AIArtem B. Ivanov

Artem B. Ivanov

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Artem B. Ivanov has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Efficient and Verified Research Data Extraction with LLM

    by Aleksandr Serdiukov, Vitaliy Dravgelis, Daniil Smutin, Amir Taldaev, Artem Ivanov, Leonid Adonin, Sergey Muravyov

    Large language models (LLMs) hold promise for automated extraction of structured biological information from scientific literature, yet their reliability in some domain-specific tasks, such as DNA probe parsing remains underexplored. We developed a verification-focused, schema-guided extraction pipeline that transforms unstructured texts from scientific articles into a normalized database of oligonucleotide probes, primers, and associated metadata. The system combined multi-turn JSON generation, strict schema validation, sequence-specific rule checks, and a post-processing recovery module that rescues systematically corrupted nucleotide outputs. Benchmarking across nine contemporary LLMs revealed distinct accuracy–hallucination trade-offs, with the context-optimized Qwen3 model achieving the highest overall extraction efficiency while maintaining low hallucination rates. Iterative prompting substantially improved fidelity but introduced notable latency and variance. Across all models, stable error profiles and the success of the recovery module indicated that most extraction failures stem from systematic and correctable formatting issues rather than semantic misunderstandings. These findings highlight both the potential and the current limitations of LLMs for structured scientific data extraction. The research provides a reproducible benchmark and extensible framework for future large-scale curation of molecular biology datasets.


  • Open Access

    Proliferative and transcriptomic response of experimental B16-F10 melanoma to modulation of murine microbiota by oral administration of Lacticaseibacillus rhamnosus K32 and Bifidobacterium adolescentis 150

    by Evgenii I. Olekhnovich, Alexandra A. Strokach, Vera A. Kanaeva, Maxim D. Morozov, Vladimir A. Veselovsky, Polina Yu. Zoruk, Artem B. Ivanov, Maya V. Odorskaya, Severina D. Koldman, Vail A. Koldman, et al.

    BACKGROUND: Probiotics are capable of modulating immune responses through interactions with the gut microbiota, potentially enhancing the efficacy of immunotherapy and reducing adverse effects of chemotherapy and radiotherapy. Certain probiotic strains have demonstrated the ability to suppress chronic inflammation and augment antitumor immunity; however, their clinical application requires further investigation. AIM: This work aimed to evaluate the effects of oral administration of the probiotic strains Lacticaseibacillus rhamnosus K32 and Bifidobacterium adolescentis 150 on tumor growth and gene expression in the B16-F10 melanoma model, as well as on gut microbiota composition in experimental animals. METHODS: The experiment was conducted in C57BL/6 mice bearing B16-F10 melanoma. Animals were divided into three groups: control (no intervention) and two experimental groups for oral administration of B. adolescentis 150 or L. rhamnosus K32, respectively. Changes in gut microbiota composition were analyzed by full-length 16S rRNA gene sequencing using Oxford Nanopore technology. The transcriptomic response of B16-F10 melanoma cells to probiotic administration was assessed by RNA sequencing. RESULTS: Substantial differences were observed in the effects of the studied probiotic strains on B16-F10 melanoma progression. B. adolescentis 150 significantly stimulated experimental tumor growth by 29% (padj. = 0.02 vs. control; padj. = 0.001 vs. L. rhamnosus K32; adj., Bonferroni correction applied). At the molecular level, this stimulation was associated with suppression of interferon signaling, activation of proliferative pathways (WNT/β-catenin, TGF-β), and reduced expression of immune cell markers in melanoma tissue. In contrast, L. rhamnosus K32 reduced tumor growth by 18% (not significant; padj. = 0.4) and was associated with increased expression of cytotoxic T lymphocyte and NK cell markers, as well as activation of interferon response pathways. Both probiotic strains induced marked alterations in gut microbiota composition, characterized by an increased relative abundance of Klebsiella spp., and were associated with activation of proinflammatory signaling pathways (NF-κB, IL-6/JAK/STAT3, IL-2/STAT5) in tumor tissue. Notably, administration of both probiotics was linked to activation of epithelial–mesenchymal transition and hypoxia in the tumor, potentially creating conditions favorable for tumor progression and metastasis. CONCLUSION: These findings highlight the complex and context-dependent effects of probiotics on tumor development and underscore the need for careful strain selection in the adjuvant therapy of melanoma and other malignancies.

