructure for health data

The healthcare industry is increasingly opening up to data exchange - not least due to the increased awareness gained during the pandemic - and is testing a variety of digital solutions. The Fraunhofer-Gesellschaft offerings stand for decentralized, distributed, data sovereign solutions, whereby technical solutions are primarily drawn upon from the industrial production environment. The systematic planning of such an infrastructure for our customers and consortia is supported in a practical way by the offer of prototypical construction and operation of such a research platform. Fraunhofer ITMP is represented in many committees and initiatives to enable the exchange of research data: according to German standards (e.g. DSGVO, ethics applications) and European understanding (GAIA-X, European Open Science Cloud and IDSA).

Making health data FAIR and computable

Extracting information and insights from unstructured and "unclean" data requires a data management system that makes use of adapted system alignments and agreements, standardizations and ontology catalogs, and tools and EDA workflows. In our projects we transfer data validation and method validation into validation studies. The moderation of the "questions to the data" has a high value and can be observed especially in AI applications during the project formulation. The definition, distribution and generation of training or validation data sets is a prerequisite for AI developments and can be supported by our test or synthetic cohorts.

Study and cohort analyses

Fraunhofer ITMP supports clinical and preclinical studies and cohort analyses with their expertise in

  • Analysis and regulation of Phase I to IV studies, POC studies
  • Identification of suitable target populations and optimized endpoints,
  • Statistical methods
  • Mathematical modelling
  • Evaluation algorithms and use of AI approaches (in close cooperation within the "Healthcare Analytics in Translational Medicine Partnership" with the Fraunhofer IAIS)
  • Project-specific input and output formats and dashboards

For this purpose, a broad toolbox of commercial and proprietary software tools is used. The competence of Fraunhofer ITMP is based on the integration of data scientists into the clinical routine with a focus on the indication areas of immune-mediated and inflammatory diseases at its Frankfurt location. As part of the “Heathcare Analytics in Translational Medicine Partnership” with Fraunhofer IAIS and its “Healthcare Analytics” business area, large amounts of data are used for analysis using artificial intelligence and machine learning, as well as the early use of these techniques to improve clinical care and knowledge gain.

Epigenetic age test

Cerascreen GmbH is a diagnostics company that offers medical self-tests with its approx. 70 employees. For the Genetic Age Test the epigenetic change of methylation is used as a marker. From a saliva sample a methylation pattern is created in a NGS specialized laboratory, which is interpreted with a "learning" algorithm for the determination of a biological age. Data preparation, modeling and extraction of the relevant patterns and calculation of a biological age value were our development tasks. 

Partner: Cerascreen GmbH

IMI TRANSLOCATION (AMR) InfoCentre: New Drugs 4 Bad Bugs

The TRANSLOCATION project of the Innovative Medicine Initiative aimed to investigate the molecular basis of antibiotic resistances in Gram-negative bacteria and their membranes. Fraunhofer ITMP established and operated a so-called InfoCentre for the exchange of research data between the academic laboratories (connected via electronic laboratory books) and the pharmaceutical partners. The experience gained during the development of the InfoCentre has been incorporated into the AMR accelerator program of the IMI and the tools of the InfoCentre will form the basis for planned data and knowledge management systems to be used by several AMR accelerator projects for the discovery of antibiotics on their way into the clinic.

Partners: include Glaxosmithkline Research and Development LTD, Jacobs University GmbH, Sanofi-Aventis Recherche & Developpement, Astrazeneca AB, Basilea Pharmaceutica International AG, Janssen Pharmaceutica Nv, The Hyve BV, Gritsystems As.

Additional information

Fraunhofer initiatives: Big Data and Artificial Intelligence Alliance, digital twin MED²ICIN, Medical Data Space, COPERIMOplus

Fraunhofer ITMP is a founding member of the Fraunhofer Alliance Big Data and Artificial Intelligence and represents in particular the health topics. The alliance combines the cross-sectoral expertise of more than 30 institutes, especially from the Fraunhofer I&C network, and combines this expertise of the working groups with its domain knowledge and leads information technology expertise into applications. We support companies and institutions in the implementation of big data and AI strategies, develop software and data protection compliant systems and train specialists and executives as "Data Scientists".

Examples of this fruitful cooperation are:

  • Digital patient model as basis for personalized and cost-optimized treatment - MED²ICIN
  • Infrastructure for the secure exchange of health data - Medical Data Space
  • Indication-specific knowledge spaces for AI Application for the generation of risk models - Coronavirus Personalized Risk Models COPERIMOplus
  • Trainings to become a Data Scientist & Big Data specialist - Certified Data Scientist

Auffray C, Balling R, Barroso I, Bencze L, Benson M, Bergeron J, Bernal-Delgado E, Blomberg N, Bock C, Conesa A, Del Signore S, Delogne C, Devilee P, Di Meglio A, Eijkemans M, Flicek P, Graf N, Grimm V, Guchelaar HJ, Guo YK, Gut IG, Hanbury A, Hanif S, Hilgers RD, Honrado Á, Hose DR, Houwing-Duistermaat J, Hubbard T, Janacek SH, Karanikas H, Kievits T, Kohler M, Kremer A, Lanfear J, Lengauer T, Maes E, Meert T, Müller W, Nickel D, Oledzki P, Pedersen B, Petkovic M, Pliakos K, Rattray M, I Màs JR, Schneider R, Sengstag T, Serra-Picamal X, Spek W, Vaas LA, van Batenburg O, Vandelaer M, Varnai P, Villoslada P, Vizcaíno JA, Wubbe JP, Zanetti G.
Making sense of big data in health research: towards an EU action plan.
Genome Med. 2016 Jun 23;8(1):71
(Erratum in: Genome Med. 2016 Nov 7;8(1):118)
doi: 10.1186/s13073-016-0323-y


Bruce Schultz , Andrea Zaliani, Christian Ebeling, Jeanette Reinshagen, Denisa Bojkova, Vanessa Lage-Rupprecht, Reagon Karki, Sören Lukassen, Yojana Gadiya, Neal G. Ravindra, Sayoni Das, Shounak Baksi, Daniel Domingo-Fernández, Manuel Lentzen, Mark Strivens, Tamara Raschka, Jindrich Cinatl, Lauren Nicole DeLong, Phil Gribbon, Gerd Geisslinger3, Sandra Ciesek, David van Dijk, Steve Gardner, Alpha Tom Kodamullil, Holger Fröhlich, Manuel Peitsch, Marc Jacobs, Julia Hoeng, Roland Eils, Carsten Claussen and Martin Hofmann-Apitius.
The COVID-19 PHARMACOME: Rational Selection of Drug Repurposing Candidates from Multimodal Knowledge Harmonization.
Preprint article
doi: 10.1101/2020.09.23.308239