Unsupervised machine learning for exploratory data analysis in imaging mass spectrometry

Probe-based mass spectrometry approaches for single-cell and single-organelle measurements

Exploring the chemical content of individual cells not only reveals underlying cell-to-cell chemical heterogeneity but is also a key component in understanding how cells combine to form emergent properties of cellular networks and tissues. Recent technological advances in many analytical techniques including mass spectrometry (MS) have improved instrumental limits of detection and laser/ion probe dimensions, allowing the analysis of micron and submicron sized areas. In the case of MS, these improvements combined with MS's broad analyte detection capabilities have enabled the rise of single-cell and single-organelle chemical characterization. As the chemical coverage and throughput of single-cell measurements increase, more advanced statistical and data analysis methods have aided in data visualization and interpretation. This review focuses on secondary ion MS and matrix-assisted laser desorption/ionization MS approaches for single-cell and single-organelle characterization, which is followed by advances in mass spectral data visualization and analysis.

Untargeted Pixel-by-Pixel Imaging of Metabolite Ratio Pairs as a Novel Tool for Biomedical Discovery in Mass Spectrometry Imaging

Mass spectrometry imaging (MSI) is a powerful technology used to define the spatial distribution and relative abundance of structurally identified and yet-undefined metabolites across tissue cryosections. While numerous software packages enable pixel-by-pixel imaging of individual metabolites, the research community lacks a discovery tool that images all metabolite abundance ratio pairs. Importantly, recognition of correlated metabolite pairs informs discovery of unanticipated molecules contributing to shared metabolic pathways, uncovers hidden metabolic heterogeneity across cells and tissue subregions, and indicates single-timepoint flux through pathways of interest. Here, we describe the development and implementation of an untargeted R package workflow for pixel-by-pixel ratio imaging of all metabolites detected in an MSI experiment. Considering untargeted MSI studies of murine brain and embryogenesis, we demonstrate that ratio imaging minimizes systematic data variation introduced by sample handling and instrument drift, markedly enhances spatial image resolution, and reveals previously unrecognized metabotype-distinct tissue regions. Furthermore, ratio imaging facilitates identification of novel regional biomarkers and provides anatomical information regarding spatial distribution of metabolite-linked biochemical pathways. The algorithm described herein is applicable to any MSI dataset containing spatial information for metabolites, peptides or proteins, offering a potent tool to enhance knowledge obtained from current spatial metabolite profiling technologies.

Spatial omics reveals molecular changes in focal cortical dysplasia type II

Focal cortical dysplasia (FCD) represents a group of diverse localized cortical lesions that are highly epileptogenic and occur due to abnormal brain development caused by genetic mutations, involving the mammalian target of rapamycin (mTOR). These somatic mutations lead to mosaicism in the affected brain, posing challenges to unravel the direct and indirect functional consequences of these mutations. To comprehensively characterize the impact of mTOR mutations on the brain, we employed here a multimodal approach in a preclinical mouse model of FCD type II (Rheb), focusing on spatial omics techniques to define the proteomic and lipidomic changes. Mass Spectrometry Imaging (MSI) combined with fluorescence imaging and label free proteomics, revealed insight into the brain's lipidome and proteome within the FCD type II affected region in the mouse model. MSI visualized disrupted neuronal migration and differential lipid distribution including a reduction in sulfatides in the FCD type II-affected region, which play a role in brain myelination. MSI-guided laser capture microdissection (LMD) was conducted on FCD type II and control regions, followed by label free proteomics, revealing changes in myelination pathways by oligodendrocytes. Surgical resections of FCD type IIb and postmortem human cortex were analyzed by bulk transcriptomics to unravel the interplay between genetic mutations and molecular changes in FCD type II. Our comparative analysis of protein pathways and enriched Gene Ontology pathways related to myelination in the FCD type II-affected mouse model and human FCD type IIb transcriptomics highlights the animal model's translational value. This dual approach, including mouse model proteomics and human transcriptomics strengthens our understanding of the functional consequences arising from somatic mutations in FCD type II, as well as the identification of pathways that may be used as therapeutic strategies in the future.

Multimodal MALDI imaging mass spectrometry for improved diagnosis of melanoma

Imaging mass spectrometry (IMS) provides promising avenues to augment histopathological investigation with rich spatio-molecular information. We have previously developed a classification model to differentiate melanoma from nevi lesions based on IMS protein data, a task that is challenging solely by histopathologic evaluation. Most IMS-focused studies collect microscopy in tandem with IMS data, but this microscopy data is generally omitted in downstream data analysis. Microscopy, nevertheless, forms the basis for traditional histopathology and thus contains invaluable morphological information. In this work, we developed a multimodal classification pipeline that uses deep learning, in the form of a pre-trained artificial neural network, to extract the meaningful morphological features from histopathological images, and combine it with the IMS data. To test whether this deep learning-based classification strategy can improve on our previous results in classification of melanocytic neoplasia, we utilized MALDI IMS data with collected serial H&E stained sections for 331 patients, and compared this multimodal classification pipeline to classifiers using either exclusively microscopy or IMS data. The multimodal pipeline achieved the best performance, with ROC-AUCs of 0.968 vs. 0.938 vs. 0.931 for the multimodal, unimodal microscopy and unimodal IMS pipelines respectively. Due to the use of a pre-trained network to perform the morphological feature extraction, this pipeline does not require any training on large amounts of microscopy data. As such, this framework can be readily applied to improve classification performance in other experimental settings where microscopy data is acquired in tandem with IMS experiments.

Deep learning-assisted mass spectrometry imaging for preliminary screening and pre-classification of psychoactive substances

Currently, it is of great urgency to develop a rapid pre-classification and screening method for suspected drugs as the constantly springing up of new psychoactive substances. In most researches, psychoactive substances classification approaches depended on the similar chemical structures and pharmacological action with known drugs. Such approaches could not face the complicated circumstance of emerging new psychoactive substances. Herein, mass spectrometry imaging and convolutional neural networks (CNN) were used for preliminary screening and pre-classification of suspected psychoactive substances. Mass spectrometry imaging was performed simultaneously on two brain slices as one was from blank group and another one was from psychoactive substance-induced group. Then, fused neurotransmitter variation mass spectrometry images (Nv-MSIs) reflecting the difference of neurotransmitters between two slices were achieved through two homemade programs. A CNN model was developed to classify the Nv-MSIs. Compared with traditional classification methods, CNN achieved better estimation accuracy and required minimal data preprocessing. Also, the specific region on Nv-MSIs and weight of each neurotransmitter that affected the classification most could be unraveled by CNN. Finally, the method was successfully applied to assist the identification of a new psychoactive substance seized recently. This sample was identified as cannabinoids, which greatly promoted the screening process.

eLIMS: Ensemble Learning-Based Spatial Segmentation of Mass Spectrometry Imaging to Explore Metabolic Heterogeneity

Spatial segmentation is an essential processing method for image analysis aiming to identify the characteristic suborgans or microregions from mass spectrometry imaging (MSI) data, which is critical for understanding the spatial heterogeneity of biological information and function and the underlying molecular signatures. Due to the intrinsic characteristics of MSI data including spectral nonlinearity, high-dimensionality, and large data size, the common segmentation methods lack the capability for capturing the accurate microregions associated with biological functions. Here we proposed an ensemble learning-based spatial segmentation strategy, named eLIMS, that combines a randomized unified manifold approximation and projection (r-UMAP) dimensionality reduction module for extracting significant features and an ensemble pixel clustering module for aggregating the clustering maps from r-UMAP. Three MSI datasets are used to evaluate the performance of eLIMS, including mouse fetus, human adenocarcinoma, and mouse brain. Experimental results demonstrate that the proposed method has potential in partitioning the heterogeneous tissues into several subregions associated with anatomical structure, i.e., the suborgans of the brain region in mouse fetus data are identified as dorsal pallium, midbrain, and brainstem. Furthermore, it effectively discovers critical microregions related to physiological and pathological variations offering new insight into metabolic heterogeneity.

