SERS microscopy as a tool for comprehensive biochemical characterization in complex samples.

Surface enhanced Raman scattering (SERS) spectra of biomaterials such as cells or tissues can be used to obtain biochemical information from nanoscopic volumes in these heterogeneous samples. This tutorial review discusses the factors that determine the outcome of a SERS experiment in complex bioorganic samples. They are related to the SERS process itself, the possibility to selectively probe certain regions or constituents of a sample, and the retrieval of the vibrational information in order to identify molecules and their interaction. After introducing basic aspects of SERS experiments in the context of biocompatible environments, spectroscopy in typical microscopic settings is exemplified, including the possibilities to combine SERS with other linear and non-linear microscopic tools, and to exploit approaches that improve lateral and temporal resolution. In particular the great variation of data in a SERS experiment calls for robust data analysis tools. Approaches will be introduced that have been originally developed in the field of bioinformatics for the application to omics data and that show specific potential in the analysis of SERS data. They include the use of simulated data and machine learning tools that can yield chemical information beyond achieving spectral classification.

Exploitation of surrogate variables in random forests for unbiased analysis of mutual impact and importance of features.

MOTIVATION: Random forest is a popular machine learning approach for the analysis of high-dimensional data because it is flexible and provides variable importance measures for the selection of relevant features. However, the complex relationships between the features are usually not considered for the selection and thus also neglected for the characterization of the analysed samples. RESULTS: Here we propose two novel approaches that focus on the mutual impact of features in random forests. Mutual forest impact (MFI) is a relation parameter that evaluates the mutual association of the features to the outcome and, hence, goes beyond the analysis of correlation coefficients. Mutual impurity reduction (MIR) is an importance measure that combines this relation parameter with the importance of the individual features. MIR and MFI are implemented together with testing procedures that generate P-values for the selection of related and important features. Applications to one experimental and various simulated datasets and the comparison to other methods for feature selection and relation analysis show that MFI and MIR are very promising to shed light on the complex relationships between features and outcome. In addition, they are not affected by common biases, e.g. that features with many possible splits or high minor allele frequencies are preferred. AVAILABILITY AND IMPLEMENTATION: The approaches are implemented in Version 0.3.3 of the R package RFSurrogates that is available at github.com/AGSeifert/RFSurrogates and the data are available at doi.org/10.25592/uhhfdm.12620.

Evaluation of variable selection methods for random forests and omics data sets.

Machine learning methods and in particular random forests are promising approaches for prediction based on high dimensional omics data sets. They provide variable importance measures to rank predictors according to their predictive power. If building a prediction model is the main goal of a study, often a minimal set of variables with good prediction performance is selected. However, if the objective is the identification of involved variables to find active networks and pathways, approaches that aim to select all relevant variables should be preferred. We evaluated several variable selection procedures based on simulated data as well as publicly available experimental methylation and gene expression data. Our comparison included the Boruta algorithm, the Vita method, recurrent relative variable importance, a permutation approach and its parametric variant (Altmann) as well as recursive feature elimination (RFE). In our simulation studies, Boruta was the most powerful approach, followed closely by the Vita method. Both approaches demonstrated similar stability in variable selection, while Vita was the most robust approach under a pure null model without any predictor variables related to the outcome. In the analysis of the different experimental data sets, Vita demonstrated slightly better stability in variable selection and was less computationally intensive than Boruta. In conclusion, we recommend the Boruta and Vita approaches for the analysis of high-dimensional data sets. Vita is considerably faster than Boruta and thus more suitable for large data sets, but only Boruta can also be applied in low-dimensional settings.

Integrating biological knowledge and gene expression data using pathway-guided random forests: a benchmarking study.

MOTIVATION: High-throughput technologies allow comprehensive characterization of individuals on many molecular levels. However, training computational models to predict disease status based on omics data is challenging. A promising solution is the integration of external knowledge about structural and functional relationships into the modeling process. We compared four published random forest-based approaches using two simulation studies and nine experimental datasets. RESULTS: The self-sufficient prediction error approach should be applied when large numbers of relevant pathways are expected. The competing methods hunting and learner of functional enrichment should be used when low numbers of relevant pathways are expected or the most strongly associated pathways are of interest. The hybrid approach synthetic features is not recommended because of its high false discovery rate. AVAILABILITY AND IMPLEMENTATION: An R package providing functions for data analysis and simulation is available at GitHub (https://github.com/szymczak-lab/PathwayGuidedRF). An accompanying R data package (https://github.com/szymczak-lab/DataPathwayGuidedRF) stores the processed and quality controlled experimental datasets downloaded from Gene Expression Omnibus (GEO). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Surrogate minimal depth as an importance measure for variables in random forests.

