Machine Learning Links Two New Genes to Ischemic Stroke
A team of scientists from HSE University and the Kurchatov Institute used machine learning methods to investigate genetic predisposition to stroke. Their analysis of the genomes of over 5,000 people identified 131 genes linked to the risk of ischemic stroke. For two of these genes, the association was found for the first time. The paper has been published in PeerJ Computer Science.
Ischemic stroke is a major cause of death and disability worldwide. This condition occurs when blood supply to a part of the brain is interrupted, causing cell death and impaired brain function. Scientists have long studied the genetic factors influencing stroke risk, but a definitive list of genes linked to stroke predisposition has yet to be established. There are hopes that artificial intelligence methods may provide answers in this regard.
A team of scientists from the HSE Faculty of Computer Science and the Kurchatov Institute proposed using machine learning algorithms to analyse genetic predisposition to stroke. They analysed genomic data from 5,500 unrelated individuals over the age of 55, including ischemic stroke survivors and their healthy counterparts. Samples for the study were collected from 11 laboratories in Europe and 13 in the United States.
The analysis was based on the concept of ranking through learning. First, the researchers developed a predictive model in which the key parameter was the presence or absence of a stroke. Single nucleotide polymorphisms (SNPs), which are variations in the genome at specific sites, were used as markers. The scientists then ranked these markers and selected the most significant ones.
SNPs were analysed and selected using various methods, enabling a new analysis of the data and the identification of genes previously not associated with ischemic stroke. The list of 'suspicious' genetic markers common to two or more methods highlights the reliability of the results.
Working with such a large dataset—nearly 900,000 SNPs per 5,500 participants—required us to move beyond purely statistical analysis methods. Machine learning made it possible to process all of this. As a result, we identified 131 genes, most of which had already been linked to ischemic stroke. However, for two of these genes, this was the first time we discovered the association,' explains Dmitry Ignatov, Head of the Laboratory for Models and Methods of Computational Pragmatics at HSE University.
In particular, the scientists found an association between stroke and ACOT11, a gene involved in fatty acid metabolism and shown in animal experiments to affect inflammatory processes and blood lipid levels. The second gene newly linked to ischemic stroke is UBQLN1, which is involved in the mechanisms that protect cells from oxidative stress. There is evidence that a mutation in this gene is associated with neurodegenerative diseases.
These discoveries could help develop multigenic risk models that predict a person's predisposition to stroke. Information about the newly associated genes could also serve as the foundation for developing drugs and therapies aimed at reducing the risk of ischemic stroke.
Gennady Khvorykh
'Identifying two new stroke-associated genes is an excellent outcome for any method. Our machine learning approach clearly holds strong potential for detecting genes linked to diseases that result from a variety of factors,' comments Gennady Khvorykh, Chief Specialist at the Kurchatov Institute.
The proposed approach to analysing genetic markers demonstrates versatility and can be effectively adapted for a wide range of studies beyond ischemic stroke. This methodology can be applied to any diseases or markers with data available in the 'sample—SNP—class' format.
'Although we initially developed this tool for a specific task, the results reveal its potential in a broader context. The ability to work with a variety of genetic data makes our method valuable to researchers across various fields of biology and medicine,' says Stefan Nikolić, graduate of the Faculty of Computer Science and the Doctoral School of Computer Science at HSE University.
See also:
First Digital Adult Reading Test Available on RuStore
HSE University's Centre for Language and Brain has developed the first standardised tool for assessing Russian reading skills in adults—the LexiMetr-A test. The test is now available digitally on the RuStore platform. This application allows for a quick and effective diagnosis of reading disorders, including dyslexia, in people aged 18 and older.
Low-Carbon Exports Reduce CO2 Emissions
Researchers at the HSE Faculty of Economic Sciences and the Federal Research Centre of Coal and Coal Chemistry have found that exporting low-carbon goods contributes to a better environment in Russian regions and helps them reduce greenhouse gas emissions. The study results have been published in R-Economy.
