At-line monitoring of key parameters of nisin fermentation by near infrared spectroscopy,chemometric modeling and model improvement

An analytical procedure has been developed for at-line (fast off-line) monitoring of 4 key parameters including nisin titer (NT), the concentration of reducing sugars, cell concentration and pH during a nisin fermentation process. This procedure is based on near infrared (NIR) spectroscopy and Partial Least Squares (PLS). Samples without any preprocessing were collected at intervals of 1 h during fifteen batch of fermentations. These fermentation processes were implemented in 3 different 5 l fermentors at various conditions. NIR spectra of the samples were collected in 10 min. And then, PLS was used for modeling the relationship between NIR spectra and the key parameters which were determined by reference methods. Monte Carlo Partial Least Squares (MCPLS) was applied to identify the outliers and select the most efficacious methods for preprocessing spectra, wavelengths and the suitable number of latent variables (n _LV). Then, the optimum models for determining NT, concentration of reducing sugars, cell concentration and pH were established. The correlation coefficients of calibration set (R _c) were 0.8255, 0.9000, 0.9883 and 0.9581, respectively. These results demonstrated that this method can be successfully applied to at-line monitor of NT, concentration of reducing sugars, cell concentration and pH during nisin fermentation processes.     

Prediction of problematic wine fermentations using artificial neural networks

Artificial neural networks (ANNs) have been used for the recognition of non-linear patterns, a characteristic of bioprocesses like wine production. In this work, ANNs were tested to predict problems of wine fermentation. A database of about 20,000 data from industrial fermentations of Cabernet Sauvignon and 33 variables was used. Two different ways of inputting data into the model were studied, by points and by fermentation. Additionally, different sub-cases were studied by varying the predictor variables (total sugar, alcohol, glycerol, density, organic acids and nitrogen compounds) and the time of fermentation (72, 96 and 256 h). The input of data by fermentations gave better results than the input of data by points. In fact, it was possible to predict 100% of normal and problematic fermentations using three predictor variables: sugars, density and alcohol at 72 h (3 days). Overall, ANNs were capable of obtaining 80% of prediction using only one predictor variable at 72 h; however, it is recommended to add more fermentations to confirm this promising result.     

Case study: Comparing the use of nonlinear discriminating analysis and Artificial Neural Networks in the classification of three fish species: acaras (Geophagus brasiliensis), tilapias (Tilapia rendalli) and mullets (Mugil liza)

This study used the Discriminant Analysis statistical technique and Artificial Neural Networks, multilayer perceptron, in the classification of three fish species sampled in the state of Rio de Janeiro, Brazil: Geophagus brasiliensis (acaras), Tilapia rendall (tilapias) and Mugil liza (mullets). These fish were sexed when possible, weighed, measured, and had their Gonadosomatic and Hepatosomatic Indices calculated, as well as their Condition Factor. The use of an Artificial Neural Network (ANN) presented satisfactory results, even though the groups were composed of very diverse-sized animals. Without the need for non-violation assumptions and other considerations, the Artificial Neural Network was found to be the excellent alternative to classification problems of unbalanced data, such as the one presented in this study.     

Model Comparison for Breast Cancer Prognosis Based on Clinical Data

We compared the performance of several prediction techniques for breast cancer prognosis, based on AU-ROC performance (Area Under ROC) for different prognosis periods. The analyzed dataset contained 1,981 patients and from an initial 25 variables, the 11 most common clinical predictors were retained. We compared eight models from a wide spectrum of predictive models, namely; Generalized Linear Model (GLM), GLM-Net, Partial Least Square (PLS), Support Vector Machines (SVM), Random Forests (RF), Neural Networks, k-Nearest Neighbors (k-NN) and Boosted Trees. In order to compare these models, paired t-test was applied on the model performance differences obtained from data resampling. Random Forests, Boosted Trees, Partial Least Square and GLMNet have superior overall performance, however they are only slightly higher than the other models. The comparative analysis also allowed us to define a relative variable importance as the average of variable importance from the different models. Two sets of variables are identified from this analysis. The first includes number of positive lymph nodes, tumor size, cancer grade and estrogen receptor, all has an important influence on model predictability. The second set incudes variables related to histological parameters and treatment types. The short term vs long term contribution of the clinical variables are also analyzed from the comparative models. From the various cancer treatment plans, the combination of Chemo/Radio therapy leads to the largest impact on cancer prognosis.     

