Exploring the Performance of Linear and Nonlinear Models of Time-of-Flight Secondary Ion Mass Spectrometry Spectra.

Multivariate statistical tools and machine learning (ML) techniques can deconvolute hyperspectral data and control the disparity between the number of samples and features in materials science. Nevertheless, the importance of generating sufficient high-quality sample replicates in training data cannot be overlooked, as it fundamentally affects the performance of ML models. Here, we present a quantitative analysis of time-of-flight secondary ion mass spectrometry (ToF-SIMS) spectra of a simple microarray system of two food dyes using partial least-squares (PLS, linear) and random forest (RF, nonlinear) algorithms. This microarray was generated by a high-throughput sample preparation and analysis workflow for fast and efficient acquisition of quality and reproducible spectra via ToF-SIMS. We drew insights from the bias-variance trade-off, investigated the performances of PLS and RF regression models as a function of training data size, and inferred the amount of data needed to construct accurate and reliable regression models. In addition, we found that the spectral concatenation of positive and negative ToF-SIMS spectra improved the model performances. This study provides an empirical basis for future design of high-throughput microarrays and multicomponent systems, for the purpose of analysis with ToF-SIMS and ML.

Markedly Enhanced Analysis of Mass Spectrometry Images Using Weakly Supervised Machine Learning.

Supervised and unsupervised machine learning algorithms are routinely applied to time-of-flight secondary ion mass spectrometry (ToF-SIMS) imaging data and, more broadly, to mass spectrometry imaging (MSI). These algorithms have accelerated large-scale, single-pixel analysis, classification, and regression. However, there is relatively little research on methods suited for so-called weakly supervised problems, where ground-truth class labels exist at the image level, but not at the individual pixel level. Unsupervised learning methods are usually applied to these problems. However, these methods cannot make use of available labels. Here a novel method specifically designed for weakly supervised MSI data is presented. A dual-stream multiple instance learning (MIL) approach is adapted from computational pathology that reveals the spatial-spectral characteristics distinguishing different classes of MSI images. The method uses an information entropy-regularized attention mechanism to identify characteristic class pixels that are then used to extract characteristic mass spectra. This work provides a proof-of-concept exemplification using printed ink samples imaged by ToF-SIMS. A second application-oriented study is also presented, focusing on the analysis of a mixed powder sample type. Results demonstrate the potential of the MIL method for broader application in MSI, with implications for understanding subtle spatial-spectral characteristics in various applications and contexts.

Identifying factors controlling cellular uptake of gold nanoparticles by machine learning.

There is strong interest to improve the therapeutic potential of gold nanoparticles (GNPs) while ensuring their safe development. The utility of GNPs in medicine requires a molecular-level understanding of how GNPs interact with biological systems. Despite considerable research efforts devoted to monitoring the internalisation of GNPs, there is still insufficient understanding of the factors responsible for the variability in GNP uptake in different cell types. Data-driven models are useful for identifying the sources of this variability. Here, we trained multiple machine learning models on 2077 data points for 193 individual nanoparticles from 59 independent studies to predict cellular uptake level of GNPs and compared different algorithms for their efficacies of prediction. The five ensemble learners (Xgboost, random forest, bootstrap aggregation, gradient boosting, light gradient boosting machine) made the best predictions of GNP uptake, accounting for 80-90% of the variance in the test data. The models identified particle size, zeta potential, GNP concentration and exposure duration as the most important drivers of cellular uptake. We expect this proof-of-concept study will foster the more effective use of accumulated cellular uptake data for GNPs and minimise any methodological bias in individual studies that may lead to under- or over-estimation of cellular internalisation rates.

Rational Atom Substitution to Obtain Efficient, Lead-Free Photocatalytic Perovskites Assisted by Machine Learning and DFT Calculations.

Inorganic lead-free halide perovskites, devoid of toxic or rare elements, have garnered considerable attention as photocatalysts for pollution control, CO2 reduction and hydrogen production. In the extensive perovskite design space, factors like substitution or doping level profoundly impact their performance. To address this complexity, a synergistic combination of machine learning models and theoretical calculations were used to efficiently screen substitution elements that enhanced the photoactivity of substituted Cs2 AgBiBr6 perovskites. Machine learning models determined the importance of d10 orbitals, highlighting how substituent electron configuration affects electronic structure of Cs2 AgBiBr6 . Conspicuously, d10 -configured Zn2+ boosted the photoactivity of Cs2 AgBiBr6 . Experimental verification validated these model results, revealing a 13-fold increase in photocatalytic toluene conversion compared to the unsubstituted counterpart. This enhancement resulted from the small charge carrier effective mass, as well as the creation of shallow trap states, shifting the conduction band minimum, introducing electron-deficient Br, and altering the distance between the B-site cations d band centre and the halide anions p band centre, a parameter tuneable through d10 configuration substituents. This study exemplifies the application of computational modelling in photocatalyst design and elucidating structure-property relationships. It underscores the potential of synergistic integration of calculations, modelling, and experimental analysis across various applications.

