Investigation of the applicability of Zernike moments to the classification of SDS 2D-PAGE maps.

The aim of this work is to investigate the performance of multivariate classification techniques like partial least squares-discriminant analysis (PLS-DA) and linear discriminant analysis (LDA) when using Zernike moments as global image descriptors, in the classification of sodium dodecyl sulphate (SDS) two-dimensional polyacrylamide gel electrophoresis (2D-PAGE) maps affected by different levels of deformation. Synthetic sets of images simulating real SDS 2D-PAGE maps were analysed in controlled conditions to obtain information on the robustness and limits of applicability of the classification techniques operating on the basis of a given image decomposition method.

A new algorithm for the simulation of sodium dodecil sulfate two-dimensional polyacrylamide gel electrophoresis data sets.

A new algorithm for generating simulated sodium dodecil sulfate two-dimensional polyacrylamide gel electrophoresis (SDS 2D-PAGE) map images was developed. To choose the simulation strategy able to provide realistic 2D-PAGE maps, several parameters that characterize the statistical features of the images and data sets of images were taken into account, such as the distribution of size, intensity, and volume of the spots and their changes of position and volume along different replications of the same 2D-PAGE map. In this way, also the low reproducibility of replications of the same SDS 2D-PAGE maps was taken into account. The present algorithm can be usefully employed for the development of new classification and/or image analysis algorithms applied to bidimensional electrophoretic data sets, given the usually small number of experimental replications available.

The principle of exhaustiveness versus the principle of parsimony: a new approach for the identification of biomarkers from proteomic spot volume datasets based on principal component analysis.

The field of biomarkers discovery is one of the leading research areas in proteomics. One of the most exploited approaches to this purpose consists of the identification of potential biomarkers from spot volume datasets produced by 2D gel electrophoresis. In this case, problems may arise due to the large number of spots present in each map and the small number of maps available for each class (control/pathological). Multivariate methods are therefore usually applied together with variable selection procedures, to provide a subset of potential candidates. The variable selection procedures available usually pursue the so-called principle of parsimony: the most parsimonious set of spots is selected, providing the best classification performances. This approach is not effective in proteomics since all potential biomarkers must be identified: not only the most discriminating spots, usually related to general responses to inflammatory events, but also the smallest differences and all redundant molecules, i.e. biomarkers showing similar behaviour. The principle of exhaustiveness should be pursued rather than parsimony. To solve this problem, a new ranking and classification method, "Ranking-PCA", based on principal component analysis and variable selection in forward search, is proposed here for the exhaustive identification of all possible biomarkers. The method is successfully applied to three different proteomic datasets to prove its effectiveness.

2D-PAGE maps analysis.

Due to the low reproducibility affecting 2D gel-electrophoresis and the complex maps provided by this technique, the use of effective and robust methods for the comparison and classification of 2D maps is a fundamental tool for the development of automated diagnostic methods. A review of classical and recently developed methods for the comparison of 2D maps is presented here. The methods proposed regard both the analysis of spot volume datasets through multivariate statistical tools (pattern recognition methods, cluster analysis, and classification methods) and the analysis of 2D map images through fuzzy logic, three-way PCA, and the use of moment functions. The theoretical basis of each procedure is briefly introduced, together with a review of the most interesting applications present in recent literature.

A new method of comparing 2D-PAGE maps based on the computation of Zernike moments and multivariate statistical tools.

The aim of this work was to obtain the correct classification of a set of two-dimensional polyacrylamide gel electrophoresis map images using the Zernike moments as discriminant variables. For each 2D-PAGE image, the Zernike moments were computed up to a maximum p order of 100. Partial least squares discriminant analysis with variable selection, based on a backward elimination algorithm, was applied to the moments calculated in order to select those that provided the lowest error in cross-validation. The new method was tested on four datasets: (1) samples belonging to neuroblastoma; (2) samples of human lymphoma; (3) samples from pancreatic cancer cells (two cell lines of control and drug-treated cancer cells); (4) samples from colon cancer cells (total lysates and nuclei treated or untreated with a histone deacetylase inhibitor). The results demonstrate that the Zernike moments can be successfully applied for fast classification purposes. The final aim is to build models that can be used to achieve rapid diagnosis of these illnesses.

Application of partial least squares discriminant analysis and variable selection procedures: a 2D-PAGE proteomic study.

