malbacR: A Package for Standardized Implementation of Batch Correction Methods for Omics Data

LC-HRMS Lipidomic Fingerprints in Serbian Cohort of Schizophrenia Patients

Schizophrenia (SCH) is a major mental illness that causes impaired cognitive function and long-term disability, so the requirements for reliable biomarkers for early diagnosis and therapy of SCH are essential. The objective of this work was an untargeted lipidomic study of serum samples from a Serbian cohort including 30 schizophrenia (SCH) patients and 31 non-psychiatric control (C) individuals by applying liquid chromatography (LC) coupled with high-resolution mass spectrometry (HRMS) and chemometric analyses. Principal component analysis (PCA) of all samples indicated no clear separation between SCH and C groups but indicated clear gender separation in the C group. Multivariate statistical analyses (PCA and orthogonal partial least squares discriminant analysis (OPLS-DA)) of gender-differentiated SCH and C groups established forty-nine differential lipids in the differentiation of male SCH (SCH-M) patients and male controls (C-M), while sixty putative biomarkers were identified in the differentiation of female SCH patients (SCH-F) and female controls (C-F). Lipidomic study of gender-differentiated groups, between SCH-M and C-M and between SCH-F and C-F groups, confirmed that lipids metabolism was altered and the content of the majority of the most affected lipid classes, glycerophospholipids (GP), sphingolipids (SP), glycerolipids (GL) and fatty acids (FA), was decreased compared to controls. From differential lipid metabolites with higher content in both SCH-M and SCH-F patients groups compared to their non-psychiatric controls, there were four common lipid molecules: ceramides Cer 34:2, and Cer 34:1, lysophosphatidylcholine LPC 16:0 and triacylglycerol TG 48:2. Significant alteration of lipids metabolism confirmed the importance of metabolic pathways in the pathogenesis of schizophrenia.

Evaluating Machine Learning Methods of Analyzing Multiclass Metabolomics

Multiclass metabolomic studies have become popular for revealing the differences in multiple stages of complex diseases, various lifestyles, or the effects of specific treatments. In multiclass metabolomics, there are multiple data manipulation steps for analyzing raw data, which consist of data filtering, the imputation of missing values, data normalization, marker identification, sample separation, classification, and so on. In each step, several to dozens of machine learning methods can be chosen for the given data set, with potentially hundreds or thousands of method combinations in the whole data processing chain. Therefore, a clear understanding of these machine learning methods is helpful for selecting an appropriate method combination for obtaining stable and reliable analytical results of specific data. However, there has rarely been an overall introduction or evaluation of these methods based on multiclass metabolomic data. Herein, detailed descriptions of these machine learning methods in multiple data manipulation steps are reviewed. Moreover, an assessment of these methods was performed using a benchmark data set for multiclass metabolomics. First, 12 imputation methods for imputing missing values were evaluated based on the PSS (Procrustes statistical shape analysis) and NRMSE (normalized root-mean-square error) values. Second, 17 normalization methods for processing multiclass metabolomic data were evaluated by applying the PMAD (pooled median absolute deviation) value. Third, different methods of identifying markers of multiclass metabolomics were evaluated based on the CWrel (relative weighted consistency) value. Fourth, nine classification methods for constructing multiclass models were assessed using the AUC (area under the curve) value. Performance evaluations of machine learning methods are highly recommended to select the most appropriate method combination before performing the final analysis of the given data. Overall, detailed descriptions and evaluation of various machine learning methods are expected to improve analyses of multiclass metabolomic data.