ELLIS Life Heidelberg: a bridge between artificial intelligence and the life sciences
The great potential of artificial intelligence (AI) and machine learning for the life sciences – from basic research in biology to medical applications – has largely been neglected to date. A new research unit aims to support AI research in the life sciences and to forge international links with the activities in Heidelberg. The unit is part of the European Laboratory for Learning and Intelligent Systems (ELLIS). ELLIS Life Heidelberg was founded by researchers from the German Cancer Research Center, the European Molecular Biology Laboratory, and the University of Heidelberg and will initially be funded by the founding institutions for five years.
Technological progress is allowing increasingly detailed and ever larger datasets to be created in the life sciences and medicine. Yet generating new knowledge from these data often remains an unsolved problem for scientists: Data from molecular diagnostics are heterogeneous in nature, and the medically important signals are often difficult to discover. Very subtle points are often decisive in assessing medical images, and there is frequently a lack of structural datasets with complete medical notes that are necessary to train the algorithms. In addition, the data privacy of patients and study participants needs to be protected when these new analytical methods are used too.
The aim of the new ELLIS Unit in Heidelberg is to harness the huge potential of artificial intelligence (AI) and machine learning in medicine and the life sciences.
The unit is part of ELLIS, the European Laboratory for Learning and Intelligent Systems, an international association of researchers structured along the lines of the European Molecular Biology Laboratory (EMBL) that aims to promote research in the field of AI in Europe. Leading scientists working on basic research in AI, the AI fields of application, and in industry cooperate closely at the ELLIS sites, of which there are now 28 in 14 different countries. The founding idea behind ELLIS is that Europe should help shape how machine learning and AI change the world. To do so, an international research structure needs to be created that can help reinforce the competitiveness of AI research in Europe.
As Theresia Bauer, Science Minister of Baden-Württemberg, remarked, "AI and machine learning are key technologies and drivers of innovation for our future. As a center of research, Baden-Württemberg offers huge potential in this area, including the research institutions in Heidelberg, which are leaders in the development of AI applications in the field of medicine and the life sciences. I am delighted and proud that, with the addition of Heidelberg, Baden-Württemberg now has three ELLIS units working at the groundbreaking interface between AI and the life sciences. This will benefit 'AI made in BW' as a whole."
ELLIS Life Heidelberg focuses on issues in the life sciences – ranging from deciphering basic principles of life to health and cancer research. The unit will develop new AI methods, but also act as an innovation center to link technologies with data from the life sciences and make them available to the research community.
Priority areas include methods to overcome the heterogeneous nature of 'omics' data from molecular analyses and the interpretation of data from medical imaging. Plans have also been made to develop methods to implement ethical and data protection guidelines. The unit's tasks also include developing innovative modeling strategies that guarantee the necessary transparency and responsibilities for decision-making in medical applications.
The ELLIS Unit pools the expertise of scientists from three leading research institutions in Heidelberg: the European Molecular Biology Laboratory (EMBL), the University of Heidelberg, and the German Cancer Research Center (DKFZ). The founding members already play a key role in the ELLIS network, particularly in the ELLIS Health Program, which will now be linked with the activities in Heidelberg.
"In Heidelberg, we want to demonstrate the huge potential of AI and machine learning to address the great challenges of biomedicine, oncology, and the health sciences as a whole more effectively," explained Oliver Stegle from DKFZ, co-director and coordinator of the new unit.
In addition to the research activities already planned, an interdisciplinary training program for young scientists is to be set up in Heidelberg. This new initiative is open to joint projects with industry and is already being supported by an existing network of industry partners.
"ELLIS Heidelberg is designed to be a bridge linking the life sciences with the world of AI," explained Anna Kreshuk from EMBL, co-director of the ELLIS Unit. "It offers a unique opportunity to pool the outstanding research in the field of machine learning in Heidelberg and to help solve important medical problems," added Carsten Rother from the University of Heidelberg, the third co-director of the new unit.
With more than 3,000 employees, the German Cancer Research Center (Deutsches Krebsforschungszentrum, DKFZ) is Germany’s largest biomedical research institute. DKFZ scientists identify cancer risk factors, investigate how cancer progresses and develop new cancer prevention strategies. They are also developing new methods to diagnose tumors more precisely and treat cancer patients more successfully. The DKFZ's Cancer Information Service (KID) provides patients, interested citizens and experts with individual answers to questions relating to cancer.
To transfer promising approaches from cancer research to the clinic and thus improve the prognosis of cancer patients, the DKFZ cooperates with excellent research institutions and university hospitals throughout Germany:
The DKFZ is 90 percent financed by the Federal Ministry of Education and Research and 10 percent by the state of Baden-Württemberg. The DKFZ is a member of the Helmholtz Association of German Research Centers.