Imaging with mass spectrometry: Which ionization technique is best?

The use of mass spectrometry (MS) to acquire molecular images of biological tissues and other substrates has developed into an indispensable analytical tool over the past 25 years. Imaging mass spectrometry technologies are widely used today to study the in situ spatial distributions for a variety of analytes. Early MS images were acquired using secondary ion mass spectrometry and matrix-assisted laser desorption/ionization. Researchers have also designed and developed other ionization techniques in recent years to probe surfaces and generate MS images, including desorption electrospray ionization (DESI), nanoDESI, laser ablation electrospray ionization, and infrared matrix-assisted laser desorption electrospray ionization. Investigators now have a plethora of ionization techniques to select from when performing imaging mass spectrometry experiments. This brief perspective will highlight the utility and relative figures of merit of these techniques within the context of their use in imaging mass spectrometry.

Extended similarity methods for efficient data mining in imaging mass spectrometry

Imaging mass spectrometry is a label-free imaging modality that allows for the spatial mapping of many compounds directly in tissues. In an imaging mass spectrometry experiment, a raster of the tissue surface produces a mass spectrum at each sampled x, y position, resulting in thousands of individual mass spectra, each comprising a pixel in the resulting ion images. However, efficient analysis of imaging mass spectrometry datasets can be challenging due to the hyperspectral characteristics of the data. Each spectrum contains several thousand unique compounds at discrete m/z values that result in unique ion images, which demands robust and efficient algorithms for searching, statistical analysis, and visualization. Some traditional post-processing techniques are fundamentally ill-equipped to dissect these types of data. For example, while principal component analysis (PCA) has long served as a useful tool for mining imaging mass spectrometry datasets to identify correlated analytes and biological regions of interest, the interpretation of the PCA scores and loadings can be non-trivial. The loadings often contain negative peaks in the PCA-derived pseudo-spectra, which are difficult to ascribe to underlying tissue biology. Herein, we have utilized extended similarity indices to streamline the interpretation of imaging mass spectrometry data. This novel workflow uses PCA as a pixel-selection method to parse out the most and least correlated pixels, which are then compared using the extended similarity indices. The extended similarity indices complement PCA by removing all non-physical artifacts and streamlining the interpretation of large volumes of imaging mass spectrometry spectra simultaneously. The linear complexity, O(N), of these indices suggests that large imaging mass spectrometry datasets can be analyzed in a 1 : 1 scale of time and space with respect to the size of the input data. The extended similarity indices algorithmic workflow is exemplified here by identifying discrete biological regions of mouse brain tissue.

Mass spectrometry for neurosurgery: Intraoperative support in decision-making

Ambient ionization mass spectrometry was proved to be a powerful tool for oncological surgery. Still, it remains a translational technique on the way from laboratory to clinic. Brain surgery is the most sensitive to resection accuracy field since the balance between completeness of resection and minimization of nerve fiber damage determines patient outcome and quality of life. In this review, we summarize efforts made to develop various intraoperative support techniques for oncological neurosurgery and discuss difficulties arising on the way to clinical implementation of mass spectrometry-guided brain surgery.

A Framework for Unsupervised Profiling of Malaria Vectors' Insecticide Resistance Using Machine Learning Technique

Background: There is a need to identify different insecticide resistance profiles that represent circumscription-encapsulation of knowledge about malaria vectors' insecticide resistance to increase our understanding of malaria vectors' insecticide resistance dynamics. Methods: Data used in this study are part of the aggregation of over 20,000 mosquito collections done between 1957 and 2018. We applied two data preprocessing steps. We developed three clustering machine learning models based on the K-means algorithm with three selected datasets. The elbow method was used to fine-tune the hyperparameters. We used the silhouette score to assess the clustering results produced by each of the three models. The proposed framework incorporates continuous learning, allowing the machine learning models to learn continuously. Results: For the first model, the optimal number of clusters (profiles) k was 17. For the second model, we found four profiles. For the third model, the optimal number of profiles was 7. Discussion: We found that the insecticide resistance profiles have dynamic resistance levels with respect to the insecticide component, species component, location component, and time component. This profiling task provided knowledge about the evolution of malaria vectors' insecticide resistance in the African continent by encapsulating the information on the complex interaction between the different dimensions of malaria vectors' insecticide resistance into different profiles. Policy makers can use the knowledge about the different profiles found from the analysis of available insecticide resistance monitoring data (through profiling) by using our proposed approach to set up malaria vector control strategies that consider the locations, species present in those locations, and potentially efficient insecticides.

Quantitative mass spectrometry imaging (qMSI): A tutorial

Mass spectrometry imaging (MSI) is an analytical technique that enables the simultaneous detection of hundreds to thousands of chemical species while retaining their spatial information; usually, MSI is applied to biological tissues. Combining these elements can create ion images, which allows for the identification and localization of multiple chemical species within the sample. Being able to produce molecular images of biological tissues has already impacted the study of health and disease; however, the next logical step is being able to combine MSI with quantitative mass spectrometry methods to both quantify and determine the localization of disease progression or drug action. In this tutorial, we will detail the main factors to consider when designing a qMSI experiment and highlight the methods that have been developed to overcome these added complexities, specifically for those newer to the field of MSI.

Application of artificial intelligence in (waste)water disinfection: Emphasizing the regulation of disinfection by-products formation and residues prediction

Water/wastewater ((waste)water) disinfection, as a critical process during drinking water or wastewater treatment, can simultaneously inactivate pathogens and remove emerging organic contaminants. Due to fluctuations of (waste)water quantity and quality during the disinfection process, conventional disinfection models cannot handle intricate nonlinear situations and provide immediate responses. Artificial intelligence (AI) techniques, which can capture complex variations and accurately predict/adjust outputs on time, exhibit excellent performance for (waste)water disinfection. In this review, AI application data within the disinfection domain were searched and analyzed using CiteSpace. Then, the application of AI in the (waste)water disinfection process was comprehensively reviewed, and in addition to conventional disinfection processes, novel disinfection processes were also examined. Then, the application of AI in disinfection by-products (DBPs) formation control and disinfection residues prediction was discussed, and unregulated DBPs were also examined. Current studies have suggested that among AI techniques, fuzzy logic-based neuro systems exhibit superior control performance in (waste)water disinfection, while single AI technology is insufficient to support their applications in full-scale (waste)water treatment plants. Thus, attention should be paid to the development of hybrid AI technologies, which can give full play to the characteristics of different AI technologies and achieve a more refined effectiveness. This review provides comprehensive information for an in-depth understanding of AI application in (waste)water disinfection and reducing undesirable risks caused by disinfection processes.

