Marketa Jakubickova
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Marketa Jakubickova has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
Helena Vitkova
Department of Biomedical Engineering, Brno University of Technology
2 shared publicationsMartina Lengerova
Division of Clinical Microbiology and Immunology, Department of Laboratory Medicine, University Hospital Brno
2 shared publicationsMatej Bezdicek
Division of Clinical Microbiology and Immunology, Department of Laboratory Medicine, University Hospital Brno
2 shared publicationsJevhenij Vorochta
Department of Biomedical Engineering, Brno University of Technology
1 shared publicationKaterina Sabatova
Department of Biomedical Engineering, Brno University of Technology, Technicka 12, Brno, 61200, Czechia
1 shared publicationMichaela Zbudilova
Department of Biomedical Engineering, Brno University of Technology, Technicka 12, Brno, 61200, Czechia
1 shared publication
Latest Publications
- Open Access
- 18 February 2026
- Published by Frontiers Media SA in Frontiers in Microbiology
- Vol. 17, 1748934
Basecalling-free resistance gene identification using a hybrid transformer in raw nanopore signals
Nanopore sequencing enables real-time access to raw signal data, which brings new possibilities for rapid genomic diagnostics. However, current workflows still primarily rely on basecalling, a computationally intensive step that slows subsequent analysis and limits real-time use. In addition, most current approaches that work with raw signals focus on simple read-level classification tasks and are not designed to detect and localize specific genes, particularly complex genomic features such as antibiotic resistance genes (ARGs). Here, we show that the hybrid convolutional-transformer model, NanoResFormer, can detect clinically relevant ARGs directly from raw nanopore signals without basecalling. The model captures both local and long-range signal patterns and employs a floating-window strategy to process inputs of varying lengths efficiently. In proof-of-concept experiments, NanoResFormer achieved a sensitivity of 92.6% and a precision of over 93%, with short latency, enabling real-time resistome profiling already during sequencing. The proposed approach, therefore, provides rapid access to crucial information, accelerating decision-making in clinical diagnostics and pathogen surveillance.
- 18 February 2026
- Published by Frontiers Media SA in Frontiers in Microbiology
- Vol. 17, 1748934
Open AccessBasecalling-free resistance gene identification using a hybrid transformer in raw nanopore signals
Nanopore sequencing enables real-time access to raw signal data, which brings new possibilities for rapid genomic diagnostics. However, current workflows still primarily rely on basecalling, a computationally intensive step that slows subsequent analysis and limits real-time use. In addition, most current approaches that work with raw signals focus on simple read-level classification tasks and are not designed to detect and localize specific genes, particularly complex genomic features such as antibiotic resistance genes (ARGs). Here, we show that the hybrid convolutional-transformer model, NanoResFormer, can detect clinically relevant ARGs directly from raw nanopore signals without basecalling. The model captures both local and long-range signal patterns and employs a floating-window strategy to process inputs of varying lengths efficiently. In proof-of-concept experiments, NanoResFormer achieved a sensitivity of 92.6% and a precision of over 93%, with short latency, enabling real-time resistome profiling already during sequencing. The proposed approach, therefore, provides rapid access to crucial information, accelerating decision-making in clinical diagnostics and pathogen surveillance.
- Open Access
- 1 January 2025
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 27, 4753-4759
MethylomeMiner: A novel tool for high-resolution analysis of bacterial methylation patterns from nanopore sequencing
DNA methylation plays a key role in gene regulation, genome stability, bacterial adaptation, and many other essential cellular processes. Thanks to nanopore sequencing technology, it is now possible to detect these modifications during sequencing without any prior chemical treatment. However, methylation data processing and their interpretation in a biological context remain challenging as there are no convenient and easy-to-use tools available for this purpose. Therefore, here, we present a simple Python-based tool, MethylomeMiner, to process methylation calls from nanopore sequencing. The tool allows high-confidence methylation sites to be selected based on coverage and methylation rate and assigned to coding or non-coding regions using genome annotation. In addition, the tool supports population-level analysis using pangenome data to compare methylation patterns across multiple bacterial genomes. Altogether, MethylomeMiner provides a straightforward and reproducible workflow that can be easily integrated into existing analyses and helps uncover the functional roles of DNA methylation in bacterial genomes.
- 1 January 2025
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 27, 4753-4759
Open AccessMethylomeMiner: A novel tool for high-resolution analysis of bacterial methylation patterns from nanopore sequencing
DNA methylation plays a key role in gene regulation, genome stability, bacterial adaptation, and many other essential cellular processes. Thanks to nanopore sequencing technology, it is now possible to detect these modifications during sequencing without any prior chemical treatment. However, methylation data processing and their interpretation in a biological context remain challenging as there are no convenient and easy-to-use tools available for this purpose. Therefore, here, we present a simple Python-based tool, MethylomeMiner, to process methylation calls from nanopore sequencing. The tool allows high-confidence methylation sites to be selected based on coverage and methylation rate and assigned to coding or non-coding regions using genome annotation. In addition, the tool supports population-level analysis using pangenome data to compare methylation patterns across multiple bacterial genomes. Altogether, MethylomeMiner provides a straightforward and reproducible workflow that can be easily integrated into existing analyses and helps uncover the functional roles of DNA methylation in bacterial genomes.