The GENOMENAL platform served as the technological foundation for the first Russian hackathon on genetic data interpretation, "Genome IQ" held from April 8 to 10 at the Tomsk National Research Medical Center (NMRC). Experts from Moscow, St. Petersburg, Novosibirsk, Yakutsk, and Tomsk participated in this competition, which focused on interpreting whole-genome sequencing data.
NOVEL provided the technological infrastructure for the event. "At the hackathon, we saw that our innovative approach works and that complex clinical cases can be solved. The use of modern software, AI algorithms, and a competitive team format increases the speed and quality of whole-genome data analysis," noted Dmitry Shtokalo, CEO of NOVEL.
Over two days, teams analyzed challenging cases from leading research centers, while on the third day, they tackled unsolved problems. A school for early-career specialists ran in parallel. The prize fund of 500,000 rubles was topped by "Team XX," which won 126,000 rubles.
The hackathon confirmed that using domestic software like GENOMENAL and consolidating best practices helps build a strong community of specialists to solve the challenges of modern medicine.
On March 18, 2026, the Scientific Council on Therapeutic Sciences under the Department of Medical Sciences of the Russian Academy of Sciences held a meeting centered on the evolution of artificial intelligence. The session, titled “How Artificial Intelligence is Transforming Therapeutic Practice: Reality and Prospects,” featured a presentation by our Chief Innovation Officer, Yuri Vyatkin.
Yuri highlighted the current capabilities of AI in the medical field, emphasizing that effective data analysis requires more than just processing text, images, or audio. He argued that a multimodal approach is essential, medical AI must integrate diverse data types, including text, imaging, video, signals, and structured data to reflect real-world clinical scenarios. Since diagnosis and therapy in actual practice rarely rely on a single source, the closer a model aligns with a real clinical case, the more critical this integration becomes. Furthermore, Yuri noted several key shifts in the landscape: multimodality as the modern large-scale AI models are increasingly moving toward multimodal processing, foundational Models when the special medical foundational models have emerged with improved capabilities for handling long-form text, and strategic Focus when AI is shifting from pure diagnosis toward recommending comprehensive patient management strategies.
While contemporary multimodal models already provide significant assistance in diagnosis, therapy, and prevention, Yuri maintains that they will not fully replace physicians in the near future. Instead, AI should be viewed as a powerful tool designed to augment and enhance a doctor’s clinical expertise.
A new version, Genomenal 2.12.0, has been released.
Key Changes
Integrated the GenCC database, providing comprehensive data on gene-disease relationships.
Implemented filtering for genetic variants and copy number variations (CNV) using MONDO disease ontology terms.
Enabled direct editing of search condition values for genetic variants within the SNV Viewer table.
Useful Additions
Added configuration support for BWA-MEM alignment tool parameters.
For amplicon panel analysis, users can now disable filtering for sequencing artifacts related to strand and orientation bias.
Alternative polymorphic contigs are now excluded from analysis by default.
Added processing time statistics for sequenced samples.
Improvements
Updated the OMIM database to the November 2025 version.
Significantly accelerated the base quality score recalibration (BQSR) stage.
A new version, Genomenal 2.11.0, has been released.
Key Changes
Useful Additions
Improvements
Employees of NOVEL contributed to the article "Transcriptomic Analysis of TDP1-Knockout HEK293A Cells Treated with a TDP1 Inhibitor (Usnic Acid Derivative)," published in the International Journal of Molecular Sciences.