Imaging plant metabolism in situ

Mass spectrometry imaging (MSI) has emerged as an invaluable analytical technique for investigating the spatial distribution of molecules within biological systems. In the realm of plant science, MSI is increasingly employed to explore metabolic processes across a wide array of plant tissues, including those in leaves, fruits, stems, roots, and seeds, spanning various plant systems such as model species, staple and energy crops, and medicinal plants. By generating spatial maps of metabolites, MSI has elucidated the distribution patterns of diverse metabolites and phytochemicals, encompassing lipids, carbohydrates, amino acids, organic acids, phenolics, terpenes, alkaloids, vitamins, pigments, and others, thereby providing insights into their metabolic pathways and functional roles. In this review, we present recent MSI studies that demonstrate the advances made in visualizing the plant spatial metabolome. Moreover, we emphasize the technical progress that enhances the identification and interpretation of spatial metabolite maps. Within a mere decade since the inception of plant MSI studies, this robust technology is poised to continue as a vital tool for tackling complex challenges in plant metabolism.

A Machine Learning-Driven Comparison of Ion Images Obtained by MALDI and MALDI-2 Mass Spectrometry Imaging

Matrix-assisted laser desorption ionization mass spectrometry imaging (MALDI-MSI) enables label-free imaging of biomolecules in biological tissues. However, many species remain undetected due to their poor ionization efficiencies. MALDI-2 (laser-induced post-ionization) is the most widely used post-ionization method for improving analyte ionization efficiencies. Mass spectra acquired using MALDI-2 constitute a combination of ions generated by both MALDI and MALDI-2 processes. Until now, no studies have focused on a detailed comparison between the ion images (as opposed to the generated m/z values) produced by MALDI and MALDI-2 for mass spectrometry imaging (MSI) experiments. Herein, we investigated the ion images produced by both MALDI and MALDI-2 on the same tissue section using correlation analysis (to explore similarities in ion images for ions common to both MALDI and MALDI-2) and a deep learning approach. For the latter, we used an analytical workflow based on the Xception convolutional neural network, which was originally trained for human-like natural image classification but which we adapted to elucidate similarities and differences in ion images obtained using the two MSI techniques. Correlation analysis demonstrated that common ions yielded similar spatial distributions with low-correlation species explained by either poor signal intensity in MALDI or the generation of additional unresolved signals using MALDI-2. Using the Xception-based method, we identified many regions in the t-SNE space of spatially similar ion images containing MALDI and MALDI-2-related signals. More notably, the method revealed distinct regions containing only MALDI-2 ion images with unique spatial distributions that were not observed using MALDI. These data explicitly demonstrate the ability of MALDI-2 to reveal molecular features and patterns as well as histological regions of interest that are not visible when using conventional MALDI.

DeepION: A Deep Learning-Based Low-Dimensional Representation Model of Ion Images for Mass Spectrometry Imaging

Mass spectrometry imaging (MSI) is a high-throughput imaging technique capable of the qualitative and quantitative in situ detection of thousands of ions in biological samples. Ion image representation is a technique that produces a low-dimensional vector embedded with significant spectral and spatial information on an ion image, which further facilitates the distance-based similarity measurement for the identification of colocalized ions. However, given the low signal-to-noise ratios inherent in MSI data coupled with the scarcity of annotated data sets, achieving an effective ion image representation for each ion image remains a challenge. In this study, we propose DeepION, a novel deep learning-based method designed specifically for ion image representation, which is applied to the identification of colocalized ions and isotope ions. In DeepION, contrastive learning is introduced to ensure that the model can generate the ion image representation in a self-supervised manner without manual annotation. Since data augmentation is a crucial step in contrastive learning, a unique data augmentation strategy is designed by considering the characteristics of MSI data, such as the Poisson distribution of ion abundance and a random pattern of missing values, to generate plentiful ion image pairs for DeepION model training. Experimental results of rat brain tissue MSI show that DeepION outperforms other methods for both colocalized ion and isotope ion identification, demonstrating the effectiveness of ion image representation. The proposed model could serve as a crucial tool in the biomarker discovery and drug development of the MSI technique.

Combining imaging mass spectrometry and immunohistochemistry to analyse the lipidome of spinal cord inflammation

Inflammation is a complex process that accompanies many pathologies. Actually, dysregulation of the inflammatory process is behind many autoimmune diseases. Thus, treatment of such pathologies may benefit from in-depth knowledge of the metabolic changes associated with inflammation. Here, we developed a strategy to characterize the lipid fingerprint of inflammation in a mouse model of spinal cord injury. Using lipid imaging mass spectrometry (LIMS), we scanned spinal cord sections from nine animals injected with lysophosphatidylcholine, a chemical model of demyelination. The lesions were demonstrated to be highly heterogeneous, and therefore, comparison with immunofluorescence experiments carried out in the same section scanned by LIMS was required to accurately identify the morphology of the lesion. Following this protocol, three main areas were defined: the lesion core, the peri-lesion, which is the front of the lesion and is rich in infiltrating cells, and the uninvolved tissue. Segmentation of the LIMS experiments allowed us to isolate the lipid fingerprint of each area in a precise way, as demonstrated by the analysis using classification models. A clear difference in lipid signature was observed between the lesion front and the epicentre, where the damage was maximized. This study is a first step to unravel the changes in the lipidome associated with inflammation in the context of diverse pathologies, such as multiple sclerosis.

Adipose tissue composition determines its computed tomography radiodensity

OBJECTIVES

Adipose tissue radiodensity in computed tomography (CT) performed before surgeries can predict surgical difficulty. Despite its clinical importance, little is known about what influences radiodensity. This study combines desorption electrospray ionization mass spectrometry imaging (DESI-MSI) and electrospray ionization (ESI) with machine learning to unveil how chemical composition of adipose tissue determines its radiodensity.

METHODS

Patients in the study underwent abdominal surgeries. Before surgery, CT radiodensity of fat near operated sites was measured. Fifty-three fat samples were collected and analyzed by DESI-MSI, ESI, and histology, and then sorted by radiodensity, demographic parameters, and adipocyte size. A non-negative matrix factorization (NMF) algorithm was developed to differentiate between high and low radiodensities.

RESULTS

No associations between radiodensity and patient age, gender, weight, height, or fat origin were found. Body mass index showed negative correlation with radiodensity. A substantial difference in chemical composition between adipose tissues of high and low radiodensities was observed. More radiodense tissues exhibited greater abundance of high molecular weight species, such as phospholipids of various types, ceramides, cholesterol esters and diglycerides, and about 70% smaller adipocyte size. Less radiodense tissue showed high abundance of short acyl-tail fatty acids.

CONCLUSIONS

This study unveils the connection between abdominal adipose tissue radiodensity and its chemical composition. Because the radiodensity of the fat around the surgical site is associated with surgical difficulty, it is important to understand how adipose tissue composition affects this parameter. We conclude that fat tissue with a higher content of various phospholipids and waxy lipids is more CT radiodense.

CLINICAL RELEVANCE STATEMENT

This study establishes the connection between the CT radiodensity of adipose tissue and its chemical composition. Clinicians may use this information for preoperative planning of surgical procedures, potentially modifying their surgical approach (for example, performing partial nephrectomy openly rather than laparoscopically).

KEY POINTS

• Adipose tissue radiodensity values in computed tomography images taken prior to the surgery can potentially predict surgery difficulty. • Fifty-three human specimens were analyzed by advanced mass spectrometry, molecular imaging, and machine learning to establish the key features that determine Hounsfield units' values of adipose tissue. • The findings of this research will enable clinicians to better prepare for surgical procedures and select operative strategies.

