Artificial intelligence to help tumour immunology

The success of cancer therapy depends not only on the type of tumour, but also on the surrounding tissue. Tumours influence it to their advantage, promote the growth of blood vessels or kill migrating immune cells. The aim of researchers at the ImmunoSensation2 Cluster of Excellence and Hausdorff Center for Mathematics (HCM) led by Prof. Kevin Thurley at the University of Bonn is to develop methods that can be used to predict the nature of the tumour microenvironment created in this way. The Federal Ministry of Education and Research (BMBF) is funding the „InterpretTME“ project with around 800,000 euros over the next three years.

Cancer therapy has been revolutionised in the past decade by the new methods of immunotherapy. Here, a tumour is not attacked directly, but the existing cells of the immune system are used. These are actually capable of recognising and eliminating malignant tumour cells. However, many tumours have the ability to prevent or severely restrict an effective immune response. The aim of immunotherapy is to enable the misdirected immune system to recognise and destroy the tumour cells again.

Cancer immunotherapy is not promising for all patients. It has been shown that resistance to cancer immunotherapies is often linked to the composition of the tumour microenvironment (TME). In oncology, the properties of the TME are already being used as biomarkers to predict the development of cancer. Imaging techniques are used to map the type and position of the individual cells within the TME. Patterns of gigantic cell clusters are created, which in their entirety and structure influence the success or failure of cancer immunotherapy. How exactly this works, however, remains elusive.

says Prof. Kevin Thurley from the Institute of Cancer Research. Kevin Thurley from the Institute of Experimental Oncology, who heads the working group „Systems Biology of Inflammation“ of the interdisciplinary research unit „Mathematics and Life Sciences“ of the Clusters of Excellence ImmunoSensation2 and Hausdorff Centre for Mathematics (HCM). „Using a combination of mathematical modelling and artificial intelligence methods, we will investigate these phenomena in detail, in direct collaboration with experimental and clinical research at the UKB.”

Artificial intelligence for analysing tissues

Methods for analysing images based on artificial intelligence (AI) are already well advanced. The situation is different when it comes to simulating complex systems - given the large number of interacting cells within a tissue. Due to the large number of cell types involved, the different cellular processes taking place there and the complex tissue architecture, such a simulation is computationally intensive. However, it can help to simulate the TME of a tumour and thus draw conclusions about tumour development.

Information on immunotherapy through machine learning

The overarching goal of „InterpretTME“ is the development of interpretable machine learning (ML) methods for the investigation of complex cell systems. These will be used to gain insights into the nature of TMEs. “Machine learning methods are already used in many places in the clinic to process image data“, explains Prof Jan Hasenauer, from the Life & Medical Sciences Institute (LIMES) at the University of Bonn. „We will go one step further and investigate the extent to which information about mechanisms can also be obtained.” On the one hand, we want to investigate the role that individual immune cell types present in the TME play in the development of different tumour types. In addition, the researchers want to determine what effect chemotherapeutics and biological drugs have on the TME of different tumour types. Prof Michael Hölzel and Prof Marieta Toma from the University Hospital Bonn and Prof Alexander Effland from the University of Bonn are also involved in the project.

Article of "LABO" from 01.03.2023