MassGenie: A Transformer-Based Deep Learning Method for Identifying Small Molecules from Their Mass Spectra

Artificial Intelligence in Metabolomics: A Current Review

Metabolomics and artificial intelligence (AI) form a synergistic partnership. Metabolomics generates large datasets comprising hundreds to thousands of metabolites with complex relationships. AI, aiming to mimic human intelligence through computational modeling, possesses extraordinary capabilities for big data analysis. In this review, we provide a recent overview of the methodologies and applications of AI in metabolomics studies in the context of systems biology and human health. We first introduce the AI concept, history, and key algorithms for machine learning and deep learning, summarizing their strengths and weaknesses. We then discuss studies that have successfully used AI across different aspects of metabolomic analysis, including analytical detection, data preprocessing, biomarker discovery, predictive modeling, and multi-omics data integration. Lastly, we discuss the existing challenges and future perspectives in this rapidly evolving field. Despite limitations and challenges, the combination of metabolomics and AI holds great promises for revolutionary advancements in enhancing human health.

Recent Developments in Machine Learning for Mass Spectrometry

Statistical analysis and modeling of mass spectrometry (MS) data have a long and rich history with several modern MS-based applications using statistical and chemometric methods. Recently, machine learning (ML) has experienced a renaissance due to advents in computational hardware and the development of new algorithms for artificial neural networks (ANN) and deep learning architectures. Moreover, recent successes of new ANN and deep learning architectures in several areas of science, engineering, and society have further strengthened the ML field. Importantly, modern ML methods and architectures have enabled new approaches for tasks related to MS that are now widely adopted in several popular MS-based subdisciplines, such as mass spectrometry imaging and proteomics. Herein, we aim to provide an introductory summary of the practical aspects of ML methodology relevant to MS. Additionally, we seek to provide an up-to-date review of the most recent developments in ML integration with MS-based techniques while also providing critical insights into the future direction of the field.

Application of Transformers in Cheminformatics

By accelerating time-consuming processes with high efficiency, computing has become an essential part of many modern chemical pipelines. Machine learning is a class of computing methods that can discover patterns within chemical data and utilize this knowledge for a wide variety of downstream tasks, such as property prediction or substance generation. The complex and diverse chemical space requires complex machine learning architectures with great learning power. Recently, learning models based on transformer architectures have revolutionized multiple domains of machine learning, including natural language processing and computer vision. Naturally, there have been ongoing endeavors in adopting these techniques to the chemical domain, resulting in a surge of publications within a short period. The diversity of chemical structures, use cases, and learning models necessitate a comprehensive summarization of existing works. In this paper, we review recent innovations in adapting transformers to solve learning problems in chemistry. Because chemical data is diverse and complex, we structure our discussion based on chemical representations. Specifically, we highlight the strengths and weaknesses of each representation, the current progress of adapting transformer architectures, and future directions.

Mechanotransducive surfaces for enhanced cell osteogenesis, a review

Novel strategies employing mechano-transducing materials eliciting biological outcomes have recently emerged for controlling cellular behaviour. Targeted cellular responses are achieved by manipulating physical, chemical, or biochemical modification of material properties. Advances in techniques such as nanopatterning, chemical modification, biochemical molecule embedding, force-tuneable materials, and artificial extracellular matrices are helping understand cellular mechanotransduction. Collectively, these strategies manipulate cellular sensing and regulate signalling cascades including focal adhesions, YAP-TAZ transcription factors, and multiple osteogenic pathways. In this minireview, we are providing a summary of the influence that these materials, particularly titanium-based orthopaedic materials, have on cells. We also highlight recent complementary methodological developments including, but not limited to, the use of metabolomics for identification of active biomolecules that drive cellular differentiation.

A Perspective on How Fibrinaloid Microclots and Platelet Pathology May be Applied in Clinical Investigations

Microscopy imaging has enabled us to establish the presence of fibrin(ogen) amyloid (fibrinaloid) microclots in a range of chronic, inflammatory diseases. Microclots may also be induced by a variety of purified substances, often at very low concentrations. These molecules include bacterial inflammagens, serum amyloid A, and the S1 spike protein of severe acute respiratory syndrome coronavirus 2. Here, we explore which of the properties of these microclots might be used to contribute to differential clinical diagnoses and prognoses of the various diseases with which they may be associated. Such properties include distributions in their size and number before and after the addition of exogenous thrombin, their spectral properties, the diameter of the fibers of which they are made, their resistance to proteolysis by various proteases, their cross-seeding ability, and the concentration dependence of their ability to bind small molecules including fluorogenic amyloid stains. Measuring these microclot parameters, together with microscopy imaging itself, along with methodologies like proteomics and imaging flow cytometry, as well as more conventional assays such as those for cytokines, might open up the possibility of a much finer use of these microclot properties in generative methods for a future where personalized medicine will be standard procedures in all clotting pathology disease diagnoses.

TransExION: a transformer based explainable similarity metric for comparing IONS in tandem mass spectrometry

Small molecule identification is a crucial task in analytical chemistry and life sciences. One of the most commonly used technologies to elucidate small molecule structures is mass spectrometry. Spectral library search of product ion spectra (MS/MS) is a popular strategy to identify or find structural analogues. This approach relies on the assumption that spectral similarity and structural similarity are correlated. However, popular spectral similarity measures, usually calculated based on identical fragment matches between the MS/MS spectra, do not always accurately reflect the structural similarity. In this study, we propose TransExION, a Transformer based Explainable similarity metric for IONS. TransExION detects related fragments between MS/MS spectra through their mass difference and uses these to estimate spectral similarity. These related fragments can be nearly identical, but can also share a substructure. TransExION also provides a post-hoc explanation of its estimation, which can be used to support scientists in evaluating the spectral library search results and thus in structure elucidation of unknown molecules. Our model has a Transformer based architecture and it is trained on the data derived from GNPS MS/MS libraries. The experimental results show that it improves existing spectral similarity measures in searching and interpreting structural analogues as well as in molecular networking. SCIENTIFIC CONTRIBUTION: We propose a transformer-based spectral similarity metrics that improves the comparison of small molecule tandem mass spectra. We provide a post hoc explanation that can serve as a good starting point for unknown spectra annotation based on database spectra.

Deep Learning-Assisted Spectrum-Structure Correlation: State-of-the-Art and Perspectives

Spectrum-structure correlation is playing an increasingly crucial role in spectral analysis and has undergone significant development in recent decades. With the advancement of spectrometers, the high-throughput detection triggers the explosive growth of spectral data, and the research extension from small molecules to biomolecules accompanies massive chemical space. Facing the evolving landscape of spectrum-structure correlation, conventional chemometrics becomes ill-equipped, and deep learning assisted chemometrics rapidly emerges as a flourishing approach with superior ability of extracting latent features and making precise predictions. In this review, the molecular and spectral representations and fundamental knowledge of deep learning are first introduced. We then summarize the development of how deep learning assist to establish the correlation between spectrum and molecular structure in the recent 5 years, by empowering spectral prediction (i.e., forward structure-spectrum correlation) and further enabling library matching and de novo molecular generation (i.e., inverse spectrum-structure correlation). Finally, we highlight the most important open issues persisted with corresponding potential solutions. With the fast development of deep learning, it is expected to see ultimate solution of establishing spectrum-structure correlation soon, which would trigger substantial development of various disciplines.

Structural annotation of unknown molecules in a miniaturized mass spectrometer based on a transformer enabled fragment tree method

Structural annotation of small molecules in tandem mass spectrometry has always been a central challenge in mass spectrometry analysis, especially using a miniaturized mass spectrometer for on-site testing. Here, we propose the Transformer enabled Fragment Tree (TeFT) method, which combines various types of fragmentation tree models and a deep learning Transformer module. It is aimed to generate the specific structure of molecules de novo solely from mass spectrometry spectra. The evaluation results on different open-source databases indicated that the proposed model achieved remarkable results in that the majority of molecular structures of compounds in the test can be successfully recognized. Also, the TeFT has been validated on a miniaturized mass spectrometer with low-resolution spectra for 16 flavonoid alcohols, achieving complete structure prediction for 8 substances. Finally, TeFT confirmed the structure of the compound contained in a Chinese medicine substance called the Anweiyang capsule. These results indicate that the TeFT method is suitable for annotating fragmentation peaks with clear fragmentation rules, particularly when applied to on-site mass spectrometry with lower mass resolution.

BitterMasS: Predicting Bitterness from Mass Spectra

Bitter compounds are common in nature and among drugs. Previously, machine learning tools were developed to predict bitterness from the chemical structure. However, known structures are estimated to represent only 5-10% of the metabolome, and the rest remain unassigned or "dark". We present BitterMasS, a Random Forest classifier that was trained on 5414 experimental mass spectra of bitter and nonbitter compounds, achieving precision = 0.83 and recall = 0.90 for an internal test set. Next, the model was tested against spectra newly extracted from the literature 106 bitter and nonbitter compounds and for additional spectra measured for 26 compounds. For these external test cases, BitterMasS exhibited 67% precision and 93% recall for the first and 58% accuracy and 99% recall for the second. The spectrum-bitterness prediction strategy was more effective than the spectrum-structure-bitterness prediction strategy and covered more compounds. These encouraging results suggest that BitterMasS can be used to predict bitter compounds in the metabolome without the need for structural assignment of individual molecules. This may enable identification of bitter compounds from metabolomics analyses, for comparing potential bitterness levels obtained by different treatments of samples and for monitoring bitterness changes overtime.

Urban and agricultural influences on the coastal dissolved organic matter pool in the Algoa Bay estuaries

While anthropogenic pollution is a major threat to aquatic ecosystem health, our knowledge of the presence of xenobiotics in coastal Dissolved Organic Matter (DOM) is still relatively poor. This is especially true for water bodies in the Global South with limited information gained mostly from targeted studies that rely on comparison with authentic standards. In recent years, non-targeted tandem mass spectrometry has emerged as a powerful tool to collectively detect and identify pollutants and biogenic DOM components in the environment, but this approach has yet to be widely utilized for monitoring ecologically important aquatic systems. In this study we compared the DOM composition of Algoa Bay, Eastern Cape, South Africa, and its two estuaries. The Swartkops Estuary is highly urbanized and severely impacted by anthropogenic pollution, while the Sundays Estuary is impacted by commercial agriculture in its catchment. We employed solid-phase extraction followed by liquid chromatography tandem mass spectrometry to annotate more than 200 pharmaceuticals, pesticides, urban xenobiotics, and natural products based on spectral matching. The identification with authentic standards confirmed the presence of methamphetamine, carbamazepine, sulfamethoxazole, N-acetylsulfamethoxazole, imazapyr, caffeine and hexa(methoxymethyl)melamine, and allowed semi-quantitative estimations for annotated xenobiotics. The Swartkops Estuary DOM composition was strongly impacted by features annotated as urban pollutants including pharmaceuticals such as melamines and antiretrovirals. By contrast, the Sundays Estuary exhibited significant enrichment of molecules annotated as agrochemicals widely used in the citrus farming industry, with predicted concentrations for some of them exceeding predicted no-effect concentrations. This study provides new insight into anthropogenic impact on the Algoa Bay system and demonstrates the utility of non-targeted tandem mass spectrometry as a sensitive tool for assessing the health of ecologically important coastal ecosystems and will serve as a valuable foundation for strategizing long-term monitoring efforts.

Computational methods for processing and interpreting mass spectrometry-based metabolomics

Metabolomics has emerged as an indispensable tool for exploring complex biological questions, providing the ability to investigate a substantial portion of the metabolome. However, the vast complexity and structural diversity intrinsic to metabolites imposes a great challenge for data analysis and interpretation. Liquid chromatography mass spectrometry (LC-MS) stands out as a versatile technique offering extensive metabolite coverage. In this mini-review, we address some of the hurdles posed by the complex nature of LC-MS data, providing a brief overview of computational tools designed to help tackling these challenges. Our focus centers on two major steps that are essential to most metabolomics investigations: the translation of raw data into quantifiable features, and the extraction of structural insights from mass spectra to facilitate metabolite identification. By exploring current computational solutions, we aim at providing a critical overview of the capabilities and constraints of mass spectrometry-based metabolomics, while introduce some of the most recent trends in data processing and analysis within the field.

Advances in the Application of Artificial Intelligence-Based Spectral Data Interpretation: A Perspective

The interpretation of spectral data, including mass, nuclear magnetic resonance, infrared, and ultraviolet-visible spectra, is critical for obtaining molecular structural information. The development of advanced sensing technology has multiplied the amount of available spectral data. Chemical experts must use basic principles corresponding to the spectral information generated by molecular fragments and functional groups. This is a time-consuming process that requires a solid professional knowledge base. In recent years, the rapid development of computer science and its applications in cheminformatics and the emergence of computer-aided expert systems have greatly reduced the difficulty in analyzing large quantities of data. For expert systems, however, the problem-solving strategy must be known in advance or extracted by human experts and translated into algorithms. Gratifyingly, the development of artificial intelligence (AI) methods has shown great promise for solving such problems. Traditional algorithms, including the latest neural network algorithms, have shown great potential for both extracting useful information and processing massive quantities of data. This Perspective highlights recent innovations covering all of the emerging AI-based spectral interpretation techniques. In addition, the main limitations and current obstacles are presented, and the corresponding directions for further research are proposed. Moreover, this Perspective gives the authors' personal outlook on the development and future applications of spectral interpretation.

Recent advances in mass spectrometry-based computational metabolomics

The computational metabolomics field brings together computer scientists, bioinformaticians, chemists, clinicians, and biologists to maximize the impact of metabolomics across a wide array of scientific and medical disciplines. The field continues to expand as modern instrumentation produces datasets with increasing complexity, resolution, and sensitivity. These datasets must be processed, annotated, modeled, and interpreted to enable biological insight. Techniques for visualization, integration (within or between omics), and interpretation of metabolomics data have evolved along with innovation in the databases and knowledge resources required to aid understanding. In this review, we highlight recent advances in the field and reflect on opportunities and innovations in response to the most pressing challenges. This review was compiled from discussions from the 2022 Dagstuhl seminar entitled "Computational Metabolomics: From Spectra to Knowledge".

MS2Query: reliable and scalable MS2 mass spectra-based analogue search

Metabolomics-driven discoveries of biological samples remain hampered by the grand challenge of metabolite annotation and identification. Only few metabolites have an annotated spectrum in spectral libraries; hence, searching only for exact library matches generally returns a few hits. An attractive alternative is searching for so-called analogues as a starting point for structural annotations; analogues are library molecules which are not exact matches but display a high chemical similarity. However, current analogue search implementations are not yet very reliable and relatively slow. Here, we present MS2Query, a machine learning-based tool that integrates mass spectral embedding-based chemical similarity predictors (Spec2Vec and MS2Deepscore) as well as detected precursor masses to rank potential analogues and exact matches. Benchmarking MS2Query on reference mass spectra and experimental case studies demonstrate improved reliability and scalability. Thereby, MS2Query offers exciting opportunities to further increase the annotation rate of metabolomics profiles of complex metabolite mixtures and to discover new biology.

