Roman Bushuiev
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Roman Bushuiev has a total of 86 co-authors. Here are the top co-authors by number of shared publications:
- Tomáš Pluskal
Institute of Organic Chemistry and Biochemistry of the Czech Academy of Sciences, Prague, Czech Republic
6 shared publications - Anton Bushuiev
Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, Prague, Czechia
5 shared publications - Josef Sivic
Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague
4 shared publications - Teo Hebra
Czech Academy of Sciences, Institute of Organic Chemistry and Biochemistry
3 shared publications Tito Damiani
Czech Academy of Sciences, Institute of Organic Chemistry and Biochemistry
3 shared publicationsAdéla Tajovská
Institute of Organic Chemistry and Biochemistry of the Czech Academy of Sciences, Flemingovo náměstí 2, Prague, Czech Republic
2 shared publications
Latest Publications
- Open Access
- 8 September 2026
- Published by American Chemical Society (ACS) in ChemRxiv
Accelerated characterization of active natural extracts with single-step microfractionation coupled to mass spectrometry and bioassays
Microfractionation is a prominent alternative for the discovery and characterization of bioactive natural products in complex extracts (e.g., plant, fungal, or microbial); however, the method faces limitations as it requires arduous scale-up for full structural characterization of selected constituents. Furthermore, the integration of microfractionation data with metabolomic data is still a complex and tedious process. To circumvent current limitations, we developed a single-step (i.e., no gram-scale isolation or orthogonal chromatographic steps) microfractionation method that delivers 94 fractions in a 96-deep-well plate, combining biological and computational metabolomic readouts at the milligram scale. Fractionation is coupled to a single-quadrupole mass analyzer, which enables integration with high-resolution metabolomic outputs through an open-source graphical interface we developed. To illustrate the method’s performance, we applied it to characterize extracts from seven plant species — Macleaya microcarpa , Macleaya cordata , Ruta corsica, Thymus camphoratus, Helleborus foetidus, Hypericum hookerianum, and Hypericum olympicum — spanning different extract complexities and biological activities. Across nine independent experiments, totaling 151 sequential injections, we obtained high chromatographic reproducibility. Throughout the study, we injected no more than 10 mg of crude extract per fractionation, and we were able to resolve 17 structures with 1 H NMR dereplication. Furthermore, we associated fraction-level bioactivity with molecular classes and candidate molecules. Our high-throughput, milligram-scale workflow reduces the need for scale-up, making it a practical first step before pursuing gram-scale isolation efforts.
- 8 September 2026
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessAccelerated characterization of active natural extracts with single-step microfractionation coupled to mass spectrometry and bioassays
Microfractionation is a prominent alternative for the discovery and characterization of bioactive natural products in complex extracts (e.g., plant, fungal, or microbial); however, the method faces limitations as it requires arduous scale-up for full structural characterization of selected constituents. Furthermore, the integration of microfractionation data with metabolomic data is still a complex and tedious process. To circumvent current limitations, we developed a single-step (i.e., no gram-scale isolation or orthogonal chromatographic steps) microfractionation method that delivers 94 fractions in a 96-deep-well plate, combining biological and computational metabolomic readouts at the milligram scale. Fractionation is coupled to a single-quadrupole mass analyzer, which enables integration with high-resolution metabolomic outputs through an open-source graphical interface we developed. To illustrate the method’s performance, we applied it to characterize extracts from seven plant species — Macleaya microcarpa , Macleaya cordata , Ruta corsica, Thymus camphoratus, Helleborus foetidus, Hypericum hookerianum, and Hypericum olympicum — spanning different extract complexities and biological activities. Across nine independent experiments, totaling 151 sequential injections, we obtained high chromatographic reproducibility. Throughout the study, we injected no more than 10 mg of crude extract per fractionation, and we were able to resolve 17 structures with 1 H NMR dereplication. Furthermore, we associated fraction-level bioactivity with molecular classes and candidate molecules. Our high-throughput, milligram-scale workflow reduces the need for scale-up, making it a practical first step before pursuing gram-scale isolation efforts.