Recent Developments and Application of Mass Spectrometry Imaging in N-Glycosylation Studies: An Overview

Among the most typical posttranslational modifications is glycosylation, which often involves the covalent binding of an oligosaccharide (glycan) to either an asparagine (N-linked) or a serine/threonine (O-linked) residue. Studies imply that the N-glycan portion of a glycoprotein could serve as a particular disease biomarker rather than the protein itself because N-linked glycans have been widely recognized to evolve with the advancement of tumors and other diseases. N-glycans found on protein asparagine sites have been especially significant. Since N-glycans play clearly defined functions in the folding of proteins, cellular transport, and transmission of signals, modifications to them have been linked to several illnesses. However, because these N-glycans' production is not template driven, they have a substantial morphological range, rendering it difficult to distinguish the species that are most relevant to biology and medicine using standard techniques. Mass spectrometry (MS) techniques have emerged as effective analytical tools for investigating the role of glycosylation in health and illness. This is due to developments in MS equipment, data collection, and sample handling techniques. By recording the spatial dimension of a glycan's distribution in situ, mass spectrometry imaging (MSI) builds atop existing methods while offering added knowledge concerning the structure and functionality of biomolecules. In this review article, we address the current development of glycan MSI, starting with the most used tissue imaging techniques and ionization sources before proceeding on to a discussion on applications and concluding with implications for clinical research.

Spatial lipidomics of coronary atherosclerotic plaque development in a familial hypercholesterolemia swine model

Coronary atherosclerosis is caused by plaque build-up, with lipids playing a pivotal role in its progression. However, lipid composition and distribution within coronary atherosclerosis remain unknown. This study aims to characterize lipids and investigate differences in lipid composition across disease stages to aid in the understanding of disease progression. Matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI) was used to visualize lipid distributions in coronary artery sections (n = 17) from hypercholesterolemic swine. We performed histology on consecutive sections to classify the artery segments and to investigate colocalization between lipids and histological regions of interest in advanced plaque, including necrotic core and inflammatory cells. Segments were classified as healthy (n = 6), mild (n = 6), and advanced disease (n = 5) artery segments. Multivariate data analysis was employed to find differences in lipid composition between the segment types, and the lipids' spatial distribution was investigated using non-negative matrix factorization (NMF). Through this process, MALDI-MSI detected 473 lipid-related features. NMF clustering described three components in positive ionization mode: triacylglycerides (TAG), phosphatidylcholines (PC), and cholesterol species. In negative ionization mode, two components were identified: one driven by phosphatidylinositol(PI)(38:4), and one driven by ceramide-phosphoethanolamine(36:1). Multivariate data analysis showed the association between advanced disease and specific lipid signatures like PC(O-40:5) and cholesterylester(CE)(18:2). Ether-linked phospholipids and LysoPC species were found to colocalize with necrotic core, and mostly CE, ceramide, and PI species colocalized with inflammatory cells. This study, therefore, uncovers distinct lipid signatures correlated with plaque development and their colocalization with necrotic core and inflammatory cells, enhancing our understanding of coronary atherosclerosis progression.

[Application advances of mass spectrometry imaging technology in environmental pollutants analysis and their toxicity research]

Environmental exposures have significant impacts on human health and can contribute to the occurrence and development of diseases. Pollutants can enter the body through ingestion, inhalation, dermal absorption, or mother-to-child transmission, and can metabolize and/or accumulate in different tissues and organs. These pollutants can recognize and interact with various biomolecules, including DNA, RNA, proteins, and metabolites, disrupting biological processes and leading to adverse effects in living organisms. Thus, it is crucial to analysis the exogenous pollutants in the body, identify potential biomarkers and investigate their toxic effects. Numerous studies have shown that the metabolism rate of environmental pollutants greatly differs in various tissues and organs, their accumulation is also heterogeneous and dynamically changing. Moreover, the synthesis and accumulation of endogenous metabolites exhibit precise spatial distributions in tissues and cells. Mapping the spatial distributions of both pollutants and endogenous metabolites can discover relevant exposure biomarkers and provide a better understanding of their toxic effects and molecular mechanisms. Mass spectrometry is currently the preferred method for the qualitative and quantitative analysis of various compounds, and has been extensively utilized in pollutant and metabolomics analyses. Mass spectrometry imaging (MSI) is an emerging technology for molecular imaging that combines the information obtained by mass spectrometry with the visualization of the two- and three-dimensional spatial distributions of various molecular species in thin sample sections. Unlike other molecular imaging techniques, MSI can perform the label-free and untargeted analysis of thousands of molecules, such as elements, metabolites, lipids, peptides, proteins, pollutants, and drugs, in a single experiment with high sensitivity and throughput. Different MSI technologies, such as matrix-assisted laser desorption ionization mass spectrometry imaging, secondary ion mass spectrometry imaging, desorption electrospray ionization mass spectrometry imaging, and laser ablation inductively coupled plasma mass spectrometry imaging, have been introduced for the mapping of compounds and elements in biological, medical, and clinical research. MSI technologies have recently been utilized to characterize the spatial distribution of pollutants in the whole body and specific tissues of organisms, assess the toxic effects of pollutants at the molecular level, and identify exposure biomarkers. Such developments have brought new perspectives to investigate the toxicity of environmental pollutants. In this review, we provide an overview of the principles, characteristics, mass analyzers, and workflows of different MSI techniques and introduce their latest application advances in the analysis of environmental pollutants and their toxic effects.

The Exometabolome of Xylella fastidiosa in Contact with Paraburkholderia phytofirmans Supernatant Reveals Changes in Nicotinamide, Amino Acids, Biotin, and Plant Hormones

Microbial competition within plant tissues affects invading pathogens' fitness. Metabolomics is a great tool for studying their biochemical interactions by identifying accumulated metabolites. Xylella fastidiosa, a Gram-negative bacterium causing Pierce's disease (PD) in grapevines, secretes various virulence factors including cell wall-degrading enzymes, adhesion proteins, and quorum-sensing molecules. These factors, along with outer membrane vesicles, contribute to its pathogenicity. Previous studies demonstrated that co-inoculating X. fastidiosa with the Paraburkholderia phytofirmans strain PsJN suppressed PD symptoms. Here, we further investigated the interaction between the phytopathogen and the endophyte by analyzing the exometabolome of wild-type X. fastidiosa and a diffusible signaling factor (DSF) mutant lacking quorum sensing, cultivated with 20% P. phytofirmans spent media. Liquid chromatography-mass spectrometry (LC-MS) and the Method for Metabolite Annotation and Gene Integration (MAGI) were used to detect and map metabolites to genomes, revealing a total of 121 metabolites, of which 25 were further investigated. These metabolites potentially relate to host adaptation, virulence, and pathogenicity. Notably, this study presents the first comprehensive profile of X. fastidiosa in the presence of a P. phytofirmans spent media. The results highlight that P. phytofirmans and the absence of functional quorum sensing affect the ratios of glutamine to glutamate (Gln:Glu) in X. fastidiosa. Additionally, two compounds with plant metabolism and growth properties, 2-aminoisobutyric acid and gibberellic acid, were downregulated when X. fastidiosa interacted with P. phytofirmans. These findings suggest that P. phytofirmans-mediated disease suppression involves modulation of the exometabolome of X. fastidiosa, impacting plant immunity.

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.

Spatial pharmacology using mass spectrometry imaging

The emerging and powerful field of spatial pharmacology can map the spatial distribution of drugs and their metabolites, as well as their effects on endogenous biomolecules including metabolites, lipids, proteins, peptides, and glycans, without the need for labeling. This is enabled by mass spectrometry imaging (MSI) that provides previously inaccessible information in diverse phases of drug discovery and development. We provide a perspective on how MSI technologies and computational tools can be implemented to reveal quantitative spatial drug pharmacokinetics and toxicology, tissue subtyping, and associated biomarkers. We also highlight the emerging potential of comprehensive spatial pharmacology through integration of multimodal MSI data with other spatial technologies. Finally, we describe how to overcome challenges including improving reproducibility and compound annotation to generate robust conclusions that will improve drug discovery and development processes.

State-of-the-art mass spectrometry imaging applications in biomedical research

Mass spectrometry imaging has advanced from a niche technique to a widely applied spatial biology tool operating at the forefront of numerous fields, most notably making a significant impact in biomedical pharmacological research. The growth of the field has gone hand in hand with an increase in publications and usage of the technique by new laboratories, and consequently this has led to a shift from general MSI reviews to topic-specific reviews. Given this development, we see the need to recapitulate the strengths of MSI by providing a more holistic overview of state-of-the-art MSI studies to provide the new generation of researchers with an up-to-date reference framework. Here we review scientific advances for the six largest biomedical fields of MSI application (oncology, pharmacology, neurology, cardiovascular diseases, endocrinology, and rheumatology). These publications thereby give examples for at least one of the following categories: they provide novel mechanistic insights, use an exceptionally large cohort size, establish a workflow that has the potential to become a high-impact methodology, or are highly cited in their field. We finally have a look into new emerging fields and trends in MSI (immunology, microbiology, infectious diseases, and aging), as applied MSI is continuously broadening as a result of technological breakthroughs.

Advances in Imaging Mass Spectrometry for Biomedical and Clinical Research

Imaging mass spectrometry (IMS) allows for the untargeted mapping of biomolecules directly from tissue sections. This technology is increasingly integrated into biomedical and clinical research environments to supplement traditional microscopy and provide molecular context for tissue imaging. IMS has widespread clinical applicability in the fields of oncology, dermatology, microbiology, and others. This review summarizes the two most widely employed IMS technologies, matrix-assisted laser desorption/ionization (MALDI) and desorption electrospray ionization (DESI), and covers technological advancements, including efforts to increase spatial resolution, specificity, and throughput. We also highlight recent biomedical applications of IMS, primarily focusing on disease diagnosis, classification, and subtyping.

A Guide to MALDI Imaging Mass Spectrometry for Tissues

Imaging mass spectrometry is a well-established technology that can easily and succinctly communicate the spatial localization of molecules within samples. This review communicates the recent advances in the field, with a specific focus on matrix-assisted laser desorption/ionization (MALDI) imaging mass spectrometry (IMS) applied on tissues. The general sample preparation strategies for different analyte classes are explored, including special considerations for sample types (fresh frozen or formalin-fixed,) strategies for various analytes (lipids, metabolites, proteins, peptides, and glycans) and how multimodal imaging strategies can leverage the strengths of each approach is mentioned. This work explores appropriate experimental design approaches and standardization of processes needed for successful studies, as well as the various data analysis platforms available to analyze data and their strengths. The review concludes with applications of imaging mass spectrometry in various fields, with a focus on medical research, and some examples from plant biology and microbe metabolism are mentioned, to illustrate the breadth and depth of MALDI IMS.

Graph Neural Networks for Parkinson's Disease Monitoring and Alerting

Graph neural networks (GNNs) have been increasingly employed in the field of Parkinson's disease (PD) research. The use of GNNs provides a promising approach to address the complex relationship between various clinical and non-clinical factors that contribute to the progression of PD. This review paper aims to provide a comprehensive overview of the state-of-the-art research that is using GNNs for PD. It presents PD and the motivation behind using GNNs in this field. Background knowledge on the topic is also presented. Our research methodology is based on PRISMA, presenting a comprehensive overview of the current solutions using GNNs for PD, including the various types of GNNs employed and the results obtained. In addition, we discuss open issues and challenges that highlight the limitations of current GNN-based approaches and identify potential paths for future research. Finally, a new approach proposed in this paper presents the integration of new tasks for the engineering of GNNs for PD monitoring and alert solutions.

Next-generation pathology practices with mass spectrometry imaging

Mass spectrometry imaging (MSI) is a powerful technique that reveals the spatial distribution of various molecules in biological samples, and it is widely used in pathology-related research. In this review, we summarize common MSI techniques, including matrix-assisted laser desorption/ionization and desorption electrospray ionization MSI, and their applications in pathological research, including disease diagnosis, microbiology, and drug discovery. We also describe the improvements of MSI, focusing on the accumulation of imaging data sets, expansion of chemical coverage, and identification of biological significant molecules, that have prompted the evolution of MSI to meet the requirements of pathology practices. Overall, this review details the applications and improvements of MSI techniques, demonstrating the potential of integrating MSI techniques into next-generation pathology practices.

Mass Spectral Imaging to Map Plant-Microbe Interactions

Plant-microbe interactions are of rising interest in plant sustainability, biomass production, plant biology, and systems biology. These interactions have been a challenge to detect until recent advancements in mass spectrometry imaging. Plants and microbes interact in four main regions within the plant, the rhizosphere, endosphere, phyllosphere, and spermosphere. This mini review covers the challenges within investigations of plant and microbe interactions. We highlight the importance of sample preparation and comparisons among time-of-flight secondary ion mass spectroscopy (ToF-SIMS), matrix-assisted laser desorption/ionization (MALDI), laser desorption ionization (LDI/LDPI), and desorption electrospray ionization (DESI) techniques used for the analysis of these interactions. Using mass spectral imaging (MSI) to study plants and microbes offers advantages in understanding microbe and host interactions at the molecular level with single-cell and community communication information. More research utilizing MSI has emerged in the past several years. We first introduce the principles of major MSI techniques that have been employed in the research of microorganisms. An overview of proper sample preparation methods is offered as a prerequisite for successful MSI analysis. Traditionally, dried or cryogenically prepared, frozen samples have been used; however, they do not provide a true representation of the bacterial biofilms compared to living cell analysis and chemical imaging. New developments such as microfluidic devices that can be used under a vacuum are highly desirable for the application of MSI techniques, such as ToF-SIMS, because they have a subcellular spatial resolution to map and image plant and microbe interactions, including the potential to elucidate metabolic pathways and cell-to-cell interactions. Promising results due to recent MSI advancements in the past five years are selected and highlighted. The latest developments utilizing machine learning are captured as an important outlook for maximal output using MSI to study microorganisms.

Robust phenotyping of highly multiplexed tissue imaging data using pixel-level clustering

While technologies for multiplexed imaging have provided an unprecedented understanding of tissue composition in health and disease, interpreting this data remains a significant computational challenge. To understand the spatial organization of tissue and how it relates to disease processes, imaging studies typically focus on cell-level phenotypes. However, images can capture biologically important objects that are outside of cells, such as the extracellular matrix. Here, we describe a pipeline, Pixie, that achieves robust and quantitative annotation of pixel-level features using unsupervised clustering and show its application across a variety of biological contexts and multiplexed imaging platforms. Furthermore, current cell phenotyping strategies that rely on unsupervised clustering can be labor intensive and require large amounts of manual cluster adjustments. We demonstrate how pixel clusters that lie within cells can be used to improve cell annotations. We comprehensively evaluate pre-processing steps and parameter choices to optimize clustering performance and quantify the reproducibility of our method. Importantly, Pixie is open source and easily customizable through a user-friendly interface.

Extended Similarity Methods for Efficient Data Mining in Imaging Mass Spectrometry

Imaging mass spectrometry is a label-free imaging modality that allows for the spatial mapping of many compounds directly in tissues. In an imaging mass spectrometry experiment, a raster of the tissue surface produces a mass spectrum at each sampled x , y position, resulting in thousands of individual mass spectra, each comprising a pixel in the resulting ion images. However, efficient analysis of imaging mass spectrometry datasets can be challenging due to the hyperspectral characteristics of the data. Each spectrum contains several thousand unique compounds at discrete m/z values that result in unique ion images, which demands robust and efficient algorithms for searching, statistical analysis, and visualization. Some traditional post-processing techniques are fundamentally ill-equipped to dissect these types of data. For example, while principal component analysis (PCA) has long served as a useful tool for mining imaging mass spectrometry datasets to identify correlated analytes and biological regions of interest, the interpretation of the PCA scores and loadings can be non-trivial. The loadings often containing negative peaks in the PCA-derived pseudo-spectra, which are difficult to ascribe to underlying tissue biology. Herein, we have utilized extended similarity indices to streamline the interpretation of imaging mass spectrometry data. This novel workflow uses PCA as a pixel-selection method to parse out the most and least correlated pixels, which are then compared using the extended similarity indices. The extended similarity indices complement PCA by removing all non-physical artifacts and streamlining the interpretation of large volumes of IMS spectra simultaneously. The linear complexity, O ( N ) , of these indices suggests that large imaging mass spectrometry datasets can be analyzed in a 1:1 scale of time and space with respect to the size of the input data. The extended similarity indices algorithmic workflow is exemplified here by identifying discrete biological regions of mouse brain tissue.

Untangling Alzheimer's disease with spatial multi-omics: a brief review

Alzheimer's disease (AD) is the most common form of neurological dementia, specified by extracellular β-amyloid plaque deposition, neurofibrillary tangles, and cognitive impairment. AD-associated pathologies like cerebral amyloid angiopathy (CAA) are also affiliated with cognitive impairment and have overlapping molecular drivers, including amyloid buildup. Discerning the complexity of these neurological disorders remains a significant challenge, and the spatiomolecular relationships between pathogenic features of AD and AD-associated pathologies remain poorly understood. This review highlights recent developments in spatial omics, including profiling and molecular imaging methods, and how they are applied to AD. These emerging technologies aim to characterize the relationship between how specific cell types and tissue features are organized in combination with mapping molecular distributions to provide a systems biology view of the tissue microenvironment around these neuropathologies. As spatial omics methods achieve greater resolution and improved molecular coverage, they are enabling deeper characterization of the molecular drivers of AD, leading to new possibilities for the prediction, diagnosis, and mitigation of this debilitating disease.

Microscopy-Directed Imaging Mass Spectrometry for Rapid High Spatial Resolution Molecular Imaging of Glomeruli

The glomerulus is a multicellular functional tissue unit (FTU) of the nephron that is responsible for blood filtration. Each glomerulus contains multiple substructures and cell types that are crucial for their function. To understand normal aging and disease in kidneys, methods for high spatial resolution molecular imaging within these FTUs across whole slide images is required. Here we demonstrate a workflow using microscopy-driven selected sampling to enable 5 μm pixel size matrix-assisted laser desorption/ionization imaging mass spectrometry (MALDI IMS) of all glomeruli within whole slide human kidney tissues. Such high spatial resolution imaging entails large numbers of pixels, increasing the data acquisition times. Automating FTU-specific tissue sampling enables high-resolution analysis of critical tissue structures, while concurrently maintaining throughput. Glomeruli were automatically segmented using coregistered autofluorescence microscopy data, and these segmentations were translated into MALDI IMS measurement regions. This allowed high-throughput acquisition of 268 glomeruli from a single whole slide human kidney tissue section. Unsupervised machine learning methods were used to discover molecular profiles of glomerular subregions and differentiate between healthy and diseased glomeruli. Average spectra for each glomerulus were analyzed using Uniform Manifold Approximation and Projection (UMAP) and k-means clustering, yielding 7 distinct groups of differentiated healthy and diseased glomeruli. Pixel-wise k-means clustering was applied to all glomeruli, showing unique molecular profiles localized to subregions within each glomerulus. Automated microscopy-driven, FTU-targeted acquisition for high spatial resolution molecular imaging maintains high-throughput and enables rapid assessment of whole slide images at cellular resolution and identification of tissue features associated with normal aging and disease.

Multimodal Image Fusion Offers Better Spatial Resolution for Mass Spectrometry Imaging

High-resolution reconstruction has attracted increasing research interest in mass spectrometry imaging (MSI), but it remains a challenging ill-posed problem. In the present study, we proposed a deep learning model to fuse multimodal images to enhance the spatial resolution of MSI data, namely, DeepFERE. Hematoxylin and eosin (H&E) stain microscopy imaging was used to pose constraints in the process of high-resolution reconstruction to alleviate the ill-posedness. A novel model architecture was designed to achieve multi-task optimization by incorporating multi-modal image registration and fusion in a mutually reinforced framework. Experimental results demonstrated that the proposed DeepFERE model is able to produce high-resolution reconstruction images with rich chemical information and a detailed structure on both visual inspection and quantitative evaluation. In addition, our method was found to be able to improve the delimitation of the boundary between cancerous and para-cancerous regions in the MSI image. Furthermore, the reconstruction of low-resolution spatial transcriptomics data demonstrated that the developed DeepFERE model may find wider applications in biomedical fields.

Navigating the bridge between wet and dry lab toxicology research to address current challenges with high-dimensional data

Toxicology research has rapidly evolved, leveraging increasingly advanced technologies in high-throughput approaches to yield important information on toxicological mechanisms and health outcomes. Data produced through toxicology studies are consequently becoming larger, often producing high-dimensional data. These types of data hold promise for imparting new knowledge, yet inherently have complexities causing them to be a rate-limiting element for researchers, particularly those that are housed in "wet lab" settings (i.e., researchers that use liquids to analyze various chemicals and biomarkers as opposed to more computationally focused, "dry lab" researchers). These types of challenges represent topics of ongoing conversation amongst our team and researchers in the field. The aim of this perspective is to i) summarize hurdles in analyzing high-dimensional data in toxicology that require improved training and translation for wet lab researchers, ii) highlight example methods that have aided in translating data analysis techniques to wet lab researchers; and iii) describe challenges that remain to be effectively addressed, to date, in toxicology research. Specific aspects include methodologies that could be introduced to wet lab researchers, including data pre-processing, machine learning, and data reduction. Current challenges discussed include model interpretability, study biases, and data analysis training. Example efforts implemented to translate these data analysis techniques are also mentioned, including online data analysis resources and hands-on workshops. Questions are also posed to continue conversation in the toxicology community. Contents of this perspective represent timely issues broadly occurring in the fields of bioinformatics and toxicology that require ongoing dialogue between wet and dry lab researchers.

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.

Rapid Multivariate Analysis Approach to Explore Differential Spatial Protein Profiles in Tissue

Spatially targeted proteomics analyzes the proteome of specific cell types and functional regions within tissue. While spatial context is often essential to understanding biological processes, interpreting sub-region-specific protein profiles can pose a challenge due to the high-dimensional nature of the data. Here, we develop a multivariate approach for rapid exploration of differential protein profiles acquired from distinct tissue regions and apply it to analyze a published spatially targeted proteomics data set collected from Staphylococcus aureus-infected murine kidney, 4 and 10 days postinfection. The data analysis process rapidly filters high-dimensional proteomic data to reveal relevant differentiating species among hundreds to thousands of measured molecules. We employ principal component analysis (PCA) for dimensionality reduction of protein profiles measured by microliquid extraction surface analysis mass spectrometry. Subsequently, k-means clustering of the PCA-processed data groups samples by chemical similarity. Cluster center interpretation revealed a subset of proteins that differentiate between spatial regions of infection over two time points. These proteins appear involved in tricarboxylic acid metabolomic pathways, calcium-dependent processes, and cytoskeletal organization. Gene ontology analysis further uncovered relationships to tissue damage/repair and calcium-related defense mechanisms. Applying our analysis in infectious disease highlighted differential proteomic changes across abscess regions over time, reflecting the dynamic nature of host-pathogen interactions.

MALDI IMS-Derived Molecular Contour Maps: Augmenting Histology Whole-Slide Images

Imaging mass spectrometry (IMS) provides untargeted, highly multiplexed maps of molecular distributions in tissue. Ion images are routinely presented as heatmaps and can be overlaid onto complementary microscopy images that provide greater context. However, heatmaps use transparency blending to visualize both images, obscuring subtle quantitative differences and distribution gradients. Here, we developed a contour mapping approach that combines information from IMS ion intensity distributions with that of stained microscopy. As a case study, we applied this approach to imaging data from Staphylococcus aureus-infected murine kidney. In a univariate, or single molecular species, use-case of the contour map representation of IMS data, certain lipids colocalizing with regions of infection were selected using Pearson's correlation coefficient. Contour maps of these lipids overlaid with stained microscopy showed enhanced visualization of lipid distributions and spatial gradients in and around the bacterial abscess as compared to traditional heatmaps. The full IMS data set comprising hundreds of individual ion images was then grouped into a smaller subset of representative patterns using non-negative matrix factorization (NMF). Contour maps of these multivariate NMF images revealed distinct molecular profiles of the major abscesses and surrounding immune response. This contour mapping workflow also enabled a molecular visualization of the transition zone at the host-pathogen interface, providing potential clues about the spatial molecular dynamics beyond what histological staining alone provides. In summary, we developed a new IMS-based contour mapping approach to augment classical stained microscopy images, providing an enhanced and more interpretable visualization of IMS-microscopy multimodal molecular imaging data sets.

Systems Immunology Approaches to Metabolism

Over the last decade, immunometabolism has emerged as a novel interdisciplinary field of research and yielded significant fundamental insights into the regulation of immune responses. Multiple classical approaches to interrogate immunometabolism, including bulk metabolic profiling and analysis of metabolic regulator expression, paved the way to appreciating the physiological complexity of immunometabolic regulation in vivo. Studying immunometabolism at the systems level raised the need to transition towards the next-generation technology for metabolic profiling and analysis. Spatially resolved metabolic imaging and computational algorithms for multi-modal data integration are new approaches to connecting metabolism and immunity. In this review, we discuss recent studies that highlight the complex physiological interplay between immune responses and metabolism and give an overview of technological developments that bear the promise of capturing this complexity most directly and comprehensively.

MSIr: Automatic Registration Service for Mass Spectrometry Imaging and Histology

Mass spectrometry imaging (MSI) is a powerful tool that can be used to simultaneously investigate the spatial distribution of different molecules in samples. However, it is difficult to comprehensively analyze complex biological systems with only a single analytical technique due to different analytical properties and application limitations. Therefore, many analytical methods have been combined to extend data interpretation, evaluate data credibility, and facilitate data mining to explore important temporal and spatial relationships in biological systems. Image registration is an initial and critical step for multimodal imaging data fusion. However, the image registration of multimodal images is not a simple task. The property difference between each data modality may include spatial resolution, image characteristics, or both. The image registrations between MSI and different imaging techniques are often achieved indirectly through histology. Many methods exist for image registration between MSI data and histological images. However, most of them are manual or semiautomatic and have their prerequisites. Here, we built MSI Registrar (MSIr), a web service for automatic registration between MSI and histology. It can help to reduce subjectivity and processing time efficiently. MSIr provides an interface for manually selecting region of interests from histological images; the user selects regions of interest to extract the corresponding spectrum indices in MSI data. In the performance evaluation, MSIr can quickly map MSI data to histological images and help pinpoint molecular components at specific locations in tissues. Most registrations were adequate and were without excessive shifts. MSIr is freely available at https://msir.cmdm.tw and https://github.com/CMDM-Lab/MSIr.

Spatial segmentation of mass spectrometry imaging data featuring selected principal components

Spatial segmentation aims to find homogeneous/heterogeneous subgroups of spectra or ion images in mass spectrometry imaging (MSI) data. The maps it generated inform researchers of vital characteristics of the data and thus provide the basis for strategizing further biological analysis. Dimensional reduction and clustering are two basic steps of segmentation. Due to the variations in the quality, resolution, density of spectral information, and sizes, not all datasets could be segmented ideally with combinations of different dimensional reduction and clustering algorithms. Here, we proposed a segmentation pipeline that utilized pattern compression by principal component analysis (PCA) and represented by principal components. Instead of preprocessed or raw MSI data, normalized principal components were used for the segmentation process. Multiple datasets of rat brains and mouse kidneys were tested, and the proposed segmentation pipeline presented the obvious advantage of easy-to-use and can be readily intergraded with other existing innovative pipelines.

Classification of Pancreatic Ductal Adenocarcinoma Using MALDI Mass Spectrometry Imaging Combined with Neural Networks

Despite numerous diagnostic and therapeutic advances, pancreatic ductal adenocarcinoma (PDAC) has a high mortality rate, and is the fourth leading cause of cancer death in developing countries. Besides its increasing prevalence, pancreatic malignancies are characterized by poor prognosis. Omics technologies have potential relevance for PDAC assessment but are time-intensive and relatively cost-intensive and limited by tissue heterogeneity. Matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI) can obtain spatially distinct peptide-signatures and enables tumor classification within a feasible time with relatively low cost. While MALDI-MSI data sets are inherently large, machine learning methods have the potential to greatly decrease processing time. We present a pilot study investigating the potential of MALDI-MSI in combination with neural networks, for classification of pancreatic ductal adenocarcinoma. Neural-network models were trained to distinguish between pancreatic ductal adenocarcinoma and other pancreatic cancer types. The proposed methods are able to correctly classify the PDAC types with an accuracy of up to 86% and a sensitivity of 82%. This study demonstrates that machine learning tools are able to identify different pancreatic carcinoma from complex MALDI data, enabling fast prediction of large data sets. Our results encourage a more frequent use of MALDI-MSI and machine learning in histopathological studies in the future.