Plant and microbial sciences as key drivers in the development of metabolomics research

This year marks the 25th anniversary of the coinage of the term metabolome [S. G. Oliver et al., Trends Biotech. 16, 373-378 (1998)]. As the field rapidly advances, it is important to take stock of the progress which has been made to best inform the disciplines future. While a medical-centric perspective on metabolomics has recently been published [M. Giera et al., Cell Metab. 34, 21-34 (2022)], this largely ignores the pioneering contributions made by the plant and microbial science communities. In this perspective, we provide a contemporary overview of all fields in which metabolomics is employed with particular emphasis on both methodological and application breakthroughs made in plant and microbial sciences that have shaped this evolving research discipline from the very early days of its establishment. This will not cover all types of metabolomics assays currently employed but will focus mainly on those utilizing mass spectrometry-based measurements since they are currently by far the most prominent. Having established the historical context of metabolomics, we will address the key challenges currently facing metabolomics and offer potential approaches by which these can be faced. Most salient among these is the fact that the vast majority of mass features are as yet not annotated with high confidence; what we may refer to as definitive identification. We discuss the potential of both standard compound libraries and artificial intelligence technologies to address this challenge and the use of natural variance-based approaches such as genome-wide association studies in attempt to assign specific functions to the myriad of structurally similar and complex specialized metabolites. We conclude by stating our contention that as these challenges are epic and that they will need far greater cooperative efforts from biologists, chemists, and computer scientists with an interest in all kingdoms of life than have been made to date. Ultimately, a better linkage of metabolome and genome data will likely also be needed particularly considering the Earth BioGenome Project.

Good practices and recommendations for using and benchmarking computational metabolomics metabolite annotation tools

BACKGROUND

Untargeted metabolomics approaches based on mass spectrometry obtain comprehensive profiles of complex biological samples. However, on average only 10% of the molecules can be annotated. This low annotation rate hampers biochemical interpretation and effective comparison of metabolomics studies. Furthermore, de novo structural characterization of mass spectral data remains a complicated and time-intensive process. Recently, the field of computational metabolomics has gained traction and novel methods have started to enable large-scale and reliable metabolite annotation. Molecular networking and machine learning-based in-silico annotation tools have been shown to greatly assist metabolite characterization in diverse fields such as clinical metabolomics and natural product discovery.

AIM OF REVIEW

We highlight recent advances in computational metabolite annotation workflows with a special focus on their evaluation and comparison with other tools. Whilst the progress is substantial and promising, we also argue that inconsistencies in benchmarking different tools hamper users from selecting the most appropriate and promising method for their research. We summarize benchmarking strategies of the different tools and outline several recommendations for benchmarking and comparing novel tools.

KEY SCIENTIFIC CONCEPTS OF REVIEW

This review focuses on recent advances in mass spectral library-based and machine learning-supported metabolite annotation workflows. We discuss large-scale library matching and analogue search, the current bloom of mass spectral similarity scores, and how molecular networking has changed the field. In addition, the potentials and challenges of machine learning-supported metabolite annotation workflows are highlighted. Overall, recent developments in computational metabolomics have started to fundamentally change metabolomics workflows, and we expect that as a community we will be able to overcome current method performance ambiguities and annotation bottlenecks.

The critical role that spectral libraries play in capturing the metabolomics community knowledge

BACKGROUND

Spectral library searching is currently the most common approach for compound annotation in untargeted metabolomics. Spectral libraries applicable to liquid chromatography mass spectrometry have grown in size over the past decade to include hundreds of thousands to millions of mass spectra and tens of thousands of compounds, forming an essential knowledge base for the interpretation of metabolomics experiments.

AIM OF REVIEW

We describe existing spectral library resources, highlight different strategies for compiling spectral libraries, and discuss quality considerations that should be taken into account when interpreting spectral library searching results. Finally, we describe how spectral libraries are empowering the next generation of machine learning tools in computational metabolomics, and discuss several opportunities for using increasingly accessible large spectral libraries.