- Open Access
- 3 July 2026
- Published by American Chemical Society (ACS) in ChemRxiv
Accelerated characterization of active natural extracts with single-step microfractionation coupled to mass spectrometry and bioassays
Microfractionation is a prominent alternative for the discovery and characterization of bioactive natural products in complex extracts (e.g., plant, fungal, or microbial); however, the method faces limitations as it requires arduous scale-up for complete characterization of molecules. Furthermore, the integration of microfractionation data with metabolomic data is still a complex and tedious process. To circumvent current limitations, we developed a microfractionation method allowing an integrated, reproducible, milligram-scale, 96-deep-well plate framework that combines biological and computational metabolomic readouts. Fractionation is coupled to a single quadrupole mass analyzer, which enables integration with high-resolution metabolomic outputs using adaptable Python scripts. To illustrate the method performances, we applied it to characterize extracts from 7 plants -- Macleya microcarpa, Macleya cordata, Ruta corsica, Thymus camphoratus, Helleborus foetidus, Hypericum hookerianum, and Hypericum olympicum -- spanning different extract complexity and biological activities. Over nine independent experiments, totaling 151 sequential injections, we obtained high reproducibility. Across the study, we utilized no more than 10 mg of crude extract per fractionation and we were able to isolate 17 compounds up to 1H NMR dereplication. Furthermore, we were able to link molecular class and specific molecules to bioactivity found in active extracts. Lastly, to facilitate the adoption of this workflow, we created a user-friendly graphical user interface. Our high-throughput, milligram-scale workflow reduces the need for scale-up and is broadly applicable to natural extracts and biological systems, thus allowing for rapid characterization of natural extracts.
- 3 July 2026
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessAccelerated characterization of active natural extracts with single-step microfractionation coupled to mass spectrometry and bioassays
Microfractionation is a prominent alternative for the discovery and characterization of bioactive natural products in complex extracts (e.g., plant, fungal, or microbial); however, the method faces limitations as it requires arduous scale-up for complete characterization of molecules. Furthermore, the integration of microfractionation data with metabolomic data is still a complex and tedious process. To circumvent current limitations, we developed a microfractionation method allowing an integrated, reproducible, milligram-scale, 96-deep-well plate framework that combines biological and computational metabolomic readouts. Fractionation is coupled to a single quadrupole mass analyzer, which enables integration with high-resolution metabolomic outputs using adaptable Python scripts. To illustrate the method performances, we applied it to characterize extracts from 7 plants -- Macleya microcarpa, Macleya cordata, Ruta corsica, Thymus camphoratus, Helleborus foetidus, Hypericum hookerianum, and Hypericum olympicum -- spanning different extract complexity and biological activities. Over nine independent experiments, totaling 151 sequential injections, we obtained high reproducibility. Across the study, we utilized no more than 10 mg of crude extract per fractionation and we were able to isolate 17 compounds up to 1H NMR dereplication. Furthermore, we were able to link molecular class and specific molecules to bioactivity found in active extracts. Lastly, to facilitate the adoption of this workflow, we created a user-friendly graphical user interface. Our high-throughput, milligram-scale workflow reduces the need for scale-up and is broadly applicable to natural extracts and biological systems, thus allowing for rapid characterization of natural extracts.
