Discriminating extra virgin olive oils from common edible oils: Comparable performance of PLS-DA models trained on low-field and high-field 1H NMR data.

INTRODUCTION: Olive oil, derived from the olive tree (Olea europaea L.), is used in cooking, cosmetics, and soap production. Due to its high value, some producers adulterate olive oil with cheaper edible oils or fraudulently mislabel oils as olive to increase profitability. Adulterated products can cause allergic reactions in sensitive individuals and can lack compounds which contribute to the perceived health benefits of olive oil, and its corresponding premium price. OBJECTIVE: There is a need for robust methods to rapidly authenticate olive oils. By utilising machine learning models trained on the nuclear magnetic resonance (NMR) spectra of known olive oil and edible oils, samples can be classified as olive and authenticated. While high-field NMRs are commonly used for their superior resolution and sensitivity, they are generally prohibitively expensive to purchase and operate for routine screening purposes. Low-field benchtop NMR presents an affordable alternative. METHODS: We compared the predictive performance of partial least squares discrimination analysis (PLS-DA) models trained on low-field 60 MHz benchtop proton (1H) NMR and high-field 400 MHz 1H NMR spectra. The data were acquired from a sample set consisting of 49 extra virgin olive oils (EVOOs) and 45 other edible oils. RESULTS: We demonstrate that PLS-DA models trained on low-field NMR spectra are highly predictive when classifying EVOOs from other oils and perform comparably to those trained on high-field spectra. We demonstrated that variance was primarily driven by regions of the spectra arising from olefinic protons and ester protons from unsaturated fatty acids in models derived from data at both field strengths.

Evaluation of normalization strategies for GC-based metabolomics.

INTRODUCTION: For many samples studied by GC-based metabolomics applications, extensive sample preparation involving extraction followed by a two-step derivatization procedure of methoximation and trimethylsilylation (TMS) is typically required to expand the metabolome coverage. Performing normalization is critical to correct for variations present in samples and any biases added during the sample preparation steps and analytical runs. Addressing the totality of variations with an adequate normalization method increases the reliability of the downstream data analysis and interpretation of the results. OBJECTIVES: Normalizing to sample mass is one of the most commonly employed strategies, while the total peak area (TPA) as a normalization factor is also frequently used as a post-acquisition technique. Here, we present a new normalization approach, total derivatized peak area (TDPA), where data are normalized to the intensity of all derivatized compounds. TDPA relies on the benefits of silylation as a universal derivatization method for GC-based metabolomics studies. METHODS: Two sample classes consisting of systematically incremented sample mass were simulated, with the only difference between the groups being the added amino acid concentrations. The samples were TMS derivatized and analyzed using comprehensive two-dimensional gas chromatography coupled to time-of-flight mass spectrometry (GC × GC-TOFMS). The performance of five normalization strategies (no normalization, normalized to sample mass, TPA, total useful peak area (TUPA), and TDPA) were evaluated on the acquired data. RESULTS: Of the five normalization techniques compared, TUPA and TDPA were the most effective. On PCA score space, they offered a clear separation between the two classes. CONCLUSION: TUPA and TDPA carry different strengths: TUPA requires peak alignment across all samples, which depends upon the completion of the study, while TDPA is free from the requirement of alignment. The findings of the study would enhance the convenient and effective use of data normalization strategies and contribute to overcoming the data normalization challenges that currently exist in the metabolomics community.

Antibacterial Activity and Untargeted Metabolomics Profiling of Acalypha arvensis Poepp.

