Journal of Chemometrics

The unit cell parameter (a) of the series of cubic ABX₃ perovskites was modeled using counter-propagation artificial neural networks. The influence of different input variables was examined by using algorithm for automatic adjustment of the relative importance of the variables. The performed analysis gave us an insight on which variables have most pronounced influences on the successful prediction of the unit cell parameter of this type of perovskites.

Toxicity of chemicals induced by different factors is an important consideration, especially during the drug research and development process. Thus, there is urgent need to develop computationally effective models that can predict the toxicity or adverse effects of chemicals for a specific class of chemicals. In this study, random forest (RF) was used to classify five toxicity data sets from Distributed Structure-Searchable Toxicity database network, using substructure fingerprints calculated directly from simple molecular structure.

The development and the validation of innovative approaches for biomarker selection are of paramount importance in many -omics technologies. In this paper, we present a publicly available metabolomic ultra performance liquid chromatography–mass spectrometry spike-in data set for apples. We illustrate some of the possibilities provided by this data set by comparing the performance of two popular biomarker-selection methods, the univariate t-test and the multivariate variable importance in projection.

Fluorescence spectrum, as well as the first and second derivative spectra in the region of 220–900 nm, was utilized to determine the concentration of triglyceride in human serum. Nonlinear partial least squares regression with cubic B-spline-function-based nonlinear transformation was employed as the chemometric method. Window genetic algorithms partial least squares was proposed as a new wavelength selection method to find the optimized spectra wavelengths combination.

In the present study, boosting partial least-squares discriminant analysis (BPLS-DA), as a new pattern recognition technique, has been designed via combining boosting and partial least-squares discriminant analysis (PLS-DA). This technique, compared with principal component analysis, PLS-DA, and linear discriminant analysis (LDA), has been employed to the NIR spectroscopic tea variety discrimination analysis. Experimental results have shown that NIR spectroscopy combined with BPLS-DA holds great potential as an accurate, rapid, and noninvasive strategy for identifying the tea quality. In addition, BPLS-DA is a well-performed pattern recognition technique superior to LDA and PLS-DA.