Converting Nanotoxicity Data to Information Using Artificial Intelligence and Simulation.

Decades of nanotoxicology research have generated extensive and diverse data sets. However, data is not equal to information. The question is how to extract critical information buried in vast data streams. Here we show that artificial intelligence (AI) and molecular simulation play key roles in transforming nanotoxicity data into critical information, i.e., constructing the quantitative nanostructure (physicochemical properties)-toxicity relationships, and elucidating the toxicity-related molecular mechanisms. For AI and molecular simulation to realize their full impacts in this mission, several obstacles must be overcome. These include the paucity of high-quality nanomaterials (NMs) and standardized nanotoxicity data, the lack of model-friendly databases, the scarcity of specific and universal nanodescriptors, and the inability to simulate NMs at realistic spatial and temporal scales. This review provides a comprehensive and representative, but not exhaustive, summary of the current capability gaps and tools required to fill these formidable gaps. Specifically, we discuss the applications of AI and molecular simulation, which can address the large-scale data challenge for nanotoxicology research. The need for model-friendly nanotoxicity databases, powerful nanodescriptors, new modeling approaches, molecular mechanism analysis, and design of the next-generation NMs are also critically discussed. Finally, we provide a perspective on future trends and challenges.

Multi-Dimensional Machine Learning Analysis of Polyaniline Films Using Stitched Hyperspectral ToF-SIMS Data.

The self-organizing map with relational perspective mapping (SOM-RPM) is an unsupervised machine learning method that can be used to visualize and interpret high-dimensional hyperspectral data. We have previously used SOM-RPM for the analysis of time-of-flight secondary ion mass spectrometry (ToF-SIMS) hyperspectral images and three-dimensional (3D) depth profiles. This provides insightful visualization of features and trends of 3D depth profile data, using a slice-by-slice view, which can be useful for highlighting structural flaws including molecular characteristics and transport of contaminants to a buried interface and characterization of spectra. Here, we apply SOM-RPM to stitched ToF-SIMS data sets, whereby the stitched data are used to train the same model to provide a direct comparison in both 2D and 3D. We conduct an analysis of spin-coated polyaniline (PANI) films on indium tin oxide-coated glass slides that were subjected to heat treatment under atmospheric conditions to model PANI as a conformal aerospace industry coating. Replicates were shown to be precisely equivalent, both spatially and by composition, indicating a clear threshold for annealing of the film. Quantitative assessment was performed on the chemical breakdown trends accompanying annealing based on peak ratios, while spectral analysis alone shows only very subtle differences which are difficult to evaluate quantitatively. The SOM-RPM method considers data sets in their totality and highlights subtle differences between samples often simply differences in peak intensity ratios.

Linear Binary Classifier to Predict Bacterial Biofilm Formation on Polyacrylates.

Bacterial infections are increasingly problematic due to the rise of antimicrobial resistance. Consequently, the rational design of materials naturally resistant to biofilm formation is an important strategy for preventing medical device-associated infections. Machine learning (ML) is a powerful method to find useful patterns in complex data from a wide range of fields. Recent reports showed how ML can reveal strong relationships between bacterial adhesion and the physicochemical properties of polyacrylate libraries. These studies used robust and predictive nonlinear regression methods that had better quantitative prediction power than linear models. However, as nonlinear models' feature importance is a local rather than global property, these models were hard to interpret and provided limited insight into the molecular details of material-bacteria interactions. Here, we show that the use of interpretable mass spectral molecular ions and chemoinformatic descriptors and a linear binary classification model of attachment of three common nosocomial pathogens to a library of polyacrylates can provide improved guidance for the design of more effective pathogen-resistant coatings. Relevant features from each model were analyzed and correlated with easily interpretable chemoinformatic descriptors to derive a small set of rules that give model features tangible meaning that elucidate relationships between the structure and function. The results show that the attachment of Pseudomonas aeruginosa and Staphylococcus aureus can be robustly predicted by chemoinformatic descriptors, suggesting that the obtained models can predict the attachment response to polyacrylates to identify anti-attachment materials to synthesize and test in the future.

Identifying SARS-CoV-2 Drugs Binding to the Spike Fatty Acid Binding Pocket Using In Silico Docking and Molecular Dynamics.