MOTIVATION: It has been shown that the machine learning approach random forest can be successfully applied to omics data, such as gene expression data, for classification or regression and to select variables that are important for prediction. However, the complex relationships between predictor variables, in particular between causal predictor variables, make the interpretation of currently applied variable selection techniques difficult. RESULTS: Here we propose a new variable selection approach called surrogate minimal depth (SMD) that incorporates surrogate variables into the concept of minimal depth (MD) variable importance. Applying SMD, we show that simulated correlation patterns can be reconstructed and that the increased consideration of variable relationships improves variable selection. When compared with existing state-of-the-art methods and MD, SMD has higher empirical power to identify causal variables while the resulting variable lists are equally stable. In conclusion, SMD is a promising approach to get more insight into the complex interplay of predictor variables and outcome in a high-dimensional data setting. AVAILABILITY AND IMPLEMENTATION: https://github.com/StephanSeifert/SurrogateMinimalDepth. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Simplifying the Preparation of Pollen Grains for MALDI-TOF MS Classification.

Matrix-assisted laser desorption ionization time of flight mass spectrometry (MALDI-TOF MS) is a well-implemented analytical technique for the investigation of complex biological samples. In MS, the sample preparation strategy is decisive for the success of the measurements. Here, sample preparation processes and target materials for the investigation of different pollen grains are compared. A reduced and optimized sample preparation process prior to MALDI-TOF measurement is presented using conductive carbon tape as target. The application of conductive tape yields in enhanced absolute signal intensities and mass spectral pattern information, which leads to a clear separation in subsequent pattern analysis. The results will be used to improve the taxonomic differentiation and identification, and might be useful for the development of a simple routine method to identify pollen based on mass spectrometry.

Taxonomic relationships of pollens from matrix-assisted laser desorption/ionization time-of-flight mass spectrometry data using multivariate statistics.

RATIONALE: Matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) has been suggested as a promising tool for the investigation of pollen, but the usefulness of this approach for classification and identification of pollen species has to be proven by an application to samples of varying taxonomic relations. METHOD: MALDI-MS in combination with hierarchical cluster analysis (HCA) and principal component analysis (PCA) was used to delineate taxonomic relations between plants based on pollen biochemistry. To assess the robustness of the approach, pollen of 74 species of the plant orders Fagales and Coniferales were probed. RESULTS: Discrimination at the levels of plant order and genus were achieved using the whole spectral range. In many cases, different species of the same genus could be distinguished. The sources of the spectral/chemical differences at the genus level can be understood using PCA. Specifically, typical mass regions for exact genus detection were identified. CONCLUSIONS: Our results indicate that the chemical information represented by MALDI-TOFMS data is useful for reconstructing taxonomic relationships and is complementary to other chemical information on pollen from other spectroscopic data.

Application of untargeted liquid chromatography-mass spectrometry to routine analysis of food using three-dimensional bucketing and machine learning.

For the detection of food adulteration, sensitive and reproducible analytical methods are required. Liquid chromatography coupled to high-resolution mass spectrometry (LC-HRMS) is a highly sensitive method that can be used to obtain analytical fingerprints consisting of a variety of different components. Since the comparability of measurements carried out with different devices and at different times is not given, specific adulterants are usually detected in targeted analyses instead of analyzing the entire fingerprint. However, this comprehensive analysis is desirable in order to stay ahead in the race against food fraudsters, who are constantly adapting their adulterations to the latest state of the art in analytics. We have developed and optimized an approach that enables the separate processing of untargeted LC­HRMS data obtained from different devices and at different times. We demonstrate this by the successful determination of the geographical origin of honey samples using a random forest model. We then show that this approach can be applied to develop a continuously learning classification model and our final model, based on data from 835 samples, achieves a classification accuracy of 94% for 126 test samples from 6 different countries.

Exploring the potential of high-resolution LC-MS in combination with ion mobility separation and surrogate minimal depth for enhanced almond origin authentication.

Almonds (Prunus dulcisMill.) are consumed worldwide and their geographical origin plays a crucial role in determining their market value. In the present study, a total of 250 almond reference samples from six countries (Australia, Spain, Iran, Italy, Morocco, and the USA) were non-polar extracted and analyzed by UPLC-ESI-IM-qToF-MS. Four harvest periods, more than 30 different varieties, including both sweet and bitter almonds, were considered in the method development. Principal component analysis showed that there are three groups of samples with similarities: Australia/USA, Spain/Italy and Iran/Morocco. For origin determination, a random forest achieved an accuracy of 88.8 %. Misclassifications occurred mainly between almonds from the USA and Australia, due to similar varieties and similar external influences such as climate conditions. Metabolites relevant for classification were selected using Surrogate Minimal Depth, with triacylglycerides containing oxidized, odd chained or short chained fatty acids and some phospholipids proven to be the most suitable marker substances. Our results show that focusing on the identified lipids (e. g., using a QqQ-MS instrument) is a promising approach to transfer the origin determination of almonds to routine analysis.

Opening the Random Forest Black Box of 1H NMR Metabolomics Data by the Exploitation of Surrogate Variables.

The untargeted metabolomics analysis of biological samples with nuclear magnetic resonance (NMR) provides highly complex data containing various signals from different molecules. To use these data for classification, e.g., in the context of food authentication, machine learning methods are used. These methods are usually applied as a black box, which means that no information about the complex relationships between the variables and the outcome is obtained. In this study, we show that the random forest-based approach surrogate minimal depth (SMD) can be applied for a comprehensive analysis of class-specific differences by selecting relevant variables and analyzing their mutual impact on the classification model of different truffle species. SMD allows the assignment of variables from the same metabolites as well as the detection of interactions between different metabolites that can be attributed to known biological relationships.

Comparative Analysis of LC-ESI-IM-qToF-MS and FT-NIR Spectroscopy Approaches for the Authentication of Organic and Conventional Eggs.

The importance of animal welfare and the organic production of chicken eggs has increased in the European Union in recent years. Legal regulation for organic husbandry makes the production of organic chicken eggs more expensive compared to conventional husbandry and thus increases the risk of food fraud. Therefore, the aim of this study was to develop a non-targeted lipidomic LC-ESI-IM-qToF-MS method based on 270 egg samples, which achieved a classification accuracy of 96.3%. Subsequently, surrogate minimal depth (SMD) was applied to select important variables identified as carotenoids and lipids based on their MS/MS spectra. The LC-MS results were compared with FT-NIR spectroscopy analysis as a low-resolution screening method and achieved 80.0% accuracy. Here, SMD selected parts of the spectrum which are associated with lipids and proteins. Furthermore, we used SMD for low-level data fusion to analyze relations between the variables of the LC-MS and the FT-NIR spectroscopy datasets. Thereby, lipid-associated bands of the FT-NIR spectrum were related to the identified lipids from the LC-MS analysis, demonstrating that FT-NIR spectroscopy partially provides similar information about the lipidome. In future applications, eggs can therefore be analyzed with FT-NIR spectroscopy to identify conspicuous samples that can subsequently be counter-tested by mass spectrometry.

Analysis of Hazelnuts (Corylus avellana L.) Stored for Extended Periods by 1H NMR Spectroscopy Monitoring Storage-Induced Changes in the Polar and Nonpolar Metabolome.

Storage is a critical step in the post-harvest processing of hazelnuts, as it can lead to mold, rancidity, and off-flavor. However, there is a lack of analytical methods to detect improper or extended storage. To comprehensively investigate the effects of hazelnut storage, samples were stored under five different conditions for up to 18 months. Subsequently, the polar and nonpolar metabolome were analyzed by 1H NMR spectroscopy and chemometric approaches for classification as well as variable selection. Increases in hexanoic, octanoic, and nonanoic acid, all products of lipid oxidation and responsible for quality defects, were found across all conditions. Furthermore, the concentration of free long-chain fatty acids increased in samples stored at high temperatures. Harsh short-term storage resulted in an increase in fumaric and lactic acid, glucose, fructose, and choline and a decrease in acetic acid.

Food Monitoring: Limitations of Accelerated Storage to Predict Molecular Changes in Hazelnuts (Corylus avellana L.) under Realistic Conditions Using UPLC-ESI-IM-QTOF-MS.

Accelerated storage is routinely used with pharmaceuticals to predict stability and degradation patterns over time. The aim of this is to assess the shelf life and quality under harsher conditions, providing crucial insights into their long-term stability and potential storage issues. This study explores the potential of transferring this approach to food matrices for shelf-life estimation. Therefore, hazelnuts were stored under accelerated short-term and realistic long-term conditions. Subsequently, they were analyzed with high resolution mass spectrometry, focusing on the lipid profile. LC-MS analysis has shown that many unique processes take place under accelerated conditions that do not occur or occur much more slowly under realistic conditions. This mainly involved the degradation of membrane lipids such as phospholipids, ceramides, and digalactosyldiacylglycerides, while oxidation processes occurred at different rates in both conditions. It can be concluded that a food matrix is far too complex and heterogeneous compared to pharmaceuticals, so that many more processes take place during accelerated storage, which is why the results cannot be used to predict molecular changes in hazelnuts stored under realistic conditions.

Effects of lifestyle and associated diseases on serum CC16 suggest complex interactions among metabolism, heart and lungs.

INTRODUCTION: Clara cell 16-kDa protein (CC16) is an anti-inflammatory, immunomodulatory secreted pulmonary protein with reduced serum concentrations in obesity according to recent data. OBJECTIVE: Studies focused solely on bodyweight, which does not properly reflect obesity-associated implications of the metabolic and reno-cardio-vascular system. The purpose of this study was therefore to examine CC16 in a broad physiological context considering cardio-metabolic comorbidities of primary pulmonary diseases. METHODS: CC16 was quantified in serum samples in a subset of the FoCus (N = 497) and two weight loss intervention cohorts (N = 99) using ELISA. Correlation and general linear regression analyses were applied to assess CC16 effects of lifestyle, gut microbiota, disease occurrence and treatment strategies. Importance and intercorrelation of determinants were validated using random forest algorithms. RESULTS: CC16 A38G gene mutation, smoking and low microbial diversity significantly decreased CC16. Pre-menopausal female displayed lower CC16 compared to post-menopausal female and male participants. Biological age and uricosuric medications increased CC16 (all p < 0.01). Adjusted linear regression revealed CC16 lowering effects of high waist-to-hip ratio (est. -11.19 [-19.4; -2.97], p = 7.99 × 10-3), severe obesity (est. -2.58 [-4.33; -0.82], p = 4.14 × 10-3) and hypertension (est. -4.31 [-7.5; -1.12], p = 8.48 × 10-3). ACEi/ARB medication (p = 2.5 × 10-2) and chronic heart failure (est. 4.69 [1.37; 8.02], p = 5.91 × 10-3) presented increasing effects on CC16. Mild associations of CC16 were observed with blood pressure, HOMA-IR and NT-proBNP, but not manifest hyperlipidemia, type 2 diabetes, diet quality and dietary weight loss intervention. CONCLUSION: A role of metabolic and cardiovascular abnormalities in the regulation of CC16 and its modifiability by behavioral and pharmacological interventions is indicated. Alterations by ACEi/ARB and uricosurics could point towards regulatory axes comprising the renin-angiotensin-aldosterone system and purine metabolism. Findings altogether strengthen the importance of interactions among metabolism, heart and lungs.

Matrix-assisted laser desorption/ionization mass spectrometric investigation of pollen and their classification by multivariate statistics.

RATIONALE: A fast and reliable online identification of pollen is not yet available. The identification of pollen is based mainly on the evaluation of morphological data obtained by microscopic methods. METHODS: Matrix-assisted laser desorption/ionization mass spectrometry (MALDI-TOF MS) was applied to the analysis of extracts and milled pollen samples. The obtained MALDI data were explored for characteristic peak patterns which could be subjected to a multivariate statistical analysis. RESULTS: Two sample preparation methods are presented, which require only minimal or no chemical extraction of the pollen. MALDI pollen spectra could be recorded showing various peak patterns. A multivariate statistics approach allowed the classification of pollen into clusters indicating similarities and differences between various species. CONCLUSIONS: These results demonstrate the potential and the reliability of MALDI-TOF MS for the identification and, in combination with multivariate statistics, also for the classification of pollen.

Multivariate Raman mapping for phenotypic characterization in plant tissue sections.

Identifying and characterizing the biochemical variation in plant tissues is an important task in many research fields. Small spectral differences of the plant cell wall that are caused by genetic or environmental influences may be superimposed by individual variation as well as by a microscopic heterogeneity in molecular composition and structure of different histological substructures. A set of 56 samples from Cucumis sativus (cucumber) plants, comprising a total of ~168,000 spectra from tissue sections of leaf, stem, and roots was investigated by Raman microspectroscopic mapping excited at 532 nm. A multivariate analysis was carried out in order to assess the variation of the spectra with respect to origin of the tissue, the histological (cell wall) substructures, and the possibility to discriminate the spectra obtained from different individuals that had been subjected to two different conditions during growth. Combining the results of principal component analysis (PCA) based classification with the original spatial information in the maps of 23 sections of leaf xylem, variation in cell wall composition is found for four different individuals that also includes a discrimination of tissue grown in the presence and absence of additional silicic acid in the irrigation water of the plants. The spectral data point to differences in a contribution by carotenoids, as well as by hydroxycinnamic acids to the spectra. The results give new insight into the chemical heterogeneity of plant tissues and may be useful for elucidating biochemical processes associated with biomineralization by vibrational spectroscopy.