  • Open Access

    MetaFX: feature extraction from whole-genome metagenomic sequencing data

    by Artem Ivanov, Vladimir Popov, Maxim Morozov, Evgenii Olekhnovich, Vladimir Ulyantsev

    Motivation: Microbial communities consist of thousands of microorganisms and viruses and have a tight connection with an environment, such as gut microbiota modulation of host body metabolism. However, the direct relationship between the presence of certain microorganism and the host state often remains unknown. Toolkits using reference-based approaches are limited to microbes present in databases. Reference-free methods often require enormous resources for metagenomic assembly or results in many poorly interpretable features based on k-mers. Results: Here we present MetaFX—an open-source library for feature extraction from whole-genome metagenomic sequencing data and classification of groups of samples. Using a large volume of metagenomic samples deposited in databases, MetaFX compares samples grouped by metadata criteria (e.g. disease, treatment, etc.) and constructs genomic features distinct for certain types of communities. Features constructed based on statistical k-mer analysis and de Bruijn graphs partition. Those features are used in machine learning models for classification of novel samples. Extracted features can be visualized on de Bruijn graphs and annotated for providing biological insights. We demonstrate the utility of MetaFX by building classification models for 590 human gut samples with inflammatory bowel disease. Our results outperform the previous research disease prediction accuracy up to 17%, and improves classification results compared to taxonomic analysis by 9±10% on average. Availability and implementation: MetaFX is a feature extraction toolkit applicable for metagenomic datasets analysis and samples classification. The source code, test data, and relevant information for MetaFX are freely accessible at https://github.com/ctlab/metafx under the MIT License. Alternatively, MetaFX can be obtained via http://doi.org/10.5281/zenodo.16949369.

  • Open Access

    Comparative analysis method for time series data objects represented as sets of strings based on de Bruijn graphs

    by A. B. Ivanov, A. A. Shalyto, V. I. Ulyantsev

    The paper considers the comparative analysis of string datasets represented as time series of samples. We propose a method to increase the accuracy of determining differences between two samples. Based on this method, a method for analyzing time series of three samples has been developed, which allows for more accurate changes investigation between samples. The use of three samples in the analysis is due to the specific nature of the practical task of processing metagenomic sample sequencing data, obtaining a larger number of which is very resource-intensive. To classify strings from one sample into detected and undetected strings in another sample, a method of comparing two samples using k-mers and the de Bruijn graph is proposed. It implements decision rules based on statistics of the frequency of k-mers occurrence, different values of the parameter k, and information about possible errors in the strings. To analyze time series of three samples (the original and final sample for one object and the modifying sample for another object), a method based on pairwise comparison of samples is developed. It is used to divide the strings of each sample into groups depending on the detection of strings in other samples. The developed method for analyzing time series has been tested on two types of generated metagenomic data, represented as a set of strings. It was shown that the method allows distinguishing organisms that have differences in genomes in at least one symbol for every 10,000 symbols. High (more than 80 %) recall and precision of the results of string classification were demonstrated when analyzing simulated complex data, with properties comparable to real data. The developed method allows comparing metagenomic samples represented as a set of strings using only the data itself and without requiring additional information. This allows for a more accurate analysis compared to existing methods that compare samples based on the results of string classification in taxonomic annotation databases. The developed methods can also be used in other areas of string data processing such as analyzing changes in author style when writing a series of texts.

  • Open Access

    Feature extraction methods for metagenome de Bruijn graphs collections based on samples classification information