- Open Access
- 11 July 2025
- Published by Springer Nature in BMC Bioinformatics
- Vol. 26 (1) , 1-17
An evaluation methodology for machine learning-based tandem mass spectra similarity prediction
Background: Untargeted tandem mass spectrometry serves as a scalable solution for the organization of small molecules. One of the most prevalent techniques for analyzing the acquired tandem mass spectrometry data (MS/MS) - called molecular networking - organizes and visualizes putatively structurally related compounds. However, a key bottleneck of this approach is the comparison of MS/MS spectra used to identify nearby structural neighbors. Machine learning (ML) approaches have emerged as a promising technique to predict structural similarity from MS/MS that may surpass the current state-of-the-art algorithmic methods. However, the comparison between these different ML methods remains a challenge because there is a lack of standardization to benchmark, evaluate, and compare MS/MS similarity methods, and there are no methods that address data leakage between training and test data in order to analyze model generalizability. Result: In this work, we present the creation of a new evaluation methodology using a train/test split that allows for the evaluation of machine learning models at varying degrees of structural similarity between training and test sets. We also introduce a training and evaluation framework that measures prediction accuracy on domain-inspired annotation and retrieval metrics designed to mirror real-world applications. We further show how two alternative training methods that leverage MS specific insights (e.g., similar instrumentation, collision energy, adduct) affect method performance and demonstrate the orthogonality of the proposed metrics. We especially highlight the role that collision energy plays in prediction errors. Finally, we release a continually updated version of our dataset online along with our data cleaning and splitting pipelines for community use. Conclusion: It is our hope that this benchmark will serve as the basis of development for future machine learning approaches in MS/MS similarity and facilitate comparison between models. We anticipate that the introduced set of evaluation metrics allows for a better reflection of practical performance.
- 11 July 2025
- Published by Springer Nature in BMC Bioinformatics
- Vol. 26 (1) , 1-17
Open AccessAn evaluation methodology for machine learning-based tandem mass spectra similarity prediction
Background: Untargeted tandem mass spectrometry serves as a scalable solution for the organization of small molecules. One of the most prevalent techniques for analyzing the acquired tandem mass spectrometry data (MS/MS) - called molecular networking - organizes and visualizes putatively structurally related compounds. However, a key bottleneck of this approach is the comparison of MS/MS spectra used to identify nearby structural neighbors. Machine learning (ML) approaches have emerged as a promising technique to predict structural similarity from MS/MS that may surpass the current state-of-the-art algorithmic methods. However, the comparison between these different ML methods remains a challenge because there is a lack of standardization to benchmark, evaluate, and compare MS/MS similarity methods, and there are no methods that address data leakage between training and test data in order to analyze model generalizability. Result: In this work, we present the creation of a new evaluation methodology using a train/test split that allows for the evaluation of machine learning models at varying degrees of structural similarity between training and test sets. We also introduce a training and evaluation framework that measures prediction accuracy on domain-inspired annotation and retrieval metrics designed to mirror real-world applications. We further show how two alternative training methods that leverage MS specific insights (e.g., similar instrumentation, collision energy, adduct) affect method performance and demonstrate the orthogonality of the proposed metrics. We especially highlight the role that collision energy plays in prediction errors. Finally, we release a continually updated version of our dataset online along with our data cleaning and splitting pipelines for community use. Conclusion: It is our hope that this benchmark will serve as the basis of development for future machine learning approaches in MS/MS similarity and facilitate comparison between models. We anticipate that the introduced set of evaluation metrics allows for a better reflection of practical performance.
- Top Cited PapersOpen Access
- 23 May 2025
- Published by Springer Nature in Nature Biotechnology
- Vol. 44 (4) , 630-640
Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS
Characterizing biological and environmental samples at a molecular level primarily uses tandem mass spectroscopy (MS/MS), yet the interpretation of tandem mass spectra from untargeted metabolomics experiments remains a challenge. Existing computational methods for predictions from mass spectra rely on limited spectral libraries and on hard-coded human expertise. Here we introduce a transformer-based neural network pre-trained in a self-supervised way on millions of unannotated tandem mass spectra from our GNPS Experimental Mass Spectra (GeMS) dataset mined from the MassIVE GNPS repository. We show that pre-training our model to predict masked spectral peaks and chromatographic retention orders leads to the emergence of rich representations of molecular structures, which we named Deep Representations Empowering the Annotation of Mass Spectra (DreaMS). Further fine-tuning the neural network yields state-of-the-art performance across a variety of tasks. We make our new dataset and model available to the community and release the DreaMS Atlas—a molecular network of 201 million MS/MS spectra constructed using DreaMS annotations.