Drugs against novel targets are needed to treat COVID-19 patients, especially as SARS-CoV-2 is capable of rapid mutation. Structure-based de novo drug design and repurposing of drugs and natural products is a rational approach to discovering potentially effective therapies. These in silico simulations can quickly identify existing drugs with known safety profiles that can be repurposed for COVID-19 treatment. Here, we employ the newly identified spike protein free fatty acid binding pocket structure to identify repurposing candidates as potential SARS-CoV-2 therapies. Using a validated docking and molecular dynamics protocol effective at identifying repurposing candidates inhibiting other SARS-CoV-2 molecular targets, this study provides novel insights into the SARS-CoV-2 spike protein and its potential regulation by endogenous hormones and drugs. Some of the predicted repurposing candidates have already been demonstrated experimentally to inhibit SARS-CoV-2 activity, but most of the candidate drugs have yet to be tested for activity against the virus. We also elucidated a rationale for the effects of steroid and sex hormones and some vitamins on SARS-CoV-2 infection and COVID-19 recovery.

Identifying medically relevant xenon protein targets by in silico screening of the structural proteome.

In a previous study, in silico screening of the binding of almost all proteins in the Protein Data Bank to each of the five noble gases xenon, krypton, argon, neon, and helium was reported. This massive and rich data set requires analysis to identify the gas-protein interactions that have the best binding strengths, those where the binding of the noble gas occurs at a site that can modulate the function of the protein, and where this modulation might generate clinically relevant effects. Here, we report a preliminary analysis of this data set using a rational, heuristic score based on binding strength and location. We report a partial prioritized list of xenon protein targets and describe how these data can be analyzed, using arginase and carbonic anhydrase as examples. Our aim is to make the scientific community aware of this massive, rich data set and how it can be analyzed to accelerate future discoveries of xenon-induced biological activity and, ultimately, the development of new "atomic" drugs.

High resolution imaging and analysis of extracellular vesicles using mass spectral imaging and machine learning.

Extracellular vesicles (EVs) are potentially useful biomarkers for disease detection and monitoring. Development of a label-free technique for imaging and distinguishing small volumes of EVs from different cell types and cell states would be of great value. Here, we have designed a method to explore the chemical changes in EVs associated with neuroinflammation using Time-of-Flight Secondary Ion Mass spectrometry (ToF-SIMS) and machine learning (ML). Mass spectral imaging was able to identify and differentiate EVs released by microglia following lipopolysaccharide (LPS) stimulation compared to a control group. This process requires a much smaller sample size (1 µL) than other molecular analysis methods (up to 50 µL). Conspicuously, we saw a reduction in free cysteine thiols (a marker of cellular oxidative stress associated with neuroinflammation) in EVs from microglial cells treated with LPS, consistent with the reduced cellular free thiol levels measured experimentally. This validates the synergistic combination of ToF-SIMS and ML as a sensitive and valuable technique for collecting and analysing molecular data from EVs at high resolution.

Machine Learning in the Development of Adsorbents for Clean Energy Application and Greenhouse Gas Capture.

Addressing climate change challenges by reducing greenhouse gas levels requires innovative adsorbent materials for clean energy applications. Recent progress in machine learning has stimulated technological breakthroughs in the discovery, design, and deployment of materials with potential for high-performance and low-cost clean energy applications. This review summarizes basic machine learning methods-data collection, featurization, model generation, and model evaluation-and reviews their use in the development of robust adsorbent materials. Key case studies are provided where these methods are used to accelerate adsorbent materials design and discovery, optimize synthesis conditions, and understand complex feature-property relationships. The review provides a concise resource for researchers wishing to use machine learning methods to rapidly develop effective adsorbent materials with a positive impact on the environment.

Discovery and Design of Radiopharmaceuticals by In silico Methods.

There has been impressive growth in the use of radiopharmaceuticals for therapy, selective toxic payload delivery, and noninvasive diagnostic imaging of disease. The increasing timeframes and costs involved in the discovery and development of new radiopharmaceuticals have driven the development of more efficient strategies for this process. Computer-Aided Drug Design (CADD) methods and Machine Learning (ML) have become more effective over the last two decades for drug and materials discovery and optimization. They are now fast, flexible, and sufficiently accurate to accelerate the discovery of new molecules and materials. Radiopharmaceuticals have also started to benefit from rapid developments in computational methods. Here, we review the types of computational molecular design techniques that have been used for radiopharmaceuticals design. We also provide a thorough examination of success stories in the design of radiopharmaceuticals, and the strengths and weaknesses of the computational methods. We begin by providing a brief overview of therapeutic and diagnostic radiopharmaceuticals and the steps involved in radiopharmaceuticals design and development. We then review the computational design methods used in radiopharmaceutical studies, including molecular mechanics, quantum mechanics, molecular dynamics, molecular docking, pharmacophore modelling, and datadriven ML. Finally, the difficulties and opportunities presented by radiopharmaceutical modelling are highlighted. The review emphasizes the potential of computational design methods to accelerate the production of these very useful clinical radiopharmaceutical agents and aims to raise awareness among radiopharmaceutical researchers about computational modelling and simulation methods that can be of benefit to this field.

