Anton Bushuiev
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Anton Bushuiev has a total of 42 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 - Josef Sivic
Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague
5 shared publications - Roman Bushuiev
Czech Academy of Sciences, Institute of Organic Chemistry and Biochemistry
5 shared publications Adéla Tajovská
Institute of Organic Chemistry and Biochemistry of the Czech Academy of Sciences, Flemingovo náměstí 2, Prague, Czech Republic
2 shared publicationsMilana Perković
Institute of Organic Chemistry and Biochemistry of the Czech Academy of Sciences, Flemingovo náměstí 2, Prague, Czech Republic
2 shared publicationsRaman Samusevich
Institute of Organic Chemistry and Biochemistry of the Czech Academy of Sciences, Prague, Czech Republic
2 shared publications
Latest Publications
- Open Access
Fast remote nucleotide sequence alignment with Riboseek
Structure prediction has reached RNA, where generating deep alignments is now the bottleneck. We developed Riboseek, a search and alignment tool for RNA and DNA that represents sequences as overlapping di-mers. Riboseek is more sensitive for homology detection than BLASTN and nhmmer, and generates alignments 250- and 376-fold faster than nhmmer and rMSA. With structure-aware realignment, it approaches rMSA’s base-pair recovery, while remaining 29-fold faster. We provide a web server and 1.7 million precomputed alignments for putatively structured RNAs. Riboseek is freely available at https://github.com/steineggerlab/riboseek .
Open AccessFast remote nucleotide sequence alignment with Riboseek
Structure prediction has reached RNA, where generating deep alignments is now the bottleneck. We developed Riboseek, a search and alignment tool for RNA and DNA that represents sequences as overlapping di-mers. Riboseek is more sensitive for homology detection than BLASTN and nhmmer, and generates alignments 250- and 376-fold faster than nhmmer and rMSA. With structure-aware realignment, it approaches rMSA’s base-pair recovery, while remaining 29-fold faster. We provide a web server and 1.7 million precomputed alignments for putatively structured RNAs. Riboseek is freely available at https://github.com/steineggerlab/riboseek .
- 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 PapersOpen Access
- 13 October 2023
- Published by American Chemical Society (ACS) in ACS Catalysis
- Vol. 13 (21) , 13863-13895
Machine Learning-Guided Protein Engineering
Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid in the discovery and annotation of promising enzymes, as well as in suggesting beneficial mutations for improving known targets. The field of machine learning for protein engineering is gathering steam, driven by recent success stories and notable progress in other areas. It already encompasses ambitious tasks such as understanding and predicting protein structure and function, catalytic efficiency, enantioselectivity, protein dynamics, stability, solubility, aggregation, and more. Nonetheless, the field is still evolving, with many challenges to overcome and questions to address. In this Perspective, we provide an overview of ongoing trends in this domain, highlight recent case studies, and examine the current limitations of machine learning-based methods. We emphasize the crucial importance of thorough experimental validation of emerging models before their use for rational protein design. We present our opinions on the fundamental problems and outline the potential directions for future research.
- 13 October 2023
- Published by American Chemical Society (ACS) in ACS Catalysis
- Vol. 13 (21) , 13863-13895
Top Cited PapersOpen AccessMachine Learning-Guided Protein Engineering
Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid in the discovery and annotation of promising enzymes, as well as in suggesting beneficial mutations for improving known targets. The field of machine learning for protein engineering is gathering steam, driven by recent success stories and notable progress in other areas. It already encompasses ambitious tasks such as understanding and predicting protein structure and function, catalytic efficiency, enantioselectivity, protein dynamics, stability, solubility, aggregation, and more. Nonetheless, the field is still evolving, with many challenges to overcome and questions to address. In this Perspective, we provide an overview of ongoing trends in this domain, highlight recent case studies, and examine the current limitations of machine learning-based methods. We emphasize the crucial importance of thorough experimental validation of emerging models before their use for rational protein design. We present our opinions on the fundamental problems and outline the potential directions for future research.