Definition and detection of data-based uniqueness in evaluating bilinear (two-way) chemical measurements

Random swapping, an effective and efficient way to boost the intensities of cross peaks in a 2D asynchronous spectrum

Analysis of mixture via chromatographic-spectroscopic and analogous experiments is a common task in analytical chemistry. A 2D/nD asynchronous spectrum is effective in retrieving spectra of pure substances even if different components cannot be separated. However, noise in the 2D/nD asynchronous spectrum becomes a bottleneck in the analysis. Finding a suitable sequence of the 1D spectra used in constructing the 2D/nD asynchronous spectrum is helpful to improve the signal-to-noise level. A 2D/nD asynchronous spectrum is often produced via a large number of 1D spectra. The resultant colossal number of the possible sequences makes stochastic search the only possible way to find a suitable sequence. Random changing (RC) and random swapping (RS) are two ways to obtain a new sequence. We found that the possibility of finding a better sequence via an RS is significantly higher than that via an RC in the advanced stage of stochastic searching. This is the reason why the performance of RS is superior to that of RC in two model systems where 2D asynchronous spectra are used. We applied the RS approach on the analysis of water/isopropanol mixtures, and satisfactory sequences are acquired with affordable computational cost. Thus, the RS approach brings about an opportunity increase the signal-to-noise level of a 2D asynchronous spectrum in the analysis of the bilinear data from complex mixed samples.

Workflow for the Supervised Learning of Chemical Data: Efficient Data Reduction-Multivariate Curve Resolution (EDR-MCR)

A new method termed efficient data reduction-multivariate curve resolution (EDR-MCR) has been devised for classification of high-dimensional data. The method introduces the coupling of EDR and MCR as a new strategy for data splitting, variable selection, and supervised classification of high dimensionality data. The method reduces data dimensionality and selects the training set using principal component analysis (PCA) and convex geometry prior to data classification. Then, the reduced data are categorized using an MCR model, in which numerical constraints are imposed to resolve the data into classes and readily interpretable pure component signal weights. The performance of the EDR and supervised MCR methods were tested for their ability to enable discrimination between the constituents of two benchmark and two high-dimensional data sets. The results were compared with the output of the application of different data splitting methods including iterative random selection (IRS), Kennard-Stone (KS), and discrimination methods including partial least-squares-discriminant analysis (PLS-DA) and the ensemble-learning frameworks of linear discriminant analysis (LDA), k-nearest neighbors (KNN), classification and regression trees (CART), and support vector machine (SVM). Overall, EDR resulted in comparable results with other data splitting methods despite the small size of the training set samples that it created. The proposed MCR approach, in comparison with other commonly used supervised techniques, has the advantages of speed in implementation, tuning of fewer parameters, flexibility in the analysis of data characterized by low sample numbers and class imbalances, improved accuracy from the inclusion of additional system information in the form of numerical constraints, and the ability to resolve pure components signal weights.

Three-way calibration using PARAFAC and MCR-ALS with previous synchronization of second-order chromatographic data through a new functional alignment of pure vectors for the quantification in the presence of retention time shifts in peak position and shape

In the present contribution is shown the application of the recently developed functional alignment of pure vectors (FAPV) as a proper algorithm to align second-order chromatographic data with severe retention time shifts in peak position and shape. FAPV decomposed a three-way chromatographic data array in their three modes (sample, spectral and elution time vectors), using a basis function to pre-process the non-linear mode (elution time) and then it aligns the functionalized pure vectors and reshapes the transformed vectors into matrices, restoring the trilinearity of second-order chromatographic data. The well-aligned three-way chromatographic data array is then successfully decomposed by advanced chemometric models such as parallel factor analysis (PARAFAC) and multivariate curve resolution - alternating least-squares (MCR-ALS) with the trilinearity constraint. The performance of this innovative analytical strategy based on PARAFAC and MCR-ALS with previous synchronization of data through FAPV algorithm is properly evaluated using real second-order chromatographic data with multiple artifacts, i.e., shifts in peak position and shape for the simultaneous quantification of amoxicillin and potassium clavulanate in commercial medicinal drugs. The present contribution compares some analytical results achieved by: (1) the usual MCR-ALS as a bilinear model applied in augmented data matrix without previous synchronization and with interval correlation optimized shifting (ICOSHIFT) and FAPV and (2) trilinear models using PARAFAC with ICOSHIFT and FAPV and trilinearity constraint in MCR-ALS with FAPV. Available results suggest that these strongly shifted and warped elution time profiles cause for the loss of trilinearity, which can be adequately restored by FAPV algorithm. PARAFAC performed a successful trilinear decomposition of three-way chromatographic data array with law values of relative prediction error (REP) in the order of 1.34-1.42% in both analytes.

A down-to-earth analyst view of rotational ambiguity in second-order calibration with multivariate curve resolution - a tutorial

Rotational ambiguity is a phenomenon with the potential of generating an uncertainty in the estimation of analyte concentrations in protocols based on matrix instrumental data processed by multivariate curve resolution - alternating least-squares (MCR-ALS). This is particularly relevant when the second-order advantage is to be achieved, i.e., when selected analytes are determined in unknown samples having unexpected constituents, not considered in the calibration set of samples. It is therefore imperative that analytical chemists developing second-order multivariate calibration methods using MCR-ALS acknowledge the relevance of this issue, and more importantly, have access to the required tools to size the relative impact of this potential source of uncertainty on the estimated analyte concentrations. The purpose of this tutorial is to provide a down-to-earth view of rotational ambiguity, by studying in detail a synthetic example mimicking a typical chromatographic-spectral experiment, where a set of calibration samples is joined with an unknown sample having an uncalibrated interference. After explaining the background information needed to understand the origin of the phenomenon, the available tools for the estimation of the feasible MCR-ALS solutions and the derived uncertainty on analyte predictions will be discussed. A multi-component experimental system will also be discussed, stressing the fact that rotational ambiguity uncertainties, however small, should always be estimated and reported.

Contribution to second-order calibration based on multivariate curve resolution with and without previous chromatographic synchronization

Rotational ambiguity in the bilinear solutions provided by multivariate curve resolution - alternating least-squares (MCR-ALS) leads to an additional source of uncertainty in the estimation of analyte concentrations by second-order multivariate calibration. The phenomenon is particularly important when measuring matrix instrumental data derived from liquid chromatography with spectral detection, where elution time profiles usually vary from sample to sample both in position and shape. This makes the data non-trilinear, precluding the use of unique trilinear decomposition models. The present report compares some analytical results achieved by: (1) the usual MCR-ALS analysis of augmented matrices built from raw matrix data and (2) a previously reported procedure based on synchronizing the MCR-ALS elution time profiles using correlation optimized warping (COW), reconstructing the augmented matrix with the spectra and the aligned chromatograms, and then applying MCR-ALS again with the trilinearity constraint, leading to unique solutions, which is possible because the warping process restores the trilinearity of the data. We show that alternative (2) does not solve the rotational ambiguity issues and artificially modifies the original data, without significant improvements in analytical performance. In the simulated systems, the best average errors for alternative (1) were about 2%, whereas for alternative (2) they were in the range 4-11%. For the experimental system, the corresponding errors were 2-3% and 3-4% respectively, i.e. with no significant improvement in going to alternative (2). All efforts should be directed to reduce the degree of rotational ambiguity by applying a full battery of chemically reasonable constraints.

A novel systematic absence of cross peaks-based 2D-COS approach for bilinear data

A novel approach to use two-dimensional correlation spectroscopy (2D-COS) to analyze bilinear data is proposed. A phenomenon called Systematic Absence of Cross Peaks (SACPs) is observed in a 2D asynchronous spectrum. Two theorems relevant to SACPs have been derived. The SACP-based 2D-COS method has been successfully applied on analyzing bilinear data from mixed samples (including one model system and two real systems). Implicit isolated peaks can be identified and assigned to different components based on characteristic pattern of SACPs even if the time-related profiles of different components are severely overlapped. Based on the results of SACPs, spectra of pure components can be retrieved. Identification of SACPs can still be achieved in the presence of artifacts. Thus, neither noise nor baseline drift can produce significant influence on the results obtained from the approach described in this paper. We have used several well-established chemometric methods, including N-Findr, VCA, and MCR with various initial settings, on two systems that can be successfully solved using the 2D-COS method. The chemometric methods mentioned above cannot provide correct spectra of pure components because of severe problem of rotational ambiguity derived from severe overlapping of the time-related profiles. Only when the information from SACPs in 2D-COS is used as additional constraints in MCR calculation, correct spectra can be obtained. That is to say, the SACP-based 2D-COS method provides intrinsic information which is crucial in the analysis of chromatographic-spectroscopic and analogous data even if the time-related profiles of different components overlap severely.

A preliminary study on constructing a high-dimensional asynchronous spectrum to analyze bilinear data

A novel approach to constructing high-dimensional asynchronous spectra (nD-Asyn) is proposed. Three theorems relevant to 1D slices of nD-Asyn are revealed. nD-Asyn is used to analyze bilinear data from mixtures containing multiple components obtained via hyphenated techniques. The spectral contribution of different components can be removed in a stepwise manner by increasing the dimensions of asynchronous spectra. As a result, the spectra of different components can be faithfully recovered even if the time-related profiles of different components severely overlap. Moreover, correct results can still be obtained via the nD-Asyn even if a considerable level of noise and baseline drift are present. The nD-Asyn approach is compared with MCR-ALS using different constraints in analyzing the data for a simulated and also for a real system. The nD-Asyn produced correct spectrum of every component. Only when complete constraints obtained from nD-Asyn method is utilized in the MCR-ALS calculation, correct spectra of all the components can be obtained. Thus, nD-Asyn can be used alone or in conjunction with MCR-ALS to analyze bilinear data containing contributions of multiple components.

Fitting-free curve resolution of spectroscopic data: Chemometric and physical chemical viewpoints

In this paper the authors have investigated spectroscopic data analysis according to a recent development, i.e. the Direct Inversion in the Spectral Subspace (DISS) procedure. DISS is a supervised curve resolution technique, consequently it can be used once the spectra of the potential pure components are known and the experimental spectrum of a chemical mixture is also presented; hence the task is to determine the composition of the unknown chemical mixture. In this paper, the original algorithm of DISS is re-examined and some further critical reasoning and essential developments are provided, including the detailed explanations of the constrained minimization task based on Lagrange multiplier regularization approach. The main conclusion is that the regularization used for DISS is needed because of the possible shifted spectra effect instead of collinearity; and this new property, i.e. treating the mild shifted spectra effect, of DISS can be considered as its main scientific advantage.