Rapid Quantification of Methamphetamine: Using Attenuated Total Reflectance Fourier Transform Infrared Spectroscopy (ATR-FTIR) and Chemometrics

In Australia and increasingly worldwide, methamphetamine is one of the most commonly seized drugs analysed by forensic chemists. The current well-established GC/MS methods used to identify and quantify methamphetamine are lengthy, expensive processes, but often rapid analysis is requested by undercover police leading to an interest in developing this new analytical technique. Ninety six illicit drug seizures containing methamphetamine (0.1%–78.6%) were analysed using Fourier Transform Infrared Spectroscopy with an Attenuated Total Reflectance attachment and Chemometrics. Two Partial Least Squares models were developed, one using the principal Infrared Spectroscopy peaks of methamphetamine and the other a Hierarchical Partial Least Squares model. Both of these models were refined to choose the variables that were most closely associated with the methamphetamine % vector. Both of the models were excellent, with the principal peaks in the Partial Least Squares model having Root Mean Square Error of Prediction 3.8, R² 0.9779 and lower limit of quantification 7% methamphetamine. The Hierarchical Partial Least Squares model had lower limit of quantification 0.3% methamphetamine, Root Mean Square Error of Prediction 5.2 and R² 0.9637. Such models offer rapid and effective methods for screening illicit drug samples to determine the percentage of methamphetamine they contain.     

Chemometric tools for classification and elucidation of protein secondary structure from infrared and circular dichroism spectroscopic measurements

Protein classification and characterization often rely on the information contained in the protein secondary structure. Protein class assignment is usually based on X-ray diffraction measurements, which need the protein in a crystallized form, or on NMR spectra, to obtain the structure of a protein in solution. Simple spectroscopic techniques, such as circular dichroism (CD) and infrared (IR) spectroscopies, are also known to be related to protein secondary structure, but they have seldom been used for protein classification. To see the potential of CD, IR, and combined CD/IR measurements for protein classification, unsupervised pattern recognition methods, Principal Component Analysis (PCA) and cluster analysis, are proposed first to check for natural grouping tendencies of proteins according to their measured spectra. Partial Least Squares Discriminant Analysis (PLS-DA), a supervised pattern recognition method, is used afterwards to test the possibility to model explicitly each protein class and to test these models in class assignment of unknown proteins. Determination of the protein secondary structure, understood as the prediction of the abundance of the different secondary structure motifs in the biomolecule, was carried out with the local regression method interval Partial Least Squares (iPLS). CD, IR, and CD/IR measurements were correlated to the fraction of the motif to be predicted, determined from X-ray measurements. iPLS builds models extracting the spectral information most correlated to a specific secondary motif and avoids the use of irrelevant spectral regions. Spectral intervals chosen by iPLS models provide structural information which can be used to confirm previous biochemical assignments or identify new motif-related spectral features. The predictive ability of the models built with the selected spectral regions has a quality similar to previous classical approaches.     

Growth, seed development and genetic analysis in wild type and Def mutant of Pisum sativum L

Background

Dementia and cognitive impairment associated with aging are a major medical and social concern. Neuropsychological testing is a key element in the diagnostic procedures of Mild Cognitive Impairment (MCI), but has presently a limited value in the prediction of progression to dementia. We advance the hypothesis that newer statistical classification methods derived from data mining and machine learning methods like Neural Networks, Support Vector Machines and Random Forests can improve accuracy, sensitivity and specificity of predictions obtained from neuropsychological testing. Seven non parametric classifiers derived from data mining methods (Multilayer Perceptrons Neural Networks, Radial Basis Function Neural Networks, Support Vector Machines, CART, CHAID and QUEST Classification Trees and Random Forests) were compared to three traditional classifiers (Linear Discriminant Analysis, Quadratic Discriminant Analysis and Logistic Regression) in terms of overall classification accuracy, specificity, sensitivity, Area under the ROC curve and Press'Q. Model predictors were 10 neuropsychological tests currently used in the diagnosis of dementia. Statistical distributions of classification parameters obtained from a 5-fold cross-validation were compared using the Friedman's nonparametric test.

Results

Press' Q test showed that all classifiers performed better than chance alone (p < 0.05). Support Vector Machines showed the larger overall classification accuracy (Median (Me) = 0.76) an area under the ROC (Me = 0.90). However this method showed high specificity (Me = 1.0) but low sensitivity (Me = 0.3). Random Forest ranked second in overall accuracy (Me = 0.73) with high area under the ROC (Me = 0.73) specificity (Me = 0.73) and sensitivity (Me = 0.64). Linear Discriminant Analysis also showed acceptable overall accuracy (Me = 0.66), with acceptable area under the ROC (Me = 0.72) specificity (Me = 0.66) and sensitivity (Me = 0.64). The remaining classifiers showed overall classification accuracy above a median value of 0.63, but for most sensitivity was around or even lower than a median value of 0.5.

Conclusions

When taking into account sensitivity, specificity and overall classification accuracy Random Forests and Linear Discriminant analysis rank first among all the classifiers tested in prediction of dementia using several neuropsychological tests. These methods may be used to improve accuracy, sensitivity and specificity of Dementia predictions from neuropsychological testing.     

COMPARISONS OF VOLATILE COMPOUNDS RELEASED DURING CONSUMPTION OF A COMPLEX FOOD BY DIFFERENT ASSESSORS WITH EXPRESSIONS OF PERCEIVED FLAVOR DETERMINED BY FREE CHOICE PROFILING

Comparisons of volatile compounds released during consumption by different assessors with individual differences in the assessors'chewing patterns, saliva production rates and ultimately their expressions of perceived flavor have received little research attention to date, although such comparisons are fundamental to the understanding of flavor. To address this, eight untrained assessors were chosen and each consumed six Cheddar cheeses during Buccal Headspace Analysis of the volatile compounds released, while in parallel measures of each assessor's mastication behavior using Electromyography, their stimulated saliva production during consumption and their sensory perceptions of the cheeses flavor during Free Choice Profiling were determined. Relationships between the volatile compounds released and the sensory and physiological measures were investigated using Principal Components Analysis, Generalised Procrustes Analysis and Partial Least Squares regression. It was found that although there were differences between assessors'mastication behavior and saliva production rates, the assessors'individual volatile profiles obtained by Buccal Headspace Analysis were similar for each cheese examined. Also, Partial Least Squares was successful in predicting the most important flavor differences between cheeses from the volatile compounds released during their consumption by different assessors.     

Monte-Carlo methods for determining optimal number of significant variables. Application to mouse urinary profiles

Three methods for variable selection are described, namely the t-statistic, Partial Least Squares Discriminant Analysis (PLS-DA) weights and regression coefficients, with the aim of determining which variables are the most significant markers for discriminating between two groups: a variable’s level of significance is related to its magnitude. Monte-Carlo methods are employed to determine empirical significance of variables, by permuting randomly the class membership 5000 times to obtain null distributions, and comparing the observed statistic for each variable with the null distribution. Seven simulations consisting of 200 samples, divided equally between two classes, and 300 variables, are constructed; in one dataset there are no induced correlations between variables, in two datasets correlations are induced but there is no induced separation between the classes, and in four datasets, separation is induced by selecting 20 of the variables to be discriminators. In addition two metabolomic datasets were analysed consisting of the GCMS of urinary extracts from mice both to determine the effect of stress and to determine the effect of diet on the urinary chemosignal. It is shown that the t-statistic combined with Monte-Carlo permutations provides similar results to PLS weights. PLS regression coefficients find the least number of markers but, for the simulations, the lowest False Positives rates.     

Metabolomic Analysis of the Effect of Postnatal Hypoxia on the Retina in a Newly Born Piglet Model

The availability of reliable biomarkers of brain injury secondary to birth asphyxia could substantially improve clinical grading, therapeutic intervention strategies, and prognosis. In this study, changes in the metabolome of retinal tissue caused by profound hypoxia in an established neonatal piglet model were investigated using an ultra performance liquid chromatography – quadrupole time of flight mass spectrometry (UPLC-QTOFMS) untargeted metabolomic approach, which included Partial Least Squares – Discriminant Analysis (PLSDA) multivariate data analysis. The initial identification of a set of discriminant metabolites from UPLC-QTOFMS data was confirmed by target UPLC-MS/MS and allowed the selection of endogenous CDP-choline as a promising candidate biomarker for hypoxia-derived brain damage assessing intensity of retinal hypoxia. Results from this study will foster further research on CDP-choline changes occurring during resuscitation.     

Quantification of polymeric mannose in wine extracts by FT-IR spectroscopy and OSC-PLS1 regression

FT-IR spectroscopy has being a widespread technique in the agro-industry for the quick assess of food components, including the wine. Using the region of wavenumbers 1200–800 cm⁻¹ of the FT-IR spectra wine polysaccharides, Partial Least Squares Regression (PLS1) independent calibration models were built for mannose quantification in complex matrices from white and in red wine extracts. With PLS1 it was not possible to build a calibration model that included both white and red wine extracts. However, a predictive ability of the model for quantification of mannose from mannoproteins based on this FT-IR spectral region was achieved by the application of orthogonal signal correction (OSC)-PLS1.     

Temperature-Dependent Kinetic Model for Nitrogen-Limited Wine Fermentations

A physical and mathematical model for wine fermentation kinetics was adapted to include the influence of temperature, perhaps the most critical factor influencing fermentation kinetics. The model was based on flask-scale white wine fermentations at different temperatures (11 to 35°C) and different initial concentrations of sugar (265 to 300 g/liter) and nitrogen (70 to 350 mg N/liter). The results show that fermentation temperature and inadequate levels of nitrogen will cause stuck or sluggish fermentations. Model parameters representing cell growth rate, sugar utilization rate, and the inactivation rate of cells in the presence of ethanol are highly temperature dependent. All other variables (yield coefficient of cell mass to utilized nitrogen, yield coefficient of ethanol to utilized sugar, Monod constant for nitrogen-limited growth, and Michaelis-Menten-type constant for sugar transport) were determined to vary insignificantly with temperature. The resulting mathematical model accurately predicts the observed wine fermentation kinetics with respect to different temperatures and different initial conditions, including data from fermentations not used for model development. This is the first wine fermentation model that accurately predicts a transition from sluggish to normal to stuck fermentations as temperature increases from 11 to 35°C. Furthermore, this comprehensive model provides insight into combined effects of time, temperature, and ethanol concentration on yeast (Saccharomyces cerevisiae) activity and physiology.     

Evaluation of yeast diversity during wine fermentations with direct inoculation and pied de cuve method at an industrial scale

The diversity and composition of yeast populations may greatly impact wine quality. This study investigated the yeast microbiota in two different types of wine fermentations: direct inoculation of a commercial starter versus pied de cuve method at an industrial scale. The pied de cuve fermentation entailed growth of the commercial inoculum used in the direct inoculation fermentation for further inoculation of additional fermentations. Yeast isolates were collected from different stages of wine fermentation and identified to the species level using Wallersterin Laboratory nutrient (WLN) agar followed by analysis of the 26S rDNA D1/D2 domain. Genetic characteristics of the Saccharomyces cerevisiae strains were assessed by a rapid PCR-based method, relying on the amplification of interdelta sequences. A total of 412 yeast colonies were obtained from all fermentations and eight different WL morphotypes were observed. Non-Saccharomyces yeast mainly appeared in the grape must and at the early stages of wine fermentation. S. cerevisiae was the dominant yeast species using both fermentation techniques. Seven distinguishing interdelta sequence patterns were found among S. cerevisiae strains, and the inoculated commercial starter, AWRI 796, dominated all stages in both direct inoculation and pied de cuve fermentations. This study revealed that S. cerevisiae was the dominant species and an inoculated starter could dominate fermentations with the pied de cuve method under controlled conditions.     

Estimating fish community diversity from environmental features in the Tagus estuary (Portugal): Multiple Linear Regression and Artificial Neural Network approaches

Relationships between environmental variables and diversity (Shannon‐Weaver index) of the fish communities in the Tagus estuary and adjacent coastal areas were analyzed. The focus was on the linearity or nonlinearity of these abiotic/biotic characteristics, with the aim to obtain an accurate short–medium term time‐scale diversity prediction from habitat variables alone. Multiple Linear Regressions (MLR) were used for the linear approach and Artificial Neural Networks (ANNs) for the nonlinear approach. MLR results in the external validation phase indicated a lack of model accuracy (R² = 0.0710; %SEP = 47.5868; E = ?0.0217; ARV = 1.0217; N = 43). Results of the best of the Artificial Neural Networks used in this study (12‐15‐15‐1 architecture) in the external validation phase (ANN: R² = 0.9736; %SEP = 7.8499; E = 0.9722; ARV = 0.0278; N = 43) were more accurate than those obtained with MLR. This indicates a clear nonlinear relationship between variables. In the best ANN model, nitrate concentration, depth, dissolved oxygen and temperature were the most important predictors of fish diversity in the Tagus estuary. The sensibility analysis indicated that the remaining variables (silicate, nitrite, transparency, salinity, slope, phosphate, water particulate organic matter, and chlorophyll a) played lesser roles in the model.     

Temperature-dependent kinetic model for nitrogen-limited wine fermentations

A physical and mathematical model for wine fermentation kinetics was adapted to include the influence of temperature, perhaps the most critical factor influencing fermentation kinetics. The model was based on flask-scale white wine fermentations at different temperatures (11 to 35 degrees C) and different initial concentrations of sugar (265 to 300 g/liter) and nitrogen (70 to 350 mg N/liter). The results show that fermentation temperature and inadequate levels of nitrogen will cause stuck or sluggish fermentations. Model parameters representing cell growth rate, sugar utilization rate, and the inactivation rate of cells in the presence of ethanol are highly temperature dependent. All other variables (yield coefficient of cell mass to utilized nitrogen, yield coefficient of ethanol to utilized sugar, Monod constant for nitrogen-limited growth, and Michaelis-Menten-type constant for sugar transport) were determined to vary insignificantly with temperature. The resulting mathematical model accurately predicts the observed wine fermentation kinetics with respect to different temperatures and different initial conditions, including data from fermentations not used for model development. This is the first wine fermentation model that accurately predicts a transition from sluggish to normal to stuck fermentations as temperature increases from 11 to 35 degrees C. Furthermore, this comprehensive model provides insight into combined effects of time, temperature, and ethanol concentration on yeast (Saccharomyces cerevisiae) activity and physiology.     

Inside Front Cover: Combining hyperspectral imaging and chemometrics to assess and interpret the effects of environmental stressors on zebrafish eye images at tissue level (J. Biophotonics 3/2018)

Raman images were used to study the effect of the contaminant chlorpyriphos‐oxon on zebrafish eye samples. Multivariate Curve Resolution‐Alternating Least Squares (MCR‐ALS) was used to obtain the distribution maps and spectral signatures of biological components present in the images analyzed. The use of MCRALS spectral signatures as starting information for Partial Least Squares‐Discriminant Analysis allowed statistical assessment of the effect of the contaminant at a specific tissue level. Further details can be found in the article by Víctor Olmos et al. ( e201700089 ).

     

Bioindication of chemical and hydromorphological habitat characteristics with benthic macro-invertebrates based on Artificial Neural Networks

This study aims to enhance the discussion about the usefulness of Artificial Neural Networks and specific input relevance detection for water quality assessment. The focus is on the development of neural modelling techniques initiating further research on predictor selection for bioindication. We tested the predictability of abiotic variables and quality indices BOD₅, conductivity, NH₃-N, NH₄-N, NO₂-N, NO₃-N, N_total, oxygen, pH-value, P_total, water temperature, chemical and morphological water quality class and saprobic index by means of benthic macro-invertebrates on 51 sampling sites of nine small streams in Central Germany. The results show that General Regression Neural Networks and modified Multi-Layer-Perceptrons can successfully be applied for modelling and predicting ecological and environmental data because of their ability to solve non-linear and multidimensional problems. Nevertheless, Linear Neural Networks have been proved suitable in some cases. Particularly, stepwise method, genetic algorithms and sensitivity analysis can be used to reduce the complexity of data sets in a reasonable way by detecting important predictors. In many cases the prediction accuracy even increases. In addition, using only the presence of species instead of their abundance provides mostly better results, simpler models and an easier collection of data. Thus, complex systems can be illustrated in easily surveyed models with low measuring and computing effort. We claim that the identification of indicator species and the assessment of complex anthropogenic impacts can be improved substantially and managed more efficiently using the neural-based approach. It is predestinated for bioindication, particularly with regard to aquatic ecosystems.     