The search for potent antimicrobial compounds is critical in the face of growing antibiotic resistance. This study explores Acalypha arvensis Poepp. (A. arvensis), a Caribbean plant traditionally used for disease treatment. The dried plant powder was subjected to successive extractions using different solvents: hexane (F1), dichloromethane (F2), methanol (F3), a 50:50 mixture of methanol and water (F4), and water (F5). Additionally, a parallel extraction was conducted using a 50:50 mixture of methanol and chloroform (F6). All the fractions were evaluated for their antimicrobial activity, and the F6 fraction was characterized using untargeted metabolomics using SPME-GC×GC-TOFMS. The extracts of A. arvensis F3, F4, and F5 showed antibacterial activity against Staphylococcus aureus ATCC 25923 (5 mg/mL), MRSA BA22038 (5 mg/mL), and Pseudomonas aeruginosa ATCC 27853 (10 mg/mL), and fraction F6 showed antibacterial activity against Staphylococcus aureus ATCC 29213 (2 mg/mL), Escherichia coli ATCC 25922 (20 mg/mL), Pseudomonas aeruginosa ATCC 27853 (10 mg/mL), Enterococcus faecalis ATCC 29212 (10 mg/mL), Staphylococcus aureus 024 (2 mg/mL), and Staphylococcus aureus 003 (2 mg/mL). Metabolomic analysis of F6 revealed 2861 peaks with 58 identified compounds through SPME and 3654 peaks with 29 identified compounds through derivatization. The compounds included methyl ester fatty acids, ethyl ester fatty acids, terpenes, ketones, sugars, amino acids, and fatty acids. This study represents the first exploration of A. arvensis metabolomics and its antimicrobial potential, providing valuable insights for plant classification, phytochemical research, and drug discovery.

Use of reconstituted kefir consortia to determine the impact of microbial composition on kefir metabolite profiles.

Kefir is fermented traditionally with kefir grains, but commercial kefir production often relies on fermentation with planktonic cultures. Kefir has been associated with many health benefits, however, the utilization of kefir grains to facilitate large industrial production of kefir is challenging and makes to difficult to ensure consistent product quality and consistency. Notably, the microbial composition of kefir fermentations has been shown to impact kefir associated health benefits. This study aimed to compare volatile compounds, organic acids, and sugar composition of kefir produced through a traditional grain fermentation and through a reconstituted kefir consortium fermentation. Additionally, the impact of two key microbial communities on metabolite production in kefir was assessed using two modified versions of the consortium, with either yeasts or lactobacilli removed. We hypothesized that the complete kefir consortium would closely resemble traditional kefir, while the consortia without yeasts or lactobacilli would differ significantly from both traditional kefir and the complete consortium fermentation. Kefir fermentations were examined after 12 and 18 h using two-dimensional gas chromatography-time-of-flight mass spectrometry (GC × GC-TOFMS) to identify volatile compounds and high performance liquid chromatography (HPLC) to identify organic acid and sugar composition. The traditional kefir differed significantly from the kefir consortium fermentation with the traditional kefir having 15-20 log2(fold change) higher levels of esters and the consortium fermented kefir having between 1 and 3 log2(fold change) higher organic acids including lactate and acetate. The use of a version of kefir consortium that lacked lactobacilli resulted in between 2 and 20 log2(fold change) lower levels of organic acids, ethanol, and butanoic acid ethyl ester, while the absence of yeast from the consortium resulted in minimal change. In summary, the kefir consortium fermentation is significantly different from traditional grain fermented kefir with respect to the profile of metabolites present, and seems to be driven by lactobacilli, as evidenced by the significant decrease in multiple metabolites when the lactobacilli were removed from the fermentation and minimal differences observed upon the removal of yeast.

Untargeted Metabolomic Profiling of Aqueous and Lyophilized Pooled Human Feces from Two Diet Cohorts Using Two-Dimensional Gas Chromatography Coupled with Time-of-Flight Mass Spectrometry.

The metabolic profiles of human feces are influenced by various genetic and environmental factors, which makes feces an attractive biosample for numerous applications, including the early detection of gut diseases. However, feces is complex, heterogeneous, and dynamic with a significant live bacterial biomass. With such challenges, stool metabolomics has been understudied compared to other biospecimens, and there is a current lack of consensus on methods to collect, prepare, and analyze feces. One of the critical steps required to accelerate the field is having a metabolomics stool reference material available. Fecal samples are generally presented in two major forms: fecal water and lyophilized feces. In this study, two-dimensional gas chromatography coupled with time-of-flight mass spectrometry (GC×GC-TOFMS) was used as an analytical platform to characterize pooled human feces, provided by the National Institute of Standards and Technology (NIST) as Research-Grade Test Materials. The collected fecal samples were derived from eight healthy individuals with two different diets: vegans and omnivores, matched by age, sex, and body mass index (BMI), and stored as fecal water and lyophilized feces. Various data analysis strategies were presented to determine the differences in the fecal metabolomic profiles. The results indicate that the sample storage condition has a major influence on the metabolic profiles of feces such that the impact from storage surpasses the metabolic differences from the diet types. The findings of the current study would contribute towards the development of a stool reference material.

PARAFAC2×N: Coupled decomposition of multi-modal data with drift in N modes.

Analysis of GC×GC-TOFMS data for large numbers of poorly-resolved peaks, and for large numbers of samples remains an enduring problem that hinders the widespread application of the technique. For multiple samples, GC×GC-TOFMS data for specific chromatographic regions manifests as a 4th order tensor of I mass spectral acquisitions, J mass channels, K modulations, and L samples. Chromatographic drift is common along both the first-dimension (modulations), and along the second-dimension (mass spectral acquisitions), while drift along the mass channel is for all practical purposes nonexistent. A number of solutions to handling GC×GC-TOFMS data have been proposed: these involve reshaping the data to make it amenable to either 2nd order decomposition techniques based on Multivariate Curve Resolution (MCR), or 3rd order decomposition techniques such as Parallel Factor Analysis 2 (PARAFAC2). PARAFAC2 has been utilised to model chromatographic drift along one mode, which has enabled its use for robust decomposition of multiple GC-MS experiments. Although extensible, it is not straightforward to implement a PARAFAC2 model that accounts for drift along multiple modes. In this submission, we demonstrate a new approach and a general theory for modelling data with drift along multiple modes, for applications in multidimensional chromatography with multivariate detection. The proposed model captures over 99.9% of variance for a synthetic data set, presenting an extreme example of peak drift and co-elution across two modes of separation.

The Metabolomic Profile of the Essential Oil from Zanthoxylum caribaeum (syn. chiloperone) Growing in Guadeloupe FWI using GC × GC-TOFMS.

The essential oil (EO) from the leaves of Zanthoxylum caribaeum (syn. Chiloperone) (Rutaceae) was studied previously for its acaricidal, antimicrobial, antioxidant, and insecticidal properties. In prior studies, the most abundant compound class found in leaf oils from Brazil, Costa Rica, and Paraguay was terpenoids. Herein, essential oil from the leaves of Zanthoxylum caribaeum (prickly yellow, bois chandelle blanc (FWI), peñas Blancas (Costa Rica), and tembetary hu (Paraguay)) growing in Guadeloupe was analyzed with comprehensive two-dimensional gas chromatography coupled to time-of-flight mass spectrometry (GC × GC-TOFMS), and thirty molecules were identified. A comparison with previously published leaf EO compositions of the same species growing in Brazil, Costa Rica, and Paraguay revealed a number of molecules in common such as ß-myrcene, limonene, ß-caryophyllene, α-humulene, and spathulenol. Some molecules identified in Zanthoxylum caribaeum from Guadeloupe showed some antimetabolic effects on enzymes; the in-depth study of this plant and its essential oil with regard to metabolic diseases merits further exploration.

Untargeted region of interest selection for gas chromatography - mass spectrometry data using a pseudo F-ratio moving window.

There are many challenges associated with analysing gas chromatography - mass spectrometry (GC-MS) data. Many of these challenges stem from the fact that electron ionization (EI) can make it difficult to recover molecular information due to the high degree of fragmentation with concomitant loss of molecular ion signal. With GC-MS data there are often many common fragment ions shared among closely-eluting peaks, necessitating sophisticated methods for analysis. Some of these methods are fully automated, but make some assumptions about the data which can introduce artifacts during the analysis. Chemometric methods such as Multivariate Curve Resolution (MCR), or Parallel Factor Analysis (PARAFAC/PARAFAC2) are particularly attractive, since they are flexible and make relatively few assumptions about the data - ideally resulting in fewer artifacts. These methods do require expert user intervention to determine the most relevant regions of interest and an appropriate number of components, k, for each region. Automated region of interest selection is needed to permit automated batch processing of chromatographic data with advanced signal deconvolution. Here, we propose a new method for automated, untargeted region of interest selection that accounts for the multivariate information present in GC-MS data to select regions of interest based on the ratio of the squared first, and second singular values from the Singular Value Decomposition (SVD) of a window that moves across the chromatogram. Assuming that the first singular value accounts largely for signal, and that the second singular value accounts largely for noise, it is possible to interpret the relationship between these two values as a probabilistic distribution of Fisher Ratios. The sensitivity of the algorithm was tested by investigating the concentration at which the algorithm can no longer pick out chromatographic regions known to contain signal. The algorithm achieved detection of features in a GC-MS chromatogram at concentrations below 10 pg on-column. The resultant probabilities can be interpreted as regions that contain features of interest.

Henry's Law Constants and Indoor Partitioning of Microbial Volatile Organic Compounds.

Microbial volatile organic compounds (MVOCs) play an essential role in many environmental fields, such as indoor air quality. Long-term exposure to odorous and toxic MVOCs can negatively affect the health of occupants. Recently, the involvement of surface reservoirs in indoor chemistry has been realized, which signifies the importance of the phase partitioning of volatile organic pollutants. However, reliable partition coefficients of many MVOCs are currently lacking. Equilibrium partition coefficients, such as Henry's law constant, H, are crucial for understanding the environmental behavior of chemicals. This study aims to experimentally determine the H values and their temperature dependence for key MVOCs under temperature relevant to the indoor environment. The H values were determined with the inert gas-stripping (IGS) method and variable phase ratio headspace (VPR-HS) technique. A two-dimensional partitioning model was applied to predict the indoor phase distribution of MVOCs and potential exposure pathways to the residences. The findings show that the MVOCs are likely distributed between the gas and weakly polar (e.g., organic-rich) reservoirs indoors. Temperature and the volume of reservoirs can sensitively affect indoor partitioning. Our results give a more comprehensive view of indoor chemical partitioning and exposure.

Global metabolome analysis of Dunaliella tertiolecta, Phaeobacter italicus R11 Co-cultures using thermal desorption - Comprehensive two-dimensional gas chromatography - Time-of-flight mass spectrometry (TD-GC×GC-TOFMS).

Dunaliella tertiolecta is a marine microalgae that has been studied extensively as a potential carbon-neutral biofuel source (Tang et al., 2011). Microalgae oil contains high quantities of energy-rich fatty acids and lipids, but is not yet commercially viable as an alternative fuel. Carefully optimised growth conditions, and more recently, algal-bacterial co-cultures have been explored as a way of improving the yield of D. tertiolecta microalgae oils. The relationship between the host microalgae and bacterial co-cultures is currently poorly understood. Here, a complete workflow is proposed to analyse the global metabolomic profile of co-cultured D. tertiolectra and Phaeobacter italicus R11, which will enable researchers to explore the chemical nature of this relationship in more detail. To the best of the authors' knowledge this study is one of the first of its kind, in which a pipeline for an entirely untargeted analysis of the algal metabolome is proposed using a practical sample preparation, introduction, and data analysis routine.

Unique ion filter-A data reduction tool for chemometric analysis of raw comprehensive two-dimensional gas chromatography-mass spectrometry data.

Comprehensive gas chromatography with time of flight mass spectrometry is a powerful tool in the analysis of complex samples. Chemometric analysis of raw chromatographic data is more useful in one- and two-dimensional separations relative to peak tables. The data volume from such experiments generally necessitates the use of data reduction tools. Such tools often sacrifice some of the multivariate information in the mass to charge ratio dimension. The unique ion filter reduces the over-redundancy in two-dimensional gas chromatography-mass spectrometry data by limiting the data to a few unique/pseudo-unique ions, sub-peaks/slices in the first dimension, and spectra in the second dimension. We explore the performance of this algorithm through careful inspection of two-dimensional gas chromatography-mass spectrometry data before and after application of the filter. A reduction (99%) in the number of variables in a two-dimensional gas chromatography-mass spectrometry chromatogram passed on to subsequent analysis was observed. Feature selection times for model optimization reduced from 229 (±13) to 6.8 (±0.5) min when the filter was applied. An estimate of two unique/pseudo-unique ions, one sub-peak in the first dimension and five spectra in the second dimension were considered to provide a true representation of each chromatogram and provided enough information to achieve 100% model prediction accuracy.

Infection of canola by the root pathogen Plasmodiophora brassicae increases resistance to aboveground herbivory by bertha armyworm, Mamestra configurata Walker (Lepidoptera: Noctuidae).

Infection of plants by pathogens can result in the upregulation of induced defenses; plants may be more or less susceptible to attack by insect herbivores following infection. We investigated the interaction between canola, Brassica napus L., plants infected with clubroot, Plasmodiophora brassicae Woronin, and a generalist herbivore the bertha armyworm (BAW) Mamestra configurata Walker using two canola cultivars that varied in susceptibility to clubroot disease. Volatile organic compounds released from experimental plants differed with infection and female adult BAW could discriminate between canola plants inoculated with P. brassicae and disease-free plants. Adult female moths preferentially laid eggs on disease-free plants of the susceptible cultivar to P. brassicae. Inoculation of resistant canola with P. brassicae, however, did not influence oviposition by female BAW. The fitness of BAW larvae was reduced when they were reared on susceptible canola inoculated with P. brassicae. Salicylic acid and its conjugates in susceptible canola plants were induced following P. brassicae inoculation as compared to disease-free susceptible plants. We conclude that suppression of BAW oviposition and offspring fitness may result in part from a change in the volatile profile of the plant as a result of inoculation and the induction of defenses in inoculated susceptible canola.

Towards Standardization of Data Normalization Strategies to Improve Urinary Metabolomics Studies by GC×GC-TOFMS.

Urine is a popular biofluid for metabolomics studies due to its simple, non-invasive collection and its availability in large quantities, permitting frequent sampling, replicate analyses, and sample banking. The biggest disadvantage with using urine is that it exhibits significant variability in concentration and composition within an individual over relatively short periods of time (arising from various external factors and internal processes regulating the body's water and solute content). In treating the data from urinary metabolomics studies, one must account for the natural variability of urine concentrations to avoid erroneous data interpretation. Amongst various proposed approaches to account for broadly varying urine sample concentrations, normalization to creatinine has been widely accepted and is most commonly used. MS total useful signal (MSTUS) is another normalization method that has been recently reported for mass spectrometry (MS)-based metabolomics studies. Herein, we explored total useful peak area (TUPA), a modification of MSTUS that is applicable to GC×GC-TOFMS (and data from other separations platforms), for sample normalization in urinary metabolomics studies. Performance of TUPA was compared to the two most common normalization approaches, creatinine adjustment and Total Peak Area (TPA) normalization. Each normalized dataset was evaluated using Principal Component Analysis (PCA). The results showed that TUPA outperformed alternative normalization methods to overcome urine concentration variability. Results also conclusively demonstrate the risks in normalizing data to creatinine.

Comprehensive characterization of mainstream marijuana and tobacco smoke.

Recent increases in marijuana use and legalization without adequate knowledge of the risks necessitate the characterization of the billions of nanoparticles contained in each puff of smoke. Tobacco smoke offers a benchmark given that it has been extensively studied. Tobacco and marijuana smoke particles are quantitatively similar in volatility, shape, density and number concentration, albeit with differences in size, total mass and chemical composition. Particles from marijuana smoke are on average 29% larger in mobility diameter than particles from tobacco smoke and contain 3.4× more total mass. New measurements of semi-volatile fractions determine over 97% of the mass and volume of the particles from either smoke source are comprised of semi-volatile compounds. For tobacco and marijuana smoke, respectively, 4350 and 2575 different compounds are detected, of which, 670 and 536 (231 in common) are tentatively identified, and of these, 173 and 110 different compounds (69 in common) are known to cause negative health effects through carcinogenic, mutagenic, teratogenic, or other toxic mechanisms. This study demonstrates striking similarities between marijuana and tobacco smoke in terms of their physical and chemical properties.

Thermodynamics-based retention maps to guide column choices for comprehensive multi-dimensional gas chromatography.

Comprehensive two-dimensional gas chromatography (GC × GC) provides enhanced separation power over its one-dimensional counterpart - gas chromatography (GC). This enhancement is achieved by the inclusion of a secondary column, the choice of which is a major determinant on the quality of the ultimate separation. When developing and optimizing a new GC × GC method, the choices of stationary phase chemistries, geometries and configurations (which phase serves in which dimension) are of fundamental importance, and must often be addressed even before the manipulation of instrumental conditions. These choices are often made using educated guesses, literature searches, or trial and error. Thermodynamic models of GC separations; however, provide a fast and easy means of acquiring information for guiding these choices. By using characteristic thermodynamic parameters (characteristic temperatures, Tchar, and characteristic thermal constants, θchar), we demonstrate the generation of maps that can inform the choices of column chemistries, phase ratios and configurations for GC × GC separations.

Thermodynamics-based modelling of gas chromatography separations across column geometries and systems, including the prediction of peak widths.

Thermodynamics-based models have been demonstrated to be useful for predicting retention time and peak widths in gas chromatography and two-dimensional gas chromatography separations. However, the collection of data to train the models can be time consuming, which lessens the practical utility of the method. In this contribution, a method for obtaining thermodynamic-based data to predict peak widths in temperature-programmed gas chromatography is presented. Experimental work to collect data for peak width prediction is identical to that required to collect data for retention time prediction using approaches that we have presented previously. Using this combined approach, chromatograms including retention times and peak widths are predicted with very high accuracy. Typical errors in retention time are < 0.5%, while errors in peak width are typically < 5% as demonstrated using polycycic aromatic hydrocarbons and a mixture containing compounds with aldehyde, ketone, alkene, alkane, alcohol, and ester functionalities.

A simple, fast, and accurate thermodynamic-based approach for transfer and prediction of GC retention times between columns and instruments Part II: Estimation of target column geometry.

The transfer of thermodynamic parameters governing retention of a molecule in gas chromatography from a reference column to a target column is a difficult problem. Successful transfer demands a mechanism whereby the column geometries of both columns can be determined with high accuracy. This is the second part in a series of three papers. In Part I of this work we introduced a new approach to determine the actual effective geometry of a reference column and thermodynamic-based parameters of a suite of compounds on the column. Part II, presented here, illustrates the rapid estimation of the effective inner diameter (or length) and the effective phase ratio of a target column. The estimation model based on the principle of least squares; a fast Quasi-Newton optimization algorithm was developed to provide adequate computational speed. The model and optimization algorithm were tested and validated using simulated and experimental data. This study, together with the work in Parts I and III, demonstrates a method that improves the transferability of thermodynamic models of gas chromatography retention between gas chromatography columns.

A simple, fast, and accurate thermodynamic-based approach for transfer and prediction of gas chromatography retention times between columns and instruments Part III: Retention time prediction on target column.

This is the third part of a three-part series of papers. In Part I, we presented a method for determining the actual effective geometry of a reference column as well as the thermodynamic-based parameters of a set of probe compounds in an in-house mixture. Part II introduced an approach for estimating the actual effective geometry of a target column by collecting retention data of the same mixture of probe compounds on the target column and using their thermodynamic parameters, acquired on the reference column, as a bridge between both systems. Part III, presented here, demonstrates the retention time transfer and prediction from the reference column to the target column using experimental data for a separate mixture of compounds. To predict the retention time of a new compound, we first estimate its thermodynamic-based parameters on the reference column (using geometric parameters determined previously). The compound's retention time on a second column (of previously determined geometry) is then predicted. The models and the associated optimization algorithms were tested using simulated and experimental data. The accuracy of predicted retention times shows that the proposed approach is simple, fast, and accurate for retention time transfer and prediction between gas chromatography columns.

A simple, fast, and accurate thermodynamic-based approach for transfer and prediction of gas chromatography retention times between columns and instruments Part I: Estimation of reference column geometry and thermodynamic parameters.

The transfer of retention times based on thermodynamic models between columns can aid in separation optimization and compound identification in gas chromatography. Although earlier investigations have been reported, this problem remains unsuccessfully addressed. One barrier is poor predictive accuracy when moving from a reference column or system to a new target column or system. This is attributed to challenges associated with the accurate determination of the effective geometric parameters of the columns. To overcome this, we designed least squares-based models that account for geometric parameters of the columns and thermodynamic parameters of compounds as they partition between mobile and stationary phases. Quasi-Newton-based algorithms were then used to perform the numerical optimization. In this first of three parts, the model used to determine the geometric parameters of the reference column and the thermodynamic parameters of compounds subjected to separation is introduced. As will be shown, the overall approach significantly improves the predictive accuracy and transferability of thermodynamic data (and retention times) between columns of the same stationary phase chemistry. The data required for the determination of the thermodynamic parameters and retention time prediction are obtained from fast and simple experiments. The proposed model and optimization algorithms were tested and validated using simulated and experimental data.

Disentangling Structural Confusion through Machine Learning: Structure Prediction and Polymorphism of Equiatomic Ternary Phases ABC.

A method to predict the crystal structure of equiatomic ternary compositions based only on the constituent elements was developed using cluster resolution feature selection (CR-FS) and support vector machine (SVM) classification. The supervised machine-learning model was first trained with 1037 individual compounds that adopt the most populated ternary 1:1:1 structure types (TiNiSi-, ZrNiAl-, PbFCl-, LiGaGe-, YPtAs-, UGeTe-, and LaPtSi-type) and then validated using an additional 519 compounds. The CR-FS algorithm improves class discrimination and indicates that 113 variables including size, electronegativity, number of valence electrons, and position on the periodic table (group number) influence the structure preference. The final model prediction sensitivity, specificity, and accuracy were 97.3%, 93.9%, and 96.9%, respectively, establishing that this method is capable of reliably predicting the crystal structure given only its composition. The power of CR-FS and SVM classification is further demonstrated by segregating the crystal structure of polymorphs, specifically to examine polymorphism in TiNiSi- and ZrNiAl-type structures. Analyzing 19 compositions that are experimentally reported in both structure types, this machine-learning model correctly identifies, with high confidence (>0.7), the low-temperature polymorph from its high-temperature form. Interestingly, machine learning also reveals that certain compositions cannot be clearly differentiated and lie in a "confused" region (0.3-0.7 confidence), suggesting that both polymorphs may be observed in a single sample at certain experimental conditions. The ensuing synthesis and characterization of TiFeP adopting both TiNiSi- and ZrNiAl-type structures in a single sample, even after long annealing times (3 months), validate the occurrence of the region of structural uncertainty predicted by machine learning.