Energy Interplay in Materials: Unlocking Next-Generation Synchronous Multisource Energy Conversion with Layered 2D Crystals.

Layered 2D crystals have unique properties and rich chemical and electronic diversity, with over 6000 2D crystals known and, in principle, millions of different stacked hybrid 2D crystals accessible. This diversity provides unique combinations of properties that can profoundly affect the future of energy conversion and harvesting devices. Notably, this includes catalysts, photovoltaics, superconductors, solar-fuel generators, and piezoelectric devices that will receive broad commercial uptake in the near future. However, the unique properties of layered 2D crystals are not limited to individual applications and they can achieve exceptional performance in multiple energy conversion applications synchronously. This synchronous multisource energy conversion (SMEC) has yet to be fully realized but offers a real game-changer in how devices will be produced and utilized in the future. This perspective highlights the energy interplay in materials and its impact on energy conversion, how SMEC devices can be realized, particularly through layered 2D crystals, and provides a vision of the future of effective environmental energy harvesting devices with layered 2D crystals.

European Registry of Materials: global, unique identifiers for (undisclosed) nanomaterials.

Management of nanomaterials and nanosafety data needs to operate under the FAIR (findability, accessibility, interoperability, and reusability) principles and this requires a unique, global identifier for each nanomaterial. Existing identifiers may not always be applicable or sufficient to definitively identify the specific nanomaterial used in a particular study, resulting in the use of textual descriptions in research project communications and reporting. To ensure that internal project documentation can later be linked to publicly released data and knowledge for the specific nanomaterials, or even to specific batches and variants of nanomaterials utilised in that project, a new identifier is proposed: the European Registry of Materials Identifier. We here describe the background to this new identifier, including FAIR interoperability as defined by FAIRSharing, identifiers.org, Bioregistry, and the CHEMINF ontology, and show how it complements other identifiers such as CAS numbers and the ongoing efforts to extend the InChI identifier to cover nanomaterials. We provide examples of its use in various H2020-funded nanosafety projects.

Machine Learning for Electrocatalyst and Photocatalyst Design and Discovery.

Electrocatalysts and photocatalysts are key to a sustainable future, generating clean fuels, reducing the impact of global warming, and providing solutions to environmental pollution. Improved processes for catalyst design and a better understanding of electro/photocatalytic processes are essential for improving catalyst effectiveness. Recent advances in data science and artificial intelligence have great potential to accelerate electrocatalysis and photocatalysis research, particularly the rapid exploration of large materials chemistry spaces through machine learning. Here a comprehensive introduction to, and critical review of, machine learning techniques used in electrocatalysis and photocatalysis research are provided. Sources of electro/photocatalyst data and current approaches to representing these materials by mathematical features are described, the most commonly used machine learning methods summarized, and the quality and utility of electro/photocatalyst models evaluated. Illustrations of how machine learning models are applied to novel electro/photocatalyst discovery and used to elucidate electrocatalytic or photocatalytic reaction mechanisms are provided. The review offers a guide for materials scientists on the selection of machine learning methods for electrocatalysis and photocatalysis research. The application of machine learning to catalysis science represents a paradigm shift in the way advanced, next-generation catalysts will be designed and synthesized.

Potential COVID-19 Therapies from Computational Repurposing of Drugs and Natural Products against the SARS-CoV-2 Helicase.

Repurposing of existing drugs is a rapid way to find potential new treatments for SARS-CoV-2. Here, we applied a virtual screening approach using Autodock Vina and molecular dynamic simulation in tandem to screen and calculate binding energies of repurposed drugs against the SARS-CoV-2 helicase protein (non-structural protein nsp13). Amongst the top hits from our study were antivirals, antihistamines, and antipsychotics, plus a range of other drugs. Approximately 30% of our top 87 hits had published evidence indicating in vivo or in vitro SARS-CoV-2 activity. Top hits not previously reported to have SARS-CoV-2 activity included the antiviral agents, cabotegravir and RSV-604; the NK1 antagonist, aprepitant; the trypanocidal drug, aminoquinuride; the analgesic, antrafenine; the anticancer intercalator, epirubicin; the antihistamine, fexofenadine; and the anticoagulant, dicoumarol. These hits from our in silico SARS-CoV-2 helicase screen warrant further testing as potential COVID-19 treatments.

