Algorithms help distinguish diseases at the molecular level

In medicine today, doctors define and diagnose most illnesses based on symptoms. However, this does not necessarily mean that diseases in patients with similar symptoms will have identical causes or show the same molecular changes. In biomedicine, we often talk about the molecular mechanisms of a disease. These are changes in the regulation of genes, proteins or metabolic pathways at the onset of the disease. The goal of stratified medicine is to classify patients into different subtypes at the molecular level in order to provide more targeted treatments.

To extract disease subtypes from large patient datasets, new machine learning algorithms may be useful. They are designed to independently recognize patterns and correlations in broad clinical measurements. The junior research group LipiTUM, led by Dr. Josch Konstantin Pauling from the Chair of Experimental Bioinformatics, has developed an algorithm for this purpose.

Complex analysis via an automated web tool

Their method combines the results of existing algorithms to obtain more accurate and robust predictions of clinical subtypes. This unifies the features and benefits of each algorithm and eliminates their tedious adjustment. “This greatly facilitates the application of the analysis to clinical research,” reports Dr. Pauling. “For this reason, we have developed a web-based tool that enables online analysis of molecular clinical data by practitioners without prior knowledge of bioinformatics.”

On the website (https://exbio.wzw.tum.de/mosbi/), researchers can submit their data for automated analysis and use the results to interpret their studies. “Another important aspect for us was the visualization of results. Previous approaches were not able to generate intuitive visualizations of the relationships between patient groups, clinical factors and molecular signatures. This will change with the web-based visualization produced by our MoSBi tool. says Tim Rose, a scientist at the TUM School of Life Sciences. MoSBi stands for “Molecular Signatures using Biclustering”. “Biclustering” is the name of the technology used by the algorithm.

Asking clinically relevant questions

With this tool, researchers can now, for example, plot data from cancer studies and simulations for various scenarios. They have already demonstrated the potential of their method in a large-scale clinical study. In a cooperative study conducted with researchers from the Max Planck Institute Dresden, the Technical University of Dresden and the University Clinic Kiel, they investigated the change in lipid metabolism in the liver of patients with fatty liver disease. non-alcoholic (NAFLD).

This widespread disease is associated with obesity and diabetes. It develops from non-alcoholic fatty liver disease (NAFL), in which lipids are deposited in liver cells, to non-alcoholic steatohepatitis (NASH), in which the liver becomes more inflamed, to cirrhosis of the liver and to tumor formation. Apart from dietary adjustments, no treatment has been found to date. Because the disease is characterized and diagnosed by the accumulation of various lipids in the liver, it is important to understand their molecular composition.

Liver disease biomarkers

Using MoSBi methods, the researchers were able to demonstrate the heterogeneity of NAFL-stage patient livers at the molecular level. “From a molecular perspective, the liver cells of many NAFL patients were almost identical to those of NASH patients, while others were still broadly similar to those of healthy patients. We were also able to confirm our predictions using clinical data,” says Dr. Pauling. “We were then able to identify two potential lipid biomarkers for disease progression.” This is important for the early recognition of the disease and its progression and the development of targeted treatments.

The research group is already working on other applications of their method to better understand other diseases. “Algorithms will play an even greater role in biomedical research in the future than they already do today. They can greatly facilitate the detection of complex mechanisms and the search for more targeted therapeutic approaches,” says Dr Pauling.

Source of the story:

Materials provided by Technical University of Munich (TUM). Note: Content may be edited for style and length.

Sharon D. Cole