[Application of Intelligent Optimization Algorithms to Wavelength Selection of Near-Infrared Spectroscopy].

Near infrared spectroscopy (NIRS) is a kind of indirect analysis technology, whose application depends on the setting up of relevant calibration model. In order to improve interpretability, accuracy and modeling efficiency of the prediction model, wavelength selection becomes very important and it can minimize redundant information of near infrared spectrum. Intelligent optimization algorithm is a sort of commonly wavelength selection method which establishes algorithm model by mathematical abstraction from the background of biological behavior or movement form of material, then iterative calculation to solve combinatorial optimization problems. Its core strategy is screening effective wavelength points in multivariate calibration modeling by using some objective functions as a standard with successive approximation method. In this work, five intelligent optimization algorithms, including ant colony optimization (ACO), genetic algorithm (GA), particle swarm optimization (PSO), random frog (RF) and simulated annealing (SA) algorithm, were used to select characteristic wavelength from NIR data of tobacco leaf for determination of total nitrogen and nicotine content and together with partial least squares (PLS) to construct multiple correction models. The comparative analysis results of these models showed that, the total nitrogen optimums models of dataset A and B were PSO-PLS and GA-PLS models. GA-PLS and SA-PLS models were the optimums for nicotine, respectively. Although not all predicting performance of these optimization models was superior to that of full spectrum PLS models, they were simplified greatly and their forecasting accuracy, precision, interpretability and stability were improved. Therefore, this research will have great significance and plays an important role for the practical application. Meanwhile, it could be concluded that the informative wavelength combination for total nitrogen were 4 587~4 878 and 6 700~7 200 cm(-1), and that for tobacco nicotine were 4 500~4 700 and 5 800~6 000 cm(-1). These selected wavelengths have actually physical significance.

Calibration transfer via an extreme learning machine auto-encoder.

In order to solve the spectra standardization problem in near-infrared (NIR) spectroscopy, a Transfer via Extreme learning machine Auto-encoder Method (TEAM) has been proposed in this study. A comparative study among TEAM, piecewise direct standardization (PDS), generalized least squares (GLS) and calibration transfer methods based on canonical correlation analysis (CCA) was conducted, and the performances of these algorithms were benchmarked with three spectral datasets: corn, tobacco and pharmaceutical tablet spectra. The results show that TEAM is a stable method and can significantly reduce prediction errors compared with PDS, GLS and CCA. TEAM can also achieve the best RMSEPs in most cases with a small number of calibration sets. TEAM is implemented in Python language and available as an open source package at https://github.com/zmzhang/TEAM.

The model adaptive space shrinkage (MASS) approach: a new method for simultaneous variable selection and outlier detection based on model population analysis.

Variable selection and outlier detection are important processes in chemical modeling. Usually, they affect each other. Their performing orders also strongly affect the modeling results. Currently, many studies perform these processes separately and in different orders. In this study, we examined the interaction between outliers and variables and compared the modeling procedures performed with different orders of variable selection and outlier detection. Because the order of outlier detection and variable selection can affect the interpretation of the model, it is difficult to decide which order is preferable when the predictabilities (prediction error) of the different orders are relatively close. To address this problem, a simultaneous variable selection and outlier detection approach called Model Adaptive Space Shrinkage (MASS) was developed. This proposed approach is based on model population analysis (MPA). Through weighted binary matrix sampling (WBMS) from model space, a large number of partial least square (PLS) regression models were built, and the elite parts of the models were selected to statistically reassign the weight of each variable and sample. Then, the whole process was repeated until the weights of the variables and samples converged. Finally, MASS adaptively found a high performance model which consisted of the optimized variable subset and sample subset. The combination of these two subsets could be considered as the cleaned dataset used for chemical modeling. In the proposed approach, the problem of the order of variable selection and outlier detection is avoided. One near infrared spectroscopy (NIR) dataset and one quantitative structure-activity relationship (QSAR) dataset were used to test this approach. The result demonstrated that MASS is a useful method for data cleaning before building a predictive model.

Application of GC-MS coupled with chemometrics for scanning serum metabolic biomarkers from renal fibrosis rat.

Renal interstitial fibrosis closely relates to chronic kidney disease and is regarded as the final common pathway in most cases of end-stage renal disease. Metabolomic biomarkers can facilitate early diagnosis and allow better understanding of the pathogenesis underlying renal fibrosis. Gas chromatography-mass spectrometry (GC/MS) is one of the most promising techniques for identification of metabolites. However, the existence of the background, baseline offset, and overlapping peaks makes accurate identification of the metabolites unachievable. In this study, GC/MS coupled with chemometric methods was successfully developed to accurately identify and seek metabolic biomarkers for rats with renal fibrosis. By using these methods, seventy-six metabolites from rat serum were accurately identified and five metabolites (i.e., urea, ornithine, citric acid, galactose, and cholesterol) may be useful as potential biomarkers for renal fibrosis.