- 23 May 2025
- Published by Springer Nature in Nature Biotechnology
- Vol. 44 (4) , 630-640
Top Cited PapersOpen AccessSelf-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS
Characterizing biological and environmental samples at a molecular level primarily uses tandem mass spectroscopy (MS/MS), yet the interpretation of tandem mass spectra from untargeted metabolomics experiments remains a challenge. Existing computational methods for predictions from mass spectra rely on limited spectral libraries and on hard-coded human expertise. Here we introduce a transformer-based neural network pre-trained in a self-supervised way on millions of unannotated tandem mass spectra from our GNPS Experimental Mass Spectra (GeMS) dataset mined from the MassIVE GNPS repository. We show that pre-training our model to predict masked spectral peaks and chromatographic retention orders leads to the emergence of rich representations of molecular structures, which we named Deep Representations Empowering the Annotation of Mass Spectra (DreaMS). Further fine-tuning the neural network yields state-of-the-art performance across a variety of tasks. We make our new dataset and model available to the community and release the DreaMS Atlas—a molecular network of 201 million MS/MS spectra constructed using DreaMS annotations.
- Open Access
MARTS-DB: A Database of Mechanisms And Reactions of Terpene Synthases
Terpene synthases (TPS) are enzymes that catalyze some of the most complex reactions in nature, the cyclizations of terpenes, the carbon backbones to the largest group of natural products, terpenoids. On average, more than half of the carbon atoms in a terpene scaffold undergo a change in connectivity or configuration during these enzymatic cascades. Understanding TPS reaction mechanisms remains challenging, often requiring intricate computational modeling and isotopic labeling studies. Moreover, the relationship between TPS sequence and catalytic function is difficult to decipher, and data-driven approaches remain limited due to the lack of comprehensive, high-quality data sources. To address this gap, we introduce the Mechanisms And Reactions of Terpene Synthases DataBase (MARTS-DB)—a manually curated, structured, and searchable database that integrates TPS enzymes, the terpenes they produce, and their detailed reaction mechanisms. MARTS-DB includes over 2,600 reactions catalyzed by 1,334 annotated enzymes from across all domains of life. Where available, reaction mechanisms are mapped as stepwise cascades. Accessible at https://www.marts-db.org, the database provides advanced search functionality and supports full dataset download in machine-readable formats. It also encourages community contributions to promote continuous growth. By enabling systematic exploration of TPS catalysis, MARTS-DB opens new avenues for computational analysis and machine learning, as recently demonstrated in the prediction of novel terpene synthases.
Open AccessMARTS-DB: A Database of Mechanisms And Reactions of Terpene Synthases
Terpene synthases (TPS) are enzymes that catalyze some of the most complex reactions in nature, the cyclizations of terpenes, the carbon backbones to the largest group of natural products, terpenoids. On average, more than half of the carbon atoms in a terpene scaffold undergo a change in connectivity or configuration during these enzymatic cascades. Understanding TPS reaction mechanisms remains challenging, often requiring intricate computational modeling and isotopic labeling studies. Moreover, the relationship between TPS sequence and catalytic function is difficult to decipher, and data-driven approaches remain limited due to the lack of comprehensive, high-quality data sources. To address this gap, we introduce the Mechanisms And Reactions of Terpene Synthases DataBase (MARTS-DB)—a manually curated, structured, and searchable database that integrates TPS enzymes, the terpenes they produce, and their detailed reaction mechanisms. MARTS-DB includes over 2,600 reactions catalyzed by 1,334 annotated enzymes from across all domains of life. Where available, reaction mechanisms are mapped as stepwise cascades. Accessible at https://www.marts-db.org, the database provides advanced search functionality and supports full dataset download in machine-readable formats. It also encourages community contributions to promote continuous growth. By enabling systematic exploration of TPS catalysis, MARTS-DB opens new avenues for computational analysis and machine learning, as recently demonstrated in the prediction of novel terpene synthases.
- Open Access
- 10 April 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS
Characterizing biological and environmental samples at a molecular level primarily uses tandem mass spectroscopy (MS/MS), yet the interpretation of tandem mass spectra from untargeted metabolomics experiments remains a challenge. Existing computational methods for predictions from mass spectra rely on limited spectral libraries and on hard-coded human expertise. Here, we introduce a transformer-based neural network pre-trained in a self-supervised way on millions of unannotated tandem mass spectra from our GNPS Experimental Mass Spectra (GeMS) dataset mined from the MassIVE GNPS repository. We show that pre-training our model to predict masked spectral peaks and chromatographic retention orders leads to the emergence of rich representations of molecular structures, which we name Deep Representations Empowering the Annotation of Mass Spectra (DreaMS). Further fine-tuning the neural network yields state-of-the-art performance across a variety of tasks. We make our new dataset and model available to the community and release the DreaMS Atlas -- a molecular network of 201 million MS/MS spectra constructed using DreaMS annotations.
- 10 April 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessSelf-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS
Characterizing biological and environmental samples at a molecular level primarily uses tandem mass spectroscopy (MS/MS), yet the interpretation of tandem mass spectra from untargeted metabolomics experiments remains a challenge. Existing computational methods for predictions from mass spectra rely on limited spectral libraries and on hard-coded human expertise. Here, we introduce a transformer-based neural network pre-trained in a self-supervised way on millions of unannotated tandem mass spectra from our GNPS Experimental Mass Spectra (GeMS) dataset mined from the MassIVE GNPS repository. We show that pre-training our model to predict masked spectral peaks and chromatographic retention orders leads to the emergence of rich representations of molecular structures, which we name Deep Representations Empowering the Annotation of Mass Spectra (DreaMS). Further fine-tuning the neural network yields state-of-the-art performance across a variety of tasks. We make our new dataset and model available to the community and release the DreaMS Atlas -- a molecular network of 201 million MS/MS spectra constructed using DreaMS annotations.
- Open Access
Structure-enabled enzyme function prediction unveils elusive terpenoid biosynthesis in archaea
The exponential growth of uncharacterized enzyme sequences in genomic repositories demands novel tools for functional annotation. Here, we combined alignment-driven structural domain analysis with protein language models to create EnzymeExplorer, a machine-learning pipeline for enzyme function prediction. We applied this approach to terpene synthases, which present an ideal model case because they catalyze complex carbocationic rearrangements whose product outcomes cannot be predicted from active site residues alone. We detected new structural domains and achieved state-of-the-art performance on function prediction. By analyzing the UniRef90 database, we identified terpene synthases overlooked by current computational methods. Remarkably, we uncovered and experimentally validated the widespread biosynthesis of terpenoids in archaea. Our approach offers a powerful framework for characterizing enzyme “dark matter” in the rapidly expanding genomic and metagenomic datasets.
Open AccessStructure-enabled enzyme function prediction unveils elusive terpenoid biosynthesis in archaea
The exponential growth of uncharacterized enzyme sequences in genomic repositories demands novel tools for functional annotation. Here, we combined alignment-driven structural domain analysis with protein language models to create EnzymeExplorer, a machine-learning pipeline for enzyme function prediction. We applied this approach to terpene synthases, which present an ideal model case because they catalyze complex carbocationic rearrangements whose product outcomes cannot be predicted from active site residues alone. We detected new structural domains and achieved state-of-the-art performance on function prediction. By analyzing the UniRef90 database, we identified terpene synthases overlooked by current computational methods. Remarkably, we uncovered and experimentally validated the widespread biosynthesis of terpenoids in archaea. Our approach offers a powerful framework for characterizing enzyme “dark matter” in the rapidly expanding genomic and metagenomic datasets.
- Top Cited Papers
- 1 March 2023
- Published by Springer Nature in Nature Biotechnology
- Vol. 41 (4) , 447-449
Integrative analysis of multimodal mass spectrometry data in MZmine 3
- 1 March 2023
- Published by Springer Nature in Nature Biotechnology
- Vol. 41 (4) , 447-449
Top Cited PapersIntegrative analysis of multimodal mass spectrometry data in MZmine 3