    by A. B. Ivanov, A. A. Shalyto, V. I. Ulyantsev

    The paper considers the comparative analysis of metagenomic samples collections using de Bruijn graphs. We propose methods for automatic feature extraction based on the results of comparative sample analysis, expert metadata, and statistical tests to improve the accuracy of classification models. In this paper features are connected subgraphs of the de Bruijn graph. The first method, named unique_kmers, is used to extract strings of length k (k-mers) that occur only in samples of the certain class. The second method, named stats_kmers, is used to extract k-mers whose frequency of occurrence statistically differs between sample classes. To extract interpretable features, a third method has been developed that implements the extraction of subgraphs from de Bruijn graphs based on the selected nodes obtained as a result of applying one of the first two methods. Data analysis consists of two stages: firstly, unique_kmers or stats_kmers method is applied for data preprocessing, secondly, the third method is applied to obtain interpretable features. The methods were tested on four generated datasets that model the properties of real metagenomic communities such as the presence of similar species (strains) or differences in the relative abundance of bacteria. The developed methods were used to extract features. Machine learning model was trained in extracted features to classify samples from the test datasets. For comparison, the results of taxonomic annotation of samples using the Kraken2 program were used as features. It was shown that the accuracy of samples classification increased when using features obtained using the proposed methods in classification models compared to classification models trained on taxonomic features. The developed methods are useful for comparative analysis of metagenomic sequencing data and can form the basis of decision support systems, for example, in human diseases diagnostics based on gut microbiota sequencing data.

  • Open Access

    MetaFX: feature extraction from whole-genome metagenomic sequencing data

    by Artem Ivanov, Vladimir Popov, Maxim Morozov, Evgenii Olekhnovich, Vladimir Ulyantsev

    Motivation: Microbial communities consist of thousands of microorganisms and viruses and have a tight connection with an environment, such as gut microbiota modulation of host body metabolism. However, the direct relationship between the presence of certain microorganism and host state often remains unknown. Toolkits using reference-based approaches are limited to microbes present in databases. Reference-free methods often require enormous resources for metagenomic assembly or results in many poorly interpretable features based on k-mers. Results: Here we present MetaFX – an open-source library for feature extraction from whole-genome metagenomic sequencing data and classification of groups of samples. Using a large volume of metagenomic samples deposited in databases, MetaFX compares samples grouped by metadata criteria (e.g. disease, treatment, etc) and constructs genomic features distinct for certain types of communities. Features constructed based on statistical k-mer analysis and de Bruijn graphs partition. Those features are used in machine learning models for classification of novel samples. Extracted features can be visualised on de Bruijn graphs and annotated for providing biological insights. We demonstrate the utility of MetaFX by building classification models for 590 human gut samples with inflammatory bowel disease. Our results outperform the previous research disease prediction accuracy up to 17%, and improves classification results compared to taxonomic analysis by 9 ± 10% on average. Availability: MetaFX is a feature extraction toolkit applicable for metagenomic datasets analysis and samples classification. The source code, test data, and relevant information for MetaFX are freely accessible at https://github.com/ctlab/metafx under the MIT License. Contact: abivanov@itmo.ru

  • Open Access

    Systemic metabolic depletion of gut microbiome undermines responsiveness to melanoma immunotherapy

    by Natalia V Zakharevich, Maxim D Morozov, Vera A Kanaeva, Mikhail S Filippov, Tatyana I Zyubko, Artem B Ivanov, Vladimir I Ulyantsev, Ksenia M Klimina, Evgenii I Olekhnovich

    Immunotherapy has proven to be a boon for patients battling metastatic melanoma, significantly improving their clinical condition and overall quality of life. A compelling link between the composition of the gut microbiome and the efficacy of immunotherapy has been established in both animal models and human patients. However, the precise biological mechanisms by which gut microbes influence treatment outcomes remain poorly understood. Using a robust dataset of 680 fecal metagenomes from melanoma patients, a detailed catalog of metagenome-assembled genomes (MAGs) was constructed to explore the compositional and functional properties of the gut microbiome. Our study uncovered significant findings that deepen the understanding of the intricate relationship between gut microbes and the efficacy of melanoma immunotherapy. In particular, we discovered the specific metagenomic profile of patients with favorable treatment outcomes, characterized by a prevalence of MAGs with increased overall metabolic potential and proficiency in polysaccharide utilization, along with those responsible for cobalamin and amino acid production. Furthermore, our investigation of the biosynthetic pathways of short-chain fatty acids, known for their immunomodulatory role, revealed a differential abundance of these pathways among the specific MAGs. Among others, the cobalamin-dependent Wood–Ljungdahl pathway of acetate synthesis was directly associated with responsiveness to melanoma immunotherapy.