KEY SCIENTIFIC CONCEPTS OF REVIEW

This review focuses on the current state of spectral libraries for untargeted LC-MS/MS based metabolomics. We show how the number of entries in publicly accessible spectral libraries has increased more than 60-fold in the past eight years to aid molecular interpretation and we discuss how the role of spectral libraries in untargeted metabolomics will evolve in the near future.

Multi-Task Neural Networks and Molecular Fingerprints to Enhance Compound Identification from LC-MS/MS Data

Mass spectrometry (MS) is widely used for the identification of chemical compounds by matching the experimentally acquired mass spectrum against a database of reference spectra. However, this approach suffers from a limited coverage of the existing databases causing a failure in the identification of a compound not present in the database. Among the computational approaches for mining metabolite structures based on MS data, one option is to predict molecular fingerprints from the mass spectra by means of chemometric strategies and then use them to screen compound libraries. This can be carried out by calibrating multi-task artificial neural networks from large datasets of mass spectra, used as inputs, and molecular fingerprints as outputs. In this study, we prepared a large LC-MS/MS dataset from an on-line open repository. These data were used to train and evaluate deep-learning-based approaches to predict molecular fingerprints and retrieve the structure of unknown compounds from their LC-MS/MS spectra. Effects of data sparseness and the impact of different strategies of data curing and dimensionality reduction on the output accuracy have been evaluated. Moreover, extensive diagnostics have been carried out to evaluate modelling advantages and drawbacks as a function of the explored chemical space.

Strategies for structure elucidation of small molecules based on LC–MS/MS data from complex biological samples

LC–MS/MS is a major analytical platform for metabolomics, which has become a recent hotspot in the research fields of life and environmental sciences. By contrast, structure elucidation of small molecules based on LC–MS/MS data remains a major challenge in the chemical and biological interpretation of untargeted metabolomics datasets. In recent years, several strategies for structure elucidation using LC–MS/MS data from complex biological samples have been proposed, these strategies can be simply categorized into two types, one based on structure annotation of mass spectra and for the other on retention time prediction. These strategies have helped many scientists conduct research in metabolite-related fields and are indispensable for the development of future tools. Here, we summarized the characteristics of the current tools and strategies for structure elucidation of small molecules based on LC–MS/MS data, and further discussed the directions and perspectives to improve the power of the tools or strategies for structure elucidation.

Untargeted metabolomics of COVID-19 patient serum reveals potential prognostic markers of both severity and outcome

INTRODUCTION

The diagnosis of COVID-19 is normally based on the qualitative detection of viral nucleic acid sequences. Properties of the host response are not measured but are key in determining outcome. Although metabolic profiles are well suited to capture host state, most metabolomics studies are either underpowered, measure only a restricted subset of metabolites, compare infected individuals against uninfected control cohorts that are not suitably matched, or do not provide a compact predictive model.

OBJECTIVES

Here we provide a well-powered, untargeted metabolomics assessment of 120 COVID-19 patient samples acquired at hospital admission. The study aims to predict the patient's infection severity (i.e., mild or severe) and potential outcome (i.e., discharged or deceased).

METHODS

High resolution untargeted UHPLC-MS/MS analysis was performed on patient serum using both positive and negative ionization modes. A subset of 20 intermediary metabolites predictive of severity or outcome were selected based on univariate statistical significance and a multiple predictor Bayesian logistic regression model was created.

RESULTS

The predictors were selected for their relevant biological function and include deoxycytidine and ureidopropionate (indirectly reflecting viral load), kynurenine (reflecting host inflammatory response), and multiple short chain acylcarnitines (energy metabolism) among others. Currently, this approach predicts outcome and severity with a Monte Carlo cross validated area under the ROC curve of 0.792 (SD 0.09) and 0.793 (SD 0.08), respectively. A blind validation study on an additional 90 patients predicted outcome and severity at ROC AUC of 0.83 (CI 0.74-0.91) and 0.76 (CI 0.67-0.86).

CONCLUSION

Prognostic tests based on the markers discussed in this paper could allow improvement in the planning of COVID-19 patient treatment.