Opening the Random Forest Black Box of the Metabolome by the Application of Surrogate Minimal Depth.

For the untargeted analysis of the metabolome of biological samples with liquid chromatography-mass spectrometry (LC-MS), high-dimensional data sets containing many different metabolites are obtained. Since the utilization of these complex data is challenging, different machine learning approaches have been developed. Those methods are usually applied as black box classification tools, and detailed information about class differences that result from the complex interplay of the metabolites are not obtained. Here, we demonstrate that this information is accessible by the application of random forest (RF) approaches and especially by surrogate minimal depth (SMD) that is applied to metabolomics data for the first time. We show this by the selection of important features and the evaluation of their mutual impact on the multi-level classification of white asparagus regarding provenance and biological identity. SMD enables the identification of multiple features from the same metabolites and reveals meaningful biological relations, proving its high potential for the comprehensive utilization of high-dimensional metabolomics data.

Application of random forest based approaches to surface-enhanced Raman scattering data.

Surface-enhanced Raman scattering (SERS) is a valuable analytical technique for the analysis of biological samples. However, due to the nature of SERS it is often challenging to exploit the generated data to obtain the desired information when no reporter or label molecules are used. Here, the suitability of random forest based approaches is evaluated using SERS data generated by a simulation framework that is also presented. More specifically, it is demonstrated that important SERS signals can be identified, the relevance of predefined spectral groups can be evaluated, and the relations of different SERS signals can be analyzed. It is shown that for the selection of important SERS signals Boruta and surrogate minimal depth (SMD) and for the analysis of spectral groups the competing method Learner of Functional Enrichment (LeFE) should be applied. In general, this investigation demonstrates that the combination of random forest approaches and SERS data is very promising for sophisticated analysis of complex biological samples.

Combining Chemical Information From Grass Pollen in Multimodal Characterization.

The analysis of pollen chemical composition is important to many fields, including agriculture, plant physiology, ecology, allergology, and climate studies. Here, the potential of a combination of different spectroscopic and spectrometric methods regarding the characterization of small biochemical differences between pollen samples was evaluated using multivariate statistical approaches. Pollen samples, collected from three populations of the grass Poa alpina, were analyzed using Fourier-transform infrared (FTIR) spectroscopy, Raman spectroscopy, surface enhanced Raman scattering (SERS), and matrix assisted laser desorption/ionization mass spectrometry (MALDI-TOF MS). The variation in the sample set can be described in a hierarchical framework comprising three populations of the same grass species and four different growth conditions of the parent plants for each of the populations. Therefore, the data set can work here as a model system to evaluate the classification and characterization ability of the different spectroscopic and spectrometric methods. ANOVA Simultaneous Component Analysis (ASCA) was applied to achieve a separation of different sources of variance in the complex sample set. Since the chosen methods and sample preparations probe different parts and/or molecular constituents of the pollen grains, complementary information about the chemical composition of the pollen can be obtained. By using consensus principal component analysis (CPCA), data from the different methods are linked together. This enables an investigation of the underlying global information, since complementary chemical data are combined. The molecular information from four spectroscopies was combined with phenotypical information gathered from the parent plants, thereby helping to potentially link pollen chemistry to other biotic and abiotic parameters.

Optical Nanosensing of Lipid Accumulation due to Enzyme Inhibition in Live Cells.

Drugs that influence enzymes of lipid metabolism can cause pathological accumulation of lipids in animal cells. Here, gold nanoparticles, acting as nanosensors that deliver surface-enhanced Raman scattering (SERS) spectra from living cells provide molecular evidence of lipid accumulation in lysosomes after treatment of cultured cells with the three tricyclic antidepressants (TCA) desipramine, amitryptiline, and imipramine. The vibrational spectra elucidate to great detail and with very high sensitivity the composition of the drug-induced lipid accumulations, also observed in fixed samples by electron microscopy and X-ray nanotomography. The nanoprobes show that mostly sphingomyelin is accumulated in the lysosomes but also other lipids, in particular, cholesterol. The observation of sphingomyelin accumulation supports the impairment of the enzyme acid sphingomyelinase. The SERS data were analyzed by random forest based approaches, in particular, by minimal depth variable selection and surrogate minimal depth (SMD), shown here to be particularly useful machine learning tools for the analysis of the lipid signals that contribute only weakly to SERS spectra of cells. SMD is used for the identification of molecular colocalization and interactions of the drug molecules with lipid membranes and for discriminating between the biochemical effects of the three different TCA molecules, in agreement with their different activity. The spectra also indicate that the protein composition is significantly changed in cells treated with the drugs.