Researchers from the University of Bielefeld have developed new Artificial Intelligence (AI) methods which can accurately predict the development of ALS in disease.
ALS disease is a severe, hereditary condition that affects the motor nervous system. Scientists still do not fully understand the heritability of the disease. A research team led by Professor Dr Alexander Schönhuth from Bielefeld University’s Faculty of Technology has unveiled more information on the hereditary nature of ALS using AI.
The researchers recorded and deciphered the genotype profiles of 3,000 patients with ALS disease. This enabled them to learn more about how the disease develops. A new method devised by the research team allowed them to predict ALS disease in people with 87% accuracy.
The study, titled ‘Predicting the prevalence of complex genetic diseases from individual genotype profiles using capsule networks’, has been published in Nature Machine Intelligence.
The role of genetics in ALS disease
Over time, patients with ALS disease lose the ability to move; however, the brain remains completely functional. Professor Schönhuth and his team focused their research on developing new methods and tools for analysing genomes in ALS disease patients.
“There is still a great deal about ALS that we do not understand. We know that ALS is a hereditary disease, but 80% of this heritability is still unexplained,” said Professor Schönhuth.
Around 5-10% of all ALS cases are genetically inherited. Mutations in more than a dozen genes have been found to cause hereditary ALS. About 25-40% of all cases are caused by defects in the C9ORF72 gene, which produces a protein found in motor neurons and nerve cells in the brain.
“Many hereditary diseases reveal overlapping, so-called additive effects of genetic factors. An example is schizophrenia. The more of these factors the genes reveal, the more likely it is that a person will develop schizophrenia. We can, therefore, easily recognise the genetic disposition based on the genes. With ALS, in contrast, things are much more complex,” he continued.
The new prediction method is highly accurate
The researchers assumed that individual factors were likely to lead to ALS disease. They hypothesised that if these factors occurred together, no disease would develop.
“Our method can make predictions about the disease, and it is much more accurate than other methods. We have found more than 900 genes that play a role in identifying the disease and 644 genes that interact in complex ways. These need to be investigated further in other fields of research,” Professor Schönhuth said.
“Each gene is engaged in different biological processes: the more we learn about the genes, the more we learn about the processes. In this way, our results will help people affected by ALS disease to adapt their lifestyle and reduce their risk of suffering from the disease. In addition, drugs could also be developed that influence specific processes,” he concluded.