Two-Dimensional and Three-Dimensional Time-of-Flight Secondary Ion Mass Spectrometry Image Feature Extraction Using a Spatially Aware Convolutional Autoencoder.

Feature extraction algorithms are an important class of unsupervised methods used to reduce data dimensionality. They have been applied extensively for time-of-flight secondary ion mass spectrometry (ToF-SIMS) imaging─commonly, matrix factorization (MF) techniques such as principal component analysis have been used. A limitation of MF is the assumption of linearity, which is generally not accurate for ToF-SIMS data. Recently, nonlinear autoencoders have been shown to outperform MF techniques for ToF-SIMS image feature extraction. However, another limitation of most feature extraction methods (including autoencoders) that is particularly important for hyperspectral data is that they do not consider spatial information. To address this limitation, we describe the application of the convolutional autoencoder (CNNAE) to hyperspectral ToF-SIMS imaging data. The CNNAE is an artificial neural network developed specifically for hyperspectral data that uses convolutional layers for image encoding, thereby explicitly incorporating pixel neighborhood information. We compared the performance of the CNNAE with other common feature extraction algorithms for two biological ToF-SIMS imaging data sets. We investigated the extracted features and used the dimensionality-reduced data to train additional ML algorithms. By converting two-dimensional convolutional layers to three-dimensional (3D), we also showed how the CNNAE can be extended to 3D ToF-SIMS images. In general, the CNNAE produced features with significantly higher contrast and autocorrelation than other techniques. Furthermore, histologically recognizable features in the data were more accurately represented. The extension of the CNNAE to 3D data also provided an important proof of principle for the analysis of more complex 3D data sets.

Computational Repurposing of Drugs and Natural Products Against SARS-CoV-2 Main Protease (Mpro) as Potential COVID-19 Therapies.

We urgently need to identify drugs to treat patients suffering from COVID-19 infection. Drugs rarely act at single molecular targets. Off-target effects are responsible for undesirable side effects and beneficial synergy between targets for specific illnesses. They have provided blockbuster drugs, e.g., Viagra for erectile dysfunction and Minoxidil for male pattern baldness. Existing drugs, those in clinical trials, and approved natural products constitute a rich resource of therapeutic agents that can be quickly repurposed, as they have already been assessed for safety in man. A key question is how to screen such compounds rapidly and efficiently for activity against new pandemic pathogens such as SARS-CoV-2. Here, we show how a fast and robust computational process can be used to screen large libraries of drugs and natural compounds to identify those that may inhibit the main protease of SARS-CoV-2. We show that the shortlist of 84 candidates with the strongest predicted binding affinities is highly enriched (≥25%) in compounds experimentally validated in vivo or in vitro to have activity in SARS-CoV-2. The top candidates also include drugs and natural products not previously identified as having COVID-19 activity, thereby providing leads for experimental validation. This predictive in silico screening pipeline will be valuable for repurposing existing drugs and discovering new drug candidates against other medically important pathogens relevant to future pandemics.

Applications of multivariate analysis and unsupervised machine learning to ToF-SIMS images of organic, bioorganic, and biological systems.

Time-of-flight secondary ion mass spectrometry (ToF-SIMS) imaging offers a powerful, label-free method for exploring organic, bioorganic, and biological systems. The technique is capable of very high spatial resolution, while also producing an enormous amount of information about the chemical and molecular composition of a surface. However, this information is inherently complex, making interpretation and analysis of the vast amount of data produced by a single ToF-SIMS experiment a considerable challenge. Much research over the past few decades has focused on the application and development of multivariate analysis (MVA) and machine learning (ML) techniques that find meaningful patterns and relationships in these datasets. Here, we review the unsupervised algorithms-that is, algorithms that do not require ground truth labels-that have been applied to ToF-SIMS images, as well as other algorithms and approaches that have been used in the broader family of mass spectrometry imaging (MSI) techniques. We first give a nontechnical overview of several commonly used classes of unsupervised algorithms, such as matrix factorization, clustering, and nonlinear dimensionality reduction. We then review the application of unsupervised algorithms to various organic, bioorganic, and biological systems including cells and tissues, organic films, residues and coatings, and spatially structured systems such as polymer microarrays. We then cover several novel algorithms employed for other MSI techniques that have received little attention from ToF-SIMS imaging researchers. We conclude with a brief outline of potential future directions for the application of MVA and ML algorithms to ToF-SIMS images.