Same symptom – different cause?

Nowadays, doctors use the symptoms to define and diagnose most diseases. However, this does not necessarily mean that patients with similar symptoms also have the same cause of the disease or the same molecular changes. In biomedicine, one often speaks of the molecular mechanisms of a disease, i.e. how the regulation of genes, proteins or metabolic pathways changes when a disease breaks out. The aim of stratified medicine is to divide patients into different subtypes at the molecular level in order to provide them with more targeted treatment, according to the Technical University of Munich press release.

New algorithms from the field of machine learning can help to identify disease subtypes from large patient data. The aim of these is to independently recognize patterns and connections from extensive clinical measurements. The junior research group LipiTUM around group leaders dr Josch Konstantin Pauling from the Chair of Experimental Bioinformatics developed such an algorithm.

Complex analyzes via automated web application

Their method combines the results of existing algorithms to make more accurate and robust predictions of clinical subtypes. This combines the advantages and properties of several algorithms and eliminates the need for time-consuming adaptation. “This makes it much easier to use in clinical research,” reports Dr. Pauling. “For this reason, we have also developed a web-based application on which the analysis of molecular data can be carried out online without prior bioinformatics knowledge.”

Application for clinically relevant questions

With this tool, researchers now have the opportunity, for example, to display data from cancer studies and simulations for different scenarios. They have already been able to demonstrate the potential of the method in a large-scale clinical study. In a collaboration with researchers from the Max Planck Institute in Dresden, the Technical University of Dresden, and the University Hospital in Kiel, they investigated changes in the lipid (fat) metabolism in the liver of patients with non-alcoholic fatty liver disease (NAFLD).

This widespread disease is linked to obesity and diabetes. It develops from non-alcoholic fatty liver (NAFL), in which fat is stored in liver cells, through non-alcoholic steatohepatitis (NASH), the additional inflammation of the liver, to liver cirrhosis and tumor formation. There is currently no treatment other than changing your diet. Since the disease is characterized and diagnosed by the accumulation of different fats in the liver, it is important to understand their molecular composition.

Biomarkers for liver disease

Using the MoSBi method, they were able to show how heterogeneous the livers of patients with the NAFL stage are at the molecular level. “From a molecular point of view, the liver cells of many NAFL patients were already almost identical to those of NASH patients, while others still showed extensive similarities to healthy patients. We were also able to confirm our predictions based on clinical information,” says Dr. Pauling. “As a result, we were also able to identify two potential lipid biomarkers for disease progression.” This is important so that the disease and its development can be recognized and treated as early as possible.

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.