Russian Scientists Assess Dangers of Internal Waves During Underwater Volcanic Eruptions
Mathematicians at HSE University in Nizhny Novgorod and the A.V. Gaponov-Grekhov Institute of Applied Physics of the Russian Academy of Sciences studied internal waves generated in the ocean after the explosive eruption of an underwater volcano. The researchers calculated how the waves vary depending on ocean depth and the radius of the explosion source. It turns out that the strongest wave in the first group does not arrive immediately, but after a significant delay. This data can help predict the consequences of eruptions and enable advance preparation for potential threats. The article has been published in Natural Hazards. The research was carried out with support from the Russian Science Foundation (link in Russian).
Centre for Language and Brain Begins Cooperation with Academy of Sciences of Sakha Republic
HSE University's Centre for Language and Brain and the Academy of Sciences of the Republic of Sakha (Yakutia) have signed a partnership agreement, opening up new opportunities for research on the region's understudied languages and bilingualism. Thanks to modern methods, such as eye tracking and neuroimaging, scientists will be able to answer questions about how bilingualism works at the brain level.
How the Brain Responds to Prices: Scientists Discover Neural Marker for Price Perception
Russian scientists have discovered how the brain makes purchasing decisions. Using electroencephalography (EEG) and magnetoencephalography (MEG), researchers found that the brain responds almost instantly when a product's price deviates from expectations. This response engages brain regions involved in evaluating rewards and learning from past decisions. Thus, perceiving a product's value is not merely a conscious choice but also a function of automatic cognitive mechanisms. The results have been published in Frontiers in Human Neuroscience.
AI Predicts Behaviour of Quantum Systems
Scientists from HSE University, in collaboration with researchers from the University of Southern California, have developed an algorithm that rapidly and accurately predicts the behaviour of quantum systems, from quantum computers to solar panels. This methodology enabled the simulation of processes in the MoS₂ semiconductor and revealed that the movement of charged particles is influenced not only by the number of defects but also by their location. These defects can either slow down or accelerate charge transport, leading to effects that were previously difficult to account for with standard methods. The study has been published in Proceedings of the National Academy of Sciences (PNAS).
Electrical Brain Stimulation Helps Memorise New Words
A team of researchers at HSE University, in collaboration with scientists from Russian and foreign universities, has investigated the impact of electrical brain stimulation on learning new words. The experiment shows that direct current stimulation of language centres—Broca's and Wernicke's areas—can improve and speed up the memorisation of new words. The findings have been published in Neurobiology of Learning and Memory.
Artificial Intelligence Improves Risk Prediction of Complex Diseases
Neural network models developed at the HSE AI Research Centre have significantly improved the prediction of risks for obesity, type 1 diabetes, psoriasis, and other complex diseases. A joint study with Genotek Ltd showed that deep learning algorithms outperform traditional methods, particularly in cases involving complex gene interactions (epistasis). The findings have been published in Frontiers in Medicine.
Cerium Glows Yellow: Chemists Discover How to Control Luminescence of Rare Earth Elements
Researchers at HSE University and the Institute of Petrochemical Synthesis of the Russian Academy of Sciences have discovered a way to control both the colour and brightness of the glow emitted by rare earth elements. Their luminescence is generally predictable—for example, cerium typically emits light in the ultraviolet range. However, the scientists have demonstrated that this can be altered. They created a chemical environment in which a cerium ion began to emit a yellow glow. The findings could contribute to the development of new light sources, displays, and lasers. The study has been published in Optical Materials.
Genetic Prediction of Cancer Recurrence: Scientists Verify Reliability of Computer Models
In biomedical research, machine learning algorithms are often used to analyse data—for instance, to predict cancer recurrence. However, it is not always clear whether these algorithms are detecting meaningful patterns or merely fitting random noise in the data. Scientists from HSE University, IBCh RAS, and Moscow State University have developed a test that makes it possible to determine this distinction. It could become an important tool for verifying the reliability of algorithms in medicine and biology. The study has been published on arXiv.