Next-generation sequencing reveals significant bacterial diversity of botrytized wine

While wine fermentation has long been known to involve complex microbial communities, the composition and role of bacteria other than a select set of lactic acid bacteria (LAB) has often been assumed either negligible or detrimental. This study served as a pilot study for using barcoded amplicon next-generation sequencing to profile bacterial community structure in wines and grape musts, comparing the taxonomic depth achieved by sequencing two different domains of prokaryotic 16S rDNA (V4 and V5). This study was designed to serve two goals: 1) to empirically determine the most taxonomically informative 16S rDNA target region for barcoded amplicon sequencing of wine, comparing V4 and V5 domains of bacterial 16S rDNA to terminal restriction fragment length polymorphism (TRFLP) of LAB communities; and 2) to explore the bacterial communities of wine fermentation to better understand the biodiversity of wine at a depth previously unattainable using other techniques. Analysis of amplicons from the V4 and V5 provided similar views of the bacterial communities of botrytized wine fermentations, revealing a broad diversity of low-abundance taxa not traditionally associated with wine, as well as atypical LAB communities initially detected by TRFLP. The V4 domain was determined as the more suitable read for wine ecology studies, as it provided greater taxonomic depth for profiling LAB communities. In addition, targeted enrichment was used to isolate two species of Alphaproteobacteria from a finished fermentation. Significant differences in diversity between inoculated and uninoculated samples suggest that Saccharomyces inoculation exerts selective pressure on bacterial diversity in these fermentations, most notably suppressing abundance of acetic acid bacteria. These results determine the bacterial diversity of botrytized wines to be far higher than previously realized, providing further insight into the fermentation dynamics of these wines, and demonstrate the utility of next-generation sequencing for wine ecology studies.     

Helminth Colonization Is Associated with Increased Diversity of the Gut Microbiota

Soil-transmitted helminths colonize more than 1.5 billion people worldwide, yet little is known about how they interact with bacterial communities in the gut microbiota. Differences in the gut microbiota between individuals living in developed and developing countries may be partly due to the presence of helminths, since they predominantly infect individuals from developing countries, such as the indigenous communities in Malaysia we examine in this work. We compared the composition and diversity of bacterial communities from the fecal microbiota of 51 people from two villages in Malaysia, of which 36 (70.6%) were infected by helminths. The 16S rRNA V4 region was sequenced at an average of nineteen thousand sequences per samples. Helminth-colonized individuals had greater species richness and number of observed OTUs with enrichment of Paraprevotellaceae, especially with Trichuris infection. We developed a new approach of combining centered log-ratio (clr) transformation for OTU relative abundances with sparse Partial Least Squares Discriminant Analysis (sPLS-DA) to enable more robust predictions of OTU interrelationships. These results suggest that helminths may have an impact on the diversity, bacterial community structure and function of the gut microbiota.     

Tumor classification by partial least squares using microarray gene expression data

MOTIVATION: One important application of gene expression microarray data is classification of samples into categories, such as the type of tumor. The use of microarrays allows simultaneous monitoring of thousands of genes expressions per sample. This ability to measure gene expression en masse has resulted in data with the number of variables p(genes) far exceeding the number of samples N. Standard statistical methodologies in classification and prediction do not work well or even at all when N < p. Modification of existing statistical methodologies or development of new methodologies is needed for the analysis of microarray data. RESULTS: We propose a novel analysis procedure for classifying (predicting) human tumor samples based on microarray gene expressions. This procedure involves dimension reduction using Partial Least Squares (PLS) and classification using Logistic Discrimination (LD) and Quadratic Discriminant Analysis (QDA). We compare PLS to the well known dimension reduction method of Principal Components Analysis (PCA). Under many circumstances PLS proves superior; we illustrate a condition when PCA particularly fails to predict well relative to PLS. The proposed methods were applied to five different microarray data sets involving various human tumor samples: (1) normal versus ovarian tumor; (2) Acute Myeloid Leukemia (AML) versus Acute Lymphoblastic Leukemia (ALL); (3) Diffuse Large B-cell Lymphoma (DLBCLL) versus B-cell Chronic Lymphocytic Leukemia (BCLL); (4) normal versus colon tumor; and (5) Non-Small-Cell-Lung-Carcinoma (NSCLC) versus renal samples. Stability of classification results and methods were further assessed by re-randomization studies.