Search

Abstract: Multivariate spectral analysis has been widely applied in chemistry and other fields. Spectral data consisting of measurements at hundreds and even thousands of analytical channels can now be obtained in a few seconds. It is widely accepted that before a multivariate regression model is built, a well-performed variable selection can be helpful to improve the predictive ability of the model. In this paper, the concept of traditional wavelength variable selection has been extended and the idea of variable weighting is incorporated into least-squares support vector machine (LS-SVM). A recently proposed global optimization method, particle swarm optimization (PSO) algorithm is used to search for the weights of variables and the hyper-parameters involved in LS-SVM optimizing the training of a calibration set and the prediction of an independent validation set. All the computation process of this method is automatic. Two real data sets are investigated and the results are compared those of PLS, uninformative variable elimination-PLS (UVE-PLS) and LS-SVM models to demonstrate the advantages of the proposed method. [Copyright &y& Elsevier]

Abstract: In the present study a new version of nonlinear partial least-square method based on artificial neural network transformation (ANN-NLPLS) has been proposed. This algorithm firstly transforms the training descriptors into the hidden layer outputs using the universal nonlinear mapping carried by an artificial neural network, and then utilizes PLS to relate the outputs of the hidden layer to the bioactivities. The weights between the input and hidden layers are optimized by a particle swarm optimization (PSO) method using the criterion of minimized model error via PLS modeling. An F-statistic is introduced to determine automatically the number of PLS components during the weight optimization. The performance is assessed using a simulated data set and two quantitative structure–activity relation (QSAR) data sets. Results of these three data sets demonstrate that ANN-NLPLS offers enhanced capacity in modeling nonlinearity while circumventing the overfitting frequently involved in nonlinear modeling. [Copyright &y& Elsevier]

Biomarker selection has played an increasingly important part in modern medicine with advances of omics techniques. Kohonen self-organizing map is a well-established variable reduction algorithm in identifying significant biomarkers based on variable clustering. However, high dimensionality but small sample size of omics data makes self-organizing map-based model problematic in terms of selection stability and reproducibility. A novel feature screening system is presented in this study by coupling bootstrap with synergy self-organizing map-based orthogonal partial least squares discriminant analysis for stable and biologically meaningful metabolic biomarker selection. In the proposed feature screening system, particle swarm optimization algorithm is utilized to configure synergy self-organizing map-based orthogonal partial least squares discriminant analysis to perform the combination of clusters in a heuristic learning manner, enabling flexible selection of more informative features cost-effectively. Based on the paradigm of ensemble feature selection, bootstrap is adopted to explore significant variables consistently identified across multiple feature selectors rather than a single one. The feasibility of the novel feature screening system is evaluated by two most common inherited metabolic diseases, methylmalonic academia and propionic academia, using urinary metabolomics data. With the desirable classification performance, the proposed feature screening system outperforms simpler techniques in the identification of more features closely correlated with the metabolic mechanisms and the stability of selected candidate biomarkers against sample variations. Besides, the novel feature screening system greatly degrades the sensitivity of identified candidate biomarkers to the network size of self-organizing map, benefiting the identification of a suitable and stable final candidate biomarker list. Image 1 • A novel feature screening system was developed for stable metabolic biomarker selection. • Strategies of cluster combination and ensemble feature selection were involved. • Urinary metabolomics data of methylmalonic academia and propionic academia samples were modeled. • Desirable results were obtained in stable metabolic biomarker selection for inherited metabolic diseases. [ABSTRACT FROM AUTHOR]

Urinary metabolomics coupled with GC-MS has become a leading technology in newborn screening. Because of non-specificity, complexity and high-variety in clinical characteristics and metabolomic profiling, the simultaneous detection of multiple inherited metabolic diseases (IMDs) is often challenging. As a substantial health problem, a competent chemometrics multi-class classification system for the early detection and diagnosis of IMDs would be advantageous. Beyond the commonly used binarization techniques of one-against-all (OAA) and one-against-one (OAO), an exhaustive and parallel half-against-half (EPHAH) decomposition is described in this study to deal with multi-class classification. For a K -class problem, EPHAH employs uniform class binary partition strategy to induce the binary classifier evaluating a half of K classes against the other half. With K -class problem exhaustively decomposed into all uniform binary partitions of K classes, EPHAH parallelly arranges the corresponding binary classifiers and aggregates their outputs to obtain the multi-class prediction using max-wins voting strategy. Based on orthogonal partial least squares discriminant analysis (OPLS-DA) with feature selection using particle swarm optimization (PSO) algorithm, EPHAH is investigated by GC-MS urinary metabolomics data among healthy controls and 9 most common IMDs. The results show that EPHAH enables a complete learning of the complex multi-class decision boundaries of 10 classes, exhibiting significant superiority in classification accuracies over OAA, OAO and traditional HAH. Meanwhile, compared with OAO using the same max-wins voting strategy, EPHAH gives an effective break of the tie problem in classification and enhanced resolution in votes. • An exhaustive and parallel half-against-half (EPHAH) decomposition was proposed for multi-class classification. • EPHAH involved uniform class binary partition and parallel arrangement with exhaustive decomposition of K -class problem. • EPHAH coupled with OPLS-DA profiled GC-MS urinary metabolomics data of multi-class IMDs with desired results. • A competent system for multi-class IMDs simultaneous detection was developed, aiding their early detection and diagnosis. [ABSTRACT FROM AUTHOR]