Divide and Conquer: A Flexible Deep Learning Strategy for Exploring Metabolic Heterogeneity from Mass Spectrometry Imaging Data

Research on metabolic heterogeneity provides an important basis for the study of the molecular mechanism of a disease and personalized treatment. The screening of metabolism-related sub-regions that affect disease development is essential for the more focused exploration on disease progress aberrant phenotypes, even carcinogenesis and metastasis. The mass spectrometry imaging (MSI) technique has distinct advantages to reveal the heterogeneity of an organism based on in situ molecular profiles. The challenge of heterogeneous analysis has been to perform an objective identification among biological tissues with different characteristics. By introducing the divide-and-conquer strategy to architecture design and application, we establish here a flexible unsupervised deep learning model, called divide-and-conquer (dc)-DeepMSI, for metabolic heterogeneity analysis from MSI data without prior knowledge of histology. dc-DeepMSI can be used to identify either spatially contiguous regions of interest (ROIs) or spatially sporadic ROIs by designing two specific modes, spat-contig and spat-spor. Comparison results on fetus mouse data demonstrate that the dc-DeepMSI outperforms state-of-the-art MSI segmentation methods. We demonstrate that the novel learning strategy successfully obtained sub-regions that are statistically linked to the invasion status and molecular phenotypes of breast cancer as well as organizing principles during developmental phase.

Delineating regions of interest for mass spectrometry imaging by multimodally corroborated spatial segmentation

Mass spectrometry imaging (MSI), which localizes molecules in a tag-free, spatially resolved manner, is a powerful tool for the understanding of underlying biochemical mechanisms of biological phenomena. When analyzing MSI data, it is essential to delineate regions of interest (ROIs) that correspond to tissue areas of different anatomical or pathological labels. Spatial segmentation, obtained by clustering MSI pixels according to their mass spectral similarities, is a popular approach to automate ROI definition. However, how to select the number of clusters (#Clusters), which determines the granularity of segmentation, remains to be resolved, and an inappropriate #Clusters may lead to ROIs not biologically real. Here we report a multimodal fusion strategy to enable an objective and trustworthy selection of #Clusters by utilizing additional information from corresponding histology images. A deep learning-based algorithm is proposed to extract "histomorphological feature spectra" across an entire hematoxylin and eosin image. Clustering is then similarly performed to produce histology segmentation. Since ROIs originating from instrumental noise or artifacts would not be reproduced cross-modally, the consistency between histology and MSI segmentation becomes an effective measure of the biological validity of the results. So, #Clusters that maximize the consistency is deemed as most probable. We validated our strategy on mouse kidney and renal tumor specimens by producing multimodally corroborated ROIs that agreed excellently with ground truths. Downstream analysis based on the said ROIs revealed lipid molecules highly specific to tissue anatomy or pathology. Our work will greatly facilitate MSI-mediated spatial lipidomics, metabolomics, and proteomics research by providing intelligent software to automatically and reliably generate ROIs.

Rapid and Accurate Discrimination of Mycobacterium abscessus Subspecies Based on Matrix-Assisted Laser Desorption Ionization-Time of Flight Spectrum and Machine Learning Algorithms

Mycobacterium abscessus complex (MABC) has been reported to cause complicated infections. Subspecies identification of MABC is crucial for adequate treatment due to different antimicrobial resistance properties amid subspecies. However, long incubation days are needed for the traditional antibiotic susceptibility testing (AST). Delayed effective antibiotics administration often causes unfavorable outcomes. Thus, we proposed a novel approach to identify subspecies and potential antibiotic resistance, guiding early and accurate treatment. Subspecies of MABC isolates were determined by secA1, rpoB, and hsp65. Matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) spectra were analyzed, and informative peaks were detected by random forest (RF) importance. Machine learning (ML) algorithms were used to build models for classifying MABC subspecies based on spectrum. The models were validated by repeated five-fold cross-validation to avoid over-fitting. In total, 102 MABC isolates (52 subspecies abscessus and 50 subspecies massiliense) were analyzed. Top informative peaks including m/z 6715, 4739, etc. were identified. RF model attained AUROC of 0.9166 (95% CI: 0.9072-0.9196) and outperformed other algorithms in discriminating abscessus from massiliense. We developed a MALDI-TOF based ML model for rapid and accurate MABC subspecies identification. Due to the significant correlation between subspecies and corresponding antibiotics resistance, this diagnostic tool guides a more precise and timelier MABC subspecies-specific treatment.

DiviK: divisive intelligent K-means for hands-free unsupervised clustering in big biological data

BACKGROUND

Investigating molecular heterogeneity provides insights into tumour origin and metabolomics. The increasing amount of data gathered makes manual analyses infeasible-therefore, automated unsupervised learning approaches are utilised for discovering tissue heterogeneity. However, automated analyses require experience setting the algorithms' hyperparameters and expert knowledge about the analysed biological processes. Moreover, feature engineering is needed to obtain valuable results because of the numerous features measured.

RESULTS

We propose DiviK: a scalable stepwise algorithm with local data-driven feature space adaptation for segmenting high-dimensional datasets. The algorithm is compared to the optional solutions (regular k-means, spatial and spectral approaches) combined with different feature engineering techniques (None, PCA, EXIMS, UMAP, Neural Ions). Three quality indices: Dice Index, Rand Index and EXIMS score, focusing on the overall composition of the clustering, coverage of the tumour region and spatial cluster consistency, are used to assess the quality of unsupervised analyses. Algorithms were validated on mass spectrometry imaging (MSI) datasets-2D human cancer tissue samples and 3D mouse kidney images. DiviK algorithm performed the best among the four clustering algorithms compared (overall quality score 1.24, 0.58 and 162 for d(0, 0, 0), d(1, 1, 1) and the sum of ranks, respectively), with spectral clustering being mostly second. Feature engineering techniques impact the overall clustering results less than the algorithms themselves (partial [Formula: see text] effect size: 0.141 versus 0.345, Kendall's concordance index: 0.424 versus 0.138 for d(0, 0, 0)).

CONCLUSIONS

DiviK could be the default choice in the exploration of MSI data. Thanks to its unique, GMM-based local optimisation of the feature space and deglomerative schema, DiviK results do not strongly depend on the feature engineering technique applied and can reveal the hidden structure in a tissue sample. Additionally, DiviK shows high scalability, and it can process at once the big omics data with more than 1.5 mln instances and a few thousand features. Finally, due to its simplicity, DiviK is easily generalisable to an even more flexible framework. Therefore, it is helpful for other -omics data (as single cell spatial transcriptomic) or tabular data in general (including medical images after appropriate embedding). A generic implementation is freely available under Apache 2.0 license at https://github.com/gmrukwa/divik .

Emerging Computational Methods in Mass Spectrometry Imaging

Mass spectrometry imaging (MSI) is a powerful analytical technique that generates maps of hundreds of molecules in biological samples with high sensitivity and molecular specificity. Advanced MSI platforms with capability of high-spatial resolution and high-throughput acquisition generate vast amount of data, which necessitates the development of computational tools for MSI data analysis. In addition, computation-driven MSI experiments have recently emerged as enabling technologies for further improving the MSI capabilities with little or no hardware modification. This review provides a critical summary of computational methods and resources developed for MSI data analysis and interpretation along with computational approaches for improving throughput and molecular coverage in MSI experiments. This review is focused on the recently developed artificial intelligence methods and provides an outlook for a future paradigm shift in MSI with transformative computational methods.