Search

Feature relationships are complex and may contain important information. k top scoring pairs ( k -TSP) studies feature relationships by the horizontal comparison. This study examines feature relationships and proposes vertical and horizontal k -TSP (VH- k -TSP) to identify the discriminative feature pairs by evaluating feature pairs based on the vertical and horizontal comparisons. Complexity is introduced to compute the discriminative abilities of feature pairs by means of these two comparisons. VH- k -TSP was compared with support vector machine-recursive feature elimination, relative simplicity-support vector machine, k -TSP and M- k -TSP on nine public genomics datasets. For multi-class problems, one-to-one method was used. The experiments showed that VH- k -TSP outperformed the four methods in most cases. Then, VH- k -TSP was applied to a metabolomics data of liver disease. An accuracy rate of 88.11 ± 3.30% in discrimination between cirrhosis and hepatocellular carcinoma was obtained by VH- k -TSP, better than 77.39 ± 4.10% and 79.28 ± 3.73% obtained by k -TSP and M- k -TSP, respectively. Hence combining the vertical and horizontal comparisons could define more discriminative feature pairs. [ABSTRACT FROM AUTHOR]

Studies exploring the association of tetrabromobisphenol A (TBBPA) with breast cancer and related mechanisms are limited. To investigate the relationship between TBBPA levels in breast adipose and breast cancer, we carried out case-control research. As well as further examine the mediating role of adipose metabolites between TBBPA and breast cancer using the metabolomics approach. In this study, the concentration of TBBPA was determined utilizing ultra-performance liquid chromatography tandem mass spectrometry (UPLC-MS/MS) after a solid phase extraction (SPE) pretreatment. High-performance liquid chromatography tandem mass spectrometry (HPLC-MS/MS) was employed to analyze adipose metabolomics. Evaluation of metabolites linked to TBBPA exposure and breast cancer was performed utilizing mediation analysis. With an estimated OR (95%CI) of 1.153 (1.023, 1.299), TBBPA was firmly linked with breast cancer. We also used propensity score matching analysis and sensitivity analysis to reduce the effect of confounding factors on the results. Metabolomics of adipose suggested significant perturbation in the linoleic acid metabolism pathway. In addition, for PC (16:0/16:0) as phospholipids, a mediation effect on the associations of TBBPA exposure with breast cancer risks was observed (estimated mediation percentage: 56.58%). Understanding the relationship between TBBPA exposure and the risk of breast cancer may be facilitated by the findings, which point to potential mediation metabolites. [Display omitted] • First mediation analysis of the relationship between TBBPA and breast cancer risk. • TBBPA were associated with increased risk of breast cancer. • Metabolomics indicated a perturbation of the linoleic acid metabolic pathway. • Phospholipids may mediate the association between TBBPA exposure and breast cancer. [ABSTRACT FROM AUTHOR]

Analyzing the biological data by considering the molecule interactions may induce a more accurate identification of disease-related biomarkers. In this study, a novel feature selection method based on molecule (feature) interactive effect network is proposed, denoted as Distance Correlation Gain-Network (DCG-Net). In DCG-Net, DCG is defined to measure the interactive effects between pairwise features with respect to the process of physiological and pathological changes and infer the molecule interactive effect network. DCG index is suitable for discrete random variables and continuous random variables. Then a greedy searching strategy is developed to search the informational modules of the interactive features with high statistical dependence on disease outcome. To evaluate the performance of DCG-Net, it was compared with eight representative feature selection techniques including t -test, ReliefF, SVM-RFE, mRMR, IG-RFE, INDEED, MN-PCC and Dcor-SFS on ten public datasets. The experiment results showed the superior performance of DCG-Net in classification accuracy rate, sensitivity, and specificity for three different classifiers. Subsequently, DCG-Net was employed to analyze a lung adenocarcinoma metabolomics dataset, and the metabolites selected involved in the important pathway and had a better discrimination ability. The experiments demonstrate that DCG can effectively detect the molecular interactions, and incorporation of the molecule interactions is helpful to identify informational biomarkers reflecting the occurrence and development of complex diseases. [Display omitted] • A new method is proposed to extract important information based on feature interactions. • The distance correlation gain suitable for continuous and discrete random variables is defined. • A greedy searching strategy is developed to search the informational modules from the interactive effect network. • Experiments on the public datasets and the application in the metabolomics data showed the validity of the method. • The distance correlation gain is used to explore the interactions between features and construct the molecular network. [ABSTRACT FROM AUTHOR]

