HSE Scientists Develop DeepGQ: AI-based 'Google Maps' for G-Quadruplexes
Researchers at the HSE AI Research Centre have developed an AI model that opens up new possibilities for the diagnosis and treatment of serious diseases, including brain cancer and neurodegenerative disorders. Using artificial intelligence, the team studied G-quadruplexes—structures that play a crucial role in cellular function and in the development of organs and tissues. The findings have been published in Scientific Reports.
DNA can be thought of as a long chain of symbols made up of four letters: A, C, G, and T. Beyond the sequence itself, the way the DNA strand is folded and twisted is also crucial. This structure determines which regions of the genetic code are open—accessible to the cell for reading and replication—and which remain closed. One form of such 'packaging' is a special structure known as a G-quadruplex. It can be visualised as a small nodular structure that forms in regions rich in guanine (G). Scientists have hypothesised that each cell type has its own unique set of such nodules, which helps determine the cell’s function. For example, the DNA of nerve cells in the brain differs from that of liver cells in the pattern of these specialised structures. These variations influence how different cell types develop and function. However, investigating these processes in the laboratory is expensive and does not always produce reliable results.
Researchers at the HSE AI Research Centre have developed the DeepGQ AI model, which uses deep learning to generate tissue-specific maps of G-quadruplexes. The model analyses the DNA strand in both directions simultaneously, much like reading it from left to right and from right to left. This bidirectional approach allows the program to capture a complete and accurate picture of the features of the DNA region under study.
Artem Bashkatov, Junior Research Fellow at the Centre for Biomedical Research and Technology of the AI and Digital Science Institute, explains: 'We hypothesised that the characteristics of the cellular environment—not only the DNA structure itself—play a key role in determining how different tissue-specific cell types develop. To test this idea, we developed not a single universal model, but a set of specialised DeepGQ models tailored to different tissues. For example, one model was trained exclusively on brain cells (DeepGQ Neurons), another on liver cells (DeepGQ Liver), and so on across 14 tissue types. This approach enabled each model to identify developmental patterns specific to its tissue.'
Thanks to DeepGQ, scientists now have access to a tool that enables highly accurate prediction of G-quadruplexes. Rather than relying on costly experimental studies, any laboratory investigating, for example, liver cancer or Alzheimer’s disease can use data from patient samples and apply DeepGQ to generate an accurate map of the most likely targets for experimental validation.
'DeepGQ is essentially like Google Maps for G-quadruplexes: it plots landmarks (GQs) and traffic conditions (DHSs and histones) onto a flat DNA map that is unique to each "city," or tissue,' says Maria Poptsova, Director of the Centre for Biomedical Research and Technology at the Institute of AI and Digital Sciences. 'Many serious diseases—from cancer to neurodegeneration—are disorders of lost tissue identity. Cells either forget what they are meant to become, or their specialisation programmes break down. G-quadruplexes may become promising new targets for the treatment of such diseases. If a cancer cell depends on a specific GQ structure for its survival, it may be possible to develop a drug that either disrupts or stabilises this structure until the cellular programme collapses, ultimately killing the cancer cell. In the future, this approach could lead to the creation of a DeepGQ Patient model: by analysing data from a tumour biopsy, researchers could generate a personalised map of active G-quadruplexes and use it to design a truly individualised treatment strategy.'
See also:
Scientists Develop Algorithm for More Reliable Processors in Data Centres
Researchers from HSE MIEM and Samara University have developed the LRF-3D algorithm to automatically bypass idle nodes in three-dimensional networks-on-chip. Thanks to its hierarchical architecture, the algorithm outperforms existing solutions in both speed and path accuracy, improving processor reliability for use in data centres, supercomputers, and AI computing. The source code and test results are publicly available.
Researchers Rank Recommendation Algorithms Using Sports Tournament Model
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science have developed an approach for selecting recommendation algorithms more effectively. Their approach uses pairwise comparisons of algorithms to create a tournament table, with the overall ranking based on their performance across all datasets in the tournament. This can reduce the number of algorithms that need to be tested when developing new services, saving both time and money. The study was presented at the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2026).
Researchers Develop Method for Direct Generation of Regulatory DNA
Researchers at HSE University have developed a model for generating promoters and enhancers—DNA sequences that regulate gene activity. The model works directly with DNA nucleotides, without first transforming them into a continuous numerical representation. This solution could be useful for applications in synthetic biology and gene therapy. The study results were presented at the ICLR 2026 Workshop ‘Generative AI in Genomics (Gen^2): Barriers and Frontiers.’
Researchers at HSE University and Sber Train Neural Networks to Better Predict User Preferences
The HSE FCS AI and Digital Science Institute and Sber have introduced a new architecture for recommendation systems that combines two classes of models, enabling algorithms to better predict users’ interests and needs. A preprint of the paper has been published on arxiv.org and presented at Urban ML.
Physicists Discover What Happens Inside a Stable Vortex
Large vortices with characteristic spiral arms are often observed in the atmosphere and the ocean. Physicists from HSE University have explained how these structures form and why they retain their shape. The researchers found that velocities at points located along the same vortex arc remain correlated even over long distances. At the same time, this correlation weakens rapidly with increasing distance from the vortex centre. These differences help explain the formation of spiral arms and may improve models of atmospheric and oceanic currents. The findings have been published in Physical Review Fluids.
HSE Computer Science Researchers Win Gold Medal at International Machine Learning Competition
A team comprising HSE International Laboratory of Statistical and Computational Genomics researchers Aleksei Shmelev and Nikita Chervov, 2025 graduate of the HSE Faculty of Computer Science’s Master’s programme in Data Analysis in Biology and Medicine Ivan Gevorkov, and two students from the United States achieved an outstanding result at the 2026 NeuroGolf international machine learning championship. The team won a gold medal and placed seventh overall.
‘Working with AI Solves a Wide Range of Engineering Problems’
Artificial intelligence is a working tool based on a balanced combination of algorithms and engineering. Experts and doctoral students from the HSE Moscow Institute of Electronics and Mathematics explain how AI technologies can improve an application, device, or system, and what engineering tasks are solved in the process.
‘The Peak of Stupidity’ and ‘The Valley of Despair’: HSE Economists Propose an Explanation for the Dunning–Kruger Effect
The Dunning–Kruger effect, which describes a sharp surge in self-confidence among beginners followed by an equally rapid decline as they gain experience, can be explained by the nature of the learning process and the acquisition of new knowledge. This conclusion was reached by Andrey Vorchik of the HSE Faculty of Economic Sciences together with independent researcher Murat Mamyshev. They developed a mathematical model of learning and demonstrated how subjective confidence is formed and changes as knowledge accumulates, as well as how teachers can reduce the ‘valley of despair’ experienced by learners.
Toffee and Risk: Scientists Discover Why People Who Crave Sweets Make More Impulsive Choices
Having a sweet tooth may be linked not only to eating habits but also to the way people make decisions. Researchers at HSE University have found that people with a preference for sweet foods tend to behave more impulsively—not because they want immediate rewards, but because they are less willing to tolerate uncertainty. These findings may help improve treatments for addiction. The study findings have been published in Frontiers in Psychology.
Advancing Collaboration: HSE Faculty of Computer Science and Harbin Institute of Technology Hold Joint Seminar
From July 13 to 16, 2026, the Faculty of Computer Science hosted the Russian–Sino Research Seminar on Machine Learning Applications, organised by the HSE Laboratory for Cloud and Mobile Technologies in partnership with the Harbin Institute of Technology (China). A delegation comprising seven students and three university representatives travelled to Moscow to take part in an intensive four-day programme.