The use of advanced forms of machine learning promises major advances in research on the human genome. “In particular, so-called deep learning could make it possible not only to ‘read’ our genetic material, as up to now, but to understand the complex biophysical relationships and mechanisms that cause physical properties to emerge from genetic predisposition,” says Harald König, leader of the new project “Deepen Genomics” at ITAS.
New forms of therapy and ethical challenges
The research team, which, besides ITAS, includes the Fraunhofer Institute for Systems and Innovation Research ISI, aims to analyze potential applications that could be developed by combining artificial intelligence (AI) with genome analysis techniques and automated laboratory platforms. For example, there is widespread hope of being able to treat cancer, cardiovascular diseases, or dementia more effectively by tailored “precision medicine”approaches.
At the same time, the project focuses on the many societal and political implications, for example, with regard to issues of research funding or the accessibility of new therapies to patients. The researchers will also examine ethical questions. For example, the trend might be to prevent common diseases such as breast cancer or diabetes by “preventive correction” of risk genes in the germ line of human embryos. “In the extreme case,” explains Harald König, “this could lead to a growing acceptance of ‘improving’ the human genome through non-medical intervention.”
Options for policy makers
Based on their technology assessment, the researchers seek to develop options for research and innovation policy and open up new paths to responsible use of this AI- and genomics-driven technology.
The project “Deepen Genomics – Opportunities and challenges of the convergence of artificial intelligence, human genomics, and genome editing” is part of the Innovation and Technology Analysis (ITA) of the Federal Ministry of Education and Research (BMBF). (20.02.2019)
- Project page on the ITAS website
- KIT press release Technikfolgen: Künstliche Intelligenz in der Medizin (Impacts of technology: Artificial intelligence in medicine)
- Innovations- und Technikanalyse (ITA) (Innovation and Technology Analysis) of the BMBF