Abstract: Filtering the discriminative metabolites from high dimension metabolome data is very important in metabolomics study. Support vector machine-recursive feature elimination (SVM-RFE) is an efficient feature selection technique and has shown promising applications in the analysis of the metabolome data. SVM-RFE measures the weights of the features according to the support vectors, noise and non-informative variables in the high dimension data may affect the hyper-plane of the SVM learning model. Hence we proposed a mutual information (MI)-SVM-RFE method which filters out noise and non-informative variables by means of artificial variables and MI, then conducts SVM-RFE to select the most discriminative features. A serum metabolomics data set from patients with chronic hepatitis B, cirrhosis and hepatocellular carcinoma analyzed by liquid chromatography–mass spectrometry (LC–MS) was used to demonstrate the validation of our method. An accuracy of 74.33±2.98% to distinguish among three liver diseases was obtained, better than 72.00±4.15% from the original SVM-RFE. Thirty-four ion features were defined to distinguish among the control and 3 liver diseases, 17 of them were identified. [Copyright &y& Elsevier]

In metabolomics research, false positive features from non-sample sources and noises usually exist in the peak table, they will make the results of screening differential metabolites or biomarkers unreliable. In this study, a method to remove false positive features (rFPF) was developed to improve the quality of the peak table. rFPF recognizes real peak profiles based on the information entropy and statistical correlation, and eliminates false positive features from non-sample sources and noises. A standard mixture with 42 standards (14 isotopic labeled internal standards and 28 common standards) and a urine sample were applied to evaluate the effectiveness of the rFPF method. The analysis results of metabolite standards showed that more than 92% false positive features were removed by rFPF, but target standards completely remained. The analysis results of urine sample showed that the number of features was significantly reduced from 7182 to 2522. Interestingly, 98% of the identified metabolites remained after removing false positive features. The proposed rFPF shows great prospects as a new data handling method for metabolomics studies. The MATLAB code and data can be downloaded from http://app.ifc.dicp.ac.cn/Confirmation/Authentication.html. Image 1 • A method for removing false positive features was developed. • A metabolite standard mixture and a urine sample were used to validate the effectiveness of the proposed method. • The proposed method largely reduced the number of false positive features but the true target features still remained. [ABSTRACT FROM AUTHOR]

Liquid chromatography-mass spectrometry (LC-MS) is an important analytical platform for metabolomics study. Peak alignment of metabolomics dataset is one of the keys for a successful metabolomics study. In this work, a MS/MS-based peak alignment method for LC-MS metabolomics data was developed. A rigorous strategy for screening endogenous reference variables was proposed. Firstly, candidate endogenous reference variables were selected based on MS, MS/MS and retention time in all samples. Multiple robust endogenous reference variables were obtained through further evaluation and confirmation. Then retention time of each metabolite feature was corrected by local linear regression using the four nearest neighbor robust reference variables. Finally, peak alignment was carried out based on corrected retention time, MS and MS/MS. Comparing with the other two peak alignment methods, the developed method showed a good performance and was suitable for metabolomics data with larger retention time drift. Our approach provides a simple and robust alignment method which is reliable to align LC-MS metabolomics dataset. [ABSTRACT FROM AUTHOR]

Liquid chromatography–mass spectrometry (LC–MS) is now a main stream technique for large-scale metabolic phenotyping to obtain a better understanding of genomic functions. However, repeatability is still an essential issue for the LC–MS based methods, and convincing strategies for long time analysis are urgently required. Our former reported pseudotargeted method which combines nontargeted and targeted analyses, is proved to be a practical approach with high-quality and information-rich data. In this study, we developed a comprehensive strategy based on the pseudotargeted analysis by integrating blank-wash, pooled quality control (QC) sample, and post-calibration for the large-scale metabolomics study. The performance of strategy was optimized from both pre- and post-acquisition sections including the selection of QC samples, insertion frequency of QC samples, and post-calibration methods. These results imply that the pseudotargeted method is rather stable and suitable for large-scale study of metabolic profiling. As a proof of concept, the proposed strategy was applied to the combination of 3 independent batches within a time span of 5 weeks, and generated about 54% of the features with coefficient of variations (CV) below 15%. Moreover, the stability and maximal capability of a single analytical batch could be extended to at least 282 injections (about 110 h) while still providing excellent stability, the CV of 63% metabolic features was less than 15%. Taken together, the improved repeatability of our strategy provides a reliable protocol for large-scale metabolomics studies. [ABSTRACT FROM AUTHOR]

Highlights: [•] Developing the simultaneous determination method of polyamine metabolome. [•] Evaluating the relationship between hepatic cancer and polyamine metabolome. [•] Presenting the polyamine metabolome. [•] Adopting the quantification method in the study of metabonomics. [Copyright &y& Elsevier]