2D gel electrophoresis is a tool for measuring protein regulation, involving image analysis by dedicated software (PDQuest, Melanie, etc.). Here, partial least squares discriminant analysis was applied to improve the results obtained by classic image analysis and to identify the significant spots responsible for the differences between two datasets. A human colon cancer HCT116 cell line was analyzed, treated and not treated with a new histone deacetylase inhibitor, RC307. The proteins regulated by RC307 were detected by analyzing the total lysates and nuclear proteome profiles. Some of the regulated spots were identified by tandem mass spectrometry. The preliminary data are encouraging and the protein modulation reported is consistent with the antitumoral effect of RC307 on the HCT116 cell line. Partial least squares discriminant analysis coupled with backward elimination variable selection allowed the identification of a larger number of spots than classic PDQuest analysis. Moreover, it allows the achievement of the best performances of the model in terms of prediction and provides therefore more robust and reliable results. From this point of view, the multivariate procedure applied can be considered a good alternative to standard differential analysis, also taking into account the interdependencies existing among the variables.

Chemical profiling and multivariate data fusion methods for the identification of the botanical origin of honey.

The characterization of 72 Italian honey samples from 8 botanical varieties was carried out by a comprehensive approach exploiting data fusion of IR, NIR and Raman spectroscopies, Proton Transfer Reaction - Time of Flight - Mass Spectrometry (PTR-MS) and electronic nose. High-, mid- and low-level data fusion approaches were tested to verify if the combination of several analytical sources can improve the classification ability of honeys from different botanical origins. Classification was performed on the fused data by Partial Least Squares - Discriminant Analysis; a strict validation protocol was used to estimate the predictive performances of the models. The best results were obtained with high-level data fusion combining Raman and NIR spectroscopy and PTR-MS, with classification performances better than those obtained on single analytical sources (accuracy of 99% and 100% on test and training samples respectively). The combination of just three analytical sources assures a limited time of analysis.

Classification of 7 monofloral honey varieties by PTR-ToF-MS direct headspace analysis and chemometrics.

Honey, in particular monofloral varieties, is a valuable commodity. Here, we present proton transfer reaction-time of flight-mass spectrometry, PTR-ToF-MS, coupled to chemometrics as a successful tool in the classification of monofloral honeys, which should serve in fraud protection against mispresentation of the floral origin of honey. We analyzed 7 different honey varieties from citrus, chestnut, sunflower, honeydew, robinia, rhododendron and linden tree, in total 70 different honey samples and a total of 206 measurements. Only subtle differences in the profiles of the volatile organic compounds (VOCs) in the headspace of the different honeys could be found. Nevertheless, it was possible to successfully apply 6 different classification methods with a total correct assignment of 81-99% in the internal validation sets. The most successful methods were stepwise linear discriminant analysis (LDA) and probabilistic neural network (PNN), giving total correct assignments in the external validation sets of 100 and 90%, respectively. Clearly, PTR-ToF-MS/chemometrics is a powerful tool in honey classification.

Use of Legendre moments for the fast comparison of two-dimensional polyacrylamide gel electrophoresis maps images.

In this paper, Legendre moments are calculated to extract the global information from a set of two-dimensional polyacrylamide gel electrophoresis map images. The dataset contains 18 samples belonging to two different cell lines (PACA44 and T3M4) of control (untreated) and drug-treated pancreatic ductal carcinoma cells. The aim of this work was to obtain the correct classification of the 18 samples, using the Legendre moments as discriminant variables. For each image the Legendre moments up to a maximum order of 100 were computed. The stepwise linear discriminant analysis (LDA) was performed in order to select the moments with the highest discriminating power. The results demonstrate that the Legendre moments can be successfully applied for fast classification purposes and similarity analysis.

Comparison of different calibration methods for the determination by FT-NIR spectroscopy of the hydroxyl number in polyester resins.

Different calibration methods have been applied for the determination of the Hydroxyl Number in polyester resins, namely Partial Least Squares (PLS), Principal Component Regression (PCR), Ordinary Least Squares with selection of the variables by genetic algorithm (OLS-GEN) and back-propagation Artificial Neural Networks (BP-ANN). The predictive ability of the regression models was estimated by splitting the dataset in training and test sets by application of the Kohonen self-organising maps. The linear methods (OLS-GEN, PLS and PCR) showed comparable results while artificial neural networks provided the best results both in fitting and prediction.

High-performance liquid chromatography-ultraviolet detection method for the simultaneous determination of typical biogenic amines and precursor amino acids. Applications in food chemistry.

A reversed-phase high-performance liquid chromatography (HPLC) method was developed for the simultaneous determination in food of biogenic amines and their precursor amino acids after a precolumn derivatization with dansyl chloride. The chromatographic conditions, selected to be suitable for mass spectrometry detection, were optimized through experimental design and artificial neural networks. The HPLC-UV method was validated by comparing the separation results with those obtained through a HPLC method, working under the same chromatographic conditions but employing mass spectrometry detection. The HPLC-UV method was then applied to the analysis of different food samples, namely, cheese, clams, salami, and beer. For all of the matrices, recoveries (relative standard deviation always <5%) always >92% were obtained. The results are discussed as a function of the total biogenic amine content and of the concentration ratio between amines and precursor amino acids.

Butene concentration prediction in ethylene/propylene/1-butene terpolymers by FT-IR spectroscopy through multivariate statistical analysis and artificial neural networks.

This paper reports the development of calibration models for quality control in the production of ethylene/propylene/1-butene terpolymers by the use of multivariate tools and FT-IR spectroscopy. 1-Butene concentration prediction is achieved in terpolymers by coupling FT-IR spectroscopy to multivariate regression tools. A dataset of 26 terpolymers (14 coming from a constrained experimental design for mixtures, plus 12 terpolymers used for external validation) was analysed by FT-IR spectroscopy. An internal method of "Polimeri Europa" plant, based on (13)C NMR spectroscopy is used to determine the percentage of 1-butene in the samples. Then, different multivariate tools are used for 1-butene concentration prediction based on the FT-IR spectra recorded. Different multivariate calibration methods were explored: principal component regression (PCR), partial least squares (PLS), stepwise OLS regression (SWR) and artificial neural networks (ANNs). The model obtained by back-propagation neural networks turned out to be the best one. The performances of the BP-ANN model were further improved by variable selection procedures based on the calculation of the first derivative of the network. The proposed approach allows the monitoring in real time of the polymer synthesis and the estimation of the characteristics of the product attainable from the concentration of 1-butene.

Optimisation of sensitivity in the multi-elemental determination of 83 isotopes by ICP-MS as a function of 21 instrumental operative conditions by modified simplex, principal component analysis and partial least squares.

The optimisation of the sensitivity in the ICP-MS determination of 83 isotopes, as a function of 21 operative parameters was performed by generating an initial experimental design that was used to define, by principal component analysis, the multi-criteria target function. The first PC, which contained an overall evaluation of the signal intensity of all isotopes, was used to rank the experiments. The modified simplex optimisation technique was then applied on the ranked experiments. The increase in signal intensity was, on the average, 3.9 times for the isotopes considered for the simplex procedure. When finally convergence was achieved, a PLS regression model calculated on the available experiments allowed to investigate the effect played by each factor on the experimental response. Simplex and PCA proved to be extremely effective to obtain the optimisation and to generate the multi-criteria target function: they can be suggested as an automatic method to perform the optimisation of the instrumental operative conditions.

Evaluation of the variables characterized by significant discriminating power in the application of SIMCA classification method to proteomic studies.

SIMCA classification can be applied to 2D-PAGE maps to identify changes occurring in cellular protein contents as a consequence of illnesses or therapies. These data sets are complex to treat due to the large number of proteins detected. A method for identifying relevant proteins from SIMCA discriminating powers is proposed, based on the Box-Cox transformation coupled to probability papers. The method successfully allowed the identification of the relevant spots from 2D maps.

Monitoring of the surface of paper samples exposed to UV light by ATR-FT-IR spectroscopy and use of multivariate control charts.

The effect of exposure of paper samples to UV light was monitored by use of ATR-FT-IR spectroscopy and multivariate statistical tools. Three types of paper were tested: common laser-printer paper, news print, and thermal fax paper. The samples were first characterised by ATR-FT-IR spectroscopy to determine natural experimental variability. They were then exposed to UV light for 30 h and the effects of the exposure were monitored by use of the same spectroscopic technique. Finally, multivariate statistical tools were applied to the final dataset, coupled with construction of multivariate control charts, to identify the effects of UV light on the sample surfaces.

Modeling of the polluting emissions from a cement production plant by partial least-squares, principal component regression, and artificial neural networks.

A Portland cement process was taken into consideration and monitored for one month with respect to polluting emissions, fuel and raw material physical-chemical properties, and operative conditions. Soft models, based on linear (partial least-squares, PLS, and principal component regression, PCR) and nonlinear (artificial neural networks, ANNs) approaches, were employed to predict the polluting emissions. The predictive ability of the three regression methods was evaluated by means of the partition of the dataset by Kohonen self-associative maps into both a training and a test set. Then, a "leave-more-out" approach, based on the use of a training set, a test set, and a production set, was adopted. The training set was used to build the models, the test set was used to select the number of latent variables or the neural network training endpoint, and the production set was used to produce genuine predictions. ANNs proved to be much more effective in prediction with respect to PLS and PCR and, at least in the case of SO2 and dust, provided a predictive ability comparable with the experimental estimated uncertainty of the response. This showed that it is possible to satisfactorily predict the two responses. Such a prediction will result in the prevention of environmental and legal problems connected to the polluting emissions.

Multivariate statistical tools applied to the characterization of the proteomic profiles of two human lymphoma cell lines by two-dimensional gel electrophoresis.

Mantle cell lymphoma (MCL) cell lines have been difficult to generate, since only few have been described so far and even fewer have been thoroughly characterized. Among them, there is only one cell line, called GRANTA-519, which is well established and universally adopted for most lymphoma studies. We succeeded in establishing a new MCL cell line, called MAVER-1, from a leukemic MCL, and performed a thorough phenotypical, cytogenetical and molecular characterization of the cell line. In the present report, the phenotypic expression of GRANTA-519 and MAVER-1 cell lines has been compared and evaluated by a proteomic approach, exploiting 2-D map analysis. By univariate statistical analysis (Student's t-test, as commonly used in most commercial software packages), most of the protein spots were found to be identical between the two cell lines. Thirty spots were found to be unique for the GRANTA-519, whereas another 11 polypeptides appeared to be expressed only by the MAVER-1 cell line. A number of these spots could be identified by MS. These data were confirmed and expanded by multivariate statistical tools (principal component analysis and soft-independent model of class analogy) that allowed identification of a larger number of differently expressed spots. Multivariate statistical tools have the advantage of reducing the risk of false positives and of identifying spots that are significantly altered in terms of correlated expression rather than absolute expression values. It is thus suggested that, in future work in differential proteomic profiling, both univariate and multivariate statistical tools should be adopted.

Monitoring of pigmented surfaces in accelerated ageing process by ATR-FT-IR spectroscopy and multivariate control charts.

This work is an extension of a method for monitoring the conservation state of pigmented surfaces presented in a previous paper. A cotton canvas painted with an organic pigment (Alizarin) was exposed to UV light in order to evaluate the effects of the applied treatment on the surface of the sample. The conservation state of the pigmented surface was monitored with ATR-FT-IR spectroscopy and multivariate control charts. The IR spectra were analysed by principal component analysis (PCA) and the relevant principal components (PCs) were used for constructing multivariate Shewhart, cumulative sums (CUSUM) and simultaneous scores monitoring and residuals tracking (SMART) control charts. These tools were successfully applied for the identification of the presence of relevant modifications occurring on the surface of the sample. Finally, with the aim to more deeply investigate what happened to the sample surface during the UV exposure, a PCA of the residuals matrix of degradation analyses only, not present in the previous paper, was performed. This analysis produced interesting results concerning the identification of the processes taking place on the irradiated surface.

The state of conservation of painted surfaces in the presence of accelerated ageing processes monitored by use of FT-Raman spectroscopy and multivariate control charts.

A new method has been developed for monitoring the degradation of paintings. Two inorganic pigments (ultramarine blue and red ochre) were blended with linseed oil and spread on canvas. Each canvas was subjected to simulated accelerated ageing in the presence of typical degradation agents (UV radiation and acidic solution). Periodically the painted surfaces were analysed by FT-Raman, to investigate the status of the surface. The data obtained were analysed by principal component analysis (PCA). Finally the Shewhart and cumulative sum control charts based on the relevant principal components (PC) and the so called scores monitoring and residuals tracking (SMART) charts were built. The method based on the use of PC to describe the process was found to enable identification of the presence of relevant modification occurring on the surface of the samples studied.