  • Open Access

    Systemic Metabolic Depletion of Intestine Microbiome Undermines Melanoma Immunotherapy Effectiveness

    by Natalia V. Zakharevich, Maxim D. Morozov, Vera A. Kanaeva, Artem B. Ivanov, Vladimir I. Ulyantsev, Ksenia M. Klimina, Evgenii I. Olekhnovich

    Immunotherapy has proven to be a boon for patients grappling with metastatic melanoma, significantly enhancing their clinical condition and overall quality of life. A compelling connection was discovered between the composition of the intestinal microbiome and the effectiveness of immunotherapy substantiated in both animal models and human patients. Nonetheless, the precise biological mechanisms through which gut microbes influence melanoma treatment outcomes remain poorly understood. This study conducted a high-resolution metagenomic meta-analysis, employing cutting-edge bioinformatics techniques including genome-resolved metagenomics, strain profiling, comparative genomics, and metabolic reconstruction. According to the obtained results, the systemic metabolic depletion of the gut microbiome causes a lack of response to immunotherapy. Specifically, the presence of bacteria adept at utilizing polysaccharides, as well as those responsible for cobalamin, amino acids, and fatty acids production, decreased in patients who experienced unfavorable treatment outcomes. In contrast, patients who had successful outcomes after immunotherapy exhibited a prevalence of amino acids and cobalamin prototrophs, while autotrophy in these substances characterized the microbiomes of patients with unsuccessful outcomes. The metabolic reconstruction of short-chain fatty acid biosynthesis pathways did not differentiate bacteria linked to treatment outcomes based on their ability to produce acetate, butyrate, or propionate. However, the cobalamin-dependent Wood-Ljungdahl pathway of acetate synthesis was directly associated with immunotherapy effectiveness.

  • Open Access

    Consistent Stool Metagenomic Biomarkers Associated with the Response To Melanoma Immunotherapy

    by Evgenii I. Olekhnovich, Artem B. Ivanov, Anna A. Babkina, Arseniy A. Sokolov, Vladimir I. Ulyantsev, Dmitry E. Fedorov, Elena N. Ilina

    In this study, we put together a list of potentially the most beneficial bacteria that were associated with a responsiveness to melanoma immunotherapy. Another important result of this study is the list of functional biomarkers of responsiveness to immunotherapy, which are dispersed among different bacterial species.


  • Open Access

    Reproducible stool metagenomic biomarkers linked to the melanoma immunotherapy positive outcome

    by Evgenii I. Olekhnovich, Artem B. Ivanov, Anna A. Babkina, Arseniy A. Sokolov, Vladimir I. Ulyantsev, Dmitry E. Fedorov, Elena N. Ilina

    The human gut microbiome plays an important role both in human’s health and disease. Recent studies have shown the undeniable influence of gut microbiota composition on cancer immunotherapy efficacy. However, these researches show a lack of consensus in defining reproducible metagenomic markers for a positive immunotherapy outcome. Accordingly, extended published data re-analysis may help reveal clearer associations between the composition of the gut microbiota and treatment response. In this study, we analyzed 358 stool metagenomes from 5 studies published earlier: 210 metagenomes from melanoma patients with positive immunotherapy outcome, 148 metagenomes from melanoma patients with negative immunotherapy outcome. The biomarkers were selected by the group comparison of patients’ stool samples with different treatment responses (47 responders vs 55 non-responders, 102 metagenomes). Selected biomarkers were verified using the available data describing the influence of the fecal microbiota transplantation on melanoma immunotherapy outcomes (9 donors, 6 responders, 19 non-responders, 256 metagenomes). According to our analysis, the resulting cross-study reproducible taxonomic biomarkers correspond to 12 Firmicutes, 4 Bacteroidetes, and 3 Actinobacteria. 140 gene groups were identified as reproducible functional biomarkers, including those potentially involved in production of immune-stimulating molecules and metabolites. In addition, we ranked taxonomic biomarkers by the number of functional biomarkers found in their metagenomic context. In other words, we predicted a list of the potential “most beneficial” bacteria for a positive response to melanoma immunotherapy. The obtained results can be used to make recommendations for the gut microbiota correction in cancer immunotherapy, and the resulting list of biomarkers can be considered for potential diagnostic ways for predicting melanoma immunotherapy outcome. Another important point is the functional biomarkers of positive immunotherapy outcome are distributed in different bacterial species that can explain the lack of consensus of defining melanoma immunotherapy beneficial species between different studies.