A new method for wavelength interval selection that intelligently optimizes the locations, widths and combinations of the intervals.

In this study, a new algorithm for wavelength interval selection, known as interval variable iterative space shrinkage approach (iVISSA), is proposed based on the VISSA algorithm. It combines global and local searches to iteratively and intelligently optimize the locations, widths and combinations of the spectral intervals. In the global search procedure, it inherits the merit of soft shrinkage from VISSA to search the locations and combinations of informative wavelengths, whereas in the local search procedure, it utilizes the information of continuity in spectroscopic data to determine the widths of wavelength intervals. The global and local search procedures are carried out alternatively to realize wavelength interval selection. This method was tested using three near infrared (NIR) datasets. Some high-performing wavelength selection methods, such as synergy interval partial least squares (siPLS), moving window partial least squares (MW-PLS), competitive adaptive reweighted sampling (CARS), genetic algorithm PLS (GA-PLS) and interval random frog (iRF), were used for comparison. The results show that the proposed method is very promising with good results both on prediction capability and stability. The MATLAB codes for implementing iVISSA are freely available on the website: .

Multiscale peak detection in wavelet space.

Accurate peak detection is essential for analyzing high-throughput datasets generated by analytical instruments. Derivatives with noise reduction and matched filtration are frequently used, but they are sensitive to baseline variations, random noise and deviations in the peak shape. A continuous wavelet transform (CWT)-based method is more practical and popular in this situation, which can increase the accuracy and reliability by identifying peaks across scales in wavelet space and implicitly removing noise as well as the baseline. However, its computational load is relatively high and the estimated features of peaks may not be accurate in the case of peaks that are overlapping, dense or weak. In this study, we present multi-scale peak detection (MSPD) by taking full advantage of additional information in wavelet space including ridges, valleys, and zero-crossings. It can achieve a high accuracy by thresholding each detected peak with the maximum of its ridge. It has been comprehensively evaluated with MALDI-TOF spectra in proteomics, the CAMDA 2006 SELDI dataset as well as the Romanian database of Raman spectra, which is particularly suitable for detecting peaks in high-throughput analytical signals. Receiver operating characteristic (ROC) curves show that MSPD can detect more true peaks while keeping the false discovery rate lower than MassSpecWavelet and MALDIquant methods. Superior results in Raman spectra suggest that MSPD seems to be a more universal method for peak detection. MSPD has been designed and implemented efficiently in Python and Cython. It is available as an open source package at .

Prediction of peptide fragment ion mass spectra by data mining techniques.

Accurate prediction of peptide fragment ion mass spectra is one of the critical factors to guarantee confident peptide identification by protein sequence database search in bottom-up proteomics. In an attempt to accurately and comprehensively predict this type of mass spectra, a framework named MS(2)PBPI is proposed. MS(2)PBPI first extracts fragment ions from large-scale MS/MS spectra data sets according to the peptide fragmentation pathways and uses binary trees to divide the obtained bulky data into tens to more than 1000 regions. For each adequate region, stochastic gradient boosting tree regression model is constructed. By constructing hundreds of these models, MS(2)PBPI is able to predict MS/MS spectra for unmodified and modified peptides with reasonable accuracy. Moreover, high consistency between predicted and experimental MS/MS spectra derived from different ion trap instruments with low and high resolving power is achieved. MS(2)PBPI outperforms existing algorithms MassAnalyzer and PeptideART.

propy: a tool to generate various modes of Chou's PseAAC.

SUMMARY: Sequence-derived structural and physiochemical features have been frequently used for analysing and predicting structural, functional, expression and interaction profiles of proteins and peptides. To facilitate extensive studies of proteins and peptides, we developed a freely available, open source python package called protein in python (propy) for calculating the widely used structural and physicochemical features of proteins and peptides from amino acid sequence. It computes five feature groups composed of 13 features, including amino acid composition, dipeptide composition, tripeptide composition, normalized Moreau-Broto autocorrelation, Moran autocorrelation, Geary autocorrelation, sequence-order-coupling number, quasi-sequence-order descriptors, composition, transition and distribution of various structural and physicochemical properties and two types of pseudo amino acid composition (PseAAC) descriptors. These features could be generally regarded as different Chou's PseAAC modes. In addition, it can also easily compute the previous descriptors based on user-defined properties, which are automatically available from the AAindex database. AVAILABILITY: The python package, propy, is freely available via http://code.google.com/p/protpy/downloads/list, and it runs on Linux and MS-Windows. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

ChemoPy: freely available python package for computational biology and chemoinformatics.