Tyrosyl-DNA phosphodiesterase 1 (TDP1) is a key enzyme for the repair of stalled topoisomerase 1 (TOP1)-DNA complexes. Previously, we obtained HEK293A cells with homozygous knockout of the TDP1 gene by the CRISPR/Cas9 method and used them as a cell model to study the mechanisms of anticancer therapy and to investigate the effect of TDP1 gene knockout on gene expression changes in the human HEK293A cell line by transcriptome analysis. In this study, we investigated the effect of a TDP1 inhibitor ((R,E)-2-acetyl-6-(2-(2-(4-bromobenzyliden) hydrazinyl) thiazol-4-yl)-3,7,9-trihydroxy-8,9b-dimethyldibenzo[b,d] furan-1(9bH)-one, OL9-119, an usnic acid derivative), capable of potentiating the antitumor effect of topotecan, as well as its combination with topotecan, on the transcriptome of wild-type and TDP1 knockout HEK293A cells. OL9-119 was found to be able to reduce cell motility by decreasing the expression of a number of genes, which may explain the antimetastatic effect of this compound. Differentially expressed genes (DEGs) related to electron transport, mitochondrial function, and protein folding were also identified under TDP1 inhibitor treatment.
The full text of the article can be found here: https://www.mdpi.com/1422-0067/26/19/9291
As part of the ONCOMARKERS-2025 conference, a hands-on training school on the NanoFor SPS sequencing platform was successfully conducted. The event took place at the Institute of Chemical Biology and Fundamental Medicine, SB RAS (Novosibirsk), and was organized with the support of:
Program Highlights:
Participants gained comprehensive, hands-on experience encompassing the entire workflow — from DNA extraction to data interpretation. The acquired skills are valuable for both diagnostic applications in hereditary disease research and broader scientific studies.
We extend our sincere gratitude to the organizers and participants for their active engagement and productive collaboration!
We are pleased to announce the release of Genomenal 2.10.0, featuring significant improvements.
Key Enhancements:
The journal iScience has published the article “Mutational pressure promotes release of public CD8+ T cell epitopes by proteasome from SARS-CoV-2 RBD of Omicron and its current lineages”, co-authored by a NOVEL researcher.
This study demonstrates that mutations in the Omicron B.1.1.529 variant significantly enhance the release of two immunodominant HLA class I epitopes: 504-GHQPYRVVVL-513 and 496-SFRPTYGVGH-505. These epitopes are generated through the efficient processing—hydrolysis—of the receptor-binding domain (RBD) by both constitutive proteasomes (c20S) and immune proteasomes (i20S). These proteasomes break down the protein into antigenic fragments, which are then presented to the immune system to trigger a protective response.
The authors highlight the global significance of HLA haplotypes capable of presenting these epitopes. Key HLA molecules, such as HLA-B07:02, HLA-B08:01, HLA-B51:01, HLA-C01:02, HLA-C06:02, and HLA-C07:02, are widely distributed among populations and cover up to 82% and 27% of the global population for the 504-GHQPYRVVVL-513 and 496-SFRPTYGVGH-505 epitopes, respectively. This explains the decrease in COVID-19 mortality rates in regions with a high prevalence of these haplotypes after December 2021, when Omicron became the dominant and persistent strain.
The full text article is here https://www.cell.com/iscience/fulltext/S2589-0042(25)00133-6.
The paper «Enhancing the reverse transcriptase function in Taq polymerase via AI-driven multiparametric rational» is published in the journal of Frontiers in Bioengineering and Biotechnology. The result is based on the AI models developed in NOVEL and Institute of Artificial Intelligence MSU.
We trained a Ridge regression model to predict multiple enzyme properties in the wild type and mutated Taq polymerase. The model is based on the embeddings of Taq polymerase primary structure generated by a protein language model. Using the regression model we conducted an in silico screen of over 18 million potential mutations, narrowing the field to 16 top candidates for comprehensive wet-lab evaluation.
This approach led to the identification of 18 enzyme variants that exhibited markedly improved reverse transcriptase activity while maintaining a favorable balance of other key properties. Several enzymes validated via this procedure were effective in single-enzyme real-time reverse-transcription PCR setups, implying their utility for the development of new tools for real-time reverse-transcription PCR technologies, such as pathogen RNA detection and gene expression analysis.
Our approach offers a robust framework for designing enzyme mutants tailored to specific biotechnological applications. The full text article is here https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2024.1495267/full.
Main updates: