Comprehensive exploration of multi-modal and multi-branch imaging markers for autism diagnosis and interpretation: insights from an advanced deep learning model.

Autism spectrum disorder is a complex neurodevelopmental condition with diverse genetic and brain involvement. Despite magnetic resonance imaging advances, autism spectrum disorder diagnosis and understanding its neurogenetic factors remain challenging. We propose a dual-branch graph neural network that effectively extracts and fuses features from bimodalities, achieving 73.9% diagnostic accuracy. To explain the mechanism distinguishing autism spectrum disorder from healthy controls, we establish a perturbation model for brain imaging markers and perform a neuro-transcriptomic joint analysis using partial least squares regression and enrichment to identify potential genetic biomarkers. The perturbation model identifies brain imaging markers related to structural magnetic resonance imaging in the frontal, temporal, parietal, and occipital lobes, while functional magnetic resonance imaging markers primarily reside in the frontal, temporal, occipital lobes, and cerebellum. The neuro-transcriptomic joint analysis highlights genes associated with biological processes, such as "presynapse," "behavior," and "modulation of chemical synaptic transmission" in autism spectrum disorder's brain development. Different magnetic resonance imaging modalities offer complementary information for autism spectrum disorder diagnosis. Our dual-branch graph neural network achieves high accuracy and identifies abnormal brain regions and the neuro-transcriptomic analysis uncovers important genetic biomarkers. Overall, our study presents an effective approach for assisting in autism spectrum disorder diagnosis and identifying genetic biomarkers, showing potential for enhancing the diagnosis and treatment of this condition.

Sunflower Pollen-Derived Microspheres Selectively Absorb DNA for microRNA Detection.

Herein, we report the finding that a naturally sunflower pollen-derived microspheres (HSECs) with hierarchical structures can selectively absorb polyC and polyA with high efficiency and affinity. HSECs exhibit the capability to selectively absorb polyC and polyA ssDNA under neutral and acidic conditions. It has been observed that the presence of metal cations, specifically Ca2+, enhances the absorption efficiency of HSECs. Mechanically, this absorption phenomenon can be attributed to both electrostatic interactions and cation-π interactions. Such an appealing property enables the functionalization of HSECs for broad potential biomedical applications, such as microRNA detection.

Brain functional activity-based classification of autism spectrum disorder using an attention-based graph neural network combined with gene expression.

Autism spectrum disorder (ASD) is a complex brain neurodevelopmental disorder related to brain activity and genetics. Most of the ASD diagnostic models perform feature selection at the group level without considering individualized information. Evidence has shown the unique topology of the individual brain has a fundamental impact on brain diseases. Thus, a data-constructing method fusing individual topological information and a corresponding classification model is crucial in ASD diagnosis and biomarker discovery. In this work, we trained an attention-based graph neural network (GNN) to perform the ASD diagnosis with the fusion of graph data. The results achieved an accuracy of 79.78%. Moreover, we found the model paid high attention to brain regions mainly involved in the social-brain circuit, default-mode network, and sensory perception network. Furthermore, by analyzing the covariation between functional magnetic resonance imaging data and gene expression, current studies detected several ASD-related genes (i.e. MUTYH, AADAT, and MAP2), and further revealed their links to image biomarkers. Our work demonstrated that the ASD diagnostic framework based on graph data and attention-based GNN could be an effective tool for ASD diagnosis. The identified functional features with high attention values may serve as imaging biomarkers for ASD.

Solid self-microemulsifying drug delivery system (S-SMEDDS) prepared by spray drying to improve the oral bioavailability of cinnamaldehyde (CA).

The aim of this study was to prepare a solid self-microemulsifying drug delivery system (S-SMEDDS) of cinnamaldehyde (CA) by spray drying technique to improve the oral bioavailability of CA. The preparation of CA S-SMEDDS with maltodextrin as the solid carrier, a core-wall material mass ratio of 1:1, a solid content of 20% (w/v), an inlet air temperature of 150 °C, an injection speed of 5.2 mL/min, and an atomization pressure of 0.1 MPa was determined by using the encapsulation rate as the index of investigation. Differential scanning calorimetry (DSC) revealed the possibility of CA being encapsulated in S-SMEDDS in an amorphous form. The in-vitro release showed that the total amount of CA released by S-SMEDDS was approximately 1.3 times higher than that of the CA suspension. Pharmacokinetic results showed that the relative oral bioavailability of CA S-SMEDDS was also increased to 1.6-fold compared to CA suspension. Additionally, we explored the mechanism of CA uptake and transport of lipid-soluble drugs CA by S-SMEDDS in a Caco-2/HT29 cell co-culture system for the first time. The results showed that CA S-SMEDDS uptake on the co-culture model was mainly an energy-dependent endocytosis mechanism, including lattice protein-mediated endocytosis and vesicle-mediated endocytosis. Transport experiments showed that CA S-SMEDDS significantly increased the permeability of CA in this model. These findings suggested that CA S-SMEDDS is an effective oral solid dosage form for increasing the oral bioavailability of lipid-soluble drug CA.

Nitrogen-doped titanium dioxide/schwertmannite nanocomposites as heterogeneous photo-Fenton catalysts with enhanced efficiency for the degradation of bisphenol A.

Potential health risks related to environmental endocrine disruptors (EEDs) have aroused research hotspots at the forefront of water treatment technologies. Herein, nitrogen-doped titanium dioxide/schwertmannite nanocomposites (N-TiO2/SCH) have been successfully developed as heterogeneous catalysts for the degradation of typical EEDs via photo-Fenton processes. Due to the sustainable Fe(III)/Fe(II) conversion induced by photoelectrons, as-prepared N-TiO2/SCH nanocomposites exhibit much enhanced efficiency for the degradation of bisphenol A (BPA; ca. 100% within 60 min under visible irradiation) in a wide pH range of 3.0-7.8, which is significantly higher than that of the pristine schwertmannite (ca. 74.5%) or N-TiO2 (ca. 10.8%). In this photo-Fenton system, the efficient degradation of BPA is mainly attributed to the oxidation by hydroxyl radical (•OH) and singlet oxygen (1O2). Moreover, the possible catalytic mechanisms and reaction pathway of BPA degradation are systematically investigated based on analytical and photoelectrochemical analyses. This work not only provides a feasible means for the development of novel heterogeneous photo-Fenton catalysts, but also lays a theoretical foundation for the potential application of mineral-based materials in wastewater treatment.

Shifting-corrected regularized regression for 1H NMR metabolomics identification and quantification.

The process of identifying and quantifying metabolites in complex mixtures plays a critical role in metabolomics studies to obtain an informative interpretation of underlying biological processes. Manual approaches are time-consuming and heavily reliant on the knowledge and assessment of nuclear magnetic resonance (NMR) experts. We propose a shifting-corrected regularized regression method, which identifies and quantifies metabolites in a mixture automatically. A detailed algorithm is also proposed to implement the proposed method. Using a novel weight function, the proposed method is able to detect and correct peak shifting errors caused by fluctuations in experimental procedures. Simulation studies show that the proposed method performs better with regard to the identification and quantification of metabolites in a complex mixture. We also demonstrate real data applications of our method using experimental and biological NMR mixtures.

Urantide alleviates atherosclerosis-related liver and kidney injury via the Wnt/ß-catenin signaling pathway in ApoE(-/-) mice.

OBJECTIVE: To investigate the role of urantide in the prevention and treatment of atherosclerosis (AS)-related liver and kidney injury by antagonizing the urotensin II/urotensin receptor (UII/UT) system and regulating the Wnt/ß-catenin signaling pathway. METHODS: Atherosclerotic ApoE-/- mice were treated with 20 mg/kg, 30 mg/kg, and 40 mg/kg urantide for 14 days. RESULTS: When ApoE-/- mice developed AS, significant pathological changes occurred in the liver and kidney, and the UII/UT system in tissue was highly activated; furthermore, the Wnt/ß-catenin signalling pathway was activated, and proteins related to this signalling pathway, such as GSK-3ß, AXIN2, CK­1, and APC, were significantly downregulated. After urantide treatment, the pathological damage to the liver and kidney was effectively improved, the activity of the UII/UT system was effectively inhibited, and the expression of the Wnt/ß-catenin signalling pathway and related proteins was restored. Wnt/ß-catenin signals were mainly localized in the cytoplasm, renal tubules, and interstitium. CONCLUSION: Urantide could improve AS-related liver and kidney injury by antagonizing the UII/UT system, and the improvements in liver and kidney function in atherosclerotic ApoE-/- mice may be related to inhibition of the Wnt/ß-catenin signalling pathway.

Partial breast reconstruction of 30 cases with peri-mammary artery perforator flaps.

BACKGROUND: Volume replacement is one of the vital techniques of oncoplastic surgery (OPS) when applying breast-conserving surgery. The clinical application of peri-mammary artery perforator flaps for this indication is uneven in China. Here, we describe the results of our clinical experience with peri-mammary artery flaps for partial breast reconstruction. METHODS: In this study, 30 patients underwent partial breast resection for quadrant breast cancer followed by partial breast reconstruction with peri-mammary artery perforator flaps, which included the thoracodorsal artery perforator flap (TDAP), anterior intercostal artery perforator flap (AICAP), lateral intercostal artery perforator flap (LICAP), and lateral thoracic artery perforator flap (LTAP). All the patients' operation plans were discussed comprehensively and were performed by sticking to every step. The satisfaction outcome was assessed with the extracted version of the BREAST-Q version 2.0, Breast Conserving Therapy Module Preoperative and Postoperative Scales both preoperatively and postoperatively. RESULTS: According to the study outcomes, the mean flap size was 5.3*4.2*2.8 cm (3.0-7.0*3.0-5.0*1.0-3.5 cm). The mean surgical time was 142 min (100-250 min). No partial flap failure was detected, and no severe complications were observed. Most patients were satisfied with the outcomes regarding the dressing, sexual life, and breast shape postoperation. Furthermore, the sensation of the surgical area, scar satisfaction, and recovery state gradually improved. Overall, LICAP and AICAP had higher scores when different flaps were compared. CONCLUSIONS: Based on this study, we found that peri-mammary artery flaps had significant value in breast-conserving surgery, especially in patients with small or medium-sized breasts. Perforators could be detected by vascular ultrasound before the operation. More than one perforator could be found most of the time. No severe complications occurred when performing a suitable plan, including discussing and recording the operation procedure; the focus of care, the choice for precise and proper perforators, and the mechanism for hiding the scars were all considered and recorded in a specific chart. Patients were satisfied with the reconstruction technique of peri-mammary artery perforator flaps after breast-conserving, and the satisfaction of AICAP and LICAP was higher. In general, this technique is suitable for partial breast reconstruction and has no negative impact on patient satisfaction.

Enhanced catalytic activity and stability of composite of cellulose film and nano zero-valent iron on Juncus effusus for activating peroxydisulfate to degrade Rhodamine B dye.

In this study, a novel peroxydisulfate (PDS) activator (CF-nZVI-JE) was prepared via in-situ loading nano zero-valent iron (nZVI) on Juncus effusus (JE) followed with wrapping a layer of cellulose film (CF). The CF-nZVI-JE had the same 3D structure as the JE, being easy to separate from aqueous solution. The loaded nZVI existed single nanoparticles with a size of 60-100 nm except chain-type agglomeration of nanoparticles due to the stabilization of JE fibers. The activation performance of the CF-nZVI-JE for PDS was evaluated with Rhodamine B (Rh B) as a representative pollutant. Under the optimal activating conditions, the degradation rate of Rh B reached 99% within 30 min in the CF-nZVI-JE/PDS system. After five cycles, the degradation rate of Rh B was still over 85%, suggesting that the CF-nZVI-JE had good reusability. More interestingly, SO4·- and ·OH radicals were simultaneously detected in the CF-nZVI-JE/PDS system, but only SO4·- existed in the JE-ZVI/PDS system, suggesting the different activation mechanism. Meanwhile, the introduction of CF not only facilitated to the mineralization of Rh B but also significantly reduced the release amount of iron ions. Hence, the CF-nZVI-JE can be employed as a promising PDS activator for the treatment of organic wastewater.

Leveraging the HMBC to Facilitate Metabolite Identification.

The accuracy and ease of metabolite assignments from a complex mixture are expected to be facilitated by employing a multispectral approach. The two-dimensional (2D) 1H-13C heteronuclear single quantum coherence (HSQC) and 2D 1H-1H-total correlation spectroscopy (TOCSY) are the experiments commonly used for metabolite assignments. The 2D 1H-13C HSQC-TOCSY and 2D 1H-13C heteronuclear multiple-bond correlation (HMBC) are routinely used by natural products chemists but have seen minimal usage in metabolomics despite the unique information, the nearly complete 1H-1H and 1H-13C and spin systems provided by these experiments that may improve the accuracy and reliability of metabolite assignments. The use of a 13C-labeled feedstock such as glucose is a routine practice in metabolomics to improve sensitivity and to emphasize the detection of specific metabolites but causes severe artifacts and an increase in spectral complexity in the HMBC experiment. To address this issue, the standard HMBC pulse sequence was modified to include carbon decoupling. Nonuniform sampling was also employed for rapid data collection. A dataset of reference 2D 1H-13C HMBC spectra was collected for 94 common metabolites. 13C-13C spin connectivity was then obtained by generating a covariance pseudo-spectrum from the carbon-decoupled HMBC and the 1H-13C HSQC-TOCSY spectra. The resulting 13C-13C pseudo-spectrum provides a connectivity map of the entire carbon backbone that uniquely describes each metabolite and would enable automated metabolite identification.

Absorption enhancement in visible range from Fano resonant silicon nanoparticle arrays embedded in single crystal Mg:Er:LiNbO3synthesized by direct ion implantation.

Fano resonant Si nanoparticles (NPs) are synthesized in single-crystal Mg:Er:LiNbO3using ion implantation and subsequent thermal annealing. The structural and optical properties of the Si NPs embedded in the crystal have been investigated. Spherical particles with radius of about 60 nm are observed by cross-sectional transmission electron microscope, while ion beam analysis are used to characterize the NPs formation process. The absorption of the Mg:Er:LiNbO3crystals have been enhanced significantly due to the embedded Si NPs, which are induced by the Fano resonance effect in the visible light wavelength band. Periodic structures of spherical Si particles model is proposed and analyzed using the Mie theory to study the optical response features and local fields. As a result, numerical simulations demonstrate that periodicities of the array of Si NPs can yield narrow resonant peaks connected with multiple light scattering by the NPs and displaying a Fano-type resonant profile. The wavelengths of the absorption peak show clear red shift with increasing the radius of NPs and the peak intensity can be enhanced by decreasing the array period. This work opens an avenue to modulate the optical filed by embedding Fano resonant Si NPs for potential application in optical devices.

Sulfamethoxazole induces brain capillaries toxicity in zebrafish by up-regulation of VEGF and chemokine signalling.

Sulfamethoxazole (SMX) is a widespread broad-spectrum bacteriostatic antibiotic. Its residual is frequently detected in the water and may therefore bioaccumulate in the brain of aquatic organisms via blood circulation. Brain capillaries toxicity is very important for brain development. However, little information is available in the literature to show the toxicity of SMX to brain development. To study the SMX's brain toxic effects and the related mechanisms, we exposed zebrafish embryos to SMX at different concentrations (0 ppm, 1 ppm, 25 ppm, 100 ppm and 250 ppm) and found that high concentration (250 ppm) of SMX would not only caused an abnormal in malformation rate, hatching rate, body length and survival rate of zebrafish embryos, but also lead to brain oedema. In addition, SMX also induced cerebral ischaemia, aggravates oxidative stress, and changes genes related to oxidative stress (sod1, cat, gpx4, and nrf2). Furthermore, ischaemia caused by SMX could promote ectopic angiogenesis in brain via activating the angiogenesis-related genes (vegfab, cxcr4a, cxcl12b) from 24 h to 53 h. Inhibition of VEGF signalling by SU5416, or inhibition of chemokine downstream PI3K signalling by LY294002, could rescue the brain capillaries toxicity and brain oedema induced by SMX. Our results provide new evidence for the brain toxicity of SMX and its residual danger in the environment and aquatic organisms.

Liposome and microemulsion loaded with ibuprofen: from preparation to mechanism of drug transport.

To compare the difference between liposome (LP) and microemulsion (ME) in delivering ibuprofen (IBU) transdermally and explore relative mechanism. IBU-LP and IBU-ME were prepared by ethanol injection and spontaneous emulsification, respectively. The percutaneous delivery was evaluated using Franz diffusion cells. Fourier transform infra-red spectroscopy (FTIR), differential scanning calorimetry (DSC), activation energy (Ea), and confocal laser scanning microscopy (CLSM) were used to investigate the transdermal mechanism. The particle size and encapsulation efficiency were 228.00 ± 8.60 nm, 86.68 ± 1.43%(w/w) for IBU-LP, and 56.74 ± 7.11 nm, 91.08 ± 3.27%(w/w) for IBU-ME. Percutaneous study showed that formulations enhanced permeation and drug retention in the skin. FTIR and DSC showed that the permeation occurred due to the interaction of the formulations with the lipid bilayer and the protein. The decrease in Ea (1.506 and 0.939 kcal/mol) revealed that the stratum corneum (SC) lipid bilayers were significantly disrupted and this destructive effect of IBU-LP was stronger. IBU-LP was superior to IBU-ME in the aspects of transdermal delivery of IBU.

Improved uptake and bioavailability of cinnamaldehyde via solid lipid nanoparticles for oral delivery.

OBJECTIVE: The purpose of this experiment was to explore the effect of Solid lipid nanoparticles (SLNs) on improving the oral absorption and bioavailability of cinnamaldehyde (CA). METHODS: CA-SLNs were prepared by high-pressure homogenization and characterized by particle size, entrapment efficiency, and morphology, thermal behavior and attenuated total reflection Fourier transform infrared (ATR-FTIR). In vitro characteristics of release, stability experiments, cytotoxicity, uptake and transport across Caco-2 cell monolayer of CA-SLNs were studied as well. In addition, CA-SLNs underwent pharmacokinetic and gastrointestinal mucosal irritation studies in rats. RESULTS: CA-SLNs exhibited a spherical shape with a particle size of 44.57 ± 0.27 nm, zeta potential of -27.66 ± 1.9 mV and entrapment efficiency of 83.63% ± 2.16%. Differential scanning calorimetry (DSC) and ATR-FTIR confirmed that CA was well encapsulated. In vitro release of CA-SLNs displayed that most of the drug (90.77% ± 5%) was released in the phosphate buffer, and only a small amount of drug (18.55% ± 5%) was released in the HCl buffer. CA-SLNs were taken up by an energy-dependent, endocytic mechanism mediated by caveolae mediated endocytosis across Caco-2 cells. The CA permeation through Caco-2 cell was facilitated by CA-SLNs. The outcome of the gastrointestinal irritation test demonstrated that CA-SLNs had no irritation to the rats' intestines. Compared with CA dispersions, incorporation of SLNs increased the oral bioavailability of CA more than 1.69-fold. CONCLUSIONS: It was concluded that CA-SLNs improved the absorption across Caco-2 cell model and improved the oral administration bioavailability of CA in rats.

Increased Power and Accuracy of Causal Locus Identification in Time Series Genome-wide Association in Sorghum.

The phenotypes of plants develop over time and change in response to the environment. New engineering and computer vision technologies track these phenotypic changes. Identifying the genetic loci regulating differences in the pattern of phenotypic change remains challenging. This study used functional principal component analysis (FPCA) to achieve this aim. Time series phenotype data were collected from a sorghum (Sorghum bicolor) diversity panel using a number of technologies including conventional color photography and hyperspectral imaging. This imaging lasted for 37 d and centered on reproductive transition. A new higher density marker set was generated for the same population. Several genes known to control trait variation in sorghum have been previously cloned and characterized. These genes were not confidently identified in genome-wide association analyses at single time points. However, FPCA successfully identified the same known and characterized genes. FPCA analyses partitioned the role these genes play in controlling phenotypes. Partitioning was consistent with the known molecular function of the individual cloned genes. These data demonstrate that FPCA-based genome-wide association studies can enable robust time series mapping analyses in a wide range of contexts. Moreover, time series analysis can increase the accuracy and power of quantitative genetic analyses.

Investigation of novel optical and waveguide characteristics for an air-graphene-LiNbO3system.

The optical characteristics of a planar thin film waveguide system composed of air-graphene-LiNbO3have been investigated. Monolayer or bilayer graphene of high quality are characterized by Raman spectroscopy, scanning electron microscopy and atomic force microscopy. The refractivity and reflectivity of the air-graphene-LiNbO3system are measured experimentally and compared with those of a LiNbO3waveguide by the prism coupling method. The reflectivity shows an overall decrease due to the lower transmittance for graphene on the LiNbO3substrate. The refractivity increases significantly at the wavelength of 1540 nm, which may be attributed to the generation of graphene surface plasmons excited by infrared radiation. A shaped air-graphene-LiNbO3waveguide is designed and simulated by Mode Solutions. The distribution of an optical field is performed and analyzed. The preparation of the proposed air-graphene-LiNbO3structure incorporates the commonly used chemical vapor deposition and thin film transfer techniques, and is compatible with existing optoelectronic integration processes, which can be employed for building various optical integrated devices.

Investigation of optical absorption enhancement of plasmonic configuration by graphene on LiNbO3-SiO2structure.

A novel plasmonic structure is demonstrated by combining graphene with a planar LiNbO3thin layer, which is simple and easy to fabricate compared to the complex design of general graphene surface plasmons devices. Graphene from the chemical vapor deposition is investigated and characterized to be a continuous and uniform monolayer or fewlayer. LiNbO3capped by graphene layer show an extraordinary absorption enhancement in an attenuated total reflection (ATR) measurement at a wide bandwidth of 500-4000 cm-1, which can be explained by resonance absorption resulting from the coupling of graphene surface plasmons with optical modes of LiNbO3-SiO2Fabry-Perot cavity and LiNbO3planar waveguide. The simulation results are generally consistent with the ATR experimental results. The absorption spectra versus temperature of this plasmonic configuration is also investigated, which show that increasing the testing temperature not only highlights the atomic vibrational peaks of graphene, but also enhances the absorption at several characteristic absorption frequencies due to the enhanced coupling between the surface plamons excitations and the optical modes.

Growth dynamics and heritability for plant high-throughput phenotyping studies using hierarchical functional data analysis.

In modern high-throughput plant phenotyping, images of plants of different genotypes are repeatedly taken throughout the growing season, and phenotypic traits of plants (e.g., plant height) are extracted through image processing. It is of interest to recover whole trait trajectories and their derivatives at both genotype and plant levels based on observations made at irregular discrete time points. We propose to model trait trajectories using hierarchical functional principal component analysis (HFPCA) and show that the problem of recovering derivatives of the trajectories is reduced to estimating derivatives of eigenfunctions, which is solved by differentiating eigenequations. Based on HFPCA, we also propose a new measure for the broad-sense heritability by allowing it to vary over time during plant growth. Simulation studies show that the proposed procedure performs better than its competitors in terms of recovering both trait trajectories and their derivatives. Interesting characteristics of plant growth and heritability dynamics are revealed in the application to a modern plant phenotyping study.

Enhancement of near-infrared photoluminescence in Mg:Er:LiNbO3 containing Au nanoparticles synthesized by direct ion implantation.

Embedded gold (Au) nanoparticles (NPs) are formed in Mg:Er:LiNbO3 single crystals by Au ion implantation and subsequent thermal annealing. Absorption of the Mg:Er:LiNbO3 crystals with Au NPs is found to be enhanced significantly in the visible light wavelength band owing to the localized surface plasmon resonance (LSPR) effect. The calculated LSPR effect by Mie theory shows good agreement with the absorption spectra. A significantly enhanced Er related photoluminescence (PL) at 1.54 µm for crystals with Au NPs is also observed compared with samples without Au NPs. Energy transfer between Au NPs and Er is found to be responsible for the PL enhancement in the as-implanted samples while local field enhancement induced by LSPR is considered the dominant factor in the annealed samples. The dependence of PL enhancement on NP size makes it possible to tailor intensity by varying the annealing temperature. An avenue to enhance and modulate the PL of dielectrics with embedding Au NPs synthesized by ion implantation is presented in this study.

Evaluation of Multivariate Classification Models for Analyzing NMR Metabolomics Data.

Analytical techniques such as NMR and mass spectrometry can generate large metabolomics data sets containing thousands of spectral features derived from numerous biological observations. Multivariate data analysis is routinely used to uncover the underlying biological information contained within these large metabolomics data sets. This is typically accomplished by classifying the observations into groups (e.g., control versus treated) and by identifying associated discriminating features. There are a variety of classification models to select from, which include some well-established techniques (e.g., principal component analysis [PCA], orthogonal projection to latent structure [OPLS], or partial least-squares projection to latent structures [PLS]) and newly emerging machine learning algorithms (e.g., support vector machines or random forests). However, it is unclear which classification model, if any, is an optimal choice for the analysis of metabolomics data. Herein, we present a comprehensive evaluation of five common classification models routinely employed in the metabolomics field and that are also currently available in our MVAPACK metabolomics software package. Simulated and experimental NMR data sets with various levels of group separation were used to evaluate each model. Model performance was assessed by classification accuracy rate, by the area under a receiver operating characteristic (AUROC) curve, and by the identification of true discriminating features. Our findings suggest that the five classification models perform equally well with robust data sets. Only when the models are stressed with subtle data set differences does OPLS emerge as the best-performing model. OPLS maintained a high-prediction accuracy rate and a large area under the ROC curve while yielding loadings closest to the true loadings with limited group separations.