MOTIVATION: Molecular representation for small molecules has been routinely used in QSAR/SAR, virtual screening, database search, ranking, drug ADME/T prediction and other drug discovery processes. To facilitate extensive studies of drug molecules, we developed a freely available, open-source python package called chemoinformatics in python (ChemoPy) for calculating the commonly used structural and physicochemical features. It computes 16 drug feature groups composed of 19 descriptors that include 1135 descriptor values. In addition, it provides seven types of molecular fingerprint systems for drug molecules, including topological fingerprints, electro-topological state (E-state) fingerprints, MACCS keys, FP4 keys, atom pairs fingerprints, topological torsion fingerprints and Morgan/circular fingerprints. By applying a semi-empirical quantum chemistry program MOPAC, ChemoPy can also compute a large number of 3D molecular descriptors conveniently. AVAILABILITY: The python package, ChemoPy, is freely available via http://code.google.com/p/pychem/downloads/list, and it runs on Linux and MS-Windows. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A novel variable selection approach that iteratively optimizes variable space using weighted binary matrix sampling.

In this study, a new optimization algorithm called the Variable Iterative Space Shrinkage Approach (VISSA) that is based on the idea of model population analysis (MPA) is proposed for variable selection. Unlike most of the existing optimization methods for variable selection, VISSA statistically evaluates the performance of variable space in each step of optimization. Weighted binary matrix sampling (WBMS) is proposed to generate sub-models that span the variable subspace. Two rules are highlighted during the optimization procedure. First, the variable space shrinks in each step. Second, the new variable space outperforms the previous one. The second rule, which is rarely satisfied in most of the existing methods, is the core of the VISSA strategy. Compared with some promising variable selection methods such as competitive adaptive reweighted sampling (CARS), Monte Carlo uninformative variable elimination (MCUVE) and iteratively retaining informative variables (IRIV), VISSA showed better prediction ability for the calibration of NIR data. In addition, VISSA is user-friendly; only a few insensitive parameters are needed, and the program terminates automatically without any additional conditions. The Matlab codes for implementing VISSA are freely available on the website: https://sourceforge.net/projects/multivariateanalysis/files/VISSA/.

Separation of nine compounds from Salvia plebeia R.Br. using two-step high-speed counter-current chromatography with different elution modes.

Nine compounds were successfully separated from Salvia plebeia R.Br. using two-step high-speed counter-current chromatography with three elution modes. Elution-extrusion counter-current chromatography was applied in the first step, while classical counter-current chromatography and recycling counter-current chromatography were used in the second step. Three solvent systems, n-hexane/ethyl acetate/ethanol/water (4:6.5:3:7, v/v), methyl tert-butyl ether/ethyl acetate/n-butanol/methanol/water (6:4:1:2:8, v/v) and n-hexane/ethyl acetate/methanol/water (5:5.5:5:5, v/v) were screened and optimized for the two-step separation. The separation yielded nine compounds, including caffeic acid (1), 6-hydroxyluteuolin-7-glucoside (2), 5,7,3',4'-tetrahydroxy-6-methoxyflavanone-7-glucoside (3), nepitrin (4), rosmarinic acid (5), homoplantaginin (6), nepetin (7), hispidulin (8), and 5,6,7,4'-tertrahydroxyflavone (9). To the best of our knowledge, 5,7,3',4'-tetrahydroxy-6-methoxyflavanone-7-glucoside and 5,6,7,4'-tertrahydroxyflavone have been separated from Salvia plebeia R.Br. for the first time. The purities and structures of these compounds were identified by high-performance liquid chromatography, electrospray ionization mass spectrometry, (1)H and (13)C NMR spectroscopy. This study demonstrates that high-speed counter-current chromatography is a useful and flexible tool for the separation of components from a complex sample.

A perspective demonstration on the importance of variable selection in inverse calibration for complex analytical systems.

Classical calibration and inverse calibration are two kinds of multivariate calibration in chemical modeling. They use strategies of modeling in component spectral space and in measured variable space, respectively. However, the intrinsic difference between these two calibration models is not fully investigated. Besides, in the case of complex analytical systems, the net analyte signal (NAS) cannot be well defined in inverse calibration due to the existence of uninformative and/or interfering variables. Therefore, application of the NAS cannot improve the predictive performance for this kind of calibration, since it is essentially a technique based on the full-spectrum. From our perspective, variable selection can significantly improve the predictive performance through removing uninformative and/or interfering variables. Although the need for variable selection in the inverse calibration model has already been experimentally demonstrated, it has not aroused so much attention. In this study, we first clarify the intrinsic difference between these two calibration models and then use a new perspective to intrinsically prove the importance of variable selection in the inverse calibration model for complex analytical systems. In addition, we have experimentally validated our viewpoint through the use of one UV dataset and two generated near infrared (NIR) datasets.

Morphological weighted penalized least squares for background correction.

Backgrounds existing in the analytical signal always impair the effectiveness of signals and compromise selectivity and sensitivity of analytical methods. In order to perform further qualitative or quantitative analysis, the background should be corrected with a reasonable method. For this purpose, a new automatic method for background correction, which is based on morphological operations and weighted penalized least squares (MPLS), has been developed in this paper. It requires neither prior knowledge about the background nor an iteration procedure or manual selection of a suitable local minimum value. The method has been successfully applied to simulated datasets as well as experimental datasets from different instruments. The results show that the method is quite flexible and could handle different kinds of backgrounds. The proposed MPLS method is implemented and available as an open source package at http://code.google.com/p/mpls.

PyDPI: freely available python package for chemoinformatics, bioinformatics, and chemogenomics studies.

The rapidly increasing amount of publicly available data in biology and chemistry enables researchers to revisit interaction problems by systematic integration and analysis of heterogeneous data. Herein, we developed a comprehensive python package to emphasize the integration of chemoinformatics and bioinformatics into a molecular informatics platform for drug discovery. PyDPI (drug-protein interaction with Python) is a powerful python toolkit for computing commonly used structural and physicochemical features of proteins and peptides from amino acid sequences, molecular descriptors of drug molecules from their topology, and protein-protein interaction and protein-ligand interaction descriptors. It computes 6 protein feature groups composed of 14 features that include 52 descriptor types and 9890 descriptors, 9 drug feature groups composed of 13 descriptor types that include 615 descriptors. In addition, it provides seven types of molecular fingerprint systems for drug molecules, including topological fingerprints, electro-topological state (E-state) fingerprints, MACCS keys, FP4 keys, atom pair fingerprints, topological torsion fingerprints, and Morgan/circular fingerprints. By combining different types of descriptors from drugs and proteins in different ways, interaction descriptors representing protein-protein or drug-protein interactions could be conveniently generated. These computed descriptors can be widely used in various fields relevant to chemoinformatics, bioinformatics, and chemogenomics. PyDPI is freely available via https://sourceforge.net/projects/pydpicao/.

Nonlinear alignment of chromatograms by means of moving window fast Fourier transfrom cross-correlation.

The preprocessing of chromatograms is essential to modern chromatography for further qualitative and quantitative analysis, especially when chromatographic instruments are used for herb products analysis involving large number of samples. To accurately compare and analyze the obtained chromatograms, it is necessary to preprocess, especially align retention time shifts. Here moving window fast Fourier transform (FFT) cross-correlation is introduced to perform nonlinear alignment of high-throughput chromatograms. Since elution characteristics of chromatograms will produce local similarity in retention time shifts, moving window procedure seems to be a better substitute of segmentation steps. The retention time shifts can be calculated and accelerated by FFT cross-correlation. The artifacts can be detected and eliminated from the retention time shifts profile since the continuity of moving window procedure. The proposed method is demonstrated in comparison with recursive alignment by FFT on chromatographic datasets from herb products analysis. It is shown that the proposed method can address nonlinear retention time shift problem in chromatograms with the simple moving window procedure, which will not introduce segments size optimization problem. In additional, the parameters are intuitive and easy to adjust, which makes it off-the-shelf toolbox for alignment of chromatograms.

Prediction of retention indices for frequently reported compounds of plant essential oils using multiple linear regression, partial least squares, and support vector machine.

Retention indices for frequently reported compounds of plant essential oils on three different stationary phases were investigated. Multivariate linear regression, partial least squares, and support vector machine combined with a new variable selection approach called random-frog recently proposed by our group, were employed to model quantitative structure-retention relationships. Internal and external validations were performed to ensure the stability and predictive ability. All the three methods could obtain an acceptable model, and the optimal results by support vector machine based on a small number of informative descriptors with the square of correlation coefficient for cross validation, values of 0.9726, 0.9759, and 0.9331 on the dimethylsilicone stationary phase, the dimethylsilicone phase with 5% phenyl groups, and the PEG stationary phase, respectively. The performances of two variable selection approaches, random-frog and genetic algorithm, are compared. The importance of the variables was found to be consistent when estimated from correlation coefficients in multivariate linear regression equations and selection probability in model spaces.

Pressor mechanism evaluation for phytochemical compounds using in silico compound-protein interaction prediction.

In this study, a method was applied to evaluate pressor mechanisms through compound-protein interactions. Our method assumed that the compounds with different pressor mechanisms should bind to different target proteins, and thereby these mechanisms could be differentiated using compound-protein interactions. Twenty-six phytochemical components and 46 tested target proteins related to blood pressure (BP) elevation were collected. Then, in silico compound-protein interactions prediction probabilities were calculated using a random forest model, which have been implemented in a web server, and the credibility was judged using related literature and other methods. Further, a heat map was constructed, it clearly showed different prediction probabilities accompanied with hierarchical clustering analysis results. Followed by a compound-protein interaction network was depicted according to the results, we can see the connectivity layout of phytochemical components with different target proteins within the BP elevation network, which guided the hypothesis generation of poly-pharmacology. Lastly, principal components analysis (PCA) was carried out upon the prediction probabilities, and pressor targets could be divided into three large classes: neurotransmitter receptors, hormones receptors and monoamine oxidases. In addition, steroid glycosides seem to be close to the region of hormone receptors, and a weak difference existed between them. This work explored the possibility for pharmacological or toxicological mechanism classification using compound-protein interactions. Such approaches could also be used to deduce pharmacological or toxicological mechanisms for uncharacterized compounds.

RxnFinder: biochemical reaction search engines using molecular structures, molecular fragments and reaction similarity.

SUMMARY: Biochemical reactions play a key role to help sustain life and allow cells to grow. RxnFinder was developed to search biochemical reactions from KEGG reaction database using three search criteria: molecular structures, molecular fragments and reaction similarity. RxnFinder is helpful to get reference reactions for biosynthesis and xenobiotics metabolism. AVAILABILITY: RxnFinder is freely available via: http://sdd.whu.edu.cn/rxnfinder. CONTACT: qnhu@whu.edu.cn.

[Direct determination of heavy metal elements in sweeteners by inductively coupled plasma mass spectrometry].

An analysis method of microwave digestion and inductively coupled plasma-mass spectrometry (ICP-MS) with octopole reaction system (ORS) was established for the determination of 10 heavy metal elements including Cr, Co, Ni, Cu, As, Cd, Sn, Sb, Hg and Pb in sweetener. Samples were decomposed by HNO3 and H2O2 followed by dilution with ultrapure water then the above 10 heavy metal elements in the solution were analyzed directly by ICP-MS. The use of ORS can eliminate the interference of polyatomic ions dramatically. 45Sc, 89Y, 115In and 209Bi as internal standard elements were used to compensate matrix effect and signal drift. The optimum conditions for the determination was tested and discussed. Under the optimal conditions, the detection limits of the 10 elements were in the range of 0.003-0.038 MICROg x L(-1), the recovery of the samples was in the range of 93.0%-106.6% and the relative standard deviation (RSD) < or = 3.4%, which showed that the method was very precise. The technique was applied for the quality control and safety evaluation of sweetener.

Noise incorporated subwindow permutation analysis for informative gene selection using support vector machines.

Selecting a small subset of informative genes plays an important role in accurate prediction of clinical tumor samples. Based on model population analysis, a novel variable selection method, called noise incorporated subwindow permutation analysis (NISPA), is proposed in this study to work with support vector machines (SVMs). The essence of NISPA lies in the point that one noise variable is added into each sampled sub-dataset and then the distribution of variable importance of the added noise could be computed and serves as the common reference to evaluate the experimental variables. Further, by using the non-parametric Mann-Whitney U test, a P value can be assigned to each variable which describes to what extent the distributions of the gene variable and the noise variable are different. According to the computed P values, all the variables could be ranked and then a small subset of informative variables could be determined to build the model. Moreover, by NISPA, we are the first to distinguish the variables into a more detailed classification as informative, uninformative (noise) and interfering variables in comparison with other methods. In this study, two microarray datasets are employed to evaluate the performance of NISPA. The results show that the prediction errors of SVM classifiers could be significantly reduced by variable selection using NISPA. It is concluded that NISPA is a